多尺度特征融合的头影标志点检测

doi:10.19678/j.issn.1000-3428.0064173

计算机工程 ›› 2023, Vol. 49 ›› Issue (3): 271-279. doi: 10.19678/j.issn.1000-3428.0064173

多尺度特征融合的头影标志点检测

任家豪¹, 张光华², 乔钢柱¹, 武秀萍³

1. 中北大学大数据学院, 太原 030051;
2. 太原学院智能与自动化系, 太原 030032;
3. 山西医科大学口腔医学院, 太原 030001

收稿日期:2022-03-14 修回日期:2022-05-04 发布日期:2022-05-25
作者简介:任家豪(1998—),男,硕士研究生,主研方向为医学图像关键点检测、深度学习;张光华,副教授、博士;乔钢柱、武秀萍,教授、博士。
基金资助:
山西省医学重点科研项目（2021XM06）；山西省“1331工程”项目（FSP-20211331）；山西省回国留学人员科研经费资助项目（2020-149）；山西省高等学校科技创新计划项目（2021L575）。

Cephalometric Mark Point Detection with Multi-scale Feature Fusion

REN Jiahao¹, ZHANG Guanghua², QIAO Gangzhu¹, WU Xiuping³

1. College of Big Data, North University of China, Taiyuan 030051, China;
2. Department of Intelligence and Automation, Taiyuan University, Taiyuan 030032, China;
3. School of Stomatology, Shanxi Medical University, Taiyuan 030001, China

Received:2022-03-14 Revised:2022-05-04 Published:2022-05-25

摘要/Abstract

摘要： 头影标志点检测对于临床诊断、治疗计划和研究至关重要。为提高自动检测的准确性，提出一种改进的多尺度特征融合检测模型AIW-Net。采用经过预训练的轻量型网络MobileNetV2作为主干网络进行特征提取，使用上、下采样路径构成中间模块，利用改进的倒残差模块减少下采样过程中的特征损失。在解码器模块中引入从粗到细的中间监督，将得到的多个尺度热图与特征图进行融合，并在跳跃连接中使用注意力门，有效抑制特征图中的背景区域响应。在ISBI 2015 Grand Challenge提供的基准数据集Test 1上进行实验，结果表明，该模型的平均径向误差为1.14 mm，在临床可接受的误差范围2 mm与2.5 mm内的成功检测率分别为86.38%与92.10%，性能优于W-Net、IW-Net等模型。

关键词: 标志点检测, 多尺度特征融合, 倒残差结构, 注意力门, 热图回归

Abstract: The detection of cephalometric mark point is extremely crucial for clinical diagnosis, treatment planning, and research.To improve the accuracy of automatic detection, an improved multi-scale feature fusion detection model, AIW-Net, is proposed.AIW-Net uses the pre-trained lightweight network MobileNetV2 as the backbone network for feature extraction. The intermediate module comprises up and down sampling paths, and the improved inverse residual module is used to reduce the feature loss in the down-sampling process.The intermediate supervision from coarse to fine is introduced into the decoder module, the obtained multi-scale heat map is fused with the feature map, and the attention gate is used in the jump connection to effectively suppress the response of the background region in the feature map.The experimental results of the benchmark dataset Test 1 provided by ISBI 2015 Grand Challenge show that the proposed model achieves a Mean Radial Error(MRE) of 1.14 mm, and a Successful Detection Rate(SDR) of 86.38% and 92.10% within the clinically acceptable error range of 2 mm and 2.5 mm, respectively, which are better than that obtained by W-Net, IW-Net and other models.

Key words: mark point detection, multi-scale feature fusion, inverse residual structure, attention gate, heatmap regression

中图分类号:

TP391.41

任家豪, 张光华, 乔钢柱, 武秀萍. 多尺度特征融合的头影标志点检测[J]. 计算机工程, 2023, 49(3): 271-279.

REN Jiahao, ZHANG Guanghua, QIAO Gangzhu, WU Xiuping. Cephalometric Mark Point Detection with Multi-scale Feature Fusion[J]. Computer Engineering, 2023, 49(3): 271-279.

