BiFTransNet: A unified and simultaneous segmentation network for gastrointestinal images of CT & MRI

• Published in: Computers in biology and medicine 2023-10, Vol.165, p.107326-107326, Article 107326
• Main Authors: Jiang, Xin, Ding, Yizhou, Liu, Mingzhe, Wang, Yong, Li, Yan, Wu, Zongda
• Format: Article
• Language: English
• Subjects: Artificial neural networks; Coders; Computed tomography; Datasets; Deep learning; Feature fusion; Image processing; Image segmentation; Intestine; Magnetic resonance imaging; Malignancy; Medical image; Medical image segmentation; Medical imaging; Medical innovations; Metric space; Modules; Multi-level loss; Neural networks; Radiation; Radiation therapy; Receptive field; Synapses; Transformers
• ISSN: 0010-4825; 1879-0534
• DOI: 10.1016/j.compbiomed.2023.107326

Gastrointestinal (GI) cancer is a malignancy affecting the digestive organs. During radiation therapy, the radiation oncologist must precisely aim the X-ray beam at the tumor while avoiding unaffected areas of the stomach and intestines. Consequently, accurate, automated GI image segmentation is urgently needed in clinical practice. While the fully convolutional network (FCN) and U-Net framework have shown impressive results in medical image segmentation, their ability to model long-range dependencies is constrained by the convolutional kernel’s restricted receptive field. The transformer has a robust capacity for global modeling owing to its inherent global self-attention mechanism. The TransUnet model leverages the strengths of both the convolutional neural network (CNN) and transformer models through a hybrid CNN-transformer encoder. However, the concatenation of high- and low-level features in the decoder is ineffective in fusing global and local information. To overcome this limitation, we propose an innovative transformer-based medical image segmentation architecture called BiFTransNet, which introduces a BiFusion module into the decoder stage, enabling effective global and local feature fusion by enabling feature integration from various modules. Further, a multilevel loss (ML) strategy is introduced to oversee the learning process of each decoder layer and optimize the use of globally and locally fused contextual features at different scales. Our method achieved a Dice score of 89.51% and an intersection-over-union (IoU) score of 86.54% on the UW-Madison Gastrointestinal Segmentation dataset. Moreover, our method attained a Dice score of 78.77% and a Hausdorff distance (HD) of 27.94% on the Synapse Multi-organ Segmentation dataset. Compared with the state-of-the-art methods, our proposed method achieves superior segmentation performance in gastrointestinal segmentation tasks. More significantly, our method can be easily extended to medical segmentation in different modalities such as CT and MRI. Our method achieves clinical multimodal medical segmentation and provides decision supports for clinical radiotherapy plans. •BiFTransNet employs BiFusion module to integrate global and local features.•Multi-level loss supervises the decoder‘s training process at different scales.•Experiments are extended to different modalities datasets such as CT and MRI.