Intrapapillary Capillary Loop Classification in Magnification Endoscopy: Open Dataset and Baseline Methodology

TL;DR

This paper introduces a large annotated dataset and a novel CNN-based method for classifying endoscopic images of the oesophagus as normal or abnormal, aiding early detection of treatable neoplasia.

Contribution

It provides a new benchmark dataset of 68,000 labeled frames and a CNN architecture that explains decision features, advancing automated ESCN detection.

Findings

Achieved 91.7% accuracy in classification

CNN heatmaps highlight IPCL patterns

Comparable to expert clinicians' accuracy

Abstract

Purpose. Early squamous cell neoplasia (ESCN) in the oesophagus is a highly treatable condition. Lesions confined to the mucosal layer can be curatively treated endoscopically. We build a computer-assisted detection (CADe) system that can classify still images or video frames as normal or abnormal with high diagnostic accuracy. Methods. We present a new benchmark dataset containing 68K binary labeled frames extracted from 114 patient videos whose imaged areas have been resected and correlated to histopathology. Our novel convolutional network (CNN) architecture solves the binary classification task and explains what features of the input domain drive the decision-making process of the network. Results. The proposed method achieved an average accuracy of 91.7 % compared to the 94.7 % achieved by a group of 12 senior clinicians. Our novel network architecture produces deeply supervised activation heatmaps that suggest the network is looking at intrapapillary capillary loop (IPCL) patterns when predicting abnormality. Conclusion. We believe that this dataset and baseline method may serve as a reference for future benchmarks on both video frame classification and explainability in the context of ESCN detection. A future work path of high clinical relevance is the extension of the classification to ESCN types.