Automatic tumour segmentation in H&E-stained whole-slide images of the pancreas
This work addresses the need for efficient tumor segmentation in pancreatic cancer diagnosis, which is incremental as it builds on existing machine learning approaches in other cancers.
The paper tackled the problem of automatically segmenting tumor areas in H&E-stained whole-slide images of the pancreas, proposing a multi-task convolutional neural network that improved median Dice scores from 0.885 to 0.934 compared to a single-task network.
Pancreatic cancer will soon be the second leading cause of cancer-related death in Western society. Imaging techniques such as CT, MRI and ultrasound typically help providing the initial diagnosis, but histopathological assessment is still the gold standard for final confirmation of disease presence and prognosis. In recent years machine learning approaches and pathomics pipelines have shown potential in improving diagnostics and prognostics in other cancerous entities, such as breast and prostate cancer. A crucial first step in these pipelines is typically identification and segmentation of the tumour area. Ideally this step is done automatically to prevent time consuming manual annotation. We propose a multi-task convolutional neural network to balance disease detection and segmentation accuracy. We validated our approach on a dataset of 29 patients (for a total of 58 slides) at different resolutions. The best single task segmentation network achieved a median Dice of 0.885 (0.122) IQR at a resolution of 15.56 $μ$m. Our multi-task network improved on that with a median Dice score of 0.934 (0.077) IQR.