Combining Pyramid Pooling and Attention Mechanism for Pelvic MR Image Semantic Segmentaion
This work addresses the time-consuming task of anatomical structure segmentation in pelvic MR images for radiologists, but it is incremental as it builds on existing segmentation techniques with specific enhancements.
The paper tackled the problem of automatically segmenting pelvic MR images to assist radiologists, addressing challenges like varying organ sizes and limited annotated data, and reported superior performance over state-of-the-art methods on a fine-grained dataset of 50 pelvic organs.
One of the time-consuming routine work for a radiologist is to discern anatomical structures from tomographic images. For assisting radiologists, this paper develops an automatic segmentation method for pelvic magnetic resonance (MR) images. The task has three major challenges 1) A pelvic organ can have various sizes and shapes depending on the axial image, which requires local contexts to segment correctly. 2) Different organs often have quite similar appearance in MR images, which requires global context to segment. 3) The number of available annotated images are very small to use the latest segmentation algorithms. To address the challenges, we propose a novel convolutional neural network called Attention-Pyramid network (APNet) that effectively exploits both local and global contexts, in addition to a data-augmentation technique that is particularly effective for MR images. In order to evaluate our method, we construct fine-grained (50 pelvic organs) MR image segmentation dataset, and experimentally confirm the superior performance of our techniques over the state-of-the-art image segmentation methods.