http://www.ecice06.com/CN/Y2023/V49/I3/271

图/表 14

20230314190614

20230314190617

20230314190621

20230314190624

20230314190629

20230314190632

20230314190635

20230314190638

20230314190641

20230314190645

20230314190648

20230314190651

20230314190655

20230314190659

参考文献

[1] GRAU V, ALCAÑIZ M, JUAN M C, et al.Automatic localization of cephalometric landmarks[J].Journal of Biomedical Informatics, 2001, 34(3):146-156.
[2] KEUSTERMANS J, MOLLEMANS W, VANDERMEULEN D, et al.Automated cephalometric landmark identification using shape and local appearance models[C]//Proceedings of the 20th International Conference on Pattern Recognition.Washington D.C., USA:IEEE Press, 2010:2464-2467.
[3] IBRAGIMOV B, LIKAR B, PERNUS F, et al.Computerized cephalometry by game theory withshape- and appearance-based landmark refinement[C]//Proceedings of International Symposium on Biomedical imaging.Washington D.C., USA:IEEE Press, 2015:26-35.
[4] OKTAY O, BAI W J, GUERRERO R, et al.Stratified decision forests for accurate anatomical landmark localization in cardiac images[J].IEEE Transactions on Medical Imaging, 2017, 36(1):332-342.
[5] CRIMINISI A, SHOTTON J, BUCCIARELLI S.Decision forests with long-range spatial context for organlocalization in CT volumes[EB/OL].[2022-02-10].https://www.microsoft.com/en-us/research/wp-content/uploads/2016/02/Criminisi_MICCAI_PMMIA_2009_.pdf.
[6] LINDNER C, COOTES T F.Fully automatic cephalometric evaluation using random forest regressionvoting[EB/OL].[2022-02-10].https://www.researchgate.net/publication/287608380_Fully_Automatic_Cephalometric_Evaluation_using_Random_Forest_Regression-Voting.
[7] 杨涵方, 周向东.基于深度稀疏辨别的跨领域图像分类[J].计算机工程, 2018, 44(4):310-316. YANG H F, ZHOU X D.Cross domain image classification based on deep sparse discrimination[J].Computer Engineering, 2018, 44(4):310-316.(in Chinese)
[8] LONG J, SHELHAMER E, DARRELL T.Fully convolutional networks for semantic segmentation[C]//Proceedings of IEEE Conference on Computer Vision and Pattern Recognition.Washington D.C., USA:IEEE Press, 2015:3431-3440.
[9] ZHAO Z Q, ZHENG P, XU S T, et al.Object detection with deep learning:a review[J].IEEE Transactions on Neural Networks and Learning Systems, 2019, 30(11):3212-3232.
[10] LEE H S, PARK M, KIM J.Cephalometric landmark detection in dental X-ray images using convolutional neural networks[EB/OL].[2022-02-10].https://www.researchgate.net/publication/314221440_Cephalometric_land mark_detection_in_dental_x-ray_images_using_convolu tional_neural_networks.
[11] AUBERT B, VAZQUEZ C, CRESSON T, et al.Automatic spine and pelvis detection in frontal X-rays using deep neural networks for patch displacement learning[C]//Proceedings of the 13th International Symposium on Biomedical Imaging.Washington D.C., USA:IEEE Press, 2016:1426-1429.
[12] ARIK S, IBRAGIMOV B, XING L.Fully automated quantitative cephalometry using convolutional neural networks[J].Journal of Medical Imaging, 2017, 4(1):14501-14510.
[13] PAYER C, ŠTERN D, BISCHOF H, et al.Regressing heatmaps for multiple landmark localization using CNNs[M]//OURSELIN S, JOSKOWICZ L, SABUNCU M R, et al.Medical Image Computing and Computer-Assisted Intervention-MICCAI.Berlin, Germany:Springer, 2016:230-238.
[14] ZHONG Z S, LI J, ZHANG Z X, et al.An attention-guided deep regression model for landmark detection in cephalograms[M]//SHEN D G, LIU T M, PETERS T M, et al.Lecture Notes in Computer Science.Berlin, Germany:Springer, 2019:540-548.
[15] 齐国强, 姚剑敏, 胡海龙, 等.引入多尺度特征图融合的人脸关键点检测网络[J].计算机应用研究, 2020, 37(12):3825-3829. QI G Q, YAO J M, HU H L, et al.Facial landmark detection network with multi-scale feature map fusion[J].Application Research of Computers, 2020, 37(12):3825-3829.(in Chinese)
[16] 张凡.基于轻量化多尺度特征融合与注意力机制的交通标志检测与识别[D].西安:长安大学, 2021. ZHANG F.Traffic sign detection and recognition based on lightweight multi-scale feature fusion and attention mechanism[D].Xi'an:Changan University, 2021.(in Chinese)
[17] 李赛, 黎浩江, 刘立志, 等.基于尺度注意力沙漏网络的头部MRI解剖点自动定位[J].光学精密工程, 2021, 29(9):2278-2286. LI S, LI H J, LIU L Z, et al.Automatic location of anatomical points in head MRI based on the scale attention hourglass network[J].Optics and Precision Engineering, 2021, 29(9):2278-2286.(in Chinese)
[18] RONNEBERGER O, FISCHER P, BROX T.U-Net:convolutional networks for biomedical image segmentation[C]//Proceedings of International Conference on Medical Image Computing and Computer-Assisted Intervention.Berlin, Germany:Springer, 2015:234-241.
[19] MILLETARI F, NAVAB N, AHMADI S A.V-Net:fully convolutional neural networks for volumetric medical image segmentation[C]//Proceedings of the 4th International Conference on 3D Vision.Washington D.C., USA:IEEE Press, 2016:565-571.
[20] TAN M X, PANG R M, LE Q V.EfficientDet:scalable and efficient object detection[C]//Proceedings of IEEE/CVF Conference on Computer Vision and Pattern Recognition.Washington D.C., USA:IEEE Press, 2020:10778-10787.
[21] LIN T Y, DOLLÁR P, GIRSHICK R, et al.Feature pyramid networks for object detection[C]//Proceedings of IEEE Conference on Computer Vision and Pattern Recognition.Washington D.C., USA:IEEE Press, 2017:936-944
[22] LIU S, QI L, QIN H F, et al.Path aggregation network for instance segmentation[C]//Proceedings of IEEE/CVF Conference on Computer Vision and Pattern Recognition.Washington D.C., USA:IEEE Press, 2018:8759-8768.
[23] SANDLER M, HOWARD A, ZHU M L, et al.MobileNetV2:inverted residuals and linear bottlenecks[C]//Proceedings of IEEE/CVF Conference on Computer Vision and Pattern Recognition.Washington D.C., USA:IEEE Press, 2018:4510-4520.
[24] OH K, OH I S, LE V N T, et al.Deep anatomical context feature learning for cephalometric landmark detection[J].IEEE Journal of Biomedical and Health Informatics, 2021, 25(3):806-817.
[25] SUN K, XIAO B, LIU D, et al.Deep high-resolution representation learning for human pose estimation[C]//Proceedings of IEEE/CVF Conference on Computer Vision and Pattern Recognition.Washington D.C., USA:IEEE Press, 2020:5686-5696.
[26] NEWELL A, YANG K Y, DENG J.Stacked hourglass networks for human pose estimation[EB/OL].[2022-02-10] https://link.springer.com/content/pdf/10.1007/978-3-319-46484-8_29.pdf.
[27] HE K M, GKIOXARI G, DOLLÁR P, et al.Mask R-CNN[C]//Proceedings of IEEE International Conference on Computer Vision.Washington D.C., USA:IEEE Press, 2017:2980-2988.
[28] UPSCHULTE E, HARMELING S, AMUNTS K, et al.Contour proposal networks for biomedical instance segmentation[EB/OL].[2022-02-10].https://arxiv.org/abs/2104.03393.

