contextflow targets early lung cancer detection by augmenting ADVANCE Chest CT with malignancy scoring from RevealDx
2024-05-02

Vienna, Austria (02.05.2024) – Chest CT experts contextflow GmbH have released a new version of their comprehensive computer-aided detection support tool, ADVANCE Chest CT. In addition to lung nodule detection, quantification, visualization and classification, the updated software now analyzes nodules for malignancy with the aim of detecting cancer early and reducing unnecessary procedures.

It’s widely known that lung cancer constitutes one of the leading causes of premature death, and thus early detection of cancer is crucial. For that very reason, contextflow has implemented a malignancy Similarity Index (mSI) feature into ADVANCE Chest CT, a clinical decision support tool that aids radiologists in the diagnosis of lung cancer, interstitial lung diseases (ILD) and chronic-obstructive pulmonary disease (COPD). 

A malignancy Similarity Index is a value from 0 to 1 that indicates the degree of similarity between a nodule in question and nodules with known outcomes in a reference set. In clinical practice, a high mSI would indicate “upgrading” followup of a nodule as compared to guideline recommendations because there is increased certainty that the nodule in question is malignant. Here, the goal is to detect cancer as early as possible in order to improve patient outcomes.

As contextflow CEO Markus Holzer puts it, “Detecting lung cancer is a challenging and time-consuming task for radiologists. Detection is not straightforward. All too often patients are scheduled for followups months after their initial exam without knowing whether they actually have cancer or not. This is extremely stressful, but thankfully we can start to change that.”

On the flip side, a low mSI score would indicate “downgrading” the nodule with the aim of reducing invasive, unnecessary procedures and patient stress. In a clinical study published in the Journal of the American College of Radiology, use of the RevealDx mSI feature was shown to detect cancer up to one year sooner in approximately 45% of cases while simultaneously reducing false positive detection rates by 18% (Adams, Scott J. et al. JACR September 2022).

As Chris Wood, CEO of RevealDx says, “Our integration with ADVANCE Chest CT simplifies the interpretation of lung nodules. Automatically detected nodules have their mSI scores calculated before the radiologist starts reading the exam, which should save time while providing clinical insight.”

The latest version of contextflow ADVANCE Chest CT also includes a nodule tracking report to visualize and quantify changes in nodules over time. contextflow ADVANCE Chest CT is a CE marked medical device under MDR. For more information, contact sales@contextflow.com or visit contextflow.com.

About contextflow 

contextflow is a spin-off of the Medical University of Vienna (MUW) and European research project KHRESMOI, supported by the Technical University of Vienna (TU). Founded by a team of AI and engineering experts in July 2016, the company has a strong interest in bringing state-of-the-art machine learning techniques to the market e.g. improved emphysema detection and lung segmentation. Its computer-aided detection software ADVANCE Chest CT is CE Marked and available for clinical use within Europe under the new MDR. Visit contextflow.com for more information. 

About RevealDx

RevealDx developed RevealAI-Lung, the world’s first CADx software for the characterization of lung nodules to receive the CE Mark. RevealAI-Lung has been validated in clinical studies that show improvement in diagnostic precision using our patented methods.  Results demonstrate the software can significantly accelerate lung cancer diagnosis and reduce unnecessary procedures. https://reveal-dx.com/

For more information, contact: 

Julie Sufana, Chief Marketing Officer, contextflow

Email: julie@contextflow.com 

Phone: +43 676 920 1032 

Chris Wood, CEO, RevealDx

Email: chris@reveal-dx.com

Phone: +01 425 895 2845

Other News

contextflow gewinnt den Wettbewerb Healthy Hub von vier Krankenkassen: Innovative Lösungen für Frauengesundheit und Früherkennung

DORTMUND, 13.03.2024. Die Gewinnerinnen und Gewinner des Healthy-Hub-Wettbewerbs 2024 wollen die Gesundheit von Frauen mit innovativer Versorgung verbessern. Die verschiedenen Angebote beziehen sich auf unterschiedliche Lebensphasen und Krankheitsbilder – von hybriden Tests gegen HPV-Viren, über die Versorgung bei frauentypischen Krankheiten wie Endometriose, bis hin zu einer innovativen Therapie bei Beschwerden in der Menopause. Menschen mit Lungenerkrankungen sollen in Sachen Früherkennung besser betreut werden. Diese Themen gehen die Siegerteams jeweils mit einer der vier Krankenkassen – BIG direkt gesund, IKK Südwest, mhplus Krankenkasse und SBK Siemens-Betriebskrankenkasse – an. Die Kassen haben den Wettbewerb bereits zum fünften Mal gemeinsam ausgerichtet.

„Im Fokus standen dieses Mal selektivvertragliche Versorgungslösungen, die insbesondere das Gender Health Gap, also die Ungleichheit der Versorgung von Frauen gegenĂĽber Männern, berĂĽcksichtigen sollten“, erläutert Dr. Elmar Waldschmitt, GeschäftsfĂĽhrer des Healthy Hub und Vorstandsbeauftragter bei der BIG.  Die medizinische Forschung und Versorgung sei leider immer noch zu stark auf Männer fokussiert.

Aus gut 40 Bewerbungen wurden die Gewinnerinnen und Gewinner ausgewählt. Diese sind:

Remi Health, Kassenpartnerin BIG direkt gesund

Remi Health hat eine Früherkennung gegen Gebärmutterhalskrebs entwickelt, bei der sich weibliche Versicherte zuhause auf Humane Papillomviren (HPV) testen können. Bei auffälligem Befund sind eine Online-Beratung und die Terminvereinbarung bei einer Gynäkologin oder einem Gynäkologen vorgesehen. Die digitale Plattform von Remi klärt zudem über die Bedeutung der Vorsorge und Früherkennung auf. „Der niedrigschwellige HPV-Test vereint Heimtests, Telemedizin und Prävention in einem nahtlosen Prozess“, erläutert Marvin Abert, Co-CEO von Remi Health. „Damit möchten wir insbesondere junge Frauen erreichen, die bislang die Krebsvorsorgeuntersuchungen nicht in Anspruch nehmen und keine Immunität durch eine HPV-Impfung besitzen. Der HPV-Selbsttest von Remi Health ist unserer Ansicht nach ein innovativer Lösungsansatz, um die Krebsvorsorge sinnvoll zu ergänzen“, sagt Christiane Heidrich, Teamleiterin Managed Care der BIG direkt gesund.

Femna Health, Kassenpartnerin SBK Siemens-Betriebskrankenkasse

Rund ein Drittel der Frauen im fertilen Alter, also in den fruchtbaren Jahren, leidet unter stark einschränkenden physischen, psychischen und sozialen Belastungen aufgrund von Zyklusbeschwerden. Darunter fallen Erkrankungen wie PMS, Endometriose oder auch Dysmenorrhö. „Die aktuelle Versorgung geht unter anderem aufgrund von mangelnden Therapiemöglichkeiten, langen Wartezeiten und fehlender individueller Betreuung diese Probleme nicht adäquat an. FEMNA hat deshalb ein hybrides Versorgungsmodell entwickelt, das Frauen eine verbesserte, vollumfängliche und sofortige Versorgung ermöglicht“, erklärt Maxie Matthiessen, Gründerin von Femna Health. „Femna Care verbessert Verhaltensmuster und hilft, Folgeerkrankungen zu vermeiden sowie die Lebensqualität betroffener Frauen zu steigern“, sagt Christina Bernards, Teamleiterin Versorgungsmanagement, SBK Siemens-Betriebskrankenkasse. „Für uns ein echtes Herzensthema, denn gerade die Frauengesundheit wird in Medizin und Forschung massiv vernachlässigt und unterfinanziert. Es wird Zeit, dass wir das ändern.“

YoniCare, Kassenpartnerin mhplus Krankenkasse

Mit YoniCare (MICADO HEALTH CARE GmbH) hat der Healthy Hub erstmals ein nicht-digitales Versorgungsprodukt im Portfolio. YoniCare ermöglicht eine Lasertherapie zur Behandlung des genitourinären Syndroms. „Der sinkende Ă–strogenspiegel in der Menopause fĂĽhrt bei Frauen unter anderem zu Scheidentrockenheit, Veränderungen im Vaginalgewebe sowie der Vaginalschleimhaut und in der Folge zu Beschwerden wie Jucken, Inkontinenz, Infekten und anderen Beschwerden“, so Mandy Wilms von der MICADO HEALTH CARE GmbH. Die Therapie kann das vaginale Epithel revitalisieren, das die Vagina und den Scheidenvorhof auskleidet. Die Beschwerden nehmen ab und die gynäkologische Gesundheit wird wiederhergestellt. „Die Therapie kann eine Hormonersatztherapie ĂĽberflĂĽssig machen und Wechselwirkungen mit Medikamenten reduzieren“, sagt Fabienne Knaub, Referentin Selektivverträge und Versorgungsanalyse der mhplus Krankenkasse. 

