Distangling Biological Noise in Cellular Images with a focus on Explainability

TL;DR

This paper develops a cellular image classification model to identify genetic perturbations and employs explainability techniques like Grad-CAM to understand model decisions, aiming to accelerate drug discovery and improve interpretability.

Contribution

The work introduces a deep learning model for cellular image classification with a focus on explainability through Grad-CAM visualizations, highlighting significant features for diagnosis.

Findings

Grad-CAM visualizations reveal key features influencing model decisions

Certain features are identified as pivotal for diagnostic accuracy

The approach enhances understanding of deep learning mechanisms in cellular analysis

Abstract

The cost of some drugs and medical treatments has risen in recent years that many patients are having to go without. A classification project could make researchers more efficient. One of the more surprising reasons behind the cost is how long it takes to bring new treatments to market. Despite improvements in technology and science, research and development continues to lag. In fact, finding new treatment takes, on average, more than 10 years and costs hundreds of millions of dollars. In turn, greatly decreasing the cost of treatments can make ensure these treatments get to patients faster. This work aims at solving a part of this problem by creating a cellular image classification model which can decipher the genetic perturbations in cell (occurring naturally or artificially). Another interesting question addressed is what makes the deep-learning model decide in a particular fashion, which can further help in demystifying the mechanism of action of certain perturbations and paves a way towards the explainability of the deep-learning model. We show the results of Grad-CAM visualizations and make a case for the significance of certain features over others. Further we discuss how these significant features are pivotal in extracting useful diagnostic information from the deep-learning model.