基于DYOLO神经网络的超声图像肾脏检测

doi:10.19678/j.issn.1000-3428.0058565

计算机工程 ›› 2021, Vol. 47 ›› Issue (7): 307-313. doi: 10.19678/j.issn.1000-3428.0058565

基于DYOLO神经网络的超声图像肾脏检测

刘奇¹, 赵丽霞², 郑曙光², 赵希梅^1,3

1. 青岛大学计算机科学技术学院, 山东青岛 266071;
2. 青岛大学附属医院腹部超声科, 山东青岛 266003;
3. 山东省数字医学与计算机辅助手术重点实验室, 山东青岛 266071

收稿日期:2020-06-08 修回日期:2020-07-14 发布日期:2020-07-15
作者简介:刘奇(1994-),男,硕士研究生,主研方向为医学图像处理、深度学习;赵丽霞、郑曙光,主治医师;赵希梅(通信作者),副教授。
基金资助:
国家自然科学基金（61303079）。

Kidney Detection Using Ultrasound Image Based on DYOLO Neural Network

LIU Qi¹, ZHAO Lixia², ZHENG Shuguang², ZHAO Ximei^1,3

1. College of Computer Science and Technology, Qingdao University, Qingdao, Shandong 266071, China;
2. Department of Abdominal Ultrasound, The Affiliated Hospital of Qingdao University, Qingdao, Shandong 266003, China;
3. Shandong Key Laboratory of Digital Medicine and Computer-assisted Surgery, Qingdao, Shandong 266071, China

Received:2020-06-08 Revised:2020-07-14 Published:2020-07-15

摘要/Abstract

摘要： 为便于慢性肾脏疾病的计算机辅助诊断，提出一种基于DYOLO神经网络学习模型的自动超声图像肾脏检测方法。将YOLOv3和可变形卷积网络集成在一个端到端学习框架中，使得DYOLO可根据肾脏的大小和形状自适应调节接收域，以适应肾脏的各种纹理特征形变，实现临床超声图像中肾脏的自动检测。在自制KidneyDetec超声图像肾脏检测数据集上的实验结果表明，该方法在DYOLO网络模型的图像输入尺寸为416像素×416像素和608像素×608像素的情况下分别取得了89.6%和90.5%的平均精度均值，相比基于深度学习的目标检测方法具有更高的检测速度和检测精度，适用于慢性肾脏疾病的早期诊断。

关键词: 慢性肾脏疾病, 计算机辅助诊断, 深度神经网络, 超声图像, 目标检测

Abstract: In order to facilitate the Computer Aided Diagnosis(CAD) of Chronic Kidney Disease(CKD),a kidney detection using ultrasound image based on DYOLO neural network model is proposed.The method integrates YOLOv3 and Deformable Convolutional Network(DCN) into an end-to-end learning framework,making DYOLO adaptively adjust the receiving area according to the size and shape of the kidney to adapt to various texture feature deformations,and realizes automatic kidney detection in clinical ultrasound images.Experimental results on a self-made ultrasound image-based kidney detection dataset,KidneyDetec,show that the mean Average Precision(mAP) of the proposed method reaches 89.6% when the image size of the DYOLO input is 416×416 pixels,and 90.5% when the image size of the DYOLO input is 608×608 pixels.Compared with deep learning-based target detection methods,the proposed method has higher detection speed and accuracy,displaying excellent applicability to the early diagnosis of chronic kidney diseases.

Key words: Chronic Kidney Disease(CKD), Computer Aided Diagnosis(CAD), Deep Neural Network(DNN), ultrasound image, object detection

中图分类号:

TP391.41

刘奇, 赵丽霞, 郑曙光, 赵希梅. 基于DYOLO神经网络的超声图像肾脏检测[J]. 计算机工程, 2021, 47(7): 307-313.