.

contextflow, Kassenpartnerin IKK SĂĽdwest

Bei Erkrankungen im Thoraxbereich ist eine FrĂĽherkennung wesentlich fĂĽr den Therapieerfolg. „Wir bieten eine KI-Software, die ergänzende Informationen zur Identifizierung und Interpretation von lungenspezifischen Bildmustern in Scans vom Computertomographen bietet“, so Markus Holzer, CEO und Co-Founder von contextflow. Das ultimative Ziel der Software ist es, Lungenkrebs so frĂĽh wie möglich zu erkennen, um Ressourcen des Gesundheitssystems zu sparen und Patientinnen und Patienten vor unnötigen Eingriffen zu schĂĽtzen. „Die Bildanalyse-KI ermöglicht den befundenden Radiologen eine schnellere und bessere Beurteilung relevanter Bildmuster von Lungenkrebs und respiratorischen Erkrankungen“, sagt Dr. Florian Brandt, Health Innovation Manager der IKK SĂĽdwest. 

Anwendungsfälle für die Versorgungspraxis entwickeln

Die vier Krankenkassen entwickeln in den nächsten Monaten gemeinsam den Gewinnerteams konkrete Anwendungsfälle, die fĂĽr den Einsatz in der Gesetzlichen Krankenversicherung (GKV) geeignet sind. „Unser Ziel ist es, dass diese innovativen Versorgungsmethoden in der Versorgungspraxis ankommen“, so Dr. Elmar Waldschmitt. Zudem wird der Kooperationspartner des Healthyhub, die GWQ ServicePlus AG, in die Entwicklung von Anfang an eingebunden. 

Ăśber den Healthy Hub

Seit 2018 engagieren sich die vier Krankenkassen BIG direkt gesund, IKK SĂĽdwest, mhplus Krankenkasse sowie SBK Siemens-Betriebskrankenkasse mit dem Healthy Hub fĂĽr die Digitalisierung des Gesundheitswesens. Ziel ist es, innovative Lösungen fĂĽr eine bessere, integrierte Versorgung zu ermöglichen. Dazu organisieren die Kassen regelmäßig Wettbewerbe fĂĽr Start-ups. So haben sie bereits 27 Start-ups in die Versorgung gebracht. 

Ăśber BIG direkt gesund 

Die BundesInnungskrankenkasse Gesundheit – kurz BIG direkt gesund – wurde 1996 in Dortmund gegrĂĽndet. Die groĂźe Idee hinter der BIG: Wir schaffen Raum fĂĽrs Menschsein. Gemeint ist damit eine moderne Online-Ausrichtung und empathischer Service, der schnell und lösungsorientiert ist. Die BIG bietet vielseitige Kommunikationswege passend zum jeweiligen Lebensstil ihrer bundesweit rund 510.000 Versicherten. Diese Kundinnen und Kunden erfahren eine wertschätzende und verständliche Beratung per Telefon, Chat, Mail oder Brief. Viele Zusatzleistungen sowie ein attraktives Bonusprogramm sind weitere groĂźe Pluspunkte. BIG direkt gesund hat ihren Rechtssitz in Berlin, ihre Hauptverwaltung in Dortmund und einen wichtigen Verwaltungsstandort in Aachen. Die BIG beschäftigt an den operativen Standorten rund 950 Mitarbeiterinnen und Mitarbeiter, in 11 BIGshops wird Beratung vor Ort angeboten.

FĂĽr RĂĽckfragen

Bettina Kiwitt

Leiterin Unternehmenskommunikation

Tel.: 0231/5557-1016

E-Mail: bettina.kiwitt@big-direkt.de

Ăśber die IKK SĂĽdwest:

Aktuell betreut die IKK Südwest mehr als 635.000 Versicherte und über 90.000 Betriebe in Hessen, Rheinland-Pfalz und im Saarland. Versicherte und Interessenten können auf eine persönliche Betreuung in unseren 21 Kundencentern in der Region vertrauen. Darüber hinaus ist die IKK Südwest an sieben Tagen in der Woche rund um die Uhr über die IKK Service-Hotline 0681/ 3876 1000 oder www.ikk-suedwest.de zu erreichen.

FĂĽr RĂĽckfragen

Mathias Gessner

Pressesprecher

Tel.: 0681/3876-1163

E-Mail: presse@ikk-sw.de

Ăśber die mhplus Krankenkasse:

Die mhplus Krankenkasse ist offen für gesetzlich Krankenversicherte. Rund 1.000 Mitarbeitende betreuen deutschlandweit mehr als eine halbe Million Versicherte. Unabhängige Tests belegen hohe Servicestandards und solide Finanzen. Der Zusatzbeitrag der mhplus beträgt seit 2023 stabil 1,58 Prozent.

FĂĽr RĂĽckfragen

Isabell Rabe

Leiterin Presse und Politik
Tel.: 07141/9790–9845

E-Mail: presse@mhplus.de

Ăśber die SBK: 

Die SBK Siemens-Betriebskrankenkasse ist die größte Betriebskrankenkasse Deutschlands und gehört zu den 20 größten gesetzlichen Krankenkassen. Als geöffnete, bundesweit tätige Krankenkasse versichert sie mehr als eine Million Menschen und betreut ĂĽber 100.000 Firmenkunden in Deutschland – mit rund 2000 Mitarbeiterinnen und Mitarbeitern in 86 Geschäftsstellen. Seit ĂĽber 100 Jahren setzt sich die SBK persönlich und engagiert fĂĽr die Interessen der Versicherten ein. Sie positioniert sich als Vorreiter fĂĽr einen echten Qualitätswettbewerb in der gesetzlichen Krankenversicherung. Voraussetzung dafĂĽr ist aus Sicht der SBK mehr Transparenz fĂĽr die Versicherten – ĂĽber relevante Finanzkennzahlen, aber auch ĂĽber Leistungsbereitschaft, Beratung und Dienstleistungsqualität von Krankenkassen. Im Sinne des Kunden vereint die SBK darĂĽber hinaus das Beste aus persönlicher und digitaler Welt und treibt die Digitalisierung im Gesundheitswesen aktiv voran. 

FĂĽr RĂĽckfragen 

Julia Mederle

Stab Unternehmenskommunikation 

Tel.: +49 89 62700-363 

E-Mail: julia.mederle@sbk.org Internet: www.sbk.org

Other News

contextflow included in Spanish study on rheumatoid arthritis and ILDs

The Spanish Society of Rheumatology is currently conducting a research study to explore the prevalence and early detection methods of interstitial lung disease (ILD) in individuals diagnosed with rheumatoid arthritis (RA). Fifteen Spanish rheumatology departments will work on the study together with the radiology departments in 2024 and 2025.

