iSL-YOLOv11: global–local attention enhanced small lesion detection in mammography images
- 1School of Computer Science, Zhuhai College of Science and Technology
- 2School of Electrical and Electronic Engineering, Changchun University of Technology
- 3Industrial Electronics Department, University of Minho
Abstract
Breast cancer is one of the most common cancers among women worldwide, and early detection plays a crucial role in improving patient survival and treatment outcomes. In clinical mammography screening, however, detecting early breast lesions continues to be challenging because small lesions are often characterized by low contrast, blurred boundaries, limited visual saliency, and interference caused by overlapping dense breast tissue. These aspects make it difficult for detection models to accurately identify subtle lesion regions in complex mammography images. To address these problems, this paper proposes an improved YOLOv11-based network architecture, iAFF-SEAM-LAE YOLOv11 (iSL-YOLOv11), that combines global and local structure-aware feature enhancement for small-lesion detection in mammography images. Specifically, C3K2_iAFF is introduced to improve adaptive feature fusion across different semantic levels, SEAM is used to enhance local structural representation under tissue overlap and occlusion, and LAE is adopted to reduce redundant computation while preserving lesion-related texture information. Experimental results show that the proposed iSL-YOLOv11 model improves the mAP50-95 score from 0.677 to 0.784 compared to the original YOLOv11 baseline, achieving a relative improvement of 15.8%. The model also achieves an mAP50 of 0.935, showing a stronger localization ability for small lesions in mammography images. These results suggest that iSL-YOLOv11 can improve the detection of small and visually ambiguous breast lesions and may provide a potential technical basis for computer-aided mammographic lesion localization.
Related
- YOLO4SWD: an improved YOLOv11-based method for waste detection and classification
- Patient acceptance and experience with contrast-enhanced mammography in women with a personal history of breast cancer: findings from the COMBO trial
- AI-assisted Decision-support Framework for Breast Density and Background Parenchymal Enhancement Assessment in Contrast-enhanced Mammography
- Image-Based Breast Implant Detection for Mammography Dataset Curation and Near-Real-Time Deployment: Comparing Foundation Models and Task-Specific Convolutional Models
- Model‐based image restoration targeting higher‐dose digital mammography: Impact on radiologists' detection of clustered microcalcifications
BibTeX
@article{sun2026islyolov11,
title = {{iSL-YOLOv11: global–local attention enhanced small lesion detection in mammography images}},
author = {Ningtao Sun and Junxi Wang and Xinyi Cao and Zhuoxi Mai and Yanchun Liang and Tao Cui and Adriano Tavares and Dalin Li},
journal = {Scientific Reports},
year = {2026},
month = jul,
doi = {10.1038/s41598-026-63154-2},
url = {https://doi.org/10.1038/s41598-026-63154-2},
note = {CC BY},
}
RIS
TY - JOUR
TI - iSL-YOLOv11: global–local attention enhanced small lesion detection in mammography images
AU - Ningtao Sun
AU - Junxi Wang
AU - Xinyi Cao
AU - Zhuoxi Mai
AU - Yanchun Liang
AU - Tao Cui
AU - Adriano Tavares
AU - Dalin Li
PY - 2026
DA - 2026/07/01
JO - Scientific Reports
DO - 10.1038/s41598-026-63154-2
UR - https://doi.org/10.1038/s41598-026-63154-2
AB - Breast cancer is one of the most common cancers among women worldwide, and early detection plays a crucial role in improving patient survival and treatment outcomes. In clinical mammography screening, however, detecting early breast lesions continues to be challenging because small lesions are often characterized by low contrast, blurred boundaries, limited visual saliency, and interference caused by overlapping dense breast tissue. These aspects make it difficult for detection models to accurately identify subtle lesion regions in complex mammography images. To address these problems, this paper proposes an improved YOLOv11-based network architecture, iAFF-SEAM-LAE YOLOv11 (iSL-YOLOv11), that combines global and local structure-aware feature enhancement for small-lesion detection in mammography images. Specifically, C3K2_iAFF is introduced to improve adaptive feature fusion across different semantic levels, SEAM is used to enhance local structural representation under tissue overlap and occlusion, and LAE is adopted to reduce redundant computation while preserving lesion-related texture information. Experimental results show that the proposed iSL-YOLOv11 model improves the mAP50-95 score from 0.677 to 0.784 compared to the original YOLOv11 baseline, achieving a relative improvement of 15.8%. The model also achieves an mAP50 of 0.935, showing a stronger localization ability for small lesions in mammography images. These results suggest that iSL-YOLOv11 can improve the detection of small and visually ambiguous breast lesions and may provide a potential technical basis for computer-aided mammographic lesion localization.
SN - 2045-2322
ER -