Improved YOLO-Based Pulmonary Nodule Detection with Spatial-SE Attention and an Aspect Ratio Penalty
The accurate identification of pulmonary nodules is critical for the early diagnosis of lung diseases; however, this task remains challenging due to inadequate feature representation and limited localization sensitivity. Current methodologies often utilize channel attention mechanisms and intersecti...
Saved in:
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2025-07-01
|
| Series: | Sensors |
| Subjects: | |
| Online Access: | https://www.mdpi.com/1424-8220/25/14/4245 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1849418363037548544 |
|---|---|
| author | Xinhang Song Haoran Xie Tianding Gao Nuo Cheng Jianping Gou |
| author_facet | Xinhang Song Haoran Xie Tianding Gao Nuo Cheng Jianping Gou |
| author_sort | Xinhang Song |
| collection | DOAJ |
| description | The accurate identification of pulmonary nodules is critical for the early diagnosis of lung diseases; however, this task remains challenging due to inadequate feature representation and limited localization sensitivity. Current methodologies often utilize channel attention mechanisms and intersection over union (IoU)-based loss functions. Yet, they frequently overlook spatial context and struggle to capture subtle variations in aspect ratios, which hinders their ability to detect small objects. In this study, we introduce an improved YOLOV11 framework that addresses these limitations through two primary components: a spatial squeeze-and-excitation (SSE) module that concurrently models channel-wise and spatial attention to enhance the discriminative features pertinent to nodules and explicit aspect ratio penalty IoU (EAPIoU) loss that imposes a direct penalty on the squared differences in aspect ratios to refine the bounding box regression process. Comprehensive experiments conducted on the LUNA16, LungCT, and Node21 datasets reveal that our approach achieves superior precision, recall, and mean average precision (mAP) across various IoU thresholds, surpassing previous state-of-the-art methods while maintaining computational efficiency. Specifically, the proposed SSE module achieves a precision of 0.781 on LUNA16, while the EAPIoU loss boosts mAP@50 to 92.4% on LungCT, outperforming mainstream attention mechanisms and IoU-based loss functions. These findings underscore the effectiveness of integrating spatially aware attention mechanisms with aspect ratio-sensitive loss functions for robust nodule detection. |
| format | Article |
| id | doaj-art-6c903ec8b28e40ed94bf8181a2d06236 |
| institution | Kabale University |
| issn | 1424-8220 |
| language | English |
| publishDate | 2025-07-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Sensors |
| spelling | doaj-art-6c903ec8b28e40ed94bf8181a2d062362025-08-20T03:32:27ZengMDPI AGSensors1424-82202025-07-012514424510.3390/s25144245Improved YOLO-Based Pulmonary Nodule Detection with Spatial-SE Attention and an Aspect Ratio PenaltyXinhang Song0Haoran Xie1Tianding Gao2Nuo Cheng3Jianping Gou4College of Computer and Information Science & College of Software, Southwest University, Beibei District, Chongqing 400715, ChinaCollege of Computer and Information Science & College of Software, Southwest University, Beibei District, Chongqing 400715, ChinaCollege of Computer and Information Science & College of Software, Southwest University, Beibei District, Chongqing 400715, ChinaCollege of Computer and Information Science & College of Software, Southwest University, Beibei District, Chongqing 400715, ChinaCollege of Computer and Information Science & College of Software, Southwest University, Beibei District, Chongqing 400715, ChinaThe accurate identification of pulmonary nodules is critical for the early diagnosis of lung diseases; however, this task remains challenging due to inadequate feature representation and limited localization sensitivity. Current methodologies often utilize channel attention mechanisms and intersection over union (IoU)-based loss functions. Yet, they frequently overlook spatial context and struggle to capture subtle variations in aspect ratios, which hinders their ability to detect small objects. In this study, we introduce an improved YOLOV11 framework that addresses these limitations through two primary components: a spatial squeeze-and-excitation (SSE) module that concurrently models channel-wise and spatial attention to enhance the discriminative features pertinent to nodules and explicit aspect ratio penalty IoU (EAPIoU) loss that imposes a direct penalty on the squared differences in aspect ratios to refine the bounding box regression process. Comprehensive experiments conducted on the LUNA16, LungCT, and Node21 datasets reveal that our approach achieves superior precision, recall, and mean average precision (mAP) across various IoU thresholds, surpassing previous state-of-the-art methods while maintaining computational efficiency. Specifically, the proposed SSE module achieves a precision of 0.781 on LUNA16, while the EAPIoU loss boosts mAP@50 to 92.4% on LungCT, outperforming mainstream attention mechanisms and IoU-based loss functions. These findings underscore the effectiveness of integrating spatially aware attention mechanisms with aspect ratio-sensitive loss functions for robust nodule detection.https://www.mdpi.com/1424-8220/25/14/4245pulmonary nodule detectionspatial attentionchannel attentionaspect ratio penaltyYOLOV11EAPIoU loss |
| spellingShingle | Xinhang Song Haoran Xie Tianding Gao Nuo Cheng Jianping Gou Improved YOLO-Based Pulmonary Nodule Detection with Spatial-SE Attention and an Aspect Ratio Penalty Sensors pulmonary nodule detection spatial attention channel attention aspect ratio penalty YOLOV11 EAPIoU loss |
| title | Improved YOLO-Based Pulmonary Nodule Detection with Spatial-SE Attention and an Aspect Ratio Penalty |
| title_full | Improved YOLO-Based Pulmonary Nodule Detection with Spatial-SE Attention and an Aspect Ratio Penalty |
| title_fullStr | Improved YOLO-Based Pulmonary Nodule Detection with Spatial-SE Attention and an Aspect Ratio Penalty |
| title_full_unstemmed | Improved YOLO-Based Pulmonary Nodule Detection with Spatial-SE Attention and an Aspect Ratio Penalty |
| title_short | Improved YOLO-Based Pulmonary Nodule Detection with Spatial-SE Attention and an Aspect Ratio Penalty |
| title_sort | improved yolo based pulmonary nodule detection with spatial se attention and an aspect ratio penalty |
| topic | pulmonary nodule detection spatial attention channel attention aspect ratio penalty YOLOV11 EAPIoU loss |
| url | https://www.mdpi.com/1424-8220/25/14/4245 |
| work_keys_str_mv | AT xinhangsong improvedyolobasedpulmonarynoduledetectionwithspatialseattentionandanaspectratiopenalty AT haoranxie improvedyolobasedpulmonarynoduledetectionwithspatialseattentionandanaspectratiopenalty AT tiandinggao improvedyolobasedpulmonarynoduledetectionwithspatialseattentionandanaspectratiopenalty AT nuocheng improvedyolobasedpulmonarynoduledetectionwithspatialseattentionandanaspectratiopenalty AT jianpinggou improvedyolobasedpulmonarynoduledetectionwithspatialseattentionandanaspectratiopenalty |