基于两阶段的多重注意力机制网络的胰腺分割

doi:10.3969/j.issn.1006-2475.2025.10.011

摘要/Abstract

摘要：
摘要：胰腺分割在计算机辅助诊断胰腺疾病中具有重要意义。胰腺具有体积小、个体差异大和边缘模糊的特点，因此胰腺分割任务具有极大的挑战性。为了解决上述问题，本文提出一种基于两阶段的多重注意力机制网络。首先，针对背景与目标不平衡这一问题，本文使用两阶段的分割方法，利用粗分割阶段裁剪出候选区域作为精细分割阶段的输入，以减少背景对分割胰腺目标的干扰。其次，设计双通道注意力机制模块并添加到解码器中，以增强模型对胰腺特征的表示能力，还引入压缩与激励注意力模块（SE Module），利用其自适应的注意力机制来适应不同形状大小的胰腺。最后，通过使用卷积注意力模块（CBAM）加强编码器与解码器之间的信息传递，提高模型的分割精度。在NIH数据集上对本文的方法进行测试，结果表明，所提方法具有较好的性能，能够有效解决胰腺在腹部CT图像中难以分割的问题。

关键词: 关键词：胰腺分割, 两阶段, 注意力机制, 双通道注意力机制模块, 卷积注意力模块

Abstract:
Abstract:Pancreas segmentation is of great significance in computer-aided diagnosis of pancreatic diseases. The pancreas is characterized by small size， large individual differences， and blurred margins， so the task of pancreas segmentation is extremely challenging. To solve the above problems, this paper proposes a new network based on two-stage multi-attention mechanism. Firstly， in order to solve the problem of imbalance between the background and the target， this paper uses a two-stage segmentation method to use the coarse segmentation stage to clip out the candidate region as the input of the fine segmentation stage. Secondly， for the problem of large individual differences in the pancreas， the channel attention mechanism block is designed to the decoder， and the Squeeze and Excited Attention Module（SE Module） is also introduced to adapt to different shapes and sizes of pancreas by using its adaptive attention mechanism. Finally， the Convolutional Attention Module （CBAM） is used to strengthen the information transmission between the encoder and the decoder to improve the segmentation accuracy of the model. The proposed method is tested on the NIH dataset， and the results show that the proposed method has good performance and can effectively solve the problem that the pancreas is difficult to segment in abdominal CT images.

Key words: Key words: pancreas segmentation, two-stage, attention mechanisms, dual-channel attention mechanism block, CBAM

中图分类号:

中图分类号：TP391

周邦湲1, 辛国江1, 梁昊2, 丁长松1. 基于两阶段的多重注意力机制网络的胰腺分割[J]. 计算机与现代化, 2025, 0(10): 67-72.

ZHOU Bangyuan1, XIN Guojiang1, LIANG Hao2, DING Changsong1. Pancreas Segmentation Based on Two-stage Network of Multiple Attention Mechanisms[J]. Computer and Modernization, 2025, 0(10): 67-72.

