计算机科学

计算机科学 ›› 2025, Vol. 52 ›› Issue (6A): 240600020-10.doi: 10.11896/jsjkx.240600020

• 智能医学工程 • 上一篇    下一篇

LST-ARBunet:一种改进的用于肺部CT图像结节检测和分割的深度学习算法

陈祥龙1,2, 李海军3   

  1. 1 三亚学院信息与智能工程学院 海南 三亚 572022
    2 三亚学院陈国良院士团队创新中心 海南 三亚 572022
    3 北京工业大学耿丹学院空天信息学院 北京 101301
  • 出版日期:2025-06-16 发布日期:2025-06-12
  • 通讯作者: 李海军(haijunli1968@163.com)
  • 作者简介:(1482103902@qq.com)
  • 基金资助:
    三亚学院硕士研究生导师“产教融合”研究项目(USY23CJRH03)

LST-ARBunet:An Improved Deep Learning Algorithm for Nodule Segmentation in Lung CT Images

CHEN Xianglong1,2, LI Haijun3   

  1. 1 School of Information and Intelligent Engineering,University of Sanya,Sanya,Hainan 572022,China
    2 Academician Guoliang Chen Team Innovation Center,University of Sanya,Sanya,Hainan 572022,China
    3 School of Aerospace Information,Gengdan Institute of Beijing University of Technology,Beijing 101301,China
  • Online:2025-06-16 Published:2025-06-12
  • About author:CHEN Xianglong,born in 2001,postgraduate,is a member of CCF(No.Q5078G).His main research interests include computer vision and data mi-ning.
    LI Haijun,born in 1968,Ph.D,associate professor,master supervisor,is a member of CCF(No.F7747M).His main research interests include computer vision and data mining.
  • Supported by:
    University of Sanya Master’s Degree Supervisor’s Research Program on “Industry-Education Integration”(USY23CJRH03).

PDF (PC)

32

摘要： 本文提出了一种新颖的深度学习模型——LST-ARBunet,以解决肺部计算机断层扫描(CT)图像中肺结节的精确分割问题。在肺结节检测领域,受结节尺寸微小、形态多样及与周围组织相似性高等因素影响,技术实现难度大。LST-ARBunet模型的主要创新在于在下采样的过程中融入Swin-Transformer结构在不同尺度上捕捉肺部影像的特征;对Swin-Transformer结构进行局部卷积前置和共享参数处理来降低模型参数量;在上采样的过程中加入自定义的注意力机制来捕获重要细节特征;并且使用残差瓶颈块(Inverted Residual Blocks)替换普通卷积,对模型进行轻量化。在公开肺结节CT数据集LIDC-IDRI上进行实验,LST-ARBunet展现出了一定的性能提升,交并比(Intersection over Union,IoU)为0.889,平均表面距离(Average Symmetric Surface Distance,ASSD)为1.453,Dice相似系数(Dice Score)为0.884,都超越了消融实验的模型以及ResUnet,PSPNet,DeepLabv3+模型。此外,LST-ARBunet在保持高分割精度的同时,还保持了相对合理的1.3 s推理时间,为临床应用提供了可行的效率平衡。本研究为肺结节分割提供了新的技术途径,未来工作将探索该模型在更多样化的临床数据集上的表现,进一步优化模型效率,并推进其在实际医疗环境中的部署与应用,为肺癌的早期检测与治疗提供强有力的支持。

关键词: U-net, Swin-Transformer, 残差瓶颈轻量化, 注意力机制, 肺结节分割

Abstract: In this paper,a novel deep learning model,LST-ARBunet,is proposed to solve the problem of accurate segmentation of lung nodules in lung computed tomography(CT) images.In the field of lung nodule detection,it is difficult to realize the technology due to factors such as tiny nodule size,diverse morphology and high similarity with surrounding tissues.The main innovations of the LST-ARBunet model are the incorporation of the Swin-Transformer structure in the downsampling process to capture the features of the lung images in different scales;the Swin-Transformer structure is subjected to a local convolutional fronts and shared parameter processing to reduce the number of model parameters;incorporating a customized attention mechanism in the upsampling process to capture important detailed features;and using inverted residual blocks instead of normal convolution to lighten the model.Experimental validation on the publicly available lung nodule CT dataset LIDC-IDRI,LST-ARBunet demonstrates some performance improvement,with an intersection over union(IoU) of 0.889 and average symmetric surface distance(ASSD) of 1.453,and Dice similarity score(Dice Score) of 0.884,all of which outperform the models of the ablation experiments as well as the ResUnet,PSPNet,and DeepLabv3+ models.In addition,LST-ARBunet maintains a high segmentation accuracy while maintaining a relatively reasonable inference time of 1.3s,providing a feasible balance of efficiency for clinical applications.This study provides a new technical approach to lung nodule segmentation,and future work will explore the model’s performance on more diverse clinical datasets,further optimize the model efficiency,and advance its deployment and application in real-world healthcare environments to provide strong support for the early detection and treatment of lung cancer.

