| 751 | 1 | 13 |
| 下载次数 | 被引频次 | 阅读次数 |
该文提出了一种融合改进的视觉状态空间模型(VMamba)和YOLOv8的网络模型YOLOMamba用于结肠镜图像息肉检测任务.YOLOMamba利用VMamba的状态空间模型(SSM)捕获长距离依赖的特性增强了模型全局特征提取能力.同时，为了适应息肉检测任务，该文通过改进VMamba,使模型在保证样本粗粒度特征提取的同时，有效提升原本SSM的局部特征提取能力.融合后的模型在仅仅具有YOLOv8 40%参数量、30%计算量的情况下，性能依旧匹敌甚至优于YOLOv8,既实现了轻量化又提升了模型精度.该文在3个公开数据集上进行了实验评估.对比目前常用目标检测模型，该文提出的YOLOMamba息肉检测算法在精度和视觉效果上均获得了提升.
Abstract：This paper proposes a novel network model, YOLOMamba, which integrates an improved VMamba(Visual State Spaces Model) and YOLOv8(You Only Look Once Version 8) for colorectal polyp detection in colonoscopy images. YOLOMamba leverages VMamba's SSM(State-Space Model) to capture long-range dependencies, enhancing the model's global feature extraction capabilities. To better adapt to the polyp detection task, this study modifies VMamba to improve its ability for extracting both coarse and fine-grained features. As a result, the fused model achieves comparable or even slightly better performance than YOLOv8 while reducing the parameter count and computational cost to 40% and 30%, respectively, of YOLOv8. Experiments conducted on three public datasets demonstrate that the proposed YOLOMamba outperforms commonly used object detection models in both accuracy and visual quality, achieving a balance between lightweight design and high precision.
[1] SIEGEL R L,MILLER K D,GODING SAUER A,et al.Colorectal cancer statistics,2020[J].CA:A cancer journal for clinicians,2020,70(3):145-164.
[2] SIEGEL R L,MILLER K D,WAGLE N S,et al.Cancer statistics,2023[J].CA:A cancer journal for clinicians,2023,73(1):17-48.
[3] 郭兰伟，郑黎阳，陈琼，等.河南省城市地区结肠镜筛查人群结直肠进展期肿瘤检出情况及其影响因素分析[J].中华肿瘤杂志，2024,46(8):794-800
[4] 于杰瑶.结肠镜下息肉图像分割方法的研究[D].哈尔滨：哈尔滨工程大学，2020.
[5] REN S,HE K,GIRSHICK R,et al.Faster R-CNN:Towards real-time object detection with region proposal networks[J].IEEE transactions on pattern analysis and machine intelligence,2016,39(6):1137-1149.
[6] JIANG P,ERGU D,LIU F,et al.A Review of Yolo algorithm developments[J].Procedia computer science,2022,199:1066-1073.
[7] GU A,DAO T.Mamba:Linear-time sequence modeling with selective state spaces[J].arXiv preprint arXiv:2312.00752,2023.
[8] JOCHER G,CHAURASIA A,QIU J.Ultralytics YOLO (Version 8.0.0) [CP/OL].(2023-05-20)[2024-09-30].https://github.com/ultralytics/ultralytics.
[9] LIU Y,TIAN Y,ZHAO Y,et al.Vmamba:Visualstate space model[J].arXiv preprint arXiv:2401.10166,2024.
[10] BA J L,KIROS J R,HINTON G E.Layer normalization[J].arXiv preprint arXiv:1607.06450,2016.
[11] CHOLLET F.Xception:Deep learning with depthwise separable convolutions[C]//Proceedings of the IEEEConference on Computer Vision and Pattern Recognition.2017:1251-1258.
[12] GHIASI G,LIN T Y,LE Q V.Nas-fpn:Learning scalable feature pyramid architecture for object detection[C]//Proceedings of the IEEE/CVFConference on Computer Vision and Pattern Recognition.2019:7036-7045.
[13] WANG K,LIEW J H,ZOU Y,et al.Panet:Few-shot image semantic segmentation with prototype alignment[C]//Proceedings of the IEEE/CVF International Conference on Computer Vision.2019:9197-9206.
[14] HE K,ZHANG X,REN S,et al.Spatialpyramid pooling in deep convolutional networks for visual recognition[J].IEEE transactions on pattern analysis and machine intelligence,2015,37(9):1904-1916.
[15] Polyp Detection Dataset[EB/OL].(2024-04-27)[2024-09-30].https://universe.roboflow.com/graduate-plqmj/polypdetection-jxnuv.
[16] XUAN K Y .Polyp_detection dataset [EB/OL].(2024-04-27)[2024-09-30].https://universe.roboflow.com/xuan-ky/polyp_detection-pkrr1 .
[17] LI K,FATHAN M I,PATEL K,et al.Colonoscopy polyp detection and classification:Dataset creation and comparative evaluations[J].Plos one,2021,16(8):e0255809.
[18] RUDER S.An overview of gradient descent optimization algorithms[J].arXiv preprint arXiv:1609.04747,2016.
[19] LI C,LI L,JIANG H,et al.YOLOv6:A single-stage object detection framework for industrial applications[J].arXiv preprint arXiv:2209.02976,2022.
[20] WANG A,CHEN H,LIU L,et al.Yolov10:Real-time end-to-end object detection[J].arXiv preprint arXiv:2405.14458,2024.
[21] Ultralytics.YOLO11 Documentation[EB/OL].(2024-11-26)[2024-11-30].https://docs.ultralytics.com/models/yolo11.
基本信息:
DOI：10.13715/j.issn.2096-644X.20241003.0002
中图分类号:R574;TP391.41;TP183
引用信息:
[1]邱春林,王冰莹,胡凯.一种结合Mamba和YOLOv8的结肠镜图像息肉检测算法[J].湘潭大学学报(自然科学版),2025,47(03):54-64.DOI:10.13715/j.issn.2096-644X.20241003.0002.
基金信息:
国家自然科学基金(62272404); 湖南省普通高等学校教学改革研究项目(202401000574); 湖南省学位与研究生教学改革研究项目(2023JGYB132)