Using deep learning for predicting cleansing quality of colon capsule endoscopy images

TL;DR

This paper applies deep learning, specifically a ResNet-18 model with pruning and explainability techniques, to predict cleansing quality in colon capsule endoscopy images, achieving high accuracy and efficiency while addressing interpretability challenges.

Contribution

The study introduces a pruning-based deep learning approach with explainability methods for assessing colon capsule endoscopy image quality, demonstrating improved efficiency without sacrificing accuracy.

Findings

Achieved 88% accuracy with 79% sparsity in the pruned model

Demonstrated the effectiveness of pruning for efficiency in medical image classification

Highlighted challenges and solutions in explainability and calibration of models

Abstract

In this study, we explore the application of deep learning techniques for predicting cleansing quality in colon capsule endoscopy (CCE) images. Using a dataset of 500 images labeled by 14 clinicians on the Leighton-Rex scale (Poor, Fair, Good, and Excellent), a ResNet-18 model was trained for classification, leveraging stratified K-fold cross-validation to ensure robust performance. To optimize the model, structured pruning techniques were applied iteratively, achieving significant sparsity while maintaining high accuracy. Explainability of the pruned model was evaluated using Grad-CAM, Grad-CAM++, Eigen-CAM, Ablation-CAM, and Random-CAM, with the ROAD method employed for consistent evaluation. Our results indicate that for a pruned model, we can achieve a cross-validation accuracy of 88% with 79% sparsity, demonstrating the effectiveness of pruning in improving efficiency from 84% without compromising performance. We also highlight the challenges of evaluating cleansing quality of CCE images, emphasize the importance of explainability in clinical applications, and discuss the challenges associated with using the ROAD method for our task. Finally, we employ a variant of adaptive temperature scaling to calibrate the pruned models for an external dataset.