Image Analysis in Digital Pathology Utilizing Machine Learning and Deep Neural Networks

Detection of regions of interest (ROIs) in whole slide images (WSIs) in a clinical setting is a highly subjective and a labor-intensive task. In this work, recent developments in machine learning and computer vision algorithms are presented to assess their possible usage and performance to enhance and accelerate clinical pathology procedures, such as ROI detection in WSIs. In this context, a state-of-the-art deep learning framework (Detectron2) was trained on two cases linked to the TUPAC16 dataset for object detection and on the JPATHOL dataset for instance segmentation. The predictions were evaluated against competing models and further possible improvements are discussed.

Automated summary

This study presents recent advancements in machine learning and computer vision algorithms for the detection of regions of interest (ROIs) in whole slide images (WSIs) in a clinical pathology setting. A state-of-the-art deep learning framework (Detectron2) is trained for object detection and instance segmentation tasks, and the predictions are evaluated against competing models.