Generation of synthetic training data for SEEG electrodes segmentation

Purpose: Stereoelectroencephalography (SEEG) is a minimally invasive surgical procedure, used to locate epileptogenic zones. An accurate identification of the metallic contacts recording the SEEG signal is crucial to ensure effectiveness of the upcoming treatment. However, due to the presence of metal, postoperative CT scans contain strong streak artefacts that interfere with deep learning segmentation algorithms and require a lot of training data to distinguish from actual contacts. We propose a method to generate synthetic data and use them to train a neural network to precisely locate SEEG electrode contacts. Methods: Random electrodes were generated following manufacturer's specifications and dimensions, and placed in acceptable regions inside metal-free CT images. Metal artefacts were simulated in the generated dataset using radon transform, beam hardening, and filtered back projection. A UNet neural network was trained for the contacts segmentation task using various training setups combining real data, basic augmented data and synthetic data. The results were compared. Results: We reported a higher accuracy when including synthetic data during the network training, while training only on real and basic augmented data more often led to misclassified artefacts or missed contacts. The network segments post-operative CT slices in less than 2 seconds using 4 GeForce RTX2080 Ti GPUs and in under a minute using a standard PC with GeForce GTX1060. Conclusion: Using synthetic data to train the network significantly improves contact detection and segmentation accuracy.

A. Pantovic , X. Ren , C. Wemmert , I. Ollivier , C. Essert

International Journal of Computer Assisted Radiology and Surgery , Volume 17 , Number 5 , page 937–943 - 2022

@Article{2-PRWO22,
 author = {Pantovic, A. and Ren, X. and Wemmert, C. and Ollivier, I. and Essert, C.},
 title = {Generation of synthetic training data for SEEG electrodes segmentation},
 journal = {International Journal of Computer Assisted Radiology and Surgery},
 number = {5},
 volume = {17},
 pages = {937–943},
 month = {May},
 year = {2022},
 doi = {10.1007/s11548-022-02585-4},
 x-international-audience = {Yes},
 x-language = {EN},
 url = {http://publis.icube.unistra.fr/2-PRWO22}
}