Publications by authors named "Haoji Dong"
Article Synopsis
- Automatic multi-organ segmentation is crucial for diagnosing diseases and planning treatments, and the MSCT-UNET hybrid network combines CNN and transformer features to enhance segmenting capabilities.
- The network utilizes multi-task contrastive learning and a cross fusion block, allowing it to capture both detailed pixel-level features and long-range dependencies in medical images.
- Evaluation on multiple datasets shows that MSCT-UNET outperforms existing methods, with the source code available for public access.
. Automated medical image segmentation is vital for the prevention and treatment of disease. However, medical data commonly exhibit class imbalance in practical applications, which may lead to unclear boundaries of specific classes and make it difficult to effectively segment certain tail classes in the results of semi-supervised medical image segmentation.
View Article and Find Full Text PDF