This collaboration will address an important healthcare issue: the early detection of ILDs, which tend to go undetected until later stages. This, in turn, negatively impacts patient outcomes, particularly when a patient suffers from cardiovascular diseases. 

It is assumed that approximately 30% of RA patients may develop diffuse ILDs, underscoring the need for effective screening criteria. To achieve this goal, the research team has outlined specific criteria for participant selection, and the study aims to recruit over 450 patients across 15 hospital centers. The study results will hopefully help define strategies for early detection of ILD in patients with RA.

contextflow ADVANCE Chest CT will deliver automatic quantification regarding the extent of ILD in the study population, enabling detailed examination of the lung parenchyma. Furthermore, the study will compare the interstitial involvement of the lung parenchyma in chest CTs assessed by radiologists and compare them to the results from the automatic detection of ILD-associated patterns by contextflow’s AI software. 

While specific lung patterns under assessment remain unclear, the integration of AI-driven analysis promises to enhance diagnostic accuracy and efficiency.

This collaborative effort aims to improve early detection and management of ILDs in RA patients, potentially leading to better outcomes and quality of life for affected individuals.

Other News

Improving IPE diagnosis in the clinical workflow: the role of AI

In July 2023, Erasmus Medical Center’s radiology department kicked off a four-year project focusing on the use of CT to improve diagnosis and treatment outcomes of incidental pulmonary embolism (IPE). The project was made possible through a grant from the NHI (Netherlands Health Institute) and is a collaboration between contextflow and esteemed partners in the Netherlands:

  • Erasmus Medical Center, Department of Radiology in Rotterdam
  • Erasmus School of Health Policy and Management (ESHPM), Department of Health Technology Assessment in Rotterdam
  • Technical University Delft, Department of Imaging Physics in Delft

The project is evolving under the guidance of the dedicated PhD student Erik Kempner at Erasmus University and will explore ways in which machine learning-based technology can be seamlessly blended into workflows to help radiologists and clinicians catch IPEs earlier and more accurately. 

Besides an obvious benefit to patients and radiologists (and a seeming benefit to hospitals and the healthcare system at large) the use of AI in clinical practice has never really been explored for IPE. Therefore, the project will look into the impact of the technological advancement of IPE detection in various settings with the aim of redefining the landscape of radiology and potentially set new benchmarks in efficiency and patient-centered care as they relate to IPE. 

This collaboration shows the power of interdisciplinary cooperation in medical technology innovation. Over the course of the next four years, the involved parties will work on producing results that could be used for setting new standards for radiology and healthcare.

What is IPE and why use AI to detect it?

Pulmonary embolism is a life-threatening condition that requires prompt diagnosis and treatment. Detecting IPE in computed tomography (CT) scans can be challenging, and the project group believes AI can help in improving the accuracy and consistency of IPE detection by analyzing and identifying subtle patterns that may go unnoticed by human observers and by reducing false negatives and false positives. 

The interpretation of medical imaging can be time-consuming, especially in busy healthcare settings. AI algorithms can rapidly analyze images and assist radiologists in the detection of IPE, potentially reducing the time required for diagnosis. 

By providing consistent and reproducible results, AI algorithms can also help reduce inter-observer variability and ensure that the same criteria are applied to every case. This standardization can lead to more reliable diagnoses, enabling better patient management and facilitating research and quality improvement initiatives.

Other News

Blackford and contextflow Announce Commercial Partnership to Bring Comprehensive Chest CT Detection Software to Healthcare Providers
2023-11-16

Edinburgh, Scotland (November 16th, 2023) – Blackford, the pioneering strategic AI platform and solutions provider, and contextflow today announced a commercial partnership to bring contextflow’s ADVANCE Chest CT solution to healthcare professionals.

Under the partnership, contextflow’s innovative technology will be integrated with Blackford’s advanced enterprise AI platform. Blackford provides healthcare professionals access to an extensive portfolio of medical AI solutions designed to drive clinical efficiency and improve patient outcomes. By integrating contextflow’s advanced detection technology into the Blackford platform, Blackford can offer healthcare providers a powerful tool for detecting ILD, COPD and lung cancer on chest CTs.

« Blackford exists to improve the lives of patients and populations – we can do this by providing tailored AI solutions to healthcare providers around the world to help enhance therapy selection and treatment optimisation », said Ben Panter, CEO of Blackford. « We are delighted to partner with contextflow to add their advanced tools for lung disease detection, quantification and monitoring of disease progression to our AI portfolio.” 

contextflow’s CE and UKCA marked technology, ADVANCE Chest CT, offers radiologists comprehensive computer-aided detection support for lung cancer, ILD, and COPD patients. The software detects, visualizes and quantifies nodules and lung disease patterns to enhance the speed and quality of radiology reports. Its upcoming malignancy scoring feature has been shown to not only detect lung cancer sooner but also to reduce both false positives and false negatives (*Adams, Scott J et al., JACR September 2022). 

As contextflow’s Chief Commercial Officer Marcel Wassink puts it, “Successful implementation of lung cancer screening programs will require the use of assistive AI to help with earlier detection and manage the workloads. We also understand that lung cancer is only one of many findings relevant to the patient’s wellbeing, and thus we are proud to offer comprehensive support for chest CT that goes beyond cancer to include ILD, COPD, and in the near future, incidental pulmonary embolism. Our partnership with Blackford will accelerate the adoption of this much-needed AI, increasing its accessibility to radiologists and patients alike.”

About Blackford 

Blackford are pioneers in the radiology AI space, with over a decade of experience working in partnership with leading hospitals and ground-breaking technology providers. We operate as a strategic AI partner, providing access to a tried-and-tested core platform, tailored services, and a portfolio of 100+ applications to help healthcare providers unlock the value of AI and improve patient outcomes. 

Our collaboration and recent arms-length acquisition by Bayer ensures that our customers and partners have the support and long-term security needed to underpin successful AI strategies. 

To learn more about Blackford’s tailored approach to AI solutions visit www.blackfordanalysis.com.  

About contextflow 

contextflow is a spin-off of the Medical University of Vienna (MUW) and European research project KHRESMOI, supported by the Technical University of Vienna (TU). Founded by a team of AI and engineering experts in July 2016, the company has a strong interest in bringing state-of-the-art machine learning techniques to the market e.g. improved emphysema detection and lung segmentation. Its computer-aided detection software ADVANCE Chest CT is CE Marked and available for clinical use within Europe under the new MDR. Visit contextflow.com for more information.

Other News

Always in the picture thanks to AI
2023-09-27

Evangelisches Klinikum Niederrhein introduces contextflow ADVANCE Chest CT in the Pulmonology Department

Lung diseases are among the most common as well as most diverse health problems worldwide. They require precise diagnoses and effective treatment strategies. In this context, artificial intelligence (AI) opens up a promising avenue for detecting a wide variety of disease conditions in affected patients as early as possible. Fanar Othman, head physician at the Clinic for Pulmonary and Bronchial Medicine at Johanniter Hospital Oberhausen, has also discovered the possibilities of deep learning-based technology for himself. He uses the CE certified software contextflow ADVANCE Chest CT to ensure that even when there is a lot to do, the pulmonologist no longer misses anything.

As part of the Lower Rhine Evangelical Hospital and Bethesda Hospital network, the department not only cares for around 3,000 patients a year in its own hospital, but also provides consultative care for three other sites in the western Ruhr region, including Dinslaken and Duisburg. As a former stronghold of the coal and steel industry, the region is also known as the « coal pot ». Particularly among the older generation, the doctors still see many patients whose health was severely affected by their work in the former mines, blast furnaces and factories. As a result, a not insignificant proportion of the medical care provided locally is for occupational lung diseases such as pneumoconiosis, silicosis, asbestosis and, unfortunately, the resulting late effects such as cancer and pleural mesothelioma. 

