Use DICOM RT for 3D Semantic Segmentation of Medical images

Apply 3D UNet (Semantic Segmentation) into medical CT image without wasting time for labeling.
Updated 22 Nov 2019

View License

When using volume images for deep learning, labeling the data is big challenge.
In the radiation therapy field, from CT images, each of human bodies, organs, and GTV etc is extracted as area data. And they are stored in the RT-Structure of DICOM RT.
the data is mainly used to plan treatment, but we can also accelerate deep learning workflow using them as label data.
Through this demo, you can learn how to convert RT-Structure data to label data and use them for training 3D UNet (Semantic Segmentation) model on MATLAB.

放射線治療の分野では撮影されたCT画像から、人体、臓器、腫瘍などそれぞれが領域として定義され、DICOM RTのRT-Structureで管理されています。

I got DICOM RT data, a lot of feedback and helpful advice from:
Dr. Takafumi Nemoto (Keio Univ., Japan)
Dr. Natsumi Futakami (Tokai Univ., Japan)
Dr. Daisuke Kawahara (Hiroshima Univ., Japan)
Dr. Taiki Magome (Komazawa Univ., Japan)
Dr. Ulrik Landberg Stephansen(Aalborg Univ., Denmark)

画像処理・コンピュータービジョン・ディープラーニング・機械学習・CNN・IPCVデモ・Deep Learning・Machine Learning・3次元・医用画像・癌・放射線治療・放射線診断・

Cite As

Takuji Fukumoto (2024). Use DICOM RT for 3D Semantic Segmentation of Medical images (, MATLAB Central File Exchange. Retrieved .

MATLAB Release Compatibility
Created with R2019b
Compatible with R2019b
Platform Compatibility
Windows macOS Linux

Community Treasure Hunt

Find the treasures in MATLAB Central and discover how the community can help you!

Start Hunting!


Version Published Release Notes