Saved in:
| Main Authors: | , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2501.03836 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866916771024338944 |
|---|---|
| author | Bai, Runci Xu, Guibao Shi, Yanze |
| author_facet | Bai, Runci Xu, Guibao Shi, Yanze |
| contents | Brain tumors can lead to neurological dysfunction, cognitive and psychological changes, increased intracranial pressure, and seizures, posing significant risks to health. The You Only Look Once (YOLO) series has shown superior accuracy in medical imaging object detection. This paper presents a novel SCC-YOLO architecture that integrates the SCConv module into YOLOv9. The SCConv module optimizes convolutional efficiency by reducing spatial and channel redundancy, enhancing image feature learning. We examine the effects of different attention mechanisms with YOLOv9 for brain tumor detection using the Br35H dataset and our custom dataset (Brain_Tumor_Dataset). Results indicate that SCC-YOLO improved mAP50 by 0.3% on the Br35H dataset and by 0.5% on our custom dataset compared to YOLOv9. SCC-YOLO achieves state-of-the-art performance in brain tumor detection. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2501_03836 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | SCC-YOLO: An Improved Object Detector for Assisting in Brain Tumor Diagnosis Bai, Runci Xu, Guibao Shi, Yanze Image and Video Processing Artificial Intelligence Computer Vision and Pattern Recognition Brain tumors can lead to neurological dysfunction, cognitive and psychological changes, increased intracranial pressure, and seizures, posing significant risks to health. The You Only Look Once (YOLO) series has shown superior accuracy in medical imaging object detection. This paper presents a novel SCC-YOLO architecture that integrates the SCConv module into YOLOv9. The SCConv module optimizes convolutional efficiency by reducing spatial and channel redundancy, enhancing image feature learning. We examine the effects of different attention mechanisms with YOLOv9 for brain tumor detection using the Br35H dataset and our custom dataset (Brain_Tumor_Dataset). Results indicate that SCC-YOLO improved mAP50 by 0.3% on the Br35H dataset and by 0.5% on our custom dataset compared to YOLOv9. SCC-YOLO achieves state-of-the-art performance in brain tumor detection. |
| title | SCC-YOLO: An Improved Object Detector for Assisting in Brain Tumor Diagnosis |
| topic | Image and Video Processing Artificial Intelligence Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2501.03836 |