A distillation based approach for the diagnosis of diseases

TL;DR

This paper introduces a lightweight, knowledge distillation-based computer vision method for rapid, accurate diagnosis of diseases like Covid-19 from chest X-ray images, suitable for low-end devices.

Contribution

The paper presents a novel distillation approach with an auxiliary network to create an extremely light model without sacrificing accuracy.

Findings

Achieved high accuracy with a 3-block convolutional network

Reduced computational costs compared to traditional methods

Enabled disease screening on low-end devices

Abstract

Presently, Covid-19 is a serious threat to the world at large. Efforts are being made to reduce disease screening times and in the development of a vaccine to resist this disease, even as thousands succumb to it everyday. We propose a novel method of automated screening of diseases like Covid-19 and pneumonia from Chest X-Ray images with the help of Computer Vision. Unlike computer vision classification algorithms which come with heavy computational costs, we propose a knowledge distillation based approach which allows us to bring down the model depth, while preserving the accuracy. We make use of an augmentation of the standard distillation module with an auxiliary intermediate assistant network that aids in the continuity of the flow of information. Following this approach, we are able to build an extremely light student network, consisting of just 3 convolutional blocks without any compromise on accuracy. We thus propose a method of classification of diseases which can not only lead to faster screening, but can also operate seamlessly on low-end devices.