Multiscale Encoder and Omni-Dimensional Dynamic Convolution Enrichment in nnU-Net for Brain Tumor Segmentation
Fuente:
arXiv
Salvato in:
| Autori principali: | , , , , , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2024
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866913509613240320 |
|---|---|
| author | Mistry, Sahaj K. Saini, Sourav Gupta, Aashray Gupta, Aayush Rai, Sunny Jakhetiya, Vinit Baid, Ujjwal Guntuku, Sharath Chandra |
| author_facet | Mistry, Sahaj K. Saini, Sourav Gupta, Aashray Gupta, Aayush Rai, Sunny Jakhetiya, Vinit Baid, Ujjwal Guntuku, Sharath Chandra |
| contents | Brain tumor segmentation plays a crucial role in computer-aided diagnosis. This study introduces a novel segmentation algorithm utilizing a modified nnU-Net architecture. Within the nnU-Net architecture's encoder section, we enhance conventional convolution layers by incorporating omni-dimensional dynamic convolution layers, resulting in improved feature representation. Simultaneously, we propose a multi-scale attention strategy that harnesses contemporary insights from various scales. Our model's efficacy is demonstrated on diverse datasets from the BraTS-2023 challenge. Integrating omni-dimensional dynamic convolution (ODConv) layers and multi-scale features yields substantial improvement in the nnU-Net architecture's performance across multiple tumor segmentation datasets. Remarkably, our proposed model attains good accuracy during validation for the BraTS Africa dataset. The ODconv source code along with full training code is available on GitHub. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2409_13229 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Multiscale Encoder and Omni-Dimensional Dynamic Convolution Enrichment in nnU-Net for Brain Tumor Segmentation Mistry, Sahaj K. Saini, Sourav Gupta, Aashray Gupta, Aayush Rai, Sunny Jakhetiya, Vinit Baid, Ujjwal Guntuku, Sharath Chandra Image and Video Processing Computer Vision and Pattern Recognition Brain tumor segmentation plays a crucial role in computer-aided diagnosis. This study introduces a novel segmentation algorithm utilizing a modified nnU-Net architecture. Within the nnU-Net architecture's encoder section, we enhance conventional convolution layers by incorporating omni-dimensional dynamic convolution layers, resulting in improved feature representation. Simultaneously, we propose a multi-scale attention strategy that harnesses contemporary insights from various scales. Our model's efficacy is demonstrated on diverse datasets from the BraTS-2023 challenge. Integrating omni-dimensional dynamic convolution (ODConv) layers and multi-scale features yields substantial improvement in the nnU-Net architecture's performance across multiple tumor segmentation datasets. Remarkably, our proposed model attains good accuracy during validation for the BraTS Africa dataset. The ODconv source code along with full training code is available on GitHub. |
| title | Multiscale Encoder and Omni-Dimensional Dynamic Convolution Enrichment in nnU-Net for Brain Tumor Segmentation |
| topic | Image and Video Processing Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2409.13229 |