Automated location of thyroid nodules in ultrasound images with improved YOLOV3 network

被引:10
|
作者
Zhang, Ling [1 ]
Zhuang, Yan [1 ]
Hua, Zhan [2 ]
Han, Lin [1 ,4 ]
Li, Cheng [2 ]
Chen, Ke [1 ]
Peng, Yulan [3 ]
Lin, Jiangli [1 ]
机构
[1] Sichuan Univ, Coll Biomed Engn, Chengdu 610065, Peoples R China
[2] China Japan Friendship Hosp, Beijing, Peoples R China
[3] Sichuan Univ, West China Hosp, Chengdu, Peoples R China
[4] Highong Intellimage Med Technol Tianjin Co Ltd, Tianjin, Peoples R China
关键词
Automatic localization; thyroid nodules; deep learning; ultrasound images;
D O I
10.3233/XST-200775
中图分类号
TH7 [仪器、仪表];
学科分类号
0804 ; 080401 ; 081102 ;
摘要
BACKGROUND: Thyroid ultrasonography is widely used to diagnose thyroid nodules in clinics. Automatic localization of nodules can promote the development of intelligent thyroid diagnosis and reduce workload of radiologists. However, besides the ultrasound image has low contrast and high noise, the thyroid nodules are diverse in shape and vary greatly in size. Thus, thyroid nodule detection in ultrasound images is still a challenging task. OBJECTIVE: This study proposes an automatic detection algorithm to locate nodules in B ultrasound images and Doppler ultrasound images. This method can be used to screen thyroid nodules and provide a basis for subsequent automatic segmentation and intelligent diagnosis. METHODS: We develop and optimize an improved YOLOV3 model for detecting thyroid nodules in ultrasound images with B-mode and Doppler mode. Improvements include (1) using the high-resolution network (HRNet) as the basic network for gradually extracting high-level semantic features to reduce the missed detection and misdetection, (2) optimizing the loss function for single target detection like nodules, and (3) obtaining the anchor boxes by clustering the candidate frames of real nodules in the dataset. RESULTS: The experimental results of applying to 8000 clinical ultrasound images show that the new method developed and tested in this study can effectively detect thyroid nodules. The method achieves 94.53% mean precision and 95.00% mean recall. CONCLUTIONS: The study demonstrates a new automated method that enables to achieve high detection accuracy and effectively locate thyroid nodules in various ultrasound images without any user interaction, which indicates its potential clinical application value for the thyroid nodule screening.
引用
收藏
页码:75 / 90
页数:16
相关论文
共 50 条
  • [1] Vehicle Detection in the Aerial Infrared Images via an Improved Yolov3 Network
    Zhang, Xunxun
    Zhu, Xu
    2019 IEEE 4TH INTERNATIONAL CONFERENCE ON SIGNAL AND IMAGE PROCESSING (ICSIP 2019), 2019, : 372 - 376
  • [2] An improved YOLOv3 model for detecting location information of ovarian cancer from CT images
    Wang, Xun
    Li, Hanlin
    Wang, Lisheng
    Yu, Yongzhi
    Zhou, Hao
    Wang, Lei
    Song, Tao
    INTELLIGENT DATA ANALYSIS, 2021, 25 (06) : 1565 - 1578
  • [3] Improved YOLOv3 Network for Insulator Detection in Aerial Images with Diverse Background Interference
    Liu, Chuanyang
    Wu, Yiquan
    Liu, Jingjing
    Sun, Zuo
    ELECTRONICS, 2021, 10 (07)
  • [4] Detection of Early Pregnancy in Ultrasound Images Using YOLOv3
    Teodor, Oana Mihaela
    Cirstoiu, Monica Mihaela
    Ichim, Loretta
    Popescu, Dan
    2022 30TH MEDITERRANEAN CONFERENCE ON CONTROL AND AUTOMATION (MED), 2022, : 188 - 193
  • [5] Efficient Object Detection Method Based on Improved YOLOv3 Network for Remote Sensing Images
    Wang, Jintao
    Xiao, Wen
    Ni, Tianwei
    2020 3RD INTERNATIONAL CONFERENCE ON ARTIFICIAL INTELLIGENCE AND BIG DATA (ICAIBD 2020), 2020, : 242 - 246
  • [6] A lightweight network for automatic thyroid nodules location and recognition with high speed and accuracy in ultrasound images
    Zhou, Sibo
    Qiu, Yuxuan
    Han, Lin
    Liao, Guoliang
    Zhuang, Yan
    Ma, Buyun
    Luo, Yan
    Lin, Jiangli
    Chen, Ke
    JOURNAL OF X-RAY SCIENCE AND TECHNOLOGY, 2022, 30 (05) : 967 - 981
  • [7] Gear Defect Detection Based on the Improved YOLOv3 Network
    Zhang Guangshi
    Ge Guangying
    Zhu Ronghua
    Sun Qun
    LASER & OPTOELECTRONICS PROGRESS, 2020, 57 (12)
  • [8] A multitask approach for automated detection and segmentation of thyroid nodules in ultrasound images
    Radhachandran, Ashwath
    Kinzel, Adam
    Chen, Joseph
    Sant, Vivek
    Patel, Maitraya
    Masamed, Rinat
    Arnold, Corey W.
    Speier, William
    COMPUTERS IN BIOLOGY AND MEDICINE, 2024, 170
  • [9] Automated Nuclei Detection on Pleural Effusion Cytopathology Images using YOLOv3
    Kilic, Busranur
    Baykal, Elif
    Ekinci, Murat
    Dogan, Hulya
    Ercin, Mustafa Emre
    Ersoz, Safak
    2019 4TH INTERNATIONAL CONFERENCE ON COMPUTER SCIENCE AND ENGINEERING (UBMK), 2019, : 418 - 422
  • [10] An improved method of Tiny YOLOV3
    Gong, Xiaotian
    Ma, Li
    Ouyang, Hangkong
    2019 5TH INTERNATIONAL CONFERENCE ON ENVIRONMENTAL SCIENCE AND MATERIAL APPLICATION, 2020, 440