So there is a lot to do for the total of five pulmonologists under the direction of Fanar Othman. « We have a large catchment area and, simply because of the size of our association, we get to see a large number of rare pathologies in addition to the usual clinical findings, » says the chief physician. « In these cases, it can already become a challenge to make the correct diagnosis and initiate appropriate therapy. » In this context, a single disease may be associated with multiple radiological patterns. Precise characterization is often laborious and examiner-dependent.

Quick access to relevant knowledge

Since last year, contextflow’s AI solution has been providing a remedy for this problem. It takes over the sifting and provision of information from CT examinations that are relevant for diagnostics. The recognition software detects even small changes in the lung parenchyma and relates them to specific diseases. For nodules, it can even show progression. The resulting findings report is generated automatically and is available directly in the PACS viewer within a few minutes. In this way, the tool saves the diagnostician from having to work through thousands of image slices every day, and at the same time, prevents anything important from being overlooked. 

Using an AI system in his department is new territory for Fanar Othman. He was made aware of ADVANCE Chest CT by his physician colleague, the head of radiology, Prof. Dr. Jörg Michael Neuerburg, who has already been using the software successfully for some time. « From the beginning, I liked how affable and user-friendly the application was, » Othman recalls. « You have to take care of practically nothing. The findings generated by the AI are prepared in a simple and clearly understandable way, so you can adopt the results without time-consuming cross-checking. There is not enough time for anything else in daily practice. Everything has to be done in a jiffy. »

Progress controls at the push of a button

When the opportunity arose to take part in a product training course initiated by contextflow, the pulmonologist jumped at the chance. During the online training, he discovered that the software can do a lot more that is valuable for his work: « For example, the AI is able to compare different series of images taken at different points in time. This makes it possible to assess the size development of nodules, which is very important for determining further therapeutics. »

In addition to calculating the diameter in a plane, the system also applies 3D volumetric analysis to evaluate the total mass of a pulmonary nodule. The volumetric measurement method is becoming increasingly important because it offers a more accurate assessment of malignancy risk, or tumor grade, compared to linear measurement, and also helps to better monitor response to therapy – especially when it comes to determining tumor doubling time. This refers to the fact that in most malignant lesions, volume increases first, followed by size.

From the pattern of findings to differential diagnosis

The software solution is also used for texture analysis, e.g. for characterizing parenchymal changes such as ground-glass opacities, reticular pattern or honeycombing. In this context, the distribution of the changes in the lung allows decisive conclusions to be drawn about the underlying clinical picture. However, differential diagnosis is a difficult and complex task due to the sheer number of existing lung pathologies. In addition, it is often the small but subtle differences that matter. Even experienced experts sometimes reach their limits here. « Sometimes it’s difficult to decide with subtle changes in the lower lobe: is this an emphysema bullae or honeycombing? The AI can differentiate such structures incredibly well, » Fanar Othman is pleased to report.

What the Oberhausen head physician also likes is that the structural parenchymal changes can be displayed in percentage form with the help of ADVANCE Chest CT: « When a check-up is due, you can’t always tell with the naked eye whether it has improved after therapy or not. If the response is not that great, it’s helpful to know by what percentage it ultimately got better. A lot of patients ask us explicitly about that, too. » So such clear feedback can have a positive effect on doctor-patient communication.

Overall, the expert is very pleased with how AI has been able to reduce the workload in his department over the past year while increasing diagnostic accuracy. He says his team is also enthusiastic and has already asked him – or rather the AI – for advice in one or two tricky cases. Othman is not worried that a machine could one day outstrip him: « I see it as an opportunity – especially in view of the fact that there is a shortage of staff anyway. AI is therefore a helpful support in the diagnostic process that makes a lot of things easier. In the end, it is still us who bring it all together with the laboratory values, clinical data and samples and come to a decision. That remains the fine art and continues to be the physician’s task. »

Other News

Improving lung segmentation for higher coverage of clinically-relevant findings: a contextflow whitepaper

This whitepaper was developed by contextflow’s Scientific and R&D teams to explain our approach behind lung segmentation. The full text is listed below. For a pdf copy, click here.

Abstract

Automatic lung segmentation in computed tomography (CT) is a critical component of computational medical image analysis. While many approaches exist, it remains a challenging problem for patients whose lungs are affected by disease. Here we describe and evaluate a lung segmentation algorithm that yields high accuracy despite disease patterns thanks to a 3D architecture and diverse training data set. We compare our algorithm with the established state-of-the-art algorithm.

Introduction

Automatic lung segmentation in chest CT scans is relevant for several reasons. It serves as a stepping stone for additional lung-specific analysis such as nodule detection or disease pattern segmentation.  Focusing on the lung area helps to improve execution speed of dependent components and to disambiguate any finding in adjacent areas. By itself, lung segmentation yields a measurement of the lung volumetry, which can be meaningful, and is necessary to assess the proportion of disease patterns covering lung tissue.

The existing computer-assisted solutions for lung segmentation make use of a wide range of approaches with different levels of complexity pertaining to various use cases, such as lung cancer screening, COVID-19, or COPD assessment (Hu et al., 2001; Armato et al., 2004; Sluimer et al., 2005; Mansoor et al., 2015; Shamim et al., 2022).

At contextflow, we segment the lungs (chest cavity) by their most inclusive definition: we include pleural cavity patterns such as pneumothorax and effusion in our segmentation, even though they are technically not part of the lungs, and designate them accordingly, since they are relevant for comprehensive lung reporting. Our algorithms segment many pathological patterns if present, including pleural cavity patterns such as pneumothorax and effusion, using this inclusive lung segmentation as a starting point. In practice, lung segmentation needs to be simultaneously fast (because it is only one step in a host of different processes to analyze the lungs) and robust, as our product focuses on the detection and quantification of lung abnormalities, including comparison with former studies, to automatically detect (major) pathological changes.

A 3D approach towards robust lung segmentation in CT

To achieve robust lung segmentation, we first focused on the construction of an adequate database. We selected cases based on their clinical content, trying to cover as many different lung pathologies and anomalies as possible to ensure maximum diversity and extensive pathologic pattern coverage (see annex for details). We also made sure to cover a wide variety of acquisition protocols, since there is a large technical heterogeneity regarding CT vendors and acquisition parameters from different institutions around the world. In these cases, the lungs were manually annotated by expert radiologists. The annotation process consisted of a loop of annotations and quality checks until the annotation passed the quality check.

Additionally we worked on the choice of a relevant model architecture. We opted for a 3D-UNet-based architecture. One of the advantages of a model using 3D operations is that 3D information can disambiguate findings hard to discern in a 2D slice. For example, it can be hard to differentiate dense pathological patterns like pleural effusion from structures with soft tissue density like the liver on one slice only. In contrast to 2D models, the 3D model is expected to perform better in these cases, as it uses 3D context to make a prediction. Another advantage is that the model produces a segmentation that is consistent axially by design, contrary to a 2D model that processes each slice independently. It was also designed to be faster, finding a compromise between input size, number of parameters and performance.

Comparative evaluation of lung segmentation accuracy

In order to assess the performance of the developed model, we compared it with a state-of-the-art, publicly-available* model (lungmask) for lung segmentation as a baseline (Hofmanninger et al., 2020). The public model is ranked amongst the best on the public challenge LOLA** (LObe and Lung Analysis) and is frequently used for research purposes for organ segmentation. The model adopts a 2D approach for model training.  

We compared the performance between contextflow 2.0 and lungmask on 1722 scans that were sampled from clinical routine without restriction on age, sex, indication or pathology, and that cover findings such as cancer, emphysema, effusion, atelectasis, fibrosis and other pulmonary diseases. For 1694 cases, at least one Region-Of-Interest (ROI) containing a pulmonary pathological pattern is available, while 120 cases have a pixel-wise segmentation mask. All annotations were created by expert radiologists.

