research-contributions
MONAILabel
| research-contributions | MONAILabel | |
|---|---|---|
| 3 | 1 | |
| 933 | 542 | |
| 1.3% | 2.8% | |
| 8.1 | 7.9 | |
| 7 days ago | 7 days ago | |
| Python | Python | |
| Apache License 2.0 | Apache License 2.0 |
Stars - the number of stars that a project has on GitHub. Growth - month over month growth in stars.
Activity is a relative number indicating how actively a project is being developed. Recent commits have higher weight than older ones.
For example, an activity of 9.0 indicates that a project is amongst the top 10% of the most actively developed projects that we are tracking.
research-contributions
-
Dicom Images Segmentation
Checkout the MONAI library: https://monai.io/. It is tailored towards processing of medical images. It offers a label module which can be used for annotation, as well as a deep learning module with a vast range of models and medical data pipelines.
-
Pretrained Resnet50 for kidney detection (Kits19)
You can find a pretrained Resnet, but probably not one that's been trained on a kidney object detection dataset. The only kidney CT dataset I know of is for segmentation, not object detection. So you'll have to convert the segmentations to bounding boxes and train your own. Take a look at monai.io for potential resources.
-
Researchers From NVIDIA & Vanderbilt University Propose ‘Swin UNETR’: A Novel Architecture for Semantic Segmentation of Brain Tumors Using Multi-Modal MRI Images
Github: https://github.com/Project-MONAI/research-contributions/tree/master/SwinUNETR
MONAILabel
-
[D] Need to find a good self-hosted medical image annotation tool.
I've also found MONAILabel(https://github.com/Project-MONAI/MONAILabel), but it apparently requires GPU which makes it really expensive. I'd rather find a cpu based solution because our task is not that complex. We only get some Dicom files (each have studies in them), and want to label them.
What are some alternatives?
gpt-2 - Code for the paper "Language Models are Unsupervised Multitask Learners"
medicaldetectiontoolkit - The Medical Detection Toolkit contains 2D + 3D implementations of prevalent object detectors such as Mask R-CNN, Retina Net, Retina U-Net, as well as a training and inference framework focused on dealing with medical images.
jukebox - Code for the paper "Jukebox: A Generative Model for Music"
pytorch-toolbelt - PyTorch extensions for fast R&D prototyping and Kaggle farming
SlicerTomoSAM - An extension of 3D Slicer using the Segment Anything Model (SAM) to aid the segmentation of 3D data from tomography or other imaging techniques.
mammography_metarepository - Meta-repository of screening mammography classifiers
Active-Learning-as-a-Service - A scalable & efficient active learning/data selection system for everyone.
Brain-Tumor-Segmentation-And-Classification - Brain Tumor Segmentation And Classification using artificial intelligence
small-text - Active Learning for Text Classification in Python
dipy - DIPY is the paragon 3D/4D+ imaging library in Python. Contains generic methods for spatial normalization, signal processing, machine learning, statistical analysis and visualization of medical images. Additionally, it contains specialized methods for computational anatomy including diffusion, perfusion and structural imaging.