参考文献

［1］中华医学会外科学分会胰腺外科学组. 中国急性胰腺炎诊治指南（2021）［J］. 浙江实用医学， 2021，26（6）:511-519.
［2］ ZHOU S H， NIE D， ADELI E， et al. High-resolution encoder-decoder networks for Iow-contrast medical image segmentaion［J］. IEEE Transactions on Image Processing， 2019，29:461-475.
［3］ BAZGIR O， BARCK K， CARANO R A D， et al. Kidney segmentation using 3D U-Net localized with expectation maximization［C］// IEEE Southwest Symposium on Image Analysis and Interpretation. IEEE， 2020:22-25.
［4］ LI C， TAN Y S， CHEN W， et al. Attention UNet++:A nested attention-aware U-Net for liver CT image segmentation［C］// 2020 IEEE International Conference on Image Processing （ICIP）. IEEE， 2020:345-349.
［5］ DINIZ J O B， FERREIRA J L， CORTES O A C， et al. An automatic approach for heart segmentation in CT scans through image processing techniques and Concat-U-Net［J］. Expert Systems with Applications， 2022，196. DOI: 10.1016/j.eswa.2022.116632.
［6］ ROTH H R， LU L， FARAG A， et al. DeepOrgan: Multi-level deep convolutional networks for automated pancreas segmentation［C］// Medical Image Computing and Computer-Assisted Intervention-MICCAI 2015. Springer， 2015:556-564.
［7］ JIANG H Y， TAN H Q， FUJITA H. A hybrid method for pancreas extraction from CT image based on level set methods［J］. Computational and Mathematical Methods in Medicine， 2013，2013（1）. DOI: 10.1155/2013/479516.
［8］ FARAG A， LU L， ROTH H R， et al. A bottom-up approach for pancreas segmentation using cascaded superpixels and （deep） image patch labeling［J］. IEEE Transactions on Image Processing， 2017，26（1）:386-399
［9］ ODA M， NAKAOKA T， KITASAKA T， et al. Organ segmentation from 3D abdominal CT images based on atlas selection and graph cut［C］// Abdominal Imaging. Computational and Clinical Applications. Springer， 2011:181-188.
［10］崔珂，田启川，廉露. 基于U-Net变体的医学图像分割算法综述［J］. 计算机工程与应用， 2024，60（11）:32-49.
［11］ HUANG M L， WU Y Z. Semantic segmentation of pancreatic medical images by using convolutional neural network［J］. Biomedical Signal Processing and Control， 2022，73. DOI: 10.1016/j.bspc.2021.103458.
［12］ LIU Z， SU J， WANG R H， et al. Pancreas co-segmentation based on dynamic ROI extraction and VGGU-Net［J］. Expert Systems with Applications， 2022，192. DOI: 10.1016/j.eswa.2021.116444.
［13］付艳贞，樊建聪. 可变形分支注意力融合网络的胰腺分割方法［J］. 小型微型计算机系统， 2024，45（11）:2717-2724.
［14］ ZHOU Y Y， XIE L X， SHEN W， et al. A fixed-point model for pancreas segmentation in abdominal CT scans［C］// International Conference on Medical Image Computing and Computer-Assisted Intervention. Springer， 2017，10433:693-701.
［15］ ZHANG D W， ZHANG J J， ZHANG Q， et al. Automatic pancreas segmentation based on lightweight DCNN modules and spatial prior propagation［J］. Pattern Recognition， 2020，114. DOI: 10.1016/j.patcog.2020.107762.
［16］ QIU C J， LIU Z， SONG Y Q， et al. RTUNet: Residual transformer UNet specifically for pancreas segmentation［J］. Biomedical Signal Processing and Control， 2023，79.DOI: 10.1016/j.bspc.2022.104173.
［17］ RONNEBERGER O， FISCHER P， BROX T. U-Net: Convolutional networks for biomedical image segmentation［C］// International Conference on Medical Image Computing and Computer-Assisted Intervention. Springer， 2015，9351:234-241.
［18］ WOO S， PARK J， LEE J Y， et al. CBAM: Convolutional block attention module［C］// Computer Vison-ECCV. Springer， 2018，11211:3-19.
［19］ HU J， SHEN L， SUN G， et al. Squeeze-and-excitation networks［C］// 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition. IEEE， 2018:7132-7141.
［20］ HAN J， MORAGA C. The influence of the sigmoid function parameters on the speed of backpropagation learning［C］// IWANN’96: Proceedings of the International Workshop on Artificial Neural Networks: From Natural to Artificial Neural Computation. IEEE， 1995:195-201.
［21］ MILLETARI F， NAVAB N， AHMADI S A. V-Net:Fully convolutional neural networks for volumetric medical image segmentation［C］// 2016 4th International Conference on 3D Vision （3DV）. IEEE， 2016:565-571.
［22］ LIN T Y， GOYAL P， GIRSHICK R， et al. Focal loss for dense object detection［C］// 2017 IEEE International Conference on Computer Vision （ICCV）. IEEE， 2017:2999-3007.
［23］刘桂霞，田郁欣，王涛，等. 基于双输入3D卷积神经网络的胰腺分割算法［J］. 吉林大学学报（工学版）， 2023，53（12）:3565-3572.
［24］ JU J G， LI J M， CHANG Z Q， et al. Incorporating multi-stage spatial visual cues and active localization offset for pancreas segmentation［J］. Pattern Recognition Letters， 2023，170:85-92.
［25］ CHEN H P， LIU Y J， SHI Z N， et al. Pancreas segmentation by two-view feature learning and multi-scale supervision［J］. Biomedical Signal Processing and Control， 2022，74. DOI: 10.1016/j.bspc.2022.103519.
［26］ ZHAO H S， SHI J P， QI X J， et al. Pyramid scene parsing network［C］// 2017 IEEE Comperence on Computer Vision and Pattern Recognition（CVPR）. IEEE， 2017:6230-6239.
［27］ CHEN L C， ZHU Y K， PAPANDREOU G， et al. Encoder-decoder with atrous separable convolution for semantic image segmentation［C］// European Conference on Computer Vision. Springer， 2018:833-851.
［28］ RADOSAVOVIC I， KOSARAJU R P， GIRSHICK R， et al. Designing network design spaces［C］// 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition （CVPR）. IEEE， 2020:10425-10433.
［29］ LIU Z， MAO H Z， WU C Y， et al. A ConvNet for the 2020s［J］. arXiv preprint arXiv: 2022.01167， 2022.