Results: segmentation accuracy evaluated by Dice coefficient

We use the widely-adopted Dice coefficient to compare how well the two models’ predictions overlap with an annotation done by a radiologist. The Dice score ranges between 0 (if there is no overlap) and 1 (complete overlap). We report the Dice coefficient for the whole lungs, the right lung and the left lung, measured on the test set in Table 1. We can see that both models achieve very high Dice on average. However, our method tends to achieve higher Dice with a lower standard deviation, which hints to a more robust segmentation performance over the diverse test dataset.

Results: focusing on regions containing disease patterns

To better assess the difference in performance between the two models, we introduce a metric called Region-Of-Interest (ROI) coverage. ROIs are labeled areas that contain a finding. Here, we consider rectangular ROIs on axial slices containing pulmonary pathological patterns. We define ROI coverage as the percentage of ROI centroids that the lung segmentation is able to cover, meaning that the center of the ROI is included in the segmentation. This metric assesses how accurate the lung segmentation model is, despite the presence of pulmonary diseases. This is crucial in its assessment as a tool to support diagnosis and assessment of lung imaging data. 

Annotating ROIs instead of a pixel-wise annotation of pathological patterns is beneficial because it is more time-efficient. In addition, some diffuse lung pathologies are difficult to annotate on a pixel-level even for expert radiologists, so coarsely annotating the entire affected region is more feasible. For this analysis we use ROIs that were created by radiologists on data that cover a wide range of pulmonary pathological patterns. 

*https://github.com/JoHof/lungmask **https://lola11.grand-challenge.org/

We report the ROI coverage figures in Table 2. The model developed by contextflow performs better overall with a coverage of 98.5% of ROIs compared to 96.5% for the open-source model. This effect is especially pronounced for patterns like masses (87.9% vs. 58.6%) and effusion (95.3% vs. 85.6%). This demonstrates that our model covers the lung pathologies more consistently than the open-source model.

Evaluating execution time

In terms of execution time, our model runs faster than the open-source one. We report the numbers for CPU execution on 8 threads for different sizes of CT scans in Table 3. By design, the open-source algorithm’s execution time directly depends on the number of slices in the input CT whereas the new model depends on the FOV (Field Of View) of the input scan. The developed model can generate lung segmentation much faster than the open-source model.

Summary

In this article we describe how we developed and evaluated a new lung segmentation algorithm. We compared it to an open-source, state-of-the-art solution over which we showed superiority with a conventional metric (Dice coefficient) and with a new clinical-finding-based metric (ROI coverage), showing a higher robustness to a wide variety of cases. Our developed solution also runs faster, making it scalable in terms of the number of scans we can process. Thus, our solution better meets the requirements for usage in clinical practice.

Annex

List of the patterns/pathologies we aim to cover with lung segmentation:

Airway wall thickening, Atelectasis, Bronchiectasis, Bulla, Consolidation, Cyst, Effusion, Emphysema, Ground glass opacification, Honeycombing, Mass, Mosaic attenuation pattern, Nodular pattern, Nodule, Pneumothorax, Pulmonary cavity, Reticular pattern, Tree-in-bud, Fibrosis, Interlobular septal thickening.

Literature

Hofmanninger J, Prayer F, Pan J, Röhrich S, Prosch H, Langs G. Automatic lung segmentation in routine imaging is primarily a data diversity problem, not a methodology problem. European Radiology Experimental. 2020 Dec;4(1):1-3.

Mansoor A, Bagci U, Foster B, Xu Z, Papadakis GZ, Folio LR, Udupa JK, Mollura DJ. Segmentation and image analysis of abnormal lungs at CT: current approaches, challenges, and future trends. Radiographics. 2015 Jul;35(4):1056-76.

Shamim S, Awan MJ, Mohd Zain A, Naseem U, Mohammed MA, Garcia-Zapirain B. Automatic COVID-19 lung infection segmentation through modified unet model. Journal of healthcare engineering. 2022 Apr 11;2022.

Armato III SG, Sensakovic WF. Automated lung segmentation for thoracic CT: impact on computer-aided diagnosis1. Academic Radiology. 2004 Sep 1;11(9):1011-21.

Hu S, Hoffman EA, Reinhardt JM. Automatic lung segmentation for accurate quantitation of volumetric X-ray CT images. IEEE transactions on medical imaging. 2001 Jun;20(6):490-8.

Sluimer I, Prokop M, Van Ginneken B. Toward automated segmentation of the pathological lung in CT. IEEE transactions on medical imaging. 2005 Aug 1;24(8):1025-38.

Other News

Plus qu’une simple dĂ©tection de nodules…
2023-08-31

Les radiologues du groupe ImapĂ´le Lyon-Villeurbanne bĂ©nĂ©ficient du support de l’IA de contextflow pour dĂ©tecter les anomalies pulmonaires.

L’Imagerie MĂ©dicale, pilier central de la mĂ©decine moderne, est devenue incontournable aujourd’hui. VĂ©ritable pierre angulaire du diagnostic patient, elle le sera encore plus demain. TournĂ© vers le futur, ImapĂ´le Lyon–Villeurbanne, le service d’Imagerie MĂ©dicale du plus grand Ă©tablissement de santĂ© privĂ© de la rĂ©gion lyonnaise, le MĂ©dipĂ´le Lyon-Villeurbanne, s’inscrit pleinement dans cette dĂ©marche et, dans cette optique, a intĂ©grĂ© contextflow ADVANCE Chest CT dans sa routine clinique. Pour mieux comprendre les motivations de l’adoption de contextflow, les critères de sĂ©lection, l’expĂ©rience de dĂ©ploiement et les bĂ©nĂ©fices observĂ©s, nous avons rencontrĂ© Samir Lounis, CEO & General Manager chez ImaOne. Il dirige et pilote l’activitĂ© du groupe ImapĂ´le.

Bonjour. Pourriez- prĂ©senter ImapĂ´le Lyon-Villeurbanne ?

Le groupe ImapĂ´le est composĂ© de 10 radiologues. Ils sont chargĂ©s d’interprĂ©ter la production d’images mĂ©dicales de deux sites : Le MĂ©dipĂ´le Lyon Villeurbanne, le plus grand hĂ´pital privĂ© d’Europe avec plus de 850 lits, et le PĂ´le MĂ©dical d’OL VallĂ©e Ă  DĂ©cines. 

Ces deux sites réalisent plus de 800 examens par jour et environ 170 000 examens par an.

Notre Ă©quipe gère cette charge de travail, et nous sommes fortement engagĂ©s dans l’utilisation de solutions d’intelligence artificielle.

Nous croyons fermement en leur potentiel pour soutenir nos radiologues et les transformer en « radiologues augmentĂ©s » grâce Ă  l’IA, afin d’une part, pouvoir fournir des diagnostics plus prĂ©cis et d’autre part, pouvoir gĂ©rer un volume d’examens beaucoup plus important.

Quelles ont Ă©tĂ© les motivations et les facteurs dĂ©terminants qui ont conduit votre dĂ©partement de radiologie Ă  envisager l’adoption de l’application contextflow dans votre pratique clinique Ă  ImapĂ´le Lyon-Villeurbanne ?

Au sein d’ImapĂ´le, une part importante de notre activitĂ© concerne la cancĂ©rologie, environ un tiers. Cela implique que nous devons interprĂ©ter un grand nombre d’images, en particulier des scanners, pour le suivi ou la dĂ©tection de pathologies chez nos patients.

Dans ce contexte, nous avons cherchĂ© une solution qui puisse nous aider Ă  dĂ©pister les lĂ©sions et Ă  suivre leur Ă©volution en termes de taille, notamment en ce qui concerne la croissance ou la diminution des lĂ©sions. 