Key words: U-net, Swin-Transformer, Residual bottleneck lightening, Attention mechanism, Lung nodule segmentation

中图分类号: 

  • TP181
[1]RONNEBERGER O,FISCHER P,BROX T.U-net:Convolu-tional networks for biomedical image segmentation[C]//International Conference on Medical Image Computing and Computer-assisted Intervention.Springer,2015:234-241.
[2]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.Springer,2018:3-11.
[3]XIAO X,LIAN S,LUO Z,et al.Weighted res-unet for high-quality retina vessel segmentation[C]//2018 9th International Conference on Information Technology in Medicine and Education(ITME).IEEE,2018:327-331.
[4]OKTAY O,SCHLEMPER J,FOLGOC L L,et al.Attention u-net:Learning where to look for the pancreas[J].arXiv:1804.03999,2018.
[5]LI X,CHEN H,QI X,et al.H-denseunet:hybrid densely con-nected unet for liver and tumor segmentation from ct volumes[J].IEEE Transactions on Medical Imaging,2018,37(12):2663-2674.
[6]ALOM M Z,HASAN M,YAKOPCIC C,et al.Recurrent residual convolutional neural network based on u-net(r2unet) for medical image segmentation[J].arXiv:1802.06955,2018.
[7]VALANARASU J M J,SINDAGI V A,HACIHALILOGLU I,et al.Kiu-net:Towards accurate segmentation of biomedical images using over-complete representations[C]//International Conference on Medical Image Computing and Computer-Assisted Intervention.Springer,2020:363-373.
[8]HUANG H,LIN L,TONG R,et al.Unet 3+:A full-scale connected unet for medical image segmentation[C]//2020 IEEE International Conference on Acoustics,Speech and Signal Processing(ICASSP 2020).IEEE,2020:1055-1059.
[9]WANG X,GIRSHICK R,GUPTA A,et al.Non-local neuralnetworks[C]//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition.2018:7794-7803.
[10]HUANG Z,WANG X,HUANG L,et al.Ccnet:Criss-cross attention for semantic segmentation[C]//Proceedings of the IEEE/CVF International Conference on Computer Vision.2019:603-612.
[11]HOU Q,ZHOU D,FENG J.Coordinate attention for efficient mobile network design[J].arXiv:2103.02907,2021.
[12]WANG G T,LI W Q,ZULUAGA M A,et al.Interactive Medical Image Segmentation Using Deep Learning With Image-Specific Fine Tuning[J].IEEE Transactions on Medical Imaging,2018,37(7):1562-1573.
[13]LI Y,FAN Y.DeepSEED:3D Squeeze-and-Excitation Encoder-Decoder Convolutional Neural Networks for Pulmonary Nodule Detection[C]//IEEE 17th International Symposium on Biomedical Imaging(ISBI 2020).Iowa City,IA,USA,2020:1866-1869.
[14]MEI J,CHENG M M,XU G,et al.SANet:A Slice-Aware Network for Pulmonary Nodule Detection[J].IEEE Transactions on Pattern Analysis and Machine Intelligence,2022,44(8):4374-4387.
[15]CELAYA A,ACTOR J A,MUTHUSIVARAJAN R,et al.PocketNet:A Smaller Neural Network for Medical Image Analysis[J].IEEE Transactions on Medical Imaging,2023,42(4):1172-1184.
[16]ORTEGA-RUÍZ M A,KARABAĞ C,ROMAN-RANGEL E,et al.DRD-UNet,a UNet-Like Architecture for Multi-Class Breast Cancer Semantic Segmentation[J].IEEE Access,2024,12:40412-40424.
[17]ARMAND T P T,BHATTACHARJEE S,CHOI H K,et al.Transformers Effectiveness in Medical Image Segmentation:A Comparative Analysis of UNet-Based Architectures[C]//International Conference on Artificial Intelligence in Information and Communication(ICAIIC 2024).IEEE,2024.
[18]JIANG W,ZHI L,ZHANG S,et al.A Dual-Branch Framework With Prior Knowledge for Precise Segmentation of Lung Nodules in Challenging CT Scans[J].IEEE Journal of Biomedical and Health Informatics,2024,28(3):1540-1551.
[19]NAGHNE R,KAZEMI A,MOGHADDASI H,et al.An Efficient Capsule-based Network for 2D Left Ventricle Segmentation in Echocardiography Images[C]//45th Annual International Conference of the IEEE Engineering in Medicine & Biology Society(EMBC 2023).Sydney,Australia,2023:1-4.
[20]LING Y,WANG Y,DAI W,et al.MTANet:Multi-Task Attention Network for Automatic Medical Image Segmentation and Classification[J].IEEE Transactions on Medical Imaging,2024,43(2):674-685.
[21]MASOOD A,NASEEM U,RAZZAK I.Multi-Scale SwinTransformer Enabled Automatic Detection and Segmentation of Lung Metastases Using CT Images[C]//IEEE 20th International Symposium on Biomedical Imaging(ISBI 2023).Cartagena,Colombia,2023:1-5.
