Saved in:
| Main Authors: | , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2503.15260 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866916656994844672 |
|---|---|
| author | Shi, Lei Fang, Xi Wang, Naiyu Zhang, Junxing |
| author_facet | Shi, Lei Fang, Xi Wang, Naiyu Zhang, Junxing |
| contents | Automatic medical image segmentation plays a crucial role in computer aided diagnosis. However, fully supervised learning approaches often require extensive and labor-intensive annotation efforts. To address this challenge, weakly supervised learning methods, particularly those using extreme points as supervisory signals, have the potential to offer an effective solution. In this paper, we introduce Deep Extreme Point Tracing (DEPT) integrated with Feature-Guided Extreme Point Masking (FGEPM) algorithm for ultrasound image segmentation. Notably, our method generates pseudo labels by identifying the lowest-cost path that connects all extreme points on the feature map-based cost matrix. Additionally, an iterative training strategy is proposed to refine pseudo labels progressively, enabling continuous network improvement. Experimental results on two public datasets demonstrate the effectiveness of our proposed method. The performance of our method approaches that of the fully supervised method and outperforms several existing weakly supervised methods. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2503_15260 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | DEPT: Deep Extreme Point Tracing for Ultrasound Image Segmentation Shi, Lei Fang, Xi Wang, Naiyu Zhang, Junxing Computer Vision and Pattern Recognition Automatic medical image segmentation plays a crucial role in computer aided diagnosis. However, fully supervised learning approaches often require extensive and labor-intensive annotation efforts. To address this challenge, weakly supervised learning methods, particularly those using extreme points as supervisory signals, have the potential to offer an effective solution. In this paper, we introduce Deep Extreme Point Tracing (DEPT) integrated with Feature-Guided Extreme Point Masking (FGEPM) algorithm for ultrasound image segmentation. Notably, our method generates pseudo labels by identifying the lowest-cost path that connects all extreme points on the feature map-based cost matrix. Additionally, an iterative training strategy is proposed to refine pseudo labels progressively, enabling continuous network improvement. Experimental results on two public datasets demonstrate the effectiveness of our proposed method. The performance of our method approaches that of the fully supervised method and outperforms several existing weakly supervised methods. |
| title | DEPT: Deep Extreme Point Tracing for Ultrasound Image Segmentation |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2503.15260 |