Mesurer une lĂ©sion est une tâche complexe et sujette Ă  de nombreuses variations. Cela dĂ©pend du plan de coupe utilisĂ© pour la mesure et de l’inclinaison de la lĂ©sion elle-mĂŞme, par exemple dans le cas d’une lĂ©sion pulmonaire.

De nombreux facteurs entrent en jeu. Nous souhaitions donc que cette mesure puisse  ĂŞtre volumĂ©trique et reproductible.

Partant de tous ces Ă©lĂ©ments, nous avons dĂ©cidĂ© d’utiliser un logiciel. Nous sommes Ă©galement impliquĂ©s dans un programme de dĂ©pistage du cancer du poumon au sein du MĂ©dipĂ´le.

En France, des Ă©tudes sont actuellement menĂ©es dans ce domaine. Au sein d’ImapĂ´le Lyon Villeurbanne, nous disposons d’un dĂ©partement de pneumologie important et nous avons voulu proposer une solution reproductible, efficace et indĂ©pendante de l’opĂ©rateur qui se trouve derrière l’Ă©cran.

Parmi les différentes solutions que nous avions identifiées, le logiciel de contextflow, qui figurait parmi les trois finalistes, nous a paru être le plus performant et le plus complet, répondant ainsi à nos besoins.

Quels ont Ă©tĂ© les critères de sĂ©lection et les Ă©valuations prĂ©liminaires effectuĂ©s avant de choisir l’application contextflow pour votre dĂ©partement de radiologie ?

Nous avons explorĂ© le marchĂ© pour rechercher des solutions adaptĂ©es Ă  notre mission, qui consiste Ă  dĂ©tecter et suivre les lĂ©sions pulmonaires dans le temps, tout en tenant compte d’autres critères tels que le dĂ©lai de retour des rĂ©sultats. Il Ă©tait essentiel que l’analyse puisse ĂŞtre rĂ©alisĂ©e rapidement, avec un retour dans le PACS et vers le mĂ©decin dans un dĂ©lai de l’ordre d’environ cinq minutes, afin de maintenir notre flux de prise en charge des patients. Après avoir comparĂ© contextflow Ă  d’autres fournisseurs, nous avons choisi contextflow parce qu’il offre plus que la simple dĂ©tection de nodules et qu’il s’intègre très bien dans notre PACS. 

L’autre point qui a Ă©tĂ© un « game changer Â» dans notre choix, c’est la capacitĂ© de contextflow Ă  pouvoir se projeter et proposer, dans un avenir proche, la dĂ©tection des embolies pulmonaires fortuites.

Nous disposons ainsi d’un outil capable de rĂ©pondre Ă  plusieurs de nos problĂ©matiques, notamment en cancĂ©rologie, pour le suivi Ă  long terme, l’analyse et la reproductibilitĂ© des mesures, ainsi que l’analyse et la quantification d’autres pathologies pulmonaires comme l’emphysème.

Pouvez-vous retracer l’historique de l’intĂ©gration de l’application logicielle contextflow dans votre dĂ©partement de radiologie, depuis sa mise en place jusqu’Ă  aujourd’hui ?

Les Ă©quipes techniques de contextflow ont Ă©tĂ© extrĂŞmement rĂ©actives. Nous avons pu les mettre en relation avec nos Ă©quipes IT et PACS, et les trois Ă©quipes ont rapidement rĂ©ussi Ă  installer la machine virtuelle pour effectuer tous les tests. Nous avions un dĂ©lai assez court pour atteindre un niveau d’intĂ©gration qui nous permettrait une utilisation transparente, sans que le mĂ©decin ne quitte son environnement. C’Ă©tait un Ă©lĂ©ment clĂ©. 

La solution contextflow est entièrement intĂ©grĂ©e dans notre flux de travail. Les envois se font automatiquement de la modalitĂ© vers la solution d’IA, et les rĂ©sultats sont renvoyĂ©s dans le PACS. Ainsi, lorsque le mĂ©decin prend connaissance de l’examen, il dispose des rĂ©sultats de contextflow. 

L’accompagnement technique et le support des Ă©quipes lors du dĂ©marrage ont Ă©tĂ© extrĂŞmement rĂ©actifs, ce qui est très positif pour contextflow. Le niveau d’intĂ©gration avec notre PACS est très Ă©levĂ©.

Quelles ont Ă©tĂ© les Ă©tapes clĂ©s du processus de mise en Ĺ“uvre de l’application contextflow dans votre dĂ©partement de radiologie en termes de formation, de personnalisation et de gestion du changement ?

En ce qui concerne contextflow, la formation s’est dĂ©roulĂ©e en deux Ă©tapes. Tout d’abord, il y a eu une formation prĂ©liminaire qui consistait essentiellement en une prĂ©sentation du produit, puis une deuxième partie oĂą l’application du produit a Ă©tĂ© prĂ©sentĂ©e. Nous avons examinĂ© un cas concret et analysĂ© les rĂ©sultats obtenus. Cette formation a Ă©tĂ© dispensĂ©e en visioconfĂ©rence Ă  diffĂ©rentes dates, afin de convenir aux disponibilitĂ©s des diffĂ©rents mĂ©decins impliquĂ©s dans le projet, ce qui a Ă©tĂ© très apprĂ©ciĂ©. 

Nous avons pu dĂ©marrer l’utilisation de la solution avec un accompagnement Ă  distance, si nĂ©cessaire, tant de la part de l’Ă©quipe de contextflow que de notre Ă©quipe IT et PACS. Tout s’est très bien passĂ©.

Après environ un mois d’utilisation, contextflow nous a proposĂ© d’accompagner nos Ă©quipes mĂ©dicales sur site, afin de bĂ©nĂ©ficier de leur expĂ©rience. Cela permettrait Ă©galement d’apporter des ajustements personnalisĂ©s Ă  l’utilisation du produit et de leur faire dĂ©couvrir des fonctionnalitĂ©s qu’ils n’auraient peut-ĂŞtre pas saisies lors des premières formations.

Cet accompagnement est toujours en cours. Nous aurons un technicien de l’application qui viendra la semaine prochaine pour rencontrer nos Ă©quipes. Il pourra Ă©galement revenir si les mĂ©decins en ressentent le besoin. Maintenant, en ce qui concerne contextflow, le gros avantage est qu’ils ne se limitent pas Ă  la dĂ©tection et au suivi des nodules dans le temps, ce qui est essentiel et très important pour le dĂ©pistage du cancer du poumon, par exemple, et le suivi des fumeurs. Mais, au contraire, il permet aussi d’analyser d’autres pathologies, notamment l’emphysème, ce qui est une quantification primordiale, surtout dans une perspective d’avenir.

Ă€ l’avenir, il permettra Ă©galement de dĂ©tecter les embolies pulmonaires fortuites, un diagnostic crucial en radiologie. Au MedipĂ´le Lyon Villeurbanne, le plus grand service d’urgence privĂ© de France, nous recevons environ 250 patients par jour, dont la moitiĂ© environ passe par le service d’imagerie, et beaucoup d’entre eux bĂ©nĂ©ficient d’un scanner. 

Nous sommes très heureux d’ĂŞtre soutenus par un logiciel de dĂ©tection basĂ© sur l’IA pour ces 250 patients, car la charge de travail des radiologues ne cesse d’augmenter. On se retrouve avec 400 Ă  500 images Ă  analyser par patient. C’est donc une bonne chose d’avoir une intelligence artificielle qui peut vous accompagner dans cette phase de dĂ©tection et mettre en Ă©vidence les zones Ă  risque.

C’est pourquoi la capacitĂ© de contextflow Ă  prendre en charge de nouvelles pathologies Ă  analyser a Ă©galement Ă©tĂ© un facteur dĂ©terminant dans le choix de la solution.

