Taming Mambas for Voxel Level 3D Medical Image Segmentation
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2024
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866917810166300672 |
|---|---|
| author | Lumetti, Luca Pipoli, Vittorio Marchesini, Kevin Ficarra, Elisa Grana, Costantino Bolelli, Federico |
| author_facet | Lumetti, Luca Pipoli, Vittorio Marchesini, Kevin Ficarra, Elisa Grana, Costantino Bolelli, Federico |
| contents | Recently, the field of 3D medical segmentation has been dominated by deep learning models employing Convolutional Neural Networks (CNNs) and Transformer-based architectures, each with their distinctive strengths and limitations. CNNs are constrained by a local receptive field, whereas transformers are hindered by their substantial memory requirements as well as they data hungriness, making them not ideal for processing 3D medical volumes at a fine-grained level. For these reasons, fully convolutional neural networks, as nnUNet, still dominate the scene when segmenting medical structures in 3D large medical volumes. Despite numerous advancements towards developing transformer variants with subquadratic time and memory complexity, these models still fall short in content-based reasoning. A recent breakthrough is Mamba, a Recurrent Neural Network (RNN) based on State Space Models (SSMs) outperforming Transformers in many long-context tasks (million-length sequences) on famous natural language processing and genomic benchmarks while keeping a linear complexity. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2410_15496 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Taming Mambas for Voxel Level 3D Medical Image Segmentation Lumetti, Luca Pipoli, Vittorio Marchesini, Kevin Ficarra, Elisa Grana, Costantino Bolelli, Federico Computer Vision and Pattern Recognition Recently, the field of 3D medical segmentation has been dominated by deep learning models employing Convolutional Neural Networks (CNNs) and Transformer-based architectures, each with their distinctive strengths and limitations. CNNs are constrained by a local receptive field, whereas transformers are hindered by their substantial memory requirements as well as they data hungriness, making them not ideal for processing 3D medical volumes at a fine-grained level. For these reasons, fully convolutional neural networks, as nnUNet, still dominate the scene when segmenting medical structures in 3D large medical volumes. Despite numerous advancements towards developing transformer variants with subquadratic time and memory complexity, these models still fall short in content-based reasoning. A recent breakthrough is Mamba, a Recurrent Neural Network (RNN) based on State Space Models (SSMs) outperforming Transformers in many long-context tasks (million-length sequences) on famous natural language processing and genomic benchmarks while keeping a linear complexity. |
| title | Taming Mambas for Voxel Level 3D Medical Image Segmentation |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2410.15496 |