Explainable Deep Learning to Profile Mitochondrial Disease Using High Dimensional Protein Expression Data
This work addresses the problem of limited understanding in untreatable mitochondrial diseases for medical researchers by providing an automated analysis method, though it appears incremental as it applies existing deep learning and explainability techniques to new data.
The authors tackled the challenge of analyzing high-dimensional protein expression data from mitochondrial diseases by applying deep learning directly to raw Imaging Mass Cytometry images, achieving better-than-expected accuracy and using explainable techniques to identify features consistent with disease progression hypotheses.
Mitochondrial diseases are currently untreatable due to our limited understanding of their pathology. We study the expression of various mitochondrial proteins in skeletal myofibres (SM) in order to discover processes involved in mitochondrial pathology using Imaging Mass Cytometry (IMC). IMC produces high dimensional multichannel pseudo-images representing spatial variation in the expression of a panel of proteins within a tissue, including subcellular variation. Statistical analysis of these images requires semi-automated annotation of thousands of SMs in IMC images of patient muscle biopsies. In this paper we investigate the use of deep learning (DL) on raw IMC data to analyse it without any manual pre-processing steps, statistical summaries or statistical models. For this we first train state-of-art computer vision DL models on all available image channels, both combined and individually. We observed better than expected accuracy for many of these models. We then apply state-of-the-art explainable techniques relevant to computer vision DL to find the basis of the predictions of these models. Some of the resulting visual explainable maps highlight features in the images that appear consistent with the latest hypotheses about mitochondrial disease progression within myofibres.