Comment l’application contextflow a-t-elle Ă©tĂ© intĂ©grĂ©e dans le système d’information radiologique existant Ă  l’ImapĂ´le, pour assurer la compatibilitĂ©, l’interopĂ©rabilitĂ© et la synchronisation des donnĂ©es cliniques ?

Ce qui est le plus important, c’est toute la phase prĂ©paratoire d’intĂ©gration. Cela nĂ©cessite un travail considĂ©rable qui s’Ă©tend sur quelques semaines, pendant lesquelles tous les acteurs impliquĂ©s peuvent Ă©changer sur les contraintes techniques. L’utilisateur final, notamment le mĂ©decin, peut exprimer ses attentes et objectifs, en particulier sur la manière dont il souhaite retrouver les rĂ©sultats dans son flux de travail.

La rĂ©ussite de cette Ă©tape se traduit par le fait que, finalement, le mĂ©decin n’a pas besoin de quitter son environnement de travail habituel. Il ouvre son PACS et y travaille – les rĂ©sultats contextuels sont lĂ  sans avoir Ă  ouvrir un nouveau programme ou Ă  changer de fenĂŞtre. L’utilisateur n’est pas confrontĂ© Ă  une interface totalement diffĂ©rente. En outre, les rĂ©sultats de contextflow peuvent ĂŞtre adaptĂ©s par le radiologue en cas de dĂ©saccord, par exemple dans le cas d’un nodule faussement positif.

Plus on parvient Ă  apporter de transparence dans l’utilisation de contextflow au sein du PACS, plus l’intĂ©gration est rĂ©ussie et plus le mĂ©decin l’utilisera rĂ©gulièrement.

Comment mesurez-vous la satisfaction globale des utilisateurs de l’application contextflow au sein de votre dĂ©partement de radiologie en termes de convivialitĂ©, de performance et de contribution Ă  la prise de dĂ©cision clinique ?

Chaque clic coĂ»te du temps et de l’argent aux radiologues, c’est pourquoi il Ă©tait prioritaire pour nous d’avoir une solution d’IA bien intĂ©grĂ©e avec le moins de clics possible.

C’est un Ă©lĂ©ment clĂ© dans l’utilisation de la solution.

Si l’on propose Ă  un mĂ©decin, qui est dĂ©jĂ  très occupĂ© et soumis Ă  une charge mentale importante liĂ©e Ă  l’analyse mĂ©dicale, des contraintes supplĂ©mentaires telles que de devoir naviguer entre diffĂ©rentes fenĂŞtres ou dossiers, il est certain que la solution ne sera pas utilisĂ©e. Il peut l’essayer une ou deux fois, mais rapidement, il se rendra compte que cela lui prendra du temps et il finira par se dire : « Je vais m’en passer » et il n’y reviendra plus.

En revanche, si l’on automatise l’ensemble du processus, c’est-Ă -dire que les images sont acquises par le scanner, envoyĂ©es automatiquement Ă  l’IA de contextflow pour analyse, que les rĂ©sultats sont renvoyĂ©s au mĂ©decin dans son environnement de travail et qu’il n’a plus qu’Ă  valider ou invalider les rĂ©sultats de l’IA pour les intĂ©grer dans son compte rendu, alors le nombre de clics est rĂ©duit au minimum.

Cela permet une convivialitĂ© très apprĂ©ciable. De plus, le degrĂ© d’intĂ©gration de la solution dans notre PACS est extrĂŞmement poussĂ©, ce qui rend notre dĂ©pendance Ă  la solution encore plus bĂ©nĂ©fique.

Quels sont les indicateurs de performance et les critères d’Ă©valuation utilisĂ©s pour mesurer l’efficacitĂ© et l’impact clinique de l’application contextflow dans votre dĂ©partement de radiologie ?

Au niveau de nos prescripteurs, nous avons une grande quantitĂ© de pneumologues et de pneumologues-oncologues au sein de notre pĂ´le. Nous avons donc une Ă©quipe de mĂ©decins spĂ©cialisĂ©s dans les affections pulmonaires. Ils ont Ă©tĂ© très satisfaits de l’application contextflow Ă  un niveau avancĂ© de l’analyse pulmonaire, notamment ici Ă  Lyon. Ils ont particulièrement apprĂ©ciĂ© la capacitĂ© de dĂ©tecter et de suivre les pathologies pulmonaires dans le temps, ainsi que la possibilitĂ© de comparer les rĂ©sultats.

Lorsqu’un patient est envoyĂ© pour une Ă©valuation après trois ou six mois de chimiothĂ©rapie, il est extrĂŞmement prĂ©cieux de disposer d’un outil tel que contextflow pour assurer la reproductibilitĂ© de l’analyse et des mesures. Cela a rĂ©ellement Ă©tĂ© un atout majeur pour nos mĂ©decins prescripteurs.

Aujourd’hui, l’utilisation de l’outil est demandĂ©e presque systĂ©matiquement par les mĂ©decins prescripteurs, car ils se sont habituĂ©s Ă  son utilisation. Ils orientent donc leurs patients vers notre centre afin que leurs examens puissent bĂ©nĂ©ficier de cette analyse complĂ©mentaire en interne. En ce qui concerne nos propres mĂ©decins, comme je l’ai mentionnĂ© prĂ©cĂ©demment, plus l’interface dans le flux de travail est transparente, plus elle est utilisĂ©e.

Ainsi, Ă  l’heure actuelle, 100 % des scanners pulmonaires passent par contextflow, bĂ©nĂ©ficiant ainsi d’une double analyse Ă  la fois mĂ©dicale et assistĂ©e par IA. 

Les retours que nous avons obtenus en discutant avec les mĂ©decins montrent clairement que l’outil a Ă©tĂ© adoptĂ© et utilisĂ© de la mĂŞme manière que d’autres outils d’IA que nous avons dans notre parc. Nous avons une Ă©quipe de mĂ©decins prĂ©curseurs dans l’adoption de l’IA, et ils sont conscients des avantages que peut leur apporter l’intelligence artificielle.


Comment aimeriez-vous que la solution contextflow Ă©volue Ă  l’avenir ?

J’aimerais beaucoup que contextflow apporte une solution pour la dĂ©tection d’embolie pulmonaire, car c’est un besoin rĂ©el pour tous les services d’imagerie mĂ©dicale d’urgence. Cela aidera considĂ©rablement les urgentistes et les mĂ©decins, accĂ©lĂ©rant ainsi la prise en charge des patients et rĂ©duisant le temps perdu lors de l’analyse. L’Ă©quipe de contextflow a pris nos remarques au sĂ©rieux et travaille dans ce sens.

Nous sommes très satisfaits de la solution actuelle. contextflow amĂ©liore continuellement la spĂ©cificitĂ© et la sensibilitĂ© de l’algorithme de dĂ©tection des nodules. Ensuite, nous envisageons d’Ă©tendre les possibilitĂ©s d’analyse des pathologies thoraciques, pas seulement pour les poumons, mais Ă©galement pour les vaisseaux et le cĹ“ur, ainsi que pour tous les organes situĂ©s dans la rĂ©gion thoracique. 

Si Ă  l’avenir, contextflow pouvait Ă©galement fournir une analyse pour ces Ă©lĂ©ments, ce serait un vĂ©ritable atout.

L’IA est considĂ©rĂ©e comme l’avenir, mais elle suscite Ă©galement des craintes. En tant qu’utilisateur, vous pouvez ĂŞtre Ă  la fois enthousiaste et rĂ©ticent vis-Ă -vis de certaines applications. Cependant, en tant qu’ĂŞtre humain, vous ĂŞtes conscient des implications et des limites de l’IA. Cela peut ouvrir la porte Ă  diverses possibilitĂ©s. Quelle est votre opinion sur ce sujet ?