选择文件类型/文献管理软件名称

选择包含的内容

多尺度特征融合的头影标志点检测

Cephalometric Mark Point Detection with Multi-scale Feature Fusion

RichHTML

PDF

可视化

被引次数

摘要/Abstract

引用本文

使用本文

图/表 14

参考文献

相关文章 6

编辑推荐

Metrics

本文评价

[1]	宋志娜, 李莎, 杨建明, 徐川. 基于特征与区域定位增强的遥感舰船目标检测[J]. 计算机工程, 2023, 49(8): 257-264.
[2]	赫晓慧, 宋定君, 李盼乐, 田智慧, 周广胜. 融合多尺度特征的遥感影像道路提取方法[J]. 计算机工程, 2022, 48(8): 196-205.
[3]	于敏, 屈丹, 司念文. 改进的RetinaNet目标检测算法[J]. 计算机工程, 2022, 48(8): 249-257.
[4]	白宗文, 弋婷婷, 周美丽, 魏嵬. 基于多尺度特征融合的人脸图像修复方法[J]. 计算机工程, 2021, 47(5): 213-220,228.
[5]	康智慧, 王全玉, 王战军. 一种端到端的人脸对齐方法[J]. 计算机工程, 2021, 47(10): 207-213.
[6]	余莉萍, 梁镇麟, 梁瑞宇. 基于改进LSTM的儿童语音情感识别模型[J]. 计算机工程, 2020, 46(6): 40-49.

模态框（Modal）标题

选择文件类型/文献管理软件名称

选择包含的内容

多尺度特征融合的头影标志点检测

Cephalometric Mark Point Detection with Multi-scale Feature Fusion

RichHTML

PDF

可视化

被引次数

摘要/Abstract

引用本文

使用本文

图/表 14

参考文献

相关文章 6

编辑推荐

Metrics

本文评价