Automatized Detection of Crohn's Disease in Intestinal Ultrasound Using Convolutional Neural Network

Dan Carter*, Ahmed Albshesh, Carmi Shimon, Batel Segal, Alex Yershov, Uri Kopylov, Adele Meyers, Rafael Y. Brzezinski, Shomron Ben Horin, Oshrit Hoffer

*Corresponding author for this work

Research output: Contribution to journalArticlepeer-review

Abstract

Introduction: The use of intestinal ultrasound (IUS) for the diagnosis and follow-up of inflammatory bowel disease is steadily growing. Although access to educational platforms of IUS is feasible, novice ultrasound operators lack experience in performing and interpreting IUS. An artificial intelligence (AI)-based operator supporting system that automatically detects bowel wall inflammation may simplify the use of IUS by less experienced operators. Our aim was to develop and validate an artificial intelligence module that can distinguish bowel wall thickening (a surrogate of bowel inflammation) from normal bowel images of IUS. Methods: We used a self-collected image data set to develop and validate a convolutional neural network module that can distinguish bowel wall thickening >3 mm (a surrogate of bowel inflammation) from normal bowel images of IUS. Results: The data set consisted of 1008 images, distributed uniformly (50% normal images, 50% abnormal images). Execution of the training phase and the classification phase was performed using 805 and 203 images, respectively. The overall accuracy, sensitivity, and specificity for detection of bowel wall thickening were 90.1%, 86.4%, and 94%, respectively. The network exhibited an average area under the ROC curve of 0.9777 for this task. Conclusions: We developed a machine-learning module based on a pretrained convolutional neural network that is highly accurate in the recognition of bowel wall thickening on intestinal ultrasound images in Crohn's disease. Incorporation of convolutional neural network to IUS may facilitate the use of IUS by inexperienced operators and allow automatized detection of bowel inflammation and standardization of IUS imaging interpretation.

Original languageEnglish
Pages (from-to)1901-1906
Number of pages6
JournalInflammatory Bowel Diseases
Volume29
Issue number12
DOIs
StatePublished - 1 Dec 2023

Funding

FundersFunder number
Medtronic
Takeda Pharmaceutical Company

    Keywords

    • Crohn's disease
    • artificial intelligence
    • intestinal ultrasound

    Fingerprint

    Dive into the research topics of 'Automatized Detection of Crohn's Disease in Intestinal Ultrasound Using Convolutional Neural Network'. Together they form a unique fingerprint.

    Cite this