Emergent symbolic language based deep medical image classification

TL;DR

This paper introduces a novel deep learning approach for medical image classification that uses emergent symbolic language to improve interpretability while maintaining high accuracy, demonstrated on immune cell and chest X-ray datasets.

Contribution

First to demonstrate the emergence of symbolic representations in deep image classification, enhancing interpretability without sacrificing performance.

Findings

EL models match or outperform state-of-the-art deep learning models

EL provides interpretable symbolic representations

Framework applied successfully to immune cell and chest X-ray classification

Abstract

Modern deep learning systems for medical image classification have demonstrated exceptional capabilities for distinguishing between image based medical categories. However, they are severely hindered by their ina-bility to explain the reasoning behind their decision making. This is partly due to the uninterpretable continuous latent representations of neural net-works. Emergent languages (EL) have recently been shown to enhance the capabilities of neural networks by equipping them with symbolic represen-tations in the framework of referential games. Symbolic representations are one of the cornerstones of highly explainable good old fashioned AI (GOFAI) systems. In this work, we demonstrate for the first time, the emer-gence of deep symbolic representations of emergent language in the frame-work of image classification. We show that EL based classification models can perform as well as, if not better than state of the art deep learning mod-els. In addition, they provide a symbolic representation that opens up an entire field of possibilities of interpretable GOFAI methods involving symbol manipulation. We demonstrate the EL classification framework on immune cell marker based cell classification and chest X-ray classification using the CheXpert dataset. Code is available online at https://github.com/AriChow/EL.