Learning Channel Importance for High Content Imaging with Interpretable Deep Input Channel Mixing

TL;DR

This paper introduces DCMIX, a novel deep learning layer that interprets the importance of different image channels in high content imaging, aiding biological understanding without sacrificing prediction accuracy.

Contribution

The paper presents DCMIX, a scalable, end-to-end trainable mixing layer that provides interpretability of channel importance in deep learning models for high content imaging.

Findings

DCMIX accurately identifies biologically relevant channels.

The method maintains high prediction performance.

Experiments on MNIST and RXRX1 datasets validate effectiveness.

Abstract

Uncovering novel drug candidates for treating complex diseases remain one of the most challenging tasks in early discovery research. To tackle this challenge, biopharma research established a standardized high content imaging protocol that tags different cellular compartments per image channel. In order to judge the experimental outcome, the scientist requires knowledge about the channel importance with respect to a certain phenotype for decoding the underlying biology. In contrast to traditional image analysis approaches, such experiments are nowadays preferably analyzed by deep learning based approaches which, however, lack crucial information about the channel importance. To overcome this limitation, we present a novel approach which utilizes multi-spectral information of high content images to interpret a certain aspect of cellular biology. To this end, we base our method on image blending concepts with alpha compositing for an arbitrary number of channels. More specifically, we introduce DCMIX, a lightweight, scaleable and end-to-end trainable mixing layer which enables interpretable predictions in high content imaging while retaining the benefits of deep learning based methods. We employ an extensive set of experiments on both MNIST and RXRX1 datasets, demonstrating that DCMIX learns the biologically relevant channel importance without scarifying prediction performance.