Application of deep learning in the diagnosis and evaluation of ulcerative colitis disease severity

Abstract

Background: Achieving endoscopic and histological remission is a critical treatment objective in ulcerative colitis (UC). Nevertheless, interobserver variability can significantly impact overall assessment performance. Objectives: We aimed to develop a deep learning algorithm for the real-time and objective evaluation of endoscopic disease activity and prediction of histological remission in UC. Design: This is a retrospective diagnostic study. Methods: Two convolutional neural network (CNN) models were constructed and trained using 12,257 endoscopic images and biopsy results sourced from 1124 UC patients who underwent colonoscopy at a single center from January 2018 to December 2022. Mayo Endoscopy Subscore (MES) and UC Endoscopic Index of Severity Score (UCEIS) assessments were conducted by two experienced and independent reviewers. Model performance was evaluated in terms of accuracy, sensitivity, and positive predictive value. The output of the CNN models was also compared with the corresponding histological results to assess histological remission prediction performance. Results: The MES-CNN model achieved 97.04% accuracy in diagnosing endoscopic remission of UC, while the MES-CNN and UCEIS-CNN models achieved 90.15% and 85.29% accuracy, respectively, in evaluating endoscopic severity of UC. For predicting histological remission, the CNN models achieved accuracy and kappa values of 91.28% and 0.826, respectively, attaining higher accuracy than human endoscopists (87.69%). Conclusion: The proposed artificial intelligence model, based on MES and UCEIS evaluations from expert gastroenterologists, offered precise assessment of inflammation in UC endoscopic images and reliably predicted histological remission.

Advances and optimization strategies in bacteriophage therapy for treating inflammatory bowel disease

“…Likewise, corticosteroids prove effective in mitigating inflammatory responses, exhibiting immunomodulatory effects and finding extensive applications in treatment ( 19 – 21 ). Glucocorticoids are commonly employed for more severe conditions than those treated with 5-ASA ( 22 ), and their administration may be escalated when 5-ASA treatment proves ineffective ( 23 ).…”

The Role of Artificial Intelligence in the Diagnosis and Treatment of Ulcerative Colitis

“…The MES-CNN model attained a diagnostic accuracy of 97.04% for assessing endoscopic remission of UC and an accuracy of 90.15% in severity evaluation. In predicting histological remission, the CNN models achieved an accuracy of 91.28% and a kappa value of 0.826, surpassing the accuracy of endoscopists of 87.69% [6]. With endoscopes being utilized in diagnostic mucosal healing, Huang underscored the reliability of the combination between CADe and endoscopic diagnostics by achieving 94.5% accuracy for diagnostic mucosal healings with the computer-aided diagnostic system using deep learning and machine learning to classify mucosal healings [22].…”

“…Deep learning models distinguish between UC and Crohn's Disease, while CADe systems accurately assess UC biopsies for prognostic prediction [5]. CNN models achieve high accuracy in assessing endoscopic and histological remission [6]. Precision medicine integrates domain insight with bioinformatics through machine learning, enhancing treatment strategies by predicting therapeutic responses to medications like infliximab [7].…”