LIU Qi, ZHAO Lixia, ZHENG Shuguang, ZHAO Ximei. Kidney Detection Using Ultrasound Image Based on DYOLO Neural Network[J]. Computer Engineering, 2021, 47(7): 307-313.

http://www.ecice06.com/CN/Y2021/V47/I7/307

图/表 9

20210721093935

20210721093938

20210721093942

20210721093946

20210721093949

20210721093953

20210721093956

20210721093959

20210721094002

参考文献

[1] WEBSTER A C,NAGLER E V,MORTON R L,et al.Chronic kidney disease[J].Lancet,2017,389(10075):1238-1252.
[2] 朱丹丹,李世军,黄丽璇,等.降低肾活检并发症发生率[J].中国卫生质量管理,2018,25(2):80-83. ZHU D D,LI S J,HUANG L X,et al.Reducing the incidence of renal biopsy complications[J].Chinese Health Quality Management,2018,25(2):80-83.(in Chinese)
[3] 宋波,宋同峰.慢性肾病辅助诊断系统的设计与实现[J].计算机测量与控制,2019,27(10):50-54. SONG B,SONG T F.Design and implementation of chronic kidney disease auxiliary diagnosis system[J].Computer Measurement and Control,2019,27(10):50-54.(in Chinese)
[4] CASTELLINO R A.Computer Aided Detection(CAD):an overview[J].Cancer Imaging,2005,5:17-19.
[5] 庞衍平,王培军,王秀艳.超声造影定量分析技术诊断早期慢性肾病的临床价值[J].医学影像学杂志,2016,26(8):1460-1463. PANG Y P,WANG P J,WANG X Y.The clinical value of ultrasound contrast quantitative analysis technology in the diagnosis of early chronic kidney disease[J].Journal of Medical Imaging,2016,26(8):1460-1463.(in Chinese)
[6] KUO C C,CHANG C M,LIU K T,et al.Automation of the kidney function prediction and classification through ultrasound-based kidney imaging using deep learning[J].Digital Medicine,2019,2(1):1-9.
[7] JACKSON P,HARDCASTLE N,DAWE N,et al.Deep learning renal segmentation for fully automated radiation dose estimation in unsealed source therapy[J].Frontiers in Oncology,2018,8:215-224.
[8] YIN S,PENG Q M,LI H M,et al.Automatic kidney segmentation in ultrasound images using subsequent boundary distance regression and pixelwise classification networks[J].Medical Image Analysis,2020,60:101602.
[9] NITHYA A,APPATHURAI A,VENKATADRI N,et al.Kidney disease detection and segmentation using artificial neural network and multi-kernel k-means clustering for ultrasound images[J].Measurement,2020,149:106952.
[10] ZHENG Q,TASTAN G,FAN Y.Transfer learning for diagnosis of congenital abnormalities of the kidney and urinary tract in children based on ultrasound imaging data[C]//Proceedings of IEEE International Symposium on Biomedical Imaging.Washington D.C.,USA:IEEE Press,2018:97-104.
[11] DAI J F,QI H Z,XIONG Y W,et al.Deformable convolutional networks[C]//Proceedings of 2017 IEEE International Conference on Computer Vision.Washington D.C.,USA:IEEE Press,2017:127-132.
[12] 郭正华,陈立福.基于自适应感受野的DC-SSD目标检测算法[J].工业控制计算机,2019,32(5):90-91,94. GUO Z H,CHEN L F.DC-SSD target detection algorithm based on adaptive receptive field[J].Industrial Control Computer,2019,32(5):90-91,94.(in Chinese)
[13] 刘宗宝.基于深度学习的水下视频目标检测与跟踪[D].哈尔滨:哈尔滨工程大学,2019. LIU Z B.Underwater video target detection and tracking based on deep learning[D].Harbin:Harbin Engineering University,2019.(in Chinese)
[14] REDMON J,FARHADI A.YOLOv3:an incremental improvement[EB/OL].[2020-05-12].https://arxiv.org/abs/1804.02767.
[15] REDMON J,FARHADI A.YOLO9000:better,faster,stronger[C]//Proceedings of 2017 IEEE Conference on Computer Vision and Pattern Recognition.Washington D.C.,USA:IEEE Press,2017:6517-6525.
[16] REDMON J,DIVVALA S K,GIRSHICK R,et al.You only look once:unified,real-time object detection[C]//Proceedings of 2016 IEEE Conference on Computer Vision and Pattern Recognition.Washington D.C.,USA:IEEE Press,2016:779-788.
[17] GIRSHICK R.Fast R-CNN[C]//Proceedings of IEEE International Conference on Computer Vision.Washington D.C.,USA:IEEE Press,2015:1440-1448.
[18] 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,2017,39(6):1137-1149.
[19] HE K M,ZHANG X Y,REN S Q,et al.Deep residual learning for image recognition[C]//Proceedings of IEEE Conference on Computer Vision & Pattern Recognition.Washington D.C.,USA:IEEE Press,2016:770-778.
[20] LIN T Y,DOLLAR 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,2017:227-233.
[21] LIU W,ANGUELOV D,ERHAN D,et al.SSD:single shot multibox detector[C]//Proceedings of European Conference on Computer Vision.Berlin,Germany:Springer,2016:127-131.
[22] GAO F,YOON H,WU T,et al.A feature transfer enabled multi-task deep learning model on medical imaging[J].Expert Systems with Applications,2020,143:112957.

