# Development of a convolutional neural network for the endoscopic classification of pouchitis in patients after restorative proctocolectomy

## TL;DR

This study developed a CNN to classify pouchitis in endoscopic images, showing promising but not yet expert-level accuracy.

## Contribution

A CNN was developed to detect and classify pouchitis using endoscopic images, with performance metrics reported.

## Key findings

- The CNN achieved 71.78% sensitivity and 90.35% specificity for detecting inflammation.
- Sensitivity for PDAI classification ranged from 38% to 67.18% across classes.
- AI performance was below human expert level, requiring larger datasets and better markers for clinical relevance.

## Abstract

The aim of this prospective single-center study is to train convolutional neural networks (CNNs) to detect the presence of pouchitis in two-dimensional (2D) images acquired during pouchoscopies and test its feasibility.

Two separate networks were constructed. The goal of network 1 was to detect whether an inflammation was present. Network 2 was designed to classify endoscopic findings of pouchitis, according to the pouchitis disease activity index (PDAI) score. The dataset was divided into three distinct sets: a training set, a validation set, and a test set. The performance was quantified using a tenfold cross-validation approach.

For the detection of inflammation, sensitivity was 71.78% with a specificity of 90.35%. When differentiating the six endoscopic findings according to the PDAI score, the sensitivity ranged from a low of 38% for the ‘ulceration’ class to a high of 67.18% for the ‘friability’ class, with a specifity of 94.12% (‘ulceration’) and 96.57% (‘friability’).

This study shows that an artificial, intelligence-based image recognition software can be trained to recognize the endoscopic features of pouchitis with reasonable accuracy. The results, although encouraging, confirm that artificial intelligence (AI) performance in this context remains below human expert level. A larger dataset, human benchmarking and more appropriate endoscopic markers are required to reach clinically relevant performance.

Trial registration This trial was registered in the ‘ClinicalTrials.gov’ database on 26 April 2021 (NCT04864587).