https://github.com/christophreich1996/oss-net
Official and maintained implementation of the paper "OSS-Net: Memory Efficient High Resolution Semantic Segmentation of 3D Medical Data" [BMVC 2021].
Science Score: 10.0%
This score indicates how likely this project is to be science-related based on various indicators:
-
○CITATION.cff file
-
○codemeta.json file
-
○.zenodo.json file
-
○DOI references
-
✓Academic publication links
Links to: arxiv.org, scholar.google -
○Academic email domains
-
○Institutional organization owner
-
○JOSS paper metadata
-
○Scientific vocabulary similarity
Low similarity (9.4%) to scientific vocabulary
Keywords
3d-vision
bmvc
bmvc2021
brats
computer-vision
deep-learning
lits
medical-imaging
oss-net
pytorch
segmentation
semantic-segmentation
Last synced: 6 months ago
·
JSON representation
Repository
Official and maintained implementation of the paper "OSS-Net: Memory Efficient High Resolution Semantic Segmentation of 3D Medical Data" [BMVC 2021].
Basic Info
- Host: GitHub
- Owner: ChristophReich1996
- License: mit
- Language: Python
- Default Branch: master
- Homepage: https://www.bmvc2021-virtualconference.com/conference/papers/paper_1488.html
- Size: 4.74 MB
Statistics
- Stars: 24
- Watchers: 4
- Forks: 2
- Open Issues: 0
- Releases: 0
Topics
3d-vision
bmvc
bmvc2021
brats
computer-vision
deep-learning
lits
medical-imaging
oss-net
pytorch
segmentation
semantic-segmentation
Created over 4 years ago
· Last pushed almost 3 years ago
https://github.com/ChristophReich1996/OSS-Net/blob/master/
# OSS-Net: Memory Efficient High Resolution Semantic Segmentation of 3D Medical Data [](https://arxiv.org/abs/2110.10640) [](https://github.com/ChristophReich1996/OSS-Net/blob/master/LICENSE) **[Christoph Reich](https://christophreich1996.github.io), [Tim Prangemeier](https://www.bcs.tu-darmstadt.de/team_sos/prangemeiertim_sos.en.jsp), [zdemir Cetin](https://www.bcs.tu-darmstadt.de/team_sos/oezdemircetin_sos.en.jsp) & [Heinz Koeppl](https://www.bcs.tu-darmstadt.de/team_sos/koepplheinz_sos.en.jsp)**
## | [Project Page](https://christophreich1996.github.io/oss_net/) | [Paper](https://www.bmvc2021-virtualconference.com/conference/papers/paper_1488.html) | [Slides](https://christophreich1996.github.io/pdfs/BMVC_Presentation_1488.pdf) | [Video](https://christophreich1996.github.io/oss_net/) |
This repository includes the official and maintained PyTorch implementation of the paper OSS-Net: Memory Efficient High Resolution Semantic Segmentation of 3D Medical Data.
## Abstract *Convolutional neural networks (CNNs) are the current state-of-the-art meta-algorithm for volumetric segmentation of medical data, for example, to localize COVID-19 infected tissue on computer tomography scans or the detection of tumour volumes in magnetic resonance imaging. A key limitation of 3D CNNs on voxelised data is that the memory consumption grows cubically with the training data resolution. Occupancy networks (O-Nets) are an alternative for which the data is represented continuously in a function space and 3D shapes are learned as a continuous decision boundary. While O-Nets are significantly more memory efficient than 3D CNNs, they are limited to simple shapes, are relatively slow at inference, and have not yet been adapted for 3D semantic segmentation of medical data. Here, we propose Occupancy Networks for Semantic Segmentation (OSS-Nets) to accurately and memory-efficiently segment 3D medical data. We build upon the original O-Net with modifications for increased expressiveness leading to improved segmentation performance comparable to 3D CNNs, as well as modifications for faster inference. We leverage local observations to represent complex shapes and prior encoder predictions to expedite inference. We showcase OSS-Net's performance on 3D brain tumour and liver segmentation against a function space baseline (O-Net), a performance baseline (3D residual U-Net), and an efficiency baseline (2D residual U-Net). OSS-Net yields segmentation results similar to the performance baseline and superior to the function space and efficiency baselines. In terms of memory efficiency, OSS-Net consumes comparable amounts of memory as the function space baseline, somewhat more memory than the efficiency baseline and significantly less than the performance baseline. As such, OSS-Net enables memory-efficient and accurate 3D semantic segmentation that can scale to high resolutions.* **If you find this research useful in your work, please cite our paper:** ```bibtex @inproceedings{Reich2021, title={{OSS-Net: Memory Efficient High Resolution Semantic Segmentation of 3D Medical Data}}, author={Reich, Christoph and Prangemeier, Tim and Cetin, {\"O}zdemir and Koeppl, Heinz}, booktitle={British Machine Vision Conference}, year={2021}, organization={British Machine Vision Association}, } ``` ## Dependencies All required Python packages can be installed by: ```shell script pip install -r requirements.txt ``` To install the official implementation of the Pad Activation Unit [1] (taken from the [official repository](https://github.com/ml-research/pau)) run: ```shell script cd pade_activation_unit/cuda python setup.py build install ``` The code is tested with [PyTorch 1.8.1](https://pytorch.org/get-started/locally/) and CUDA 11.1 on Linux with Python 3.8.5! Using other PyTorch and CUDA versions newer than [PyTorch 1.7.0](https://pytorch.org/get-started/previous-versions/) and CUDA 10.1 should also be possible. ## Data The BraTS 2020 dataset can be downloaded [here](https://www.med.upenn.edu/cbica/brats2020/registration.html) and the LiTS dataset can be downloaded [here](https://competitions.codalab.org/competitions/17094#learn_the_details). Please note, that accounts are required to login and downlaod the data on both websites. The used training and validation split of the BraTS 2020 dataset is available [here](data/bra_ts_split.txt). For generating the border maps, necessary if border based sampling is utilized, please use the [`generate_borders_bra_ts_2020.py`](scripts/generate_borders_bra_ts_2020.py) and [`generate_borders_lits.py`](scripts/generate_borders_lits.py) script. ## Trained Models **Table 1.** Segmentation results of trained networks. Weights are generally available [here](https://tudatalib.ulb.tu-darmstadt.de/handle/tudatalib/2991) and specific models are linked below. | Model | Dice () BraTS 2020 | IoU (
Owner
- Name: Christoph Reich
- Login: ChristophReich1996
- Kind: user
- Location: Germany
- Company: Technical University of Munich
- Website: christophreich1996.github.io
- Twitter: ChristophR1996
- Repositories: 41
- Profile: https://github.com/ChristophReich1996
ELLIS Ph.D. Student @ Technical University of Munich, Technische Universität Darmstadt & University of Oxford | Prev. NEC Labs
GitHub Events
Total
- Watch event: 3
Last Year
- Watch event: 3