Enhancing Thyroid Nodule Detection in Ultrasound Images: A Novel YOLOv8 Architecture with a C2fA Module and Optimized Loss Functions
Thyroid-related diseases, particularly thyroid cancer, are rising globally, emphasizing the critical need for the early detection and accurate screening of thyroid nodules. Ultrasound imaging has inherent limitations—high noise, low contrast, and blurred boundaries—that make manual interpretation su...
Saved in:
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2025-01-01
|
| Series: | Technologies |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2227-7080/13/1/28 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1832587468766969856 |
|---|---|
| author | Shidan Wang Zi-An Zhao Yuze Chen Ye-Jiao Mao James Chung-Wai Cheung |
| author_facet | Shidan Wang Zi-An Zhao Yuze Chen Ye-Jiao Mao James Chung-Wai Cheung |
| author_sort | Shidan Wang |
| collection | DOAJ |
| description | Thyroid-related diseases, particularly thyroid cancer, are rising globally, emphasizing the critical need for the early detection and accurate screening of thyroid nodules. Ultrasound imaging has inherent limitations—high noise, low contrast, and blurred boundaries—that make manual interpretation subjective and error-prone. To address these challenges, YOLO-Thyroid, an improved model for the automatic detection of thyroid nodules in ultrasound images, is presented herein. Building upon the YOLOv8 architecture, YOLO-Thyroid introduces the C2fA module—an extension of C2f that incorporates Coordinate Attention (CA)—to enhance feature extraction. Additionally, loss functions were incorporated, including class-weighted binary cross-entropy to alleviate class imbalance and SCYLLA-IoU (SIoU) to improve localization accuracy during boundary regression. A publicly available thyroid ultrasound image dataset was optimized using format conversion and data augmentation. The experimental results demonstrate that YOLO-Thyroid outperforms mainstream object detection models across multiple metrics, achieving a higher detection precision of 54%. The recall, calculated based on the detection of nodules containing at least one feature suspected of being malignant, reaches 58.2%, while the model maintains a lightweight structure. The proposed method significantly advances ultrasound nodule detection, providing an effective and practical solution for enhancing diagnostic accuracy in medical imaging. |
| format | Article |
| id | doaj-art-f58e4de523eb4fe79fbef8907fd18802 |
| institution | Kabale University |
| issn | 2227-7080 |
| language | English |
| publishDate | 2025-01-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Technologies |
| spelling | doaj-art-f58e4de523eb4fe79fbef8907fd188022025-01-24T13:50:47ZengMDPI AGTechnologies2227-70802025-01-011312810.3390/technologies13010028Enhancing Thyroid Nodule Detection in Ultrasound Images: A Novel YOLOv8 Architecture with a C2fA Module and Optimized Loss FunctionsShidan Wang0Zi-An Zhao1Yuze Chen2Ye-Jiao Mao3James Chung-Wai Cheung4School of Microelectronics and Communication Engineering, Chongqing University, Chongqing 400044, ChinaDepartment of Biomedical Engineering, Faculty of Engineering, The Hong Kong Polytechnic University, Hong Kong 999077, ChinaCollege of Computer Science, Chongqing University, Chongqing 400044, ChinaDepartment of Biomedical Engineering, Faculty of Engineering, The Hong Kong Polytechnic University, Hong Kong 999077, ChinaDepartment of Biomedical Engineering, Faculty of Engineering, The Hong Kong Polytechnic University, Hong Kong 999077, ChinaThyroid-related diseases, particularly thyroid cancer, are rising globally, emphasizing the critical need for the early detection and accurate screening of thyroid nodules. Ultrasound imaging has inherent limitations—high noise, low contrast, and blurred boundaries—that make manual interpretation subjective and error-prone. To address these challenges, YOLO-Thyroid, an improved model for the automatic detection of thyroid nodules in ultrasound images, is presented herein. Building upon the YOLOv8 architecture, YOLO-Thyroid introduces the C2fA module—an extension of C2f that incorporates Coordinate Attention (CA)—to enhance feature extraction. Additionally, loss functions were incorporated, including class-weighted binary cross-entropy to alleviate class imbalance and SCYLLA-IoU (SIoU) to improve localization accuracy during boundary regression. A publicly available thyroid ultrasound image dataset was optimized using format conversion and data augmentation. The experimental results demonstrate that YOLO-Thyroid outperforms mainstream object detection models across multiple metrics, achieving a higher detection precision of 54%. The recall, calculated based on the detection of nodules containing at least one feature suspected of being malignant, reaches 58.2%, while the model maintains a lightweight structure. The proposed method significantly advances ultrasound nodule detection, providing an effective and practical solution for enhancing diagnostic accuracy in medical imaging.https://www.mdpi.com/2227-7080/13/1/28thyroid nodule detectionultrasound imagingYOLOdeep learningmedical image analysis |
| spellingShingle | Shidan Wang Zi-An Zhao Yuze Chen Ye-Jiao Mao James Chung-Wai Cheung Enhancing Thyroid Nodule Detection in Ultrasound Images: A Novel YOLOv8 Architecture with a C2fA Module and Optimized Loss Functions Technologies thyroid nodule detection ultrasound imaging YOLO deep learning medical image analysis |
| title | Enhancing Thyroid Nodule Detection in Ultrasound Images: A Novel YOLOv8 Architecture with a C2fA Module and Optimized Loss Functions |
| title_full | Enhancing Thyroid Nodule Detection in Ultrasound Images: A Novel YOLOv8 Architecture with a C2fA Module and Optimized Loss Functions |
| title_fullStr | Enhancing Thyroid Nodule Detection in Ultrasound Images: A Novel YOLOv8 Architecture with a C2fA Module and Optimized Loss Functions |
| title_full_unstemmed | Enhancing Thyroid Nodule Detection in Ultrasound Images: A Novel YOLOv8 Architecture with a C2fA Module and Optimized Loss Functions |
| title_short | Enhancing Thyroid Nodule Detection in Ultrasound Images: A Novel YOLOv8 Architecture with a C2fA Module and Optimized Loss Functions |
| title_sort | enhancing thyroid nodule detection in ultrasound images a novel yolov8 architecture with a c2fa module and optimized loss functions |
| topic | thyroid nodule detection ultrasound imaging YOLO deep learning medical image analysis |
| url | https://www.mdpi.com/2227-7080/13/1/28 |
| work_keys_str_mv | AT shidanwang enhancingthyroidnoduledetectioninultrasoundimagesanovelyolov8architecturewithac2famoduleandoptimizedlossfunctions AT zianzhao enhancingthyroidnoduledetectioninultrasoundimagesanovelyolov8architecturewithac2famoduleandoptimizedlossfunctions AT yuzechen enhancingthyroidnoduledetectioninultrasoundimagesanovelyolov8architecturewithac2famoduleandoptimizedlossfunctions AT yejiaomao enhancingthyroidnoduledetectioninultrasoundimagesanovelyolov8architecturewithac2famoduleandoptimizedlossfunctions AT jameschungwaicheung enhancingthyroidnoduledetectioninultrasoundimagesanovelyolov8architecturewithac2famoduleandoptimizedlossfunctions |