Deep Learning With Conformal Prediction for Hierarchical Analysis of Large-Scale Whole-Slide Tissue Images

With the increasing amount of image data collected from biomedical experiments there is an urgent need for smarter and more effective analysis methods. Many scientific questions require analysis of image sub-regions related to some specific biology. Finding such regions of interest (ROIs) at low resolution and limiting the data subjected to final quantification at full resolution can reduce computational requirements and save time. In this paper we propose a three-step pipeline: First, bounding boxes for ROIs are located at low resolution. Next, ROIs are subjected to semantic segmentation into sub-regions at mid-resolution. We also estimate the confidence of the segmented sub-regions. Finally, quantitative measurements are extracted at full resolution. We use deep learning for the first two steps in the pipeline and conformal prediction for confidence assessment. We show that limiting final quantitative analysis to sub-regions with full confidence reduces noise and increases separability of observed biological effects.

Automated summary

In this paper, a three-step pipeline is proposed to analyze biomedical image data using deep learning and conformal prediction. The process involves locating ROIs at low resolution, segmenting ROIs at mid-resolution, and extracting quantitative measurements at full resolution. Limiting the analysis to sub-regions with full confidence is shown to reduce noise and increase separability of observed biological effects.