Densely Dilated Spatial Pooling Convolutional Network using benign loss functions for imbalanced volumetric prostate segmentation
This work addresses the problem of early prostate disease detection for medical imaging, but it is incremental as it builds on existing encoder-decoder networks with specific architectural and loss function modifications.
The paper tackles automated prostate segmentation from MRI, which is challenging due to appearance variability and class imbalance, by proposing a Densely Dilated Spatial Pooling Convolutional Network (DDSP ConNet) with DSC and Jaccard loss functions, achieving a score of 85.78 on the MICCAI PROMISE12 test dataset.
The high incidence rate of prostate disease poses a requirement in early detection for diagnosis. As one of the main imaging methods used for prostate cancer detection, Magnetic Resonance Imaging (MRI) has wide range of appearance and imbalance problems, making automated prostate segmentation fundamental but challenging. Here we propose a novel Densely Dilated Spatial Pooling Convolutional Network (DDSP ConNet) in encoder-decoder structure. It employs dense structure to combine dilated convolution and global pooling, thus supplies coarse segmentation results from encoder and decoder subnet and preserves more contextual information. To obtain richer hierarchical feature maps, residual long connection is furtherly adopted to fuse contexture features. Meanwhile, we adopt DSC loss and Jaccard loss functions to train our DDSP ConNet. We surprisingly found and proved that, in contrast to re-weighted cross entropy, DSC loss and Jaccard loss have a lot of benign properties in theory, including symmetry, continuity and differentiability about the parameters of network. Extensive experiments on the MICCAI PROMISE12 challenge dataset have been done to corroborate the effectiveness of our DDSP ConNet with DSC loss and Jaccard loss. Totally, our method achieves a score of 85.78 in the test dataset, outperforming most of other competitors.