RadIO是一个计算机断层扫描（CT）成像数据科学研究框架

RadIO是一个计算机断层扫描（CT）成像数据科学研究框架

RadIO

RadIO is a framework for data science research of computed tomography (CT) imaging.

Main features:

Asynchronously load DICOM and MetaImage (mhd/raw) filesDump files to blosc to compress datasets and thus accelerate loadingTransform and augment CT-scans in parallel for faster preprocessingCreate concise chainable workflows with actions or use tailored pipelines for preprocessing or model trainingTrain with ease a zoo of state-of-the-art neural networks for classification or semantic segmentationSample crops of any size from CT-scans for comprehensive trainingCustomize distribution of crop locations for improved trainingPredict on the whole scan

The documentation contains a comprehensive review of RadIO's capabilities. While tutorials provide ready-to-use code blocks and a practical demonstration of the most important RadIO features.

Tutorials

There are four tutorials available:

In the first one you can learn how to set up a dataset of CT-scans and define a basic preprocessing workflow.The second tutorial contains in-depth discussion of preprocessing and augmentation actions.The third tutorial explains how to generate batches to train a neural network.The fourth tutorial will help you configure and train a neural network to detect cancer.

Preprocess scans with chained actions

Preprocessing-module contains a set of actions to efficiently prepare a dataset of CT-scans for neural networks training.

Say, you have a bunch of DICOM scans with varying shapes. First, you create an index and define a dataset:

from radio import CTImagesBatchfrom radio.batchflow import FilesIndex, Datasetdicom_ix = FilesIndex(path='path/to/dicom/*', dirs=True) # set up the indexdicom_dataset = Dataset(index=dicom_ix, batch_class=CTImagesBatch) # init the dataset of dicom files

You may want to resize the scans to equal shape [128, 256, 256], normalize voxel densities to range [0, 255] and dump transformed scans. This preprocessing can be easily performed with the following pipeline:

pipeline = ( dicom_dataset.p .load(fmt='dicom') .resize(shape=(128, 256, 256)) .normalize_hu() .dump('/path/to/preprocessed/scans/'))pipeline.run(batch_size=20)

See the documentation for the description of preprocessing actions implemented in the module.

Preprocess scans using a pre-defined workflow

Pipelines module contains ready-to-use workflows for most frequent tasks. For instance, if you want to preprocess a dataset of scans named dicom_dataset and prepare data for training a neural network, you can simply execute the following pipeline creator (without spending much time on thinking what actions to choose for a workflow):

from radio.pipelines import get_cropsnodata_pipeline = get_crops(fmt='raw', shape=(128, 256, 256), nodules=nodules, batch_size=20, share=0.6, nodule_shape=(32, 64, 64))dicom_pipeline = dicom_dataset >> nodata_pipelinefor batch in dicom_pipeline.gen_batch(batch_size=12, shuffle=True): # ... # train a model here

See pipelines section for more information about ready-to-use workflows.

Adding a neural network to a workflow

RadIO contains proven architectures for classification, segmentation and detection, including neural networks designed specifically for cancer detection (e.g. DenseNoduleNet inspired by the state-of-the-art DenseNet, but well suited for 3D CT scans):

from radio.preprocessing import CTImagesMaskedBatch as CTIMBfrom radio.models import DenseNoduleNetfrom radio.batchflow import Ftraining_pipeline = ( dicom_dataset.p .load(fmt='raw') .fetch_nodules_info(nodules_df) .create_mask() .sample_nodules(nodule_size=(32, 64, 64), batch_size=20) .init_model('static', DenseNoduleNet, 'net') .train_model('net', feed_dict={ 'images': F(CTIMB.unpack, component='images'), 'labels': F(CTIMB.unpack, component='classification_targets') }))training_pipeline.run(batch_size=10, shuffle=True)

The models documentation contains more information about implemented architectures and their application to cancer detection.

Installation

RadIO module is in the beta stage. Your suggestions and improvements are very welcome.

RadIO supports python 3.5 or higher.

Installation as a python package

With pipenv:

pipenv install git+https://github.com/analysiscenter/radio.git#egg=radio

With pip:

pip3 install git+https://github.com/analysiscenter/radio.git

After that just import radio:

import radio

Installation as a project repository:

When cloning repo from GitHub use flag --recursive to make sure that BatchFlow submodule is also cloned.

git clone --recursive https://github.com/analysiscenter/radio.git

Citing RadIO

Please cite RadIO in your publications if it helps your research.

Khudorozhkov R., Emelyanov K., Koryagin A., Kozhevin A. RadIO library for data science research of CT images. 2017.

@misc{radio_2017_1156363, author = {Khudorozhkov R., Emelyanov K., Koryagin A., Kozhevin A.}, title = {RadIO library for data science research of CT images}, year = 2017, doi = {10.5281/zenodo.1156363}, url = {https://doi.org/10.5281/zenodo.1156363}}

版权声明：本文内容由网络用户投稿，版权归原作者所有，本站不拥有其著作权，亦不承担相应法律责任。如果您发现本站中有涉嫌抄袭或描述失实的内容，请联系我们jiasou666@gmail.com 处理，核实后本网站将在24小时内删除侵权内容。