基于边界感知与特征融合的病理图像分割网络

Pathological Image Segmentation Network Based on Boundary-Aware and Feature Fusion

摘要

针对病灶形态多样性引发的病理图像识别精度不足及特征融合过程中的语义鸿沟问题,提出一种融合Transformer与注意力机制的改进型U-Net架构.首先,设计边界感知模块强化病理图像的病灶边缘特征表达,提升模型对复杂结构的感知能力;其次,在瓶颈层引入正则化大核注意力模块以建模长程依赖,并通过逐层正则化策略缓解过拟合风险;最后,进一步引入可学习的视觉中心模块,增强全局与局部特征之间的互补.在数据集MoNuSeg和GlaS上的实验结果表明,该方法在分割精度、边界清晰度方面均优于当前主流模型.

Abstract

Aiming at the problems of insufficient accuracy of pathological image recognition and semantic gaps in feature fusion process caused by the diversity of lesion morphology, we proposed an improved U-Net architecture that integrated Transformer and attention mechanisms. Firstly, we designed a boundary-aware module to enhance the expression of lesion edge features in pathological images, thereby improving the model’s ability to perceive complex structures. Secondly, we introduced a regularized large-kernel attention module at the bottleneck layer to model long-range dependencies, and mitigated overfitting risk through a layer-wise regularization strategy. Finally, we further introduced a learnable visual center module to strengthen the complementarity between global and local features. Experimental results on the MoNuSeg and GlaS datasets show that the proposed method outperforms current mainstream models in terms of segmentation accuracy and boundary clarity.

关键词

边界感知 / 特征融合 / 病理图像 / 图像分割 / 卷积神经网络 / Transformer架构

Key words

boundary-aware / feature fusion / pathological image / image segmentation / convolutional neural network / Transformer architecture

参考文献

[1] LONG J, SHELHAMER E, DARRELL T. Fully Convolutional Networks for Semantic Segmentation[C]// Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. Piscataway, NJ: IEEE, 2015: 3431-3440.

[2] NIZ L, BIAN G B, WANG G A, et al. Pyramid Attention Aggregation Network for Semantic Segmentation of Surgical Instruments[C]// Proceedings of the AAAI Conference on Artificial Intelligence. Palo Alto: AAAI Press, 2020: 11782-11790.

[3] WEN Y, XIE K, HEL H. Segmenting Medical MRI via Recurrent Decoding Cell[C]// Proceedings of the AAAI Conference on Artificial Intelligence. Palo Alto: AAAI Press, 2020: 12452-12459.

[4] RONNEBERGER O, FISCHER P, BROX T. U-Net: Convolutional Networks for Biomedical Image Segmentation[C]// 18th International Conference on Medical Image Computing and Computer-Assisted Intervention. Berlin: Springer International Publishing, 2015: 234-241.

[5] WANG H N, CAO P, WANG J Q, et al. Uctransnet: Rethinking the Skip Connections in U-Net from a Channel-Wise Perspective with Transformer[C]// Proceedings of the AAAI Conference on Aartificial Iintelligence. Palo Alto: AAAI Press, 2022: 2441-2449.

[6] IBTEHAZ N, RAHMAN M S. MultiResUNet: Rethinking the U-Net Architecture for Multimodal Biomedical Image Segmentation[J]. Neural Networks, 2020, 121: 74-87.

[7] LUO Z C, ZHU X S, ZHANG L, et al. Rethinking U-Net: Task-Adaptive Mixture of Skip Connections for Enhanced Medical Image Segmentation[C]// Proceedings of the AAAI Conference on Artificial Intelligence. Palo Alto: AAAI Press, 2025: 5874-5882.

[8] ZHOU Z, SIDDIQUEE M M R, TAJBAKHSH N, et al. UNet++: A Nested U-Net Architecture for Medical Image Segmentation[C]// Deep Learning in Medical Image Analysis and Multimodal Learning for Clinical Decision Support. Berlin: Springer International Publishing, 2018: 3-11.

[9] 汪慎文, 周瑶. 基于改进U-Net的肝脏MRI分割方法[J]. 吉林大学学报(理学版), 2022, 60(5):1153-1160.

[10] (WANG S W, ZHOU Y. Liver MRI Segmentation Method Based on Improved U-NET[J]. Journal of Jilin University (Science Edition), 2022, 60(5): 1153-1160.)

[11] VASWANI A, SHAZEER N, PARMAR N, et al. Attention Is All You Need[EB/OL]. (2017-06-12) [2025-01-01]. https://arxiv.org/abs/1706.03762.

[12] CHEN J N, LV Y Y, YV Q H, et al. Transformers Make Strong Encoders for Medical Image Segmentation[EB/OL]. (2021-02-08) [2025-01-15]. https://arxiv.org/abs/2102.04306.

