Segmentation of renal structures based on contrast computed tomography scans

The model is the SegResNet architecture[1] for volumetric (3D) renal structures segmentation. Input is artery, vein, excretory phases after mutual registration and concatenated to 3 channel 3D tensor.

Tensorflow Detection Healthcare HuggingFace Model Link

Model Information

Current Version

0.2.2

Modality

Not specified

Anatomy Target

Not specified

Authors

shr3m, Ivan Chernenkiy, Michael Chernenkiy, Dmitry Fiev, Evgeny Sirota, Center for Neural Network Technologies / Institute of Urology and Human Reproductive Systems / Sechenov First Moscow State Medical University

Model Access

Open HuggingFace Model External Link

Research and Citation

BibTeX

@article{chernenkiy2023segmentation,
  title={Segmentation of renal structures based on contrast computed tomography scans using a convolutional neural network},
  author={Chernenkiy, IМ and Chernenkiy, MM and Fiev, DN and Sirota, ES},
  journal={Sechenov Medical Journal},
  volume={14},
  number={1},
  pages={39--49},
  year={2023}
}