On Real-time Image Reconstruction with Neural Networks for MRI-guided Radiotherapy
Fuente:
arXiv
Guardado en:
| Autores principales: | , , , , , , , , , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2022
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866916419325657088 |
|---|---|
| author | Waddington, David E. J. Hindley, Nicholas Koonjoo, Neha Chiu, Christopher Reynolds, Tess Liu, Paul Z. Y. Zhu, Bo Bhutto, Danyal Paganelli, Chiara Keall, Paul J. Rosen, Matthew S. |
| author_facet | Waddington, David E. J. Hindley, Nicholas Koonjoo, Neha Chiu, Christopher Reynolds, Tess Liu, Paul Z. Y. Zhu, Bo Bhutto, Danyal Paganelli, Chiara Keall, Paul J. Rosen, Matthew S. |
| contents | MRI-guidance techniques that dynamically adapt radiation beams to follow tumor motion in real-time will lead to more accurate cancer treatments and reduced collateral healthy tissue damage. The gold-standard for reconstruction of undersampled MR data is compressed sensing (CS) which is computationally slow and limits the rate that images can be available for real-time adaptation. Here, we demonstrate the use of automated transform by manifold approximation (AUTOMAP), a generalized framework that maps raw MR signal to the target image domain, to rapidly reconstruct images from undersampled radial k-space data. The AUTOMAP neural network was trained to reconstruct images from a golden-angle radial acquisition, a benchmark for motion-sensitive imaging, on lung cancer patient data and generic images from ImageNet. Model training was subsequently augmented with motion-encoded k-space data derived from videos in the YouTube-8M dataset to encourage motion robust reconstruction. We find that AUTOMAP-reconstructed radial k-space has equivalent accuracy to CS but with much shorter processing times after initial fine-tuning on retrospectively acquired lung cancer patient data. Validation of motion-trained models with a virtual dynamic lung tumor phantom showed that the generalized motion properties learned from YouTube lead to improved target tracking accuracy. Our work shows that AUTOMAP can achieve real-time, accurate reconstruction of radial data. These findings imply that neural-network-based reconstruction is potentially superior to existing approaches for real-time image guidance applications. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2202_05267 |
| institution | arXiv |
| publishDate | 2022 |
| record_format | arxiv |
| spellingShingle | On Real-time Image Reconstruction with Neural Networks for MRI-guided Radiotherapy Waddington, David E. J. Hindley, Nicholas Koonjoo, Neha Chiu, Christopher Reynolds, Tess Liu, Paul Z. Y. Zhu, Bo Bhutto, Danyal Paganelli, Chiara Keall, Paul J. Rosen, Matthew S. Medical Physics Computer Vision and Pattern Recognition Image and Video Processing MRI-guidance techniques that dynamically adapt radiation beams to follow tumor motion in real-time will lead to more accurate cancer treatments and reduced collateral healthy tissue damage. The gold-standard for reconstruction of undersampled MR data is compressed sensing (CS) which is computationally slow and limits the rate that images can be available for real-time adaptation. Here, we demonstrate the use of automated transform by manifold approximation (AUTOMAP), a generalized framework that maps raw MR signal to the target image domain, to rapidly reconstruct images from undersampled radial k-space data. The AUTOMAP neural network was trained to reconstruct images from a golden-angle radial acquisition, a benchmark for motion-sensitive imaging, on lung cancer patient data and generic images from ImageNet. Model training was subsequently augmented with motion-encoded k-space data derived from videos in the YouTube-8M dataset to encourage motion robust reconstruction. We find that AUTOMAP-reconstructed radial k-space has equivalent accuracy to CS but with much shorter processing times after initial fine-tuning on retrospectively acquired lung cancer patient data. Validation of motion-trained models with a virtual dynamic lung tumor phantom showed that the generalized motion properties learned from YouTube lead to improved target tracking accuracy. Our work shows that AUTOMAP can achieve real-time, accurate reconstruction of radial data. These findings imply that neural-network-based reconstruction is potentially superior to existing approaches for real-time image guidance applications. |
| title | On Real-time Image Reconstruction with Neural Networks for MRI-guided Radiotherapy |
| topic | Medical Physics Computer Vision and Pattern Recognition Image and Video Processing |
| url | https://arxiv.org/abs/2202.05267 |