[1]	师红宇, 张哲于, 杜文, 李怡. 融合空间信息的YOLOv7交通标志检测[J]. 计算机与现代化, 2025, 0(10): 7-13.
[2]	刘嵘澂1, 辛国江1, 张杨1, 朱磊2. 基于改进的DeepLabv3+模型的自然环境下舌象分割方法[J]. 计算机与现代化, 2025, 0(10): 32-36.
[3]	郭金豪, 王峰萍, 王浩琦. 面向密集场景的PB-YOLOv7行人检测方法[J]. 计算机与现代化, 2025, 0(09): 14-19.
[4]	林睿姿, 姚达, 戴欣, 沈国誉, 王嘉慧, 万伟国. 基于CycleGAN和注意力机制的人脸素描图像转换[J]. 计算机与现代化, 2025, 0(09): 61-66.
[5]	刘成, 冯广. 基于双重注意力机制的CNN-BiLSTM和LightGBM股票预测[J]. 计算机与现代化, 2025, 0(09): 97-103.
[6]	景清武, 陈洪军, 高翟, 周美美. 目标驱动的面向推荐的对话生成方法[J]. 计算机与现代化, 2025, 0(08): 16-23.
[7]	苏衍森, 牟莉. 改进YOLOv8的课堂行为检测算法[J]. 计算机与现代化, 2025, 0(08): 76-81.
[8]	高莉莎1, 彭国政2, 王翀1, 韩硕1, 项楠1, 张启哲2, 朱跃飞3, 程旭3. 基于YOLOv5的双主干网络绝缘子缺陷检测算法[J]. 计算机与现代化, 2025, 0(08): 82-88.
[9]	蔡博涵, 刘俊. 基于优化Transformer的长短期空气污染物浓度预测[J]. 计算机与现代化, 2025, 0(07): 55-62.
[10]	焦乐岩, 朱欣娟. 基于自注意力机制说话人编码器与SA-Decoder的语音克隆方法[J]. 计算机与现代化, 2025, 0(07): 69-76.
[11]	饶弘宇1, 陈馨2, 陈胜3, 夏天3, 沈力4, 吕广强5. 基于改进鲸鱼算法的Bi-LSTM电力负荷预测[J]. 计算机与现代化, 2025, 0(07): 77-82.
[12]	魏青松1, 王晓峻2, 魏源1, 曾尚琦1, 方园1. HGAT：基于混合图注意力网络的多变量时序异常检测[J]. 计算机与现代化, 2025, 0(07): 97-105.
[13]	谢培栋, 程远志, 许浩天. 海洋生物层级分类算法[J]. 计算机与现代化, 2025, 0(06): 21-27.
[14]	孙毅博, 牟莉. 基于深度学习的无人机航拍违建识别算法[J]. 计算机与现代化, 2025, 0(06): 65-70.
[15]	梁攀如, 辛国江, 丁长松. 基于改进SegFormer的胰腺图像分割方法[J]. 计算机与现代化, 2025, 0(06): 71-78.