[13] LIU Z, LIN Y T, CAO Y, et al. Swin Transformer: Hierarchical Vision Transformer Using Shifted Windows[C]// Proceedings of the IEEE/CVF International Conference on Computer Vision. Piscataway, NJ: IEEE, 2021: 10012-10022.

[14] LIN T Y, DOLLÁR P, GIRSHICK R, et al. Feature Pyramid Networks for Object Detection[C]// Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. Piscataway, NJ: IEEE, 2017: 2117-2125.

[15] 赵欣, 李森, 李智生. 基于CNN和Transformer并行编码的腹部多器官图像分割[J]. 吉林大学学报(理学版), 2024, 62(5):1145-1154.

[16] (ZHAO X, LI S, LI Z S. Abdominal Multi-organ Image Segmentation Based on Parallel Coding of CNN and Transformer[J]. Journal of Jilin University (Science Edition), 2024, 62(5): 1145-1154.)

[17] LI X M, CHEN H, QI X J, et al. H-DenseUNet: Hybrid Densely Connected UNet for Liver and Tumor Segmentation from CT Volumes[J]. IEEE Transactions on Medical Imaging, 2018, 37(12): 2663-2674.

[18] ZHANG Y D, LIU H Y, HU Q. Transfuse: Fusing Transformers and CNNS for Medical Image Segmentation[C]// 24th International Conference on Medical Image Computing and Computer Assisted Intervention. Berlin: Springer International Publishing, 2021: 14-24.

[19] DAI J P, QI H Z, XIONG Y W, et al. Deformable Convolutional Networks[C]// Proceedings of the IEEE International Conference on Computer Vision. Piscataway, NJ: IEEE, 2017: 764-773.

[20] LI X, HU X L, YANG J. Spatial Group-Wise Enhance: Improving Semantic Feature Learning in Convolutional Networks[EB/OL]. (2019-05-23) [2025-02-10]. https://arxiv.org/abs/1905.09646.

[21] QUAN Y, ZHANG D, ZHANG L Y, et al. Centralized Feature Pyramid for Object Detection[J]. IEEE Transactions on Image Processing, 2023, 32: 4341-4354.

[22] GUO M H, LU C Z, LIU Z N, et al. Visual Attention Network[J]. Computational Visual Media, 2023, 9(4): 733-752.

[23] WANG W H, XIE E Z, LI X, et al. Pyramid Vision Transformer: A Versatile Backbone for Dense Prediction without Convolutions[C]// Proceedings of the IEEE/CVF International Conference on Computer Vision. Piscataway, NJ: IEEE, 2021: 568-578.

[24] HUANG H B, ZHOU X Q, CAO J, et al. Vision Transformer with Super Token Sampling[C]// Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. Piscataway, NJ: IEEE, 2023: 22690-22699.

[25] DAI Y M, GIESEKE F, OEHMCKE S, et al. Attentional Feature Fusion[C]// Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision. Piscataway, NJ: IEEE, 2021: 3560-3569.

[26] SIRINUKUNWATTANA K, PLUIM J P W, CHEN H, et al. Gland Segmentation in Colon Histology Images: The Glas Challenge Contest[J]. Medical Image Analysis, 2017, 35: 489-502.

[27] KUMAR N, VERMA R, SHARMA S, et al. A Dataset and a Technique for Generalized Nuclear Segmentation for Computational Pathology[J]. IEEE Transactions on Medical Imaging, 2017, 36(7): 1550-1560.

[28] QI Q F, LIN L Y, ZHANG R, et al. MEDT: Using Multimodal Encoding-Decoding Network as in Transformer for Multimodal Sentiment Analysis[J]. IEEE Access, 2022, 10: 28750-28759.

[29] CAO H, WANG Y Y, CHEN J, et al. Swin-UNet: UNet-Like Pure Transformer for Medical Image Segmentation[C]// European Conference on Computer Vision. Berlin: Springer, 2022: 205-218.

[30] QIAO J, WANG X, CHEN J, et al. MBUTransNet: Multi-branch U-Shaped Network Fusion Transformer Architecture for Medical Image Segmentation[J]. International Journal of Computer Assisted Radiology and Surgery, 2023, 18: 1895-1902.

[31] XIE X S, YANG M. USCT-UNet: Rethinking the Semantic Gap in U-Net Network from U-Shaped Skip Connections with Multichannel Fusion Transformer[J]. IEEE Transactions on Neural Systems and Rehabilitation Engineering, 2024, 32: 3782-3793.

基金资助

吉林省科技发展计划重点研发项目(YDZJ202502CXJD068)

国家自然科学基金面上项目(62276112)