A deep learning based multiscale approach to segment cancer area in liver whole slide image
This work addresses a domain-specific problem in medical imaging for liver cancer diagnosis, but it is incremental as it builds on existing U-Net architectures with multi-scale enhancements.
The paper tackles liver cancer segmentation in Whole Slide Images by proposing a multi-scale deep learning method using a Gaussian pyramid and U-Net with a voting mechanism, achieving better scores than state-of-the-art approaches.
This paper addresses the problem of liver cancer segmentation in Whole Slide Image (WSI). We propose a multi-scale image processing method based on automatic end-to-end deep neural network algorithm for segmentation of cancer area. A seven-levels gaussian pyramid representation of the histopathological image was built to provide the texture information in different scales. In this work, several neural architectures were compared using the original image level for the training procedure. The proposed method is based on U-Net applied to seven levels of various resolutions (pyramidal subsumpling). The predictions in different levels are combined through a voting mechanism. The final segmentation result is generated at the original image level. Partial color normalization and weighted overlapping method were applied in preprocessing and prediction separately. The results show the effectiveness of the proposed multi-scales approach achieving better scores compared to the state-of-the-art.