KLO-Net: A Dynamic K-NN Attention U-Net with CSP Encoder for Efficient Prostate Gland Segmentation from MRI
Fuente:
arXiv
Guardado en:
| Autores principales: | , , , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2025
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866912767408078848 |
|---|---|
| author | Tian, Anning Ko, Byunghyun Qu, Kaichen Liu, Mengyuan Lee, Jeongkyu |
| author_facet | Tian, Anning Ko, Byunghyun Qu, Kaichen Liu, Mengyuan Lee, Jeongkyu |
| contents | Real-time deployment of prostate MRI segmentation on clinical workstations is often bottlenecked by computational load and memory footprint. Deep learning-based prostate gland segmentation approaches remain challenging due to anatomical variability. To bridge this efficiency gap while still maintaining reliable segmentation accuracy, we propose KLO-Net, a dynamic K-Nearest Neighbor attention U-Net with Cross Stage Partial, i.e., CSP, encoder for efficient prostate gland segmentation from MRI scan. Unlike the regular K-NN attention mechanism, the proposed dynamic K-NN attention mechanism allows the model to adaptively determine the number of attention connections for each spatial location within a slice. In addition, CSP blocks address the computational load to reduce memory consumption. To evaluate the model's performance, comprehensive experiments and ablation studies are conducted on two public datasets, i.e., PROMISE12 and PROSTATEx, to validate the proposed architecture. The detailed comparative analysis demonstrates the model's advantage in computational efficiency and segmentation quality. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2512_13902 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | KLO-Net: A Dynamic K-NN Attention U-Net with CSP Encoder for Efficient Prostate Gland Segmentation from MRI Tian, Anning Ko, Byunghyun Qu, Kaichen Liu, Mengyuan Lee, Jeongkyu Computer Vision and Pattern Recognition Machine Learning Real-time deployment of prostate MRI segmentation on clinical workstations is often bottlenecked by computational load and memory footprint. Deep learning-based prostate gland segmentation approaches remain challenging due to anatomical variability. To bridge this efficiency gap while still maintaining reliable segmentation accuracy, we propose KLO-Net, a dynamic K-Nearest Neighbor attention U-Net with Cross Stage Partial, i.e., CSP, encoder for efficient prostate gland segmentation from MRI scan. Unlike the regular K-NN attention mechanism, the proposed dynamic K-NN attention mechanism allows the model to adaptively determine the number of attention connections for each spatial location within a slice. In addition, CSP blocks address the computational load to reduce memory consumption. To evaluate the model's performance, comprehensive experiments and ablation studies are conducted on two public datasets, i.e., PROMISE12 and PROSTATEx, to validate the proposed architecture. The detailed comparative analysis demonstrates the model's advantage in computational efficiency and segmentation quality. |
| title | KLO-Net: A Dynamic K-NN Attention U-Net with CSP Encoder for Efficient Prostate Gland Segmentation from MRI |
| topic | Computer Vision and Pattern Recognition Machine Learning |
| url | https://arxiv.org/abs/2512.13902 |