3D ZNet Brain Segmentation DNN Model for MRI Brain Tumor Segmentation
Neuroimaging segmentation is a challenging task because of the complex structure, organization, anatomy, function and physiology of the brain. This project introduces Znet, an AI encoder-decoder deep learning technique for segmenting 3D MR images.
The complete self-cntained python code is available in the SOCR_3D_ZNET_python_code_V1 folder.
SOCR Team, Mohammad Ashraf Ottom, Hanif Abdul Rahman, Iyad M. Alazzam, and Ivo D. Dinov, and others.
This work is supported in part by NIH grants P20 NR015331, UL1TR002240, P30 DK089503, UL1TR002240, and NSF grants 1916425, 1734853, 1636840, 1416953, 0716055 and 1023115. Students, trainees, scholars, and researchers from SOCR, BDDS, MNORC, MIDAS, MADC, MICHR, and the broad R-statistical computing community have contributed ideas, code, and support.
- Ottom, MA, Rahman, HA, and Dinov, ID. (2022) Znet: Deep Learning Approach for 2D MRI Brain Tumor Segmentation, IEEE Journal of Translational Engineering in Health and Medicine, DOI: 10.1109/JTEHM.2022.3176737, 2168-2372, 10:1-8.
- Also see the DNN learning using 2D ZNet for Brain Segmentation.
- Pretrained ZNet models (*.pth) are available here.
- Brain Viewer.