CTDeepRot

CTDeepRot

Software

A tool for automatic rotation of spinal CT data into a standardized (HFS) patient position. The proposed method is based on the prediction of rotation angle with CNN, and it achieved nearly perfect results with an accuracy of 99.55 % and in a very short time (in the order of units of seconds per scan). We provide implementations with easy to use an example for both Matlab and Python (PyTorch), which can be used, for example, for automatic rotation correction of VerSe2020 challenge data.

A tool for automatic rotation of spinal CT data into a standardized (HFS) patient position. The proposed method is based on the prediction of rotation angle with CNN, and it achieved nearly perfect results with an accuracy of 99.55 % and in a very short time (in the order of units of seconds per scan). We provide implementations with easy to use an example for both Matlab and Python (PyTorch), which can be used, for example, for automatic rotation correction of VerSe2020 challenge data.

spine; computed tomography; deep learning; convolutional neural network; patient position

spine; computed tomography; deep learning; convolutional neural network; patient position

Ústav biomedicínského inženýrství Vysoké učení technické v Brně Technická 12 616 00 Brno Česká republika +web GitHub

Využití výsledku jiným subjektem je možné bez nabytí licence (výsledek není licencován)

https://github.com/JakubicekRoman/CTDeepRot