Lightweight YOLOv8 for tongue teeth marks and fissures detection based on C2f_DCNv3
Abstract This paper propose a significantly enhanced YOLOv8 model specifically designed for detecting tongue fissures and teeth marks in Traditional Chinese Medicine (TCM) diagnostic images. By integrating the C2f_DCNv3 module, which incorporates Deformable Convolutions (DCN), replace the original C...
Saved in:
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Nature Portfolio
2025-01-01
|
| Series: | Scientific Reports |
| Online Access: | https://doi.org/10.1038/s41598-025-86001-2 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1850099744036093952 |
|---|---|
| author | Chunyang Jin Delong Zhang Xiyuan Cao Zhidong Zhang Chenyang Xue Yanjun Zhang |
| author_facet | Chunyang Jin Delong Zhang Xiyuan Cao Zhidong Zhang Chenyang Xue Yanjun Zhang |
| author_sort | Chunyang Jin |
| collection | DOAJ |
| description | Abstract This paper propose a significantly enhanced YOLOv8 model specifically designed for detecting tongue fissures and teeth marks in Traditional Chinese Medicine (TCM) diagnostic images. By integrating the C2f_DCNv3 module, which incorporates Deformable Convolutions (DCN), replace the original C2f module, enabling the model to exhibit exceptional adaptability to intricate and irregular features, such as fine fissures and teeth marks. Furthermore, the introduction of the Squeeze-and-Excitation (SE) attention mechanism optimizes feature weighting, allowing the model to focus more accurately on key regions of the image, even in the presence of complex backgrounds. The proposed model demonstrates a significant performance improvement, achieving an average precision (mAP) of 92.77%, which marks a substantial enhancement over the original YOLOv8. Additionally, the model reduces computational cost by approximately one-third in terms of FLOPS, maintaining high accuracy while greatly decreasing the number of parameters, thus offering a more robust and resource-efficient solution. For tongue crack detection, the mAP increases to 91.34%, with notable improvements in F1 score, precision, and recall. Teeth mark detection also sees a significant boost, achieving an mAP of 94.21%. These advancements underscore the model’s outstanding performance in TCM tongue image analysis, providing a more accurate, efficient, and reliable tool for clinical diagnostic applications. |
| format | Article |
| id | doaj-art-db00575060704d8eb45206368cb3e059 |
| institution | DOAJ |
| issn | 2045-2322 |
| language | English |
| publishDate | 2025-01-01 |
| publisher | Nature Portfolio |
| record_format | Article |
| series | Scientific Reports |
| spelling | doaj-art-db00575060704d8eb45206368cb3e0592025-08-20T02:40:26ZengNature PortfolioScientific Reports2045-23222025-01-0115111310.1038/s41598-025-86001-2Lightweight YOLOv8 for tongue teeth marks and fissures detection based on C2f_DCNv3Chunyang Jin0Delong Zhang1Xiyuan Cao2Zhidong Zhang3Chenyang Xue4Yanjun Zhang5Key Laboratory of Instrumentation Science, Dynamic Measurement of Ministry of Education, North University of ChinaKey Laboratory of Instrumentation Science, Dynamic Measurement of Ministry of Education, North University of ChinaKey Laboratory of Instrumentation Science, Dynamic Measurement of Ministry of Education, North University of ChinaKey Laboratory of Instrumentation Science, Dynamic Measurement of Ministry of Education, North University of ChinaKey Laboratory of Instrumentation Science, Dynamic Measurement of Ministry of Education, North University of ChinaKey Laboratory of Instrumentation Science, Dynamic Measurement of Ministry of Education, North University of ChinaAbstract This paper propose a significantly enhanced YOLOv8 model specifically designed for detecting tongue fissures and teeth marks in Traditional Chinese Medicine (TCM) diagnostic images. By integrating the C2f_DCNv3 module, which incorporates Deformable Convolutions (DCN), replace the original C2f module, enabling the model to exhibit exceptional adaptability to intricate and irregular features, such as fine fissures and teeth marks. Furthermore, the introduction of the Squeeze-and-Excitation (SE) attention mechanism optimizes feature weighting, allowing the model to focus more accurately on key regions of the image, even in the presence of complex backgrounds. The proposed model demonstrates a significant performance improvement, achieving an average precision (mAP) of 92.77%, which marks a substantial enhancement over the original YOLOv8. Additionally, the model reduces computational cost by approximately one-third in terms of FLOPS, maintaining high accuracy while greatly decreasing the number of parameters, thus offering a more robust and resource-efficient solution. For tongue crack detection, the mAP increases to 91.34%, with notable improvements in F1 score, precision, and recall. Teeth mark detection also sees a significant boost, achieving an mAP of 94.21%. These advancements underscore the model’s outstanding performance in TCM tongue image analysis, providing a more accurate, efficient, and reliable tool for clinical diagnostic applications.https://doi.org/10.1038/s41598-025-86001-2 |
| spellingShingle | Chunyang Jin Delong Zhang Xiyuan Cao Zhidong Zhang Chenyang Xue Yanjun Zhang Lightweight YOLOv8 for tongue teeth marks and fissures detection based on C2f_DCNv3 Scientific Reports |
| title | Lightweight YOLOv8 for tongue teeth marks and fissures detection based on C2f_DCNv3 |
| title_full | Lightweight YOLOv8 for tongue teeth marks and fissures detection based on C2f_DCNv3 |
| title_fullStr | Lightweight YOLOv8 for tongue teeth marks and fissures detection based on C2f_DCNv3 |
| title_full_unstemmed | Lightweight YOLOv8 for tongue teeth marks and fissures detection based on C2f_DCNv3 |
| title_short | Lightweight YOLOv8 for tongue teeth marks and fissures detection based on C2f_DCNv3 |
| title_sort | lightweight yolov8 for tongue teeth marks and fissures detection based on c2f dcnv3 |
| url | https://doi.org/10.1038/s41598-025-86001-2 |
| work_keys_str_mv | AT chunyangjin lightweightyolov8fortongueteethmarksandfissuresdetectionbasedonc2fdcnv3 AT delongzhang lightweightyolov8fortongueteethmarksandfissuresdetectionbasedonc2fdcnv3 AT xiyuancao lightweightyolov8fortongueteethmarksandfissuresdetectionbasedonc2fdcnv3 AT zhidongzhang lightweightyolov8fortongueteethmarksandfissuresdetectionbasedonc2fdcnv3 AT chenyangxue lightweightyolov8fortongueteethmarksandfissuresdetectionbasedonc2fdcnv3 AT yanjunzhang lightweightyolov8fortongueteethmarksandfissuresdetectionbasedonc2fdcnv3 |