PSIGAN: Joint probabilistic segmentation and image distribution matching for unpaired cross-modality adaptation based MRI segmentation
About
We developed a new joint probabilistic segmentation and image distribution matching generative adversarial network (PSIGAN) for unsupervised domain adaptation (UDA) and multi-organ segmentation from magnetic resonance (MRI) images. Our UDA approach models the co-dependency between images and their segmentation as a joint probability distribution using a new structure discriminator. The structure discriminator computes structure of interest focused adversarial loss by combining the generated pseudo MRI with probabilistic segmentations produced by a simultaneously trained segmentation sub-network. The segmentation sub-network is trained using the pseudo MRI produced by the generator sub-network. This leads to a cyclical optimization of both the generator and segmentation sub-networks that are jointly trained as part of an end-to-end network. Extensive experiments and comparisons against multiple state-of-the-art methods were done on four different MRI sequences totalling 257 scans for generating multi-organ and tumor segmentation. The experiments included, (a) 20 T1-weighted (T1w) in-phase mdixon and (b) 20 T2-weighted (T2w) abdominal MRI for segmenting liver, spleen, left and right kidneys, (c) 162 T2-weighted fat suppressed head and neck MRI (T2wFS) for parotid gland segmentation, and (d) 75 T2w MRI for lung tumor segmentation. Our method achieved an overall average DSC of 0.87 on T1w and 0.90 on T2w for the abdominal organs, 0.82 on T2wFS for the parotid glands, and 0.77 on T2w MRI for lung tumors.
Related benchmarks
| Task | Dataset | Result | Rank | |
|---|---|---|---|---|
| Medical Image Segmentation | Abdominal Abd MRI -> CT (test) | Liver Score63.53 | 24 | |
| Medical Image Segmentation | Abdominal Abd CT -> MRI (test) | Liver Score34.2 | 24 | |
| Medical Image Segmentation | BraTS FLAIR | Dice0.5623 | 17 | |
| Medical Image Segmentation | MM-WHS Cardiac CT → Cardiac MRI | Dice (LVM)69.95 | 14 | |
| Medical Image Segmentation | BraTS Target domain T1 | 95HD (WT)25.7 | 14 | |
| Cardiac Image Segmentation | MM-WHS Cardiac CT → Cardiac MRI | 95HD (LVM)36.15 | 14 | |
| Brain Tumor Segmentation | BraTS T1 Target Domain (test) | WT Score47.62 | 14 | |
| Medical Image Segmentation | Abdominal Multi-Organ MRI → CT | 95HD (Liver)34.66 | 14 | |
| Medical Image Segmentation | Abdominal Multi-Organ CT → MRI | 95HD (Liver)60.94 | 14 | |
| Brain Tumor Segmentation | BraTS T1CE Target Domain (test) | WT Score21.68 | 14 |