Automatic Thyroid Nodule Detection in Ultrasound Imaging With Improved YOLOv5 Neural Network

被引:3
作者
Yang, Daqing [1 ]
Xia, Jianfu [1 ]
Li, Rizeng [1 ]
Li, Wencai [1 ]
Liu, Jisheng [1 ]
Wang, Rongjian [1 ]
Qu, Dong [2 ]
You, Jie [3 ]
机构
[1] Shanghai Univ, Affiliated Hosp 2, Wenzhou Cent Hosp, Dept Gen Surg, Wenzhou 325000, Peoples R China
[2] Shanghai Univ, Affiliated Hosp 2, Wenzhou Cent Hosp, Dept Radiol, Wenzhou 325000, Peoples R China
[3] Wenzhou Med Univ, Affiliated Hosp 1, Dept Thyroid Surg, Wenzhou 325000, Peoples R China
关键词
Computer-aided diagnosis; thyroid nodules; ultrasound; YOLOv5; network; attention module; label smoothing; DEEP; CLASSIFICATION; IMAGES;
D O I
10.1109/ACCESS.2024.3359367
中图分类号
TP [自动化技术、计算机技术];
学科分类号
0812 ;
摘要
With the incidence of thyroid cancer increasing dramatically, the burden of sonographic diagnosis lies heavy for radiologists. An automatic computer-aided diagnosis system with both precision and efficiency is in demand. This retrospective study included 191 ultrasound images of 171 patients (85 benign and 86 malignant) in Wenzhou Central Hospital. An improved You Only Look Once version 5 neural network (improved YOLOv5) is proposed in this work. It comprises the coordinate attention (CA) module and the label smoothing regularization (LSR) module, in which the CA module enables the network ability of positional information extraction. The improved neural network correctly recognizes the lesion area and nodule type with a mean average precision (mAP) of 95.3% in 8.4 ms on the test set. The ablation experiment demonstrates that the integration of the CA and the LSR module cost 1.3 ms extra inference time per image in exchange for raising the mAP by 4.4%. Afterward, 10 ultrasound images with wrong nodule types are added to the dataset for training, the result shows that the LSR module can significantly prevent the network from being misled by the bug data. Compared with other state-of-the-art networks, the improved network has superiority in both precision and robustness for diagnosing benign/malignant thyroid nodules with only a small dataset. The proposed network also has the potential to transfer to other sonographic diagnosis tasks.
引用
收藏
页码:22662 / 22670
页数:9
相关论文
共 42 条
[1]   Automated thyroid nodule detection from ultrasound imaging using deep convolutional neural networks [J].
Abdolali, Fatemeh ;
Kapur, Jeevesh ;
Jaremko, Jacob L. ;
Noga, Michelle ;
Hareendranathan, Abhilash R. ;
Punithakumar, Kumaradevan .
COMPUTERS IN BIOLOGY AND MEDICINE, 2020, 122
[2]  
[Anonymous], PASCAL VISUAL OBJECT
[3]  
[Anonymous], 1997, Machine Learning
[4]  
Bray F, 2018, CA-CANCER J CLIN, V68, P394, DOI [10.3322/caac.21609, 10.3322/caac.21492]
[5]   Thyroid Nodule Classification in Ultrasound Images by Fine-Tuning Deep Convolutional Neural Network [J].
Chi, Jianning ;
Walia, Ekta ;
Babyn, Paul ;
Wang, Jimmy ;
Groot, Gary ;
Eramian, Mark .
JOURNAL OF DIGITAL IMAGING, 2017, 30 (04) :477-486
[6]   Revised American Thyroid Association Management Guidelines for Patients with Thyroid Nodules and Differentiated Thyroid Cancer [J].
Cooper, David S. ;
Doherty, Gerard M. ;
Haugen, Bryan R. ;
Kloos, Richard T. ;
Lee, Stephanie L. ;
Mandel, Susan J. ;
Mazzaferri, Ernest L. ;
McIver, Bryan ;
Pacini, Furio ;
Schlumberger, Martin ;
Sherman, Steven I. ;
Steward, David L. ;
Tuttle, R. Michael .
THYROID, 2009, 19 (11) :1167-1214
[7]   Rich feature hierarchies for accurate object detection and semantic segmentation [J].
Girshick, Ross ;
Donahue, Jeff ;
Darrell, Trevor ;
Malik, Jitendra .
2014 IEEE CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR), 2014, :580-587
[8]   Recent advances in convolutional neural networks [J].
Gu, Jiuxiang ;
Wang, Zhenhua ;
Kuen, Jason ;
Ma, Lianyang ;
Shahroudy, Amir ;
Shuai, Bing ;
Liu, Ting ;
Wang, Xingxing ;
Wang, Gang ;
Cai, Jianfei ;
Chen, Tsuhan .
PATTERN RECOGNITION, 2018, 77 :354-377
[9]   2015 American Thyroid Association Management Guidelines for Adult Patients with Thyroid Nodules and Differentiated Thyroid Cancer: What is new and what has changed? [J].
Haugen, Bryan R. .
CANCER, 2017, 123 (03) :372-381
[10]  
He KM, 2020, IEEE T PATTERN ANAL, V42, P386, DOI [10.1109/TPAMI.2018.2844175, 10.1109/ICCV.2017.322]