Quality assurance of computer-aided detection and diagnosis in colonoscopy

Vinsard, Daniela Guerrero; Mori, Yuichi; Misawa, Masashi; Kudo, Shin Ei; Rastogi, Amit; Bağcı, Ulaş; Rex, Douglas K.; Wallace, Michael B.

doi:10.1016/j.gie.2019.03.019

Cited by 107 publications

(79 citation statements)

References 82 publications

(115 reference statements)

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…In the near future an important role for artificial intelligence (AI) in optical detection and characterization of diminutive polyps is foreseen, thus reducing or even eliminating endoscopist inter-observer variability. Several computer-aided detection and characterization systems and algorithms are being developed with promising preliminary data such as a NPV for identification and classification of diminutive rectosigmoid adenomas ranging from 91.5 % to 97 % [35][36][37][38]. More extensive research in larger clinical trial settings is necessary to confirm and expand on these results.…”

Section: E260mentioning

confidence: 99%

Optical diagnosis of diminutive polyps in the Dutch Bowel Cancer Screening Program: Are we ready to start?

et al. 2020

View full text Add to dashboard Cite

w.vandewetering@maastrichtuniversity.nl ABSTR AC T Background and study aims Implementation of optical diagnosis of diminutive polyps may potentially increase the efficacy and cost-effectiveness of colonoscopies. To adopt such strategy in clinical practice, the Preservation and Incorporation of Valuable endoscopic Innovations (PIVI) thresholds provide the basis to be met: ≥ 90 % negative predictive value (NPV) for diagnosis of adenomatous histology and ≥ 90 % agreement on surveillance intervals. We evaluated this within the Dutch Bowel Cancer Screening Program (BCSP). Patients and methods Endoscopic and histological datawere collected from participants of the national bowel cancer screening program with an unfavorable fecal immunochemical test referred for colonoscopy between February 2014 and August 2015 at four endoscopy centers. The "resect and discard" scenario was studied, resecting diminutive polyps without histological evaluation. Agreement between optical diagnosis and histological diagnosis was measured for surveillance intervals according to Dutch, European and American post-polypectomy surveillance guideline.Results Fifteen certified endoscopists participated in this study and included 3028 diminutive polyps. In 2,330 patients both optical and histological diagnosis were available. Optical diagnosis of diminutive polyps showed NPV of 84 % (95 % CI 80-87) for adenomatous histology in the rectosigmoid. Applying the 'resect and discard' strategy resulted in 90.6 %, 91.2 %, 90.9 % agreement on surveillance intervals for the Dutch, European and American guideline respectively.Conclusion Our data representing current clinical practice in the Dutch BCSP practice on optical diagnosis of diminutive polyps showed that accuracy of predicting histology remains challenging, and risk of incorrect optical diagnosis is still significant. Therefore, it is too early to safely implement these strategies.

show abstract

Section: E260mentioning

confidence: 99%

Optical diagnosis of diminutive polyps in the Dutch Bowel Cancer Screening Program: Are we ready to start?

et al. 2020

View full text Add to dashboard Cite

show abstract

“…Beispielhaft zu nennen sind Ansätze zur Analyse, welche Bildbereiche in wel-chem Ausmaß zu einer getroffenen Klassifikationsentscheidung beigetragen haben ("classification activation maps", [50]). Ein vor Kurzem erschienenes Positionspaper beschäftigt sich mit den Anforderungen, die vor allem an koloskopische Detektions-und Differenzierungssysteme zu stellen sind, und den Voraussetzungen für ihre Evaluation [51].…”

Section: Alltagstauglichkeit Robustheit Und Der Diagnostische Gunclassified

Künstliche Intelligenz in der Endoskopie: Neuronale Netze und maschinelles Sehen – Techniken und Perspektiven

