Figure 1: Informative channel identification. (a) Given highly multiplexed imaging data, we train (b) a neural network to encode a channel embedding and classify a label (e.g., tumor grade). Then, we measure (c) the classification task channel importance by adopting an interpretation method to the channel embedding. (d) We evaluate our system by comparing the predicted informative channels to expert knowledge, and provide new insights for clinicians and pathologists.
Abstract
Interest is growing rapidly in using deep learning to classify biomedical images, and interpreting these deep-learned models is necessary for life-critical decisions and scientific discovery. Effective interpretation techniques accelerate biomarker discovery and provide new insights into the etiology, diagnosis, and treatment of disease. Most interpretation techniques aim to discover spatially-salient regions within images, but few techniques consider imagery with multiple channels of information. For instance, highly multiplexed tumor and tissue images have 30-100 channels and require interpretation methods that work across many channels to provide deep molecular insights. We propose a novel channel embedding method that extracts features from each channel. We then use these features to train a classifier for prediction. Using this channel embedding, we apply an interpretation method to rank the most discriminative channels. To validate our approach, we conduct an ablation study on a synthetic dataset. Moreover, we demonstrate that our method aligns with biological findings on highly multiplexed images of breast cancer cells while outperforming baseline pipelines.
