Automating Colon Polyp Classification in Digital Pathology by Evaluation of a “Machine Learning as a Service” AI Model: Algorithm Development and Validation Study

TL;DR

This study shows that cloud-based AutoML tools can create highly accurate AI models for classifying colon polyps in digital pathology.

Contribution

The novelty lies in using accessible AutoML platforms to develop a robust AI model for colon polyp classification.

Findings

The AI model achieved 100% accuracy in identifying tubular adenoma and hyperplastic polyps.

Normal colon tissue was classified with 97% accuracy.

The model demonstrated low sensitivity and specificity error rates.

Abstract

Artificial intelligence (AI) models are increasingly being developed to improve the efficiency of pathological diagnoses. Rapid technological advancements are leading to more widespread availability of AI models that can be used by domain-specific experts (ie, pathologists and medical imaging professionals). This study presents an innovative AI model for the classification of colon polyps, developed using AutoML algorithms that are readily available from cloud-based machine learning platforms. Our aim was to explore if such AutoML algorithms could generate robust machine learning models that are directly applicable to the field of digital pathology.

The objective of this study was to evaluate the effectiveness of AutoML algorithms in generating robust machine learning models for the classification of colon polyps and to assess their potential applicability in digital pathology.

Whole-slide images from both public and institutional databases were used to develop a training set for 3 classifications of common entities found in colon polyps: hyperplastic polyps, tubular adenomas, and normal colon. The AI model was developed using an AutoML algorithm from Google’s VertexAI platform. A test subset of the data was withheld to assess model accuracy, sensitivity, and specificity.

The AI model displayed a high accuracy rate, identifying tubular adenoma and hyperplastic polyps with 100% success and normal colon with 97% success. Sensitivity and specificity error rates were very low.

This study demonstrates how accessible AutoML algorithms can readily be used in digital pathology to develop diagnostic AI models using whole-slide images. Such models could be used by pathologists to improve diagnostic efficiency.

Figures