Deep learning-based reconstruction of in vivo pelvis conductivity with a 3D patch-based convolutional neural network trained on simulated MR data
| Autor: | Soraya Gavazzi, H. Petra Kok, Peter de Boer, Lukas J.A. Stalpers, Astrid L.H.M.W. van Lier, Jan J W Lagendijk, Cornelis A. T. van den Berg, Mark H. F. Savenije, Hans Crezee |
|---|---|
| Přispěvatelé: | Radiotherapy, CCA - Cancer Treatment and Quality of Life, Graduate School, APH - Methodology |
| Jazyk: | angličtina |
| Rok vydání: | 2020 |
| Předmět: |
Accuracy and precision
MR simulations Mean squared error Conductivity Convolutional neural network Pelvis 030218 nuclear medicine & medical imaging Full Papers—Computer Processing and Modeling 03 medical and health sciences Deep Learning 0302 clinical medicine In vivo Image Processing Computer-Assisted Humans Radiology Nuclear Medicine and imaging Sensitivity (control systems) pelvis MRI Physics Ground truth Full Paper business.industry Deep learning conductivity mapping Magnetic Resonance Imaging Neural Networks Computer Artificial intelligence deep learning EPT business 030217 neurology & neurosurgery Biomedical engineering |
| Zdroj: | Magnetic resonance in medicine, 84(5), 2772-2787. John Wiley and Sons Inc. Magnetic Resonance in Medicine |
| ISSN: | 0740-3194 |
| Popis: | Purpose: To demonstrate that mapping pelvis conductivity at 3T with deep learning (DL) is feasible. Methods: 210 dielectric pelvic models were generated based on CT scans of 42 cervical cancer patients. For all dielectric models, electromagnetic and MR simulations with realistic accuracy and precision were performed to obtain (Formula presented.) and transceive phase (ϕ ±). Simulated (Formula presented.) and ϕ ± served as input to a 3D patch-based convolutional neural network, which was trained in a supervised fashion to retrieve the conductivity. The same network architecture was retrained using only ϕ ± in input. Both network configurations were tested on simulated MR data and their conductivity reconstruction accuracy and precision were assessed. Furthermore, both network configurations were used to reconstruct conductivity maps from a healthy volunteer and two cervical cancer patients. DL-based conductivity was compared in vivo and in silico to Helmholtz-based (H-EPT) conductivity. Results: Conductivity maps obtained from both network configurations were comparable. Accuracy was assessed by mean error (ME) with respect to ground truth conductivity. On average, ME < 0.1 Sm −1 for all tissues. Maximum MEs were 0.2 Sm −1 for muscle and tumour, and 0.4 Sm −1 for bladder. Precision was indicated with the difference between 90 th and 10 th conductivity percentiles, and was below 0.1 Sm −1 for fat, bone and muscle, 0.2 Sm −1 for tumour and 0.3 Sm −1 for bladder. In vivo, DL-based conductivity had median values in agreement with H-EPT values, but a higher precision. Conclusion: Anatomically detailed, noise-robust 3D conductivity maps with good sensitivity to tissue conductivity variations were reconstructed in the pelvis with DL. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|
Plný text