2020

View full text Add to dashboard Cite

ZusammenfassungKünstliche neuronale Netze als Methoden der künstlichen Intelligenz (KI) können der Endoskopie neue Möglichkeiten eröffnen, etwa im Sinne einer automatischen Polypenerkennung oder der präzisen Vorhersage des histopathologischen Befunds einer Läsion anhand ihres endoskopischen Bildes. Während erste Versuche tatsächlich ein weitreichendes Potenzial erahnen lassen, leiten sich öffentliche und medial transportierte Erwartungen häufig mehr von einer abstrakten Faszination als von der detaillierten Funktionsweise der Methoden ab. Dieser Artikel soll anhand einer selektiven Literaturübersicht ein intuitives Verständnis der Methoden vermitteln und helfen, die Lücke zwischen Funktion und Faszination zu schließen, um Potenzial und Grenzen dieser Techniken im Bereich der Endoskopie realistisch abschätzen zu können.Mit ihrem Erfolg bei der maschinellen Klassifikation von Bildern haben insbesondere „tiefe neuronale Netze“ der KI nach jahrzehntelanger Forschung zu rasant anwachsendem Interesse verholfen. Wir umreißen kurz die diesbezüglichen Entwicklungen und die Gründe für ihre Bedeutung weit über die Informatik hinaus. Durch den Vergleich von maschinellem und menschlichem Sehen wird ein Verständnis der detaillierten Funktionsweise dieser Methoden und ihrer Erfolge bei Seh-Aufgaben vermittelt. Darauf aufbauend analysieren wir die Funktionsweise jüngst demonstrierter Anwendungen in Hinblick auf methodische Perspektiven und Grenzen, die Aussagekraft bisher erbrachter Leistungsnachweise und die Notwendigkeit weiterer Tests. Zudem geben wir einen Eindruck von weiteren, konkret absehbaren Einzelanwendungen und besprechen, welchen Charakter diese dem Einsatz der künstlichen Intelligenz in der Endoskopie insgesamt geben könnten.

show abstract

“…Mori et al worked on an automated colonoscopic observation that is hoped to be able to detect and characterize diminutive polyps simultaneously. In the future, the size and morphological measurement of lesions, and guidance on therapeutic procedures should also be involved in the use of CADx systems …”

Section: Current Situation Of Ai‐aided Endoscopic Image Recognitionmentioning

confidence: 99%

Application of artificial intelligence in gastrointestinal endoscopy

et al. 2019

J of Digest Diseases

View full text Add to dashboard Cite

With recent significant improvements in artificial intelligence (AI), especially in the field of deep learning, an increasing number of studies have evaluated the use of AI in endoscopy to detect and diagnose gastrointestinal (GI) lesions. The present review summarizes current publications on the use of AI in GI endoscopy and focuses on the challenges and future of AI-aided systems. We expect AI to provide an effective and practical method for endoscopists in lesion detection and characterization as well as in quality control in endoscopy. However, so far, most studies have remained at the preclinical stage. More attention should be paid in the future to the use of AI in reallife clinical applications.Artificial intelligence (AI), first proposed in the 1950s, 1 uses computers to simulate certain thought processes and forms of intelligent behavior. In recent years, one way to achieve AI, namely machine learning, has been used in a variety of medical fields, such as radiology, pathology, ophthalmology, orthopedics, obstetrics, and gynecology, in an attempt to improve physicians' diagnoses. 2 In the field of gastrointestinal (GI) endoscopy endoscopists face heavy workloads, and different kinds of endoscopic images, such as those of esophagogastroduodenoscopy, colonoscopy and capsule endoscopy, has led specialty gastroenterology societies to call for practical and effective methods in order to improve the efficiency and quality of endoscopy in daily clinical practice.With the advent of data-driven deep learning (DL), the inefficient and incomplete feature extraction that results from manual extraction by using traditional machine learning has been thoroughly addressed, and this has revolutionized the research and development of AI. 3,4 After having been trained by a large number of labeled images, the DL algorithm can classify enormous quantities of images. 3 A variety of DL algorithms have thus been created, of which convolutional neural networks (CNN) are the most widely used for medical image recognition.However, DL has some defects, including the requirement of highquality databases and its black-box nature, which have been summarized in Table 1. AI technology used in GI endoscopy falls mainly in two groups:computer-aided detection (CADe) system and computer-aided diagnosis (CADx) system. 5 CADe system is designed to detect and track GI lesions, while CADx system focuses mainly on identifying and characterizing them. Moreover, computer-aided monitoring (CADm) systems are designed for evaluating the examination procedure and † These authors contributed equally to this article.

show abstract

Quality assurance of computer-aided detection and diagnosis in colonoscopy

Cited by 107 publications

References 82 publications

Optical diagnosis of diminutive polyps in the Dutch Bowel Cancer Screening Program: Are we ready to start?

Optical diagnosis of diminutive polyps in the Dutch Bowel Cancer Screening Program: Are we ready to start?

Künstliche Intelligenz in der Endoskopie: Neuronale Netze und maschinelles Sehen – Techniken und Perspektiven

Application of artificial intelligence in gastrointestinal endoscopy

Contact Info

Product

Resources

About