Signet Ring Cell Detection With a Semi-supervised Learning Framework
This addresses a critical need for early detection of signet ring cell carcinoma to improve patient survival rates, representing an incremental advancement as it applies existing semi-supervised techniques to a new medical domain.
The paper tackles the problem of automatically detecting signet ring cells in medical images, which is labor-intensive and error-prone for pathologists, by proposing a semi-supervised learning framework that achieves accurate detection on large real clinical data.
Signet ring cell carcinoma is a type of rare adenocarcinoma with poor prognosis. Early detection leads to huge improvement of patients' survival rate. However, pathologists can only visually detect signet ring cells under the microscope. This procedure is not only laborious but also prone to omission. An automatic and accurate signet ring cell detection solution is thus important but has not been investigated before. In this paper, we take the first step to present a semi-supervised learning framework for the signet ring cell detection problem. Self-training is proposed to deal with the challenge of incomplete annotations, and cooperative-training is adapted to explore the unlabeled regions. Combining the two techniques, our semi-supervised learning framework can make better use of both labeled and unlabeled data. Experiments on large real clinical data demonstrate the effectiveness of our design. Our framework achieves accurate signet ring cell detection and can be readily applied in the clinical trails. The dataset will be released soon to facilitate the development of the area.