Histogram of Oriented Gradients Meet Deep Learning: A Novel Multi-task Deep Network for Medical Image Semantic Segmentation
This addresses the annotation burden in medical image segmentation for researchers and practitioners, though it is incremental as it builds on existing multi-task and segmentation methods.
The paper tackles the problem of requiring ground truth annotations for auxiliary tasks in multi-task learning for medical image segmentation by generating pseudo-labels using Histogram of Oriented Gradients (HOGs) in an unsupervised manner, resulting in consistent performance improvements and winning the FetReg Endovis Sub-challenge on Semantic Segmentation at MICCAI 2021.
We present our novel deep multi-task learning method for medical image segmentation. Existing multi-task methods demand ground truth annotations for both the primary and auxiliary tasks. Contrary to it, we propose to generate the pseudo-labels of an auxiliary task in an unsupervised manner. To generate the pseudo-labels, we leverage Histogram of Oriented Gradients (HOGs), one of the most widely used and powerful hand-crafted features for detection. Together with the ground truth semantic segmentation masks for the primary task and pseudo-labels for the auxiliary task, we learn the parameters of the deep network to minimise the loss of both the primary task and the auxiliary task jointly. We employed our method on two powerful and widely used semantic segmentation networks: UNet and U2Net to train in a multi-task setup. To validate our hypothesis, we performed experiments on two different medical image segmentation data sets. From the extensive quantitative and qualitative results, we observe that our method consistently improves the performance compared to the counter-part method. Moreover, our method is the winner of FetReg Endovis Sub-challenge on Semantic Segmentation organised in conjunction with MICCAI 2021.