Breast mass lesion area detection method based on an improved YOLOv8 model
Breast cancer has a very high incidence rate worldwide, and effective screening and early diagnosis are particularly important. In this paper, two improved You Only Look Once version 8 (YOLOv8) models, the YOLOv8-GHOST and YOLOv8-P2 models, are proposed to address the difficulty of distinguishing le...
Saved in:
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
AIMS Press
2024-10-01
|
| Series: | Electronic Research Archive |
| Subjects: | |
| Online Access: | https://www.aimspress.com/article/doi/10.3934/era.2024270 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1832590760747204608 |
|---|---|
| author | Yihua Lan Yingjie Lv Jiashu Xu Yingqi Zhang Yanhong Zhang |
| author_facet | Yihua Lan Yingjie Lv Jiashu Xu Yingqi Zhang Yanhong Zhang |
| author_sort | Yihua Lan |
| collection | DOAJ |
| description | Breast cancer has a very high incidence rate worldwide, and effective screening and early diagnosis are particularly important. In this paper, two improved You Only Look Once version 8 (YOLOv8) models, the YOLOv8-GHOST and YOLOv8-P2 models, are proposed to address the difficulty of distinguishing lesions from normal tissues in mammography images. The YOLOv8-GHOST model incorporates GHOSTConv and C3GHOST modules into the original YOLOv8 model to capture richer feature information while using only 57% of the number of parameters required by the original model. The YOLOv8-P2 algorithm significantly reduces the number of necessary parameters by streamlining the number of channels in the feature map. This paper proposes the YOLOv8-GHOST-P2 model by combining the above two improvements. Experiments conducted on the MIAS and DDSM datasets show that the new models achieved significantly improved computational efficiency while maintaining high detection accuracy. Compared with the traditional YOLOv8 method, the three new models improved and achieved F1 scores of 98.38%, 98.8%, and 98.57%, while the number of parameters reduced by 42.9%, 46.64%, and 2.8%. These improvements provide a more efficient and accurate tool for clinical breast cancer screening and lay the foundation for subsequent studies. Future work will explore the potential applications of the developed models to other medical image analysis tasks. |
| format | Article |
| id | doaj-art-952421c7e4af41bfbdd00e4785a1f038 |
| institution | Kabale University |
| issn | 2688-1594 |
| language | English |
| publishDate | 2024-10-01 |
| publisher | AIMS Press |
| record_format | Article |
| series | Electronic Research Archive |
| spelling | doaj-art-952421c7e4af41bfbdd00e4785a1f0382025-01-23T07:52:53ZengAIMS PressElectronic Research Archive2688-15942024-10-0132105846586710.3934/era.2024270Breast mass lesion area detection method based on an improved YOLOv8 modelYihua Lan0Yingjie Lv1Jiashu Xu2Yingqi Zhang3Yanhong Zhang4School of Artificial Intelligence and Software Engineering, Nanyang Normal University, Nanyang 473061, ChinaSchool of Artificial Intelligence and Software Engineering, Nanyang Normal University, Nanyang 473061, ChinaSchool of Artificial Intelligence and Software Engineering, Nanyang Normal University, Nanyang 473061, ChinaSchool of Artificial Intelligence and Software Engineering, Nanyang Normal University, Nanyang 473061, ChinaSchool of Artificial Intelligence and Software Engineering, Nanyang Normal University, Nanyang 473061, ChinaBreast cancer has a very high incidence rate worldwide, and effective screening and early diagnosis are particularly important. In this paper, two improved You Only Look Once version 8 (YOLOv8) models, the YOLOv8-GHOST and YOLOv8-P2 models, are proposed to address the difficulty of distinguishing lesions from normal tissues in mammography images. The YOLOv8-GHOST model incorporates GHOSTConv and C3GHOST modules into the original YOLOv8 model to capture richer feature information while using only 57% of the number of parameters required by the original model. The YOLOv8-P2 algorithm significantly reduces the number of necessary parameters by streamlining the number of channels in the feature map. This paper proposes the YOLOv8-GHOST-P2 model by combining the above two improvements. Experiments conducted on the MIAS and DDSM datasets show that the new models achieved significantly improved computational efficiency while maintaining high detection accuracy. Compared with the traditional YOLOv8 method, the three new models improved and achieved F1 scores of 98.38%, 98.8%, and 98.57%, while the number of parameters reduced by 42.9%, 46.64%, and 2.8%. These improvements provide a more efficient and accurate tool for clinical breast cancer screening and lay the foundation for subsequent studies. Future work will explore the potential applications of the developed models to other medical image analysis tasks.https://www.aimspress.com/article/doi/10.3934/era.2024270yolov8deep learningbreast cancertarget detectionconvolutional neural network |
| spellingShingle | Yihua Lan Yingjie Lv Jiashu Xu Yingqi Zhang Yanhong Zhang Breast mass lesion area detection method based on an improved YOLOv8 model Electronic Research Archive yolov8 deep learning breast cancer target detection convolutional neural network |
| title | Breast mass lesion area detection method based on an improved YOLOv8 model |
| title_full | Breast mass lesion area detection method based on an improved YOLOv8 model |
| title_fullStr | Breast mass lesion area detection method based on an improved YOLOv8 model |
| title_full_unstemmed | Breast mass lesion area detection method based on an improved YOLOv8 model |
| title_short | Breast mass lesion area detection method based on an improved YOLOv8 model |
| title_sort | breast mass lesion area detection method based on an improved yolov8 model |
| topic | yolov8 deep learning breast cancer target detection convolutional neural network |
| url | https://www.aimspress.com/article/doi/10.3934/era.2024270 |
| work_keys_str_mv | AT yihualan breastmasslesionareadetectionmethodbasedonanimprovedyolov8model AT yingjielv breastmasslesionareadetectionmethodbasedonanimprovedyolov8model AT jiashuxu breastmasslesionareadetectionmethodbasedonanimprovedyolov8model AT yingqizhang breastmasslesionareadetectionmethodbasedonanimprovedyolov8model AT yanhongzhang breastmasslesionareadetectionmethodbasedonanimprovedyolov8model |