Liver Steatosis Segmentation with Deep Learning Methods
This work addresses liver disease diagnosis and transplantation assessment by improving steatosis quantification, but it is incremental as it applies an existing deep learning method to a specific medical imaging task.
The paper tackled the problem of segmenting overlapped steatosis droplets in liver histopathological images using Mask R-CNN with transfer learning, achieving metrics such as 75.87% Average Precision and 76.97% Jaccard index.
Liver steatosis is known as the abnormal accumulation of lipids within cells. An accurate quantification of steatosis area within the liver histopathological microscopy images plays an important role in liver disease diagnosis and trans-plantation assessment. Such a quantification analysis often requires a precise steatosis segmentation that is challenging due to abundant presence of highly overlapped steatosis droplets. In this paper, a deep learning model Mask-RCNN is used to segment the steatosis droplets in clumps. Extended from Faster R-CNN, Mask-RCNN can predict object masks in addition to bounding box detection. With transfer learning, the resulting model is able to segment overlapped steatosis regions at 75.87% by Average Precision, 60.66% by Recall,65.88% by F1-score, and 76.97% by Jaccard index, promising to support liver disease diagnosis and allograft rejection prediction in future clinical practice.