Adhesion-related small bowel obstruction: deep learning for automatic transition-zone detection by CT.

Autor: Vanderbecq Q; Department of Medical Imaging, Saint Joseph Hospital, 185 rue Raymond Losserand, 75014, Paris, France. q.vanderbecq@gmail.com.; Sorbonne Université, 75013, Paris, France. q.vanderbecq@gmail.com., Ardon R; Incepto-Medical, 128 rue La Boétie, Paris, France., De Reviers A; Incepto-Medical, 128 rue La Boétie, Paris, France., Ruppli C; Incepto-Medical, 128 rue La Boétie, Paris, France., Dallongeville A; Department of Medical Imaging, Saint Joseph Hospital, 185 rue Raymond Losserand, 75014, Paris, France., Boulay-Coletta I; Department of Medical Imaging, Saint Joseph Hospital, 185 rue Raymond Losserand, 75014, Paris, France., D'Assignies G; Incepto-Medical, 128 rue La Boétie, Paris, France., Zins M; Department of Medical Imaging, Saint Joseph Hospital, 185 rue Raymond Losserand, 75014, Paris, France.
Jazyk: angličtina
Zdroj: Insights into imaging [Insights Imaging] 2022 Jan 24; Vol. 13 (1), pp. 13. Date of Electronic Publication: 2022 Jan 24.
DOI: 10.1186/s13244-021-01150-y
Abstrakt: Background: To train a machine-learning model to locate the transition zone (TZ) of adhesion-related small bowel obstruction (SBO) on CT scans.
Materials and Methods: We used 562 CTs performed in 2005-2018 in 404 patients with adhesion-related SBO. Annotation of the TZs was performed by experienced radiologists and trained residents using bounding boxes. Preprocessing involved using a pretrained model to extract the abdominopelvic region. We modeled TZ localization as a binary classification problem by splitting the abdominopelvic region into 125 patches. We then trained a neural network model to classify each patch as containing or not containing a TZ. We coupled this with a trained probabilistic estimation of presence of a TZ in each patch. The models were first evaluated by computing the area under the receiver operating characteristics curve (AUROC). Then, to assess the clinical benefit, we measured the proportion of total abdominopelvic volume classified as containing a TZ for several different false-negative rates.
Results: The probability of containing a TZ was highest for the hypogastric region (56.9%). The coupled classification network and probability mapping produced an AUROC of 0.93. For a 15% proportion of volume classified as containing TZs, the probability of highlighted patches containing a TZ was 92%.
Conclusion: Modeling TZ localization by coupling convolutional neural network classification and probabilistic localization estimation shows the way to a possible automatic TZ detection, a complex radiological task with a major clinical impact.
(© 2022. The Author(s).)
Databáze: MEDLINE
Externí odkaz:
Nepřihlášeným uživatelům se plný text nezobrazuje