Renal Cell Carcinoma Detection and Subtyping with Minimal Point-Based Annotation in Whole-Slide Images
This work addresses the challenge of reducing annotation burden in medical imaging for pathologists, though it is incremental in applying semi-supervised learning to a specific domain.
The paper tackles the problem of detecting and subtyping renal cell carcinoma in whole-slide images with minimal annotation effort, achieving a 12% improvement in f1-score for subtyping compared to using only diagnostic labels.
Obtaining a large amount of labeled data in medical imaging is laborious and time-consuming, especially for histopathology. However, it is much easier and cheaper to get unlabeled data from whole-slide images (WSIs). Semi-supervised learning (SSL) is an effective way to utilize unlabeled data and alleviate the need for labeled data. For this reason, we proposed a framework that employs an SSL method to accurately detect cancerous regions with a novel annotation method called Minimal Point-Based annotation, and then utilize the predicted results with an innovative hybrid loss to train a classification model for subtyping. The annotator only needs to mark a few points and label them are cancer or not in each WSI. Experiments on three significant subtypes of renal cell carcinoma (RCC) proved that the performance of the classifier trained with the Min-Point annotated dataset is comparable to a classifier trained with the segmentation annotated dataset for cancer region detection. And the subtyping model outperforms a model trained with only diagnostic labels by 12% in terms of f1-score for testing WSIs.