选择文件类型/文献管理软件名称

选择包含的内容

基于DYOLO神经网络的超声图像肾脏检测

Kidney Detection Using Ultrasound Image Based on DYOLO Neural Network

RichHTML

PDF

可视化

被引次数

摘要/Abstract

引用本文

使用本文

图/表 9

参考文献

相关文章 15

编辑推荐

Metrics

本文评价

[1]	徐春波, 闫娟, 杨慧斌, 王博, 吴晗. 基于目标检测和语义分割的视觉SLAM算法[J]. 计算机工程, 2023, 49(8): 199-206, 214.
[2]	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.
[3]	刘俊豪, 王美林, 谢兴, 宋烨兴, 许莉花. 基于改进YOLOv5的皮革瑕疵检测算法[J]. 计算机工程, 2023, 49(8): 240-249.
[4]	李强龙, 周新文, 位梦恩, 甘阳洲. 基于条形池化和注意力机制的街道场景红外目标检测算法[J]. 计算机工程, 2023, 49(8): 310-320.
[5]	靳雁霞, 史志儒, 杨晶, 刘亚变, 乔星宇, 张翎. 布料与精细建模物体间的碰撞检测算法研究[J]. 计算机工程, 2023, 49(7): 269-277.
[6]	闫兴亚, 匡娅茜, 白光睿, 李月. 基于深度学习的学生课堂行为识别方法[J]. 计算机工程, 2023, 49(7): 251-258.
[7]	聂志勇, 阴宇薇, 汤佳欣, 涂志刚. 一种基于边界框关键点距离的框回归算法[J]. 计算机工程, 2023, 49(7): 65-75.
[8]	李军侠, 王星驰, 殷梓, 石德硕. 边缘深度挖掘的弱监督显著性目标检测[J]. 计算机工程, 2023, 49(7): 169-178.
[9]	吴珊, 周凤. 基于改进SSD算法的小目标检测[J]. 计算机工程, 2023, 49(7): 179-188.
[10]	齐咏生, 杜晓旭, 朱俊峰, 高胜利, 刘利强. 基于增强型轻量深度网络的牧区牲畜高效检测[J]. 计算机工程, 2023, 49(7): 278-287.
[11]	谌雨章, 黄逸姿, 张钧涵. 基于多速率空洞卷积的多尺度水下小目标检测[J]. 计算机工程, 2023, 49(6): 257-264.
[12]	罗华峰, 沈奕菲, 阮黎翔, 杜奇伟, 郑翔, 陈智麒, 张胜. 边缘环境下面向实时目标检测的帧卸载调度算法[J]. 计算机工程, 2023, 49(5): 295-301,309.
[13]	陈锐, 孙羽菲, 郭强, 隋轶丞, 周振辉, 石昌青, 张玉志. OclDNN:一种可应用于TensorFlow的通用DNN库[J]. 计算机工程, 2023, 49(4): 138-148.
[14]	陆昭吾, 王骏, 施俊. 面向自闭症辅助诊断的深度对比模糊神经网络[J]. 计算机工程, 2023, 49(4): 263-271.
[15]	王璐璐, 陈东方, 王晓峰. 一种基于锚框质量分布的动态标签分配策略[J]. 计算机工程, 2023, 49(4): 85-91,100.

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

基于DYOLO神经网络的超声图像肾脏检测

Kidney Detection Using Ultrasound Image Based on DYOLO Neural Network

RichHTML

PDF

可视化

被引次数

摘要/Abstract

引用本文

使用本文

图/表 9

参考文献

相关文章 15

编辑推荐

Metrics

本文评价