Brain Hematoma Marker Recognition Using Multitask Learning: SwinTransformer and Swin-Unet
By: Kodai Hirata, Tsuyoshi Okita
Potential Business Impact:
Makes computer vision models more accurate.
This paper proposes a method MTL-Swin-Unet which is multi-task learning using transformers for classification and semantic segmentation. For spurious-correlation problems, this method allows us to enhance the image representation with two other image representations: representation obtained by semantic segmentation and representation obtained by image reconstruction. In our experiments, the proposed method outperformed in F-value measure than other classifiers when the test data included slices from the same patient (no covariate shift). Similarly, when the test data did not include slices from the same patient (covariate shift setting), the proposed method outperformed in AUC measure.
Similar Papers
Multi-modal brain MRI synthesis based on SwinUNETR
Image and Video Processing
Creates missing MRI scans from existing ones.
Improving Prostate Gland Segmenting Using Transformer based Architectures
Image and Video Processing
Helps doctors find prostate cancer on scans.
Multi-Plane Vision Transformer for Hemorrhage Classification Using Axial and Sagittal MRI Data
Image and Video Processing
Finds brain bleeds in scans better.