Uncertainty Awareness Enables Efficient Labeling for Cancer Subtyping in Digital Pathology
This work addresses the challenge of limited labeled data availability in digital pathology, offering an incremental improvement in annotation efficiency for cancer subtyping.
The paper tackled the problem of reducing the need for extensive expert annotations in machine-learning-assisted cancer subtyping by introducing uncertainty awareness into a self-supervised contrastive learning model, achieving state-of-the-art performance with only 1-10% of strategically selected annotations on benchmark datasets.
Machine-learning-assisted cancer subtyping is a promising avenue in digital pathology. Cancer subtyping models, however, require careful training using expert annotations so that they can be inferred with a degree of known certainty (or uncertainty). To this end, we introduce the concept of uncertainty awareness into a self-supervised contrastive learning model. This is achieved by computing an evidence vector at every epoch, which assesses the model's confidence in its predictions. The derived uncertainty score is then utilized as a metric to selectively label the most crucial images that require further annotation, thus iteratively refining the training process. With just 1-10% of strategically selected annotations, we attain state-of-the-art performance in cancer subtyping on benchmark datasets. Our method not only strategically guides the annotation process to minimize the need for extensive labeled datasets, but also improves the precision and efficiency of classifications. This development is particularly beneficial in settings where the availability of labeled data is limited, offering a promising direction for future research and application in digital pathology.