PRECISe : Prototype-Reservation for Explainable Classification under Imbalanced and Scarce-Data Settings

TL;DR

PRECISe is an explainable deep learning model designed for medical image classification that effectively handles data scarcity and class imbalance, achieving high accuracy with minimal training data and providing interpretable predictions.

Contribution

The paper introduces PRECISe, a novel explainable model that addresses data scarcity and class imbalance simultaneously in medical imaging classification tasks.

Findings

Outperforms state-of-the-art methods on imbalanced datasets

Achieves ~87% accuracy with fewer than 60 training images

Produces interpretable predictions to enhance trust and utility

Abstract

Deep learning models used for medical image classification tasks are often constrained by the limited amount of training data along with severe class imbalance. Despite these problems, models should be explainable to enable human trust in the models' decisions to ensure wider adoption in high-risk situations. In this paper, we propose PRECISe, an explainable-by-design model meticulously constructed to concurrently address all three challenges. Evaluation on 2 imbalanced medical image datasets reveals that PRECISe outperforms the current state-of-the-art methods on data efficient generalization to minority classes, achieving an accuracy of ~87% in detecting pneumonia in chest x-rays upon training on <60 images only. Additionally, a case study is presented to highlight the model's ability to produce easily interpretable predictions, reinforcing its practical utility and reliability for medical imaging tasks.