[22]LIN A,CHEN B,XU J,et al.DS-TransUNet:Dual Swin Transformer U-Net for Medical Image Segmentation[J].IEEE Transactions on Instrumentation and Measurement,2022,71:1-15.
[23]JI Z L,ZHAO Z H,ZENG X Y,et al.ResDSda_U-Net:A Novel U-Net-Based Residual Network for Segmentation of Pulmonary Nodules in Lung CT Images[J].IEEE Access,2023,11:87775-87789.
[24]TANG T,ZHANG R,LIN K,et al.SM-RNet:A Scale-Aware-Based Multiattention-Guided Reverse Network for Pulmonary Nodules Segmentation[J].IEEE Transactions on Instrumentation and Measurement,2023,72:1-14.
[25]ASHA V,BHAVANISHANKAR K.Lung Cancer Detection using CT Scans:Image Processing through Deep Learning-A Review[C]//8th International Conference on Communication and Electronics Systems(ICCES 2023).Coimbatore,India,2023:1203-1213.
[26]ZANNAH R,BASHAR M,MUSHFIQ R B,et al.SemanticSegmentation on Panoramic Dental X-Ray Images Using U-Net Architectures[J].IEEE Access,2024,12:44598-44612.
[27]LIU Z,LIN Y,CAO Y,et al.Swin transformer:Hierarchical vision transformer using shifted windows[J].arXiv:2103.14030,2021.
[28]ZHOU X,ZHOU L,GONG S,et al.Swin Transformer Embedding Dual-Stream for Semantic Segmentation of Remote Sensing Imagery[J].IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing,2024,17:175-189.
[29]LI P,WANG H,WANG Z,et al.Swin Routiformer:Moss Classification Algorithm Based on Swin Transformer With Bi-Level Routing Attention[J].IEEE Access,2024,12:53396-53407.
[30]PAN S Y,LIU Y Q,HALEK S,et al.Multi-dimension unified Swin Transformer for 3D Lesion Segmentation in Multiple Anatomical Locations[C]//IEEE 20th International Symposium on Biomedical Imaging(ISBI 2023).Cartagena,Colombia,2023:1-5.
[31]PROME T A,JASIM TAHITI T.MobileNetV2 Based Cervical Cancer Classification Using Pap Smear Images[C]//International Conference on Artificial Intelligence,Computer,Data Sciences and Applications(ACDSA 2024).Victoria,Seychelles,2024:1-7.
[32]XUE M,GU L.Surgical instrument segmentation method based on improved MobileNetV2 network[C]//6th International Symposium on Computer and Information Processing Technology(ISCIPT 2021).Changsha,China,2021:744-747.
[33]HUANG G H,ZHU J W,LI J J,et al.Channel-AttentionU-Net:Channel Attention Mechanism for Semantic Segmentation of Esophagus and Esophageal Cancer[J].IEEE Access,2020,8:122798-122810.
[34]QI L,QIN X,GAO F,et al.SAWU-Net:Spatial AttentionWeighted Unmixing Network for Hyperspectral Images[J].IEEE Geoscience and Remote Sensing Letters,2023,20:1-5.
[35]HU J,SHEN L,ALBANIE S,et al.Squeeze-and-Excitation Networks[J].IEEE Transactions on Pattern Analysis and Machine Intelligence,2020,42(8):2011-2023.
[36]MING Q,XIAO X.Towards Accurate Medical Image Segmentation With Gradient-Optimized Dice Loss[J].IEEE Signal Processing Letters,2024,31:191-195.
[37]HO Y,WOOKEY S.The Real-World-Weight Cross-EntropyLoss Function:Modeling the Costs of Mislabeling[J].IEEE Access,2020,8:4806-4813.
[38]HAN F F,ZHANG G P,WANG H F,et al.A texture feature analysis for diagnosis of pulmonary nodules using LIDC-IDRI database[C]//2013 IEEE International Conference on Medical Imaging Physics and Engineering.Shenyang,China,2013:14-18.
[39]AHMED I,CHEHRI A,JEON G,et al.Automated Pulmonary Nodule Classification and Detection Using Deep Learning Architectures[J].IEEE/ACM Transactions on Computational Biology and Bioinformatics,2023,20(4):2445-2456.
[40]HUANG Y,TANG Z,CHEN D,et al.Batching Soft IoU forTraining Semantic Segmentation Networks[J].IEEE Signal Processing Letters,2020,27:66-70.
[41]XU T,SUN X,DIAO W,et al.ASSD:Feature Aligned Single-Shot Detection for Multiscale Objects in Aerial Imagery[J].IEEE Transactions on Geoscience and Remote Sensing,2022,60:1-17.
Viewed
Full text


Abstract

Cited
  Shared   
  Discussed   
No Suggested Reading articles found!
渝ICP备16013121号-4
地址：重庆市渝北区洪湖西路18号    邮编：401121  
电话：023-63500828（编辑部） 023-67039612（会议/专题） 023-67039623（财务/发票）
E-mail：jsjkx12@163.com
本系统由北京玛格泰克科技发展有限公司设计开发