Dans notre monde oĂą tout Ă©volue rapidement, bien plus rapidement que la capacitĂ© d’adaptation d’un ĂŞtre humain, les donnĂ©es, qu’elles soient mĂ©dicales ou non mĂ©dicales, sont multipliĂ©es de façon exponentielle. L’analyse de ces donnĂ©es doit donc Ă©galement ĂŞtre multipliĂ©e.

Cependant, les ĂŞtres humains n’ont pas la capacitĂ© d’adaptation instantanĂ©e Ă  un tel flux de donnĂ©es. Peut-ĂŞtre serons-nous capables de le faire dans X annĂ©es, mais aujourd’hui, nous avons besoin de solutions qui nous accompagnent dans la gestion de ce flux de donnĂ©es. Il est crucial de trier et d’analyser ces donnĂ©es et informations.

En ce qui me concerne, je peux dire que l’IA peut susciter des inquiĂ©tudes sur certains aspects. Cependant, je pense que l’IA ne remplacera pas les mĂ©decins. C’est un fait que j’ai expĂ©rimentĂ© en utilisant ces solutions depuis plusieurs annĂ©es et en les observant dans notre pratique.

En revanche, ce qui est certain, c’est que le mĂ©decin qui utilise l’IA remplacera le mĂ©decin qui n’utilise pas cette technologie. C’est lĂ  que rĂ©side le vĂ©ritable enjeu. Le monde a Ă©voluĂ© plus rapidement que la capacitĂ© d’adaptation de l’ĂŞtre humain. Il a donc besoin d’outils technologiques. Ainsi, le mĂ©decin qui intègre l’IA dans sa pratique surpassera le mĂ©decin « tout court Â».

Other News

More information and higher diagnostic reliability, thanks to AI
2023-07-21

Isala overcomes daily challenges with contextflow ADVANCE Chest CT

Health economists predict that the number of patients in Western Europe will double in the next 20 to 25 years. This will of course affect radiology, which will have to prepare for a corresponding increase in the number of examinations and findings. « If the predictions come true, we will have to become more efficient in what we do – as I do not expect the same growth in the number of radiologists. I see artificial intelligence (AI) as part of the possible solution. This applies not only to radiology, but to all activities along the care process, » says Dr. Martijn F. Boomsma, Radiologist at Isala in Zwolle. The Isala hospital group also operates smaller facilities in Meppel, Steenwijk, Kampen and Heerde. The group has a total of 1,200 beds and is one of the largest non-academic teaching hospitals in the Netherlands. The department of Medical Imaging at Isala examines over 1,200 radiological examinations per day.

The Dutch Radiological Society has also defined AI as one of the four most important developments for the next decade, and indeed radiology is already a pioneer in the application of this technology. And that’s a good thing, says Dr. Boomsma: « AI, in combination with an experienced radiologist, increases diagnostic accuracy because it can effectively support and relieve radiologists in certain aspects. » However, clinics and manufacturers would have to prove that the algorithms have a concrete positive impact on health outcomes. This could greatly improve clinical adoption as it would make a clear case for reimbursement for AI and getting AI into national guidelines. Dr. Boomsma believes his discipline is on the right track, even if it still faces a number of hurdles.

Committed partnership at eye level

The department of Medical Imaging has been using diagnostic AI applications for four years and has been using contextflow ADVANCE Chest CT since the end of 2022. Isala runs the solution on its own servers and has integrated it with its image data management system (PACS) from Sectra.

Implementing the AI algorithms was not a plug-and-play process. The hurdle was not only the vendors, but also internal processes. « We had to convince several parties and get the go-ahead from many echelons before we could start. It took a year before the application was really ready for operation, fully integrated, reliable, and with an uptime of 97 percent. The technical integration was then very simple and straightforward, » says Dr. Boomsma. This process requires a lot of commitment and perseverance from everyone involved. But it is also the point at which trust is built. « This is where true partnership shows itself, and we are still experiencing this with contextflow, » the radiologist is pleased to say. 

Dr. Boomsma also notes contextflow’s effort to continuously develop its solution in close cooperation with its users in order to optimize the workflow and thus increase diagnostic value. « This was also a decisive reason for us to choose contextflow. We see a high level of professionalism and agility, as well as the company’s vision to get the best out of AI in thoracic imaging, » he reports. This is also evident in their day-to-day interactions. « Employees respond promptly to inquiries and problems by phone or email. To this end, they always think in terms of solutions and work to solve problems as quickly as possible, » the radiologist elaborates. ADVANCE Chest CT itself stands out because it can be operated without much training. « With a little practice, you can use the software very quickly; it’s user-friendly. But it also changes the way you look at things, » Dr. Boomsma says.

Valuable support for the findings

Dr. Boomsma has developed his own approach to using the AI software. First, he looks at the key images and obtains a global overview. Then he reads the scan, incorporating the referring physician’s specific questions into the findings and preparing his report. « ADVANCE Chest CT helps me identify and quantify nodules. This allows me to clearly identify whether the disease is progressive or stable. Of course, I can also discard or change individual results I don’t consider relevant, as they are false positives or do not relate to the specific question, » says Dr. Boomsma, explaining his workflow. Not only does he use the AI for pulmonary nodules, but also for the detection and quantification of emphysema.

Meanwhile, ADVANCE Chest CT is an important support for reporting at Isala. « On an CT image without contrast, it is very difficult to find a four-millimeter lesion in the perihilar region. But the system reliably shows it to me. It allows me to make sure I haven’t missed anything. It also helps us in our daily work. For example, it is reassuring to know that the AI is always by your side during a nighttime emergency scan and to be sure that everything important can be reported,” says Dr. Boomsma. He also sees the potential to speed up the reporting of findings, citing scans without significant findings as an example. The algorithm can mark these as such, so that the radiologist only has to check them once and can then concentrate on more complex cases.

More than other AI algorithms

« ADVANCE Chest CT gives me much more information than AI solutions from other vendors. It detects and quantifies nodules, emphysema and also fibrosis. The precise information on the extent of manifestation of suspected pathology adds real value to the findings because it can be indicative and correlate with the patient’s condition and  may guide the need for therapy, » emphasizes Dr. Boomsma. Consistency of findings in general remains a challenge, due to different scan settings, inspiration etc. He highlights ADVANCE Chest CT’s SEARCH feature as another unique selling point. With a single mouse click, an overview of similar cases opens from an extensive database, which radiologists can use to support their diagnosis.

The TIMELINE module is a further facilitator. It clearly visualises the changes in the detected nodules over time showing the percentage of growth as well as the time of volume doubling. This is particularly helpful when preparing for tumour boards and multidisciplinary meetings. The integration with the Sectra PACS gives the potential to seamlessly incorporate the results into the report.

Other News

Radiology Symposium Mainz returns for a 2nd year

An impressive crowd at this year’s Radiology Symposium Mainz! For a second year running, we gathered at the Bootshaus Mainz at the end of June to discuss current radiology AI topics.

Thank you to our fabulous radiology speakers & partners, starting with host Prof. Dr. med. Peter Mildenberger from University Medical Center Mainz. Univ.-Prof. Dr. med. Christoph DĂĽber, Prof. Dr. med. Mike Notohamiprodjo, Elodie Weber, Erwin Krikken, Karin Klein, Marcel Wassink, Mark Rawanschad, PD Dr. Christian Elsner, Florian Brandt, Knut Dietrich-Thiel, Bernd SchĂĽtze, Alex Lemm, Barbara Lampl, PD Dr. Daniel Pinto dos Santos, Prof. Dr. med. Elmar Kotter, medavis GmbH, EIZO Healthcare, DFC-SYSTEMS GmbH.

We would also like to thank our friends at Sectra for their continued collaboration!

Hope to see you again next year!

Other News