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

Article type: Research Article

Authors: Zhang, Ling^a | Zhuang, Yan^a | Hua, Zhan^b | Han, Lin^{a; d} | Li, Cheng^b | Chen, Ke^a | Peng, Yulan^c | Lin, Jiangli^{a; *}

Affiliations: [a] College of Biomedical Engineering, Sichuan University, Chengdu, China | [b] China-Japan Friendship Hospital, Beijing, China | [c] West China Hospital of Sichuan University, Chengdu, China | [d] Highong Intellimage Medical Technology Tianjin Co., Ltd, Tianjin, China

Correspondence: [*] Corresponding author: Jiangli Lin, College of Biomedical Engineering, Sichuan University, Chengdu, 610065, China. Tel.: +86 13981911859; Fax: +86 028 85416050; E-mail: [email protected].

Abstract: 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.

Keywords: Automatic localization, thyroid nodules, deep learning, ultrasound images

DOI: 10.3233/XST-200775

Journal: Journal of X-Ray Science and Technology, vol. 29, no. 1, pp. 75-90, 2021