SISE-PC: Semi-supervised Image Subsampling for Explainable Pathology

TL;DR

This paper introduces SISE-PC, a semi-supervised framework that efficiently selects uncertain OCT images for labeling, enabling high-accuracy pathology classification with minimal data and reduced training costs.

Contribution

It proposes a novel active learning approach using SimCLR-based latent encoding to identify the most uncertain images, reducing annotation effort and training data requirements.

Findings

Identifies up to 2% of images as most uncertain for labeling.

Achieves up to 97% classification accuracy with minimal data.

Reduces training data and computational costs in medical image classification.

Abstract

Although automated pathology classification using deep learning (DL) has proved to be predictively efficient, DL methods are found to be data and compute cost intensive. In this work, we aim to reduce DL training costs by pre-training a Resnet feature extractor using SimCLR contrastive loss for latent encoding of OCT images. We propose a novel active learning framework that identifies a minimal sub-sampled dataset containing the most uncertain OCT image samples using label propagation on the SimCLR latent encodings. The pre-trained Resnet model is then fine-tuned with the labelled minimal sub-sampled data and the underlying pathological sites are visually explained. Our framework identifies upto 2% of OCT images to be most uncertain that need prioritized specialist attention and that can fine-tune a Resnet model to achieve upto 97% classification accuracy. The proposed method can be extended to other medical images to minimize prediction costs.