UCSwin-UNet model for medical image segmentation based on cardiac haemangioma

Cardiac hemangioma is a rare benign tumour that presents diagnostic challenges due to its variable clinical symptoms, imaging features, and locations. This study proposes a novel segmentation method based on a Convolutional Neural Network (CNN) and Transformer integration, with Swin-UNet as the core model. We incorporated a U-shaped convolutional neural network block into the original jump connection of Swin-UNet. The Binary Cross Entropy Loss (BCE Loss) algorithm was added, and the learning rate decay algorithm was modified to select the appropriate one by comparing loss values. This paper utilizes the publicly available cardiac angioma dataset in AI Studio, consisting of 215 images for training and testing. To evaluate the effectiveness of the proposed model, this paper demonstrates its optimality through ablation experiments and comparisons with other mainstream models. The comparison experiments show that this model improves Dice by approximately 12%, HD95 by approximately 4.7 mm, Accuracy by approximately 6.1%, and F1 score by 0.11 compared to models such as UNet, UNet++, and Deeplabv3+, etc. For the recently proposed SOTO models, such as TransUNet, Swin-UNet, and MultiResUnet, the Dice score improved by about 1.2%, HD95 reduced by about 1mm, Accuracy improved by about 0.3%, and F1 score improved by 0.015. This study introduces the UCSwin-UNet model, which adopts a U-shaped convolutional framework in the original model. After introducing a new learning rate decay strategy and incorporating the BCE Loss into the loss function, a revaluation of the weight allocation has been undertaken for each component within the loss formula. This model enhances the extraction of local features while introducing non-linearity, and multiple experiments were conducted in the paper to validate its effectiveness, accompanied by a visualization demonstration. image