Breaking Speed Limits with Simultaneous Ultra-Fast MRI Reconstruction and Tissue Segmentation

Francesco Calivá, Andrew P. Leynes, Rutwik Shah, Upasana Upadhyay Bharadwaj, Sharmila Majumdar, Peder E. Z. Larson, Valentina Pedoia
; Proceedings of the Third Conference on Medical Imaging with Deep Learning, PMLR 121:94-110, 2020.

Abstract

Magnetic Resonance Image (MRI) acquisition, reconstruction and tissue segmentation are usually considered separate problems. This can be limiting when it comes to rapidly extracting relevant clinical parameters. In many applications, availability of reconstructed images with high fidelity may not be a priority as long as biomarker extraction is reliable and feasible. Built upon this concept, we demonstrate that it is possible to perform tissue segmentation directly from highly undersampled \textit{k-}space and obtain quality results comparable to those in fully-sampled scenarios. We propose {\em TB-recon}, a 3D task-based reconstruction framework. {\em TB-recon} simultaneously reconstructs MRIs from raw data and segments tissues of interest. To do so, we devised a network architecture with a shared encoding path and two task-related decoders where features flow among tasks. We deployed {\em TB-recon} on a set of (up to $24\times$) retrospectively undersampled MRIs from the Osteoarthritis Initiative dataset, where we automatically segmented knee cartilage and menisci. An experimental study was conducted showing the superior performance of the proposed method over a combination of a standard MRI reconstruction and segmentation method, as well as alternative deep learning based solutions. In addition, our ablation study highlighted the importance of skip connections among the decoders for the segmentation task. Ultimately, we conducted a reader study, where two musculoskeletal radiologists assessed the proposed model�s reconstruction performance.

Cite this Paper


BibTeX
@InProceedings{pmlr-v121-caliva20a, title = {Breaking Speed Limits with Simultaneous Ultra-Fast MRI Reconstruction and Tissue Segmentation}, author = {Caliv\'a, Francesco and Leynes, Andrew P. and Shah, Rutwik and {Upadhyay Bharadwaj}, Upasana and Majumdar, Sharmila and Larson, Peder E. Z. and Pedoia, Valentina}, pages = {94--110}, year = {2020}, editor = {Tal Arbel and Ismail Ben Ayed and Marleen de Bruijne and Maxime Descoteaux and Herve Lombaert and Christopher Pal}, volume = {121}, series = {Proceedings of Machine Learning Research}, address = {Montreal, QC, Canada}, month = {06--08 Jul}, publisher = {PMLR}, pdf = {http://proceedings.mlr.press/v121/caliva20a/caliva20a.pdf}, url = {http://proceedings.mlr.press/v121/caliva20a.html}, abstract = {Magnetic Resonance Image (MRI) acquisition, reconstruction and tissue segmentation are usually considered separate problems. This can be limiting when it comes to rapidly extracting relevant clinical parameters. In many applications, availability of reconstructed images with high fidelity may not be a priority as long as biomarker extraction is reliable and feasible. Built upon this concept, we demonstrate that it is possible to perform tissue segmentation directly from highly undersampled \textit{k-}space and obtain quality results comparable to those in fully-sampled scenarios. We propose {\em TB-recon}, a 3D task-based reconstruction framework. {\em TB-recon} simultaneously reconstructs MRIs from raw data and segments tissues of interest. To do so, we devised a network architecture with a shared encoding path and two task-related decoders where features flow among tasks. We deployed {\em TB-recon} on a set of (up to $24\times$) retrospectively undersampled MRIs from the Osteoarthritis Initiative dataset, where we automatically segmented knee cartilage and menisci. An experimental study was conducted showing the superior performance of the proposed method over a combination of a standard MRI reconstruction and segmentation method, as well as alternative deep learning based solutions. In addition, our ablation study highlighted the importance of skip connections among the decoders for the segmentation task. Ultimately, we conducted a reader study, where two musculoskeletal radiologists assessed the proposed model�s reconstruction performance.} }
Endnote
%0 Conference Paper %T Breaking Speed Limits with Simultaneous Ultra-Fast MRI Reconstruction and Tissue Segmentation %A Francesco Calivá %A Andrew P. Leynes %A Rutwik Shah %A Upasana Upadhyay Bharadwaj %A Sharmila Majumdar %A Peder E. Z. Larson %A Valentina Pedoia %B Proceedings of the Third Conference on Medical Imaging with Deep Learning %C Proceedings of Machine Learning Research %D 2020 %E Tal Arbel %E Ismail Ben Ayed %E Marleen de Bruijne %E Maxime Descoteaux %E Herve Lombaert %E Christopher Pal %F pmlr-v121-caliva20a %I PMLR %J Proceedings of Machine Learning Research %P 94--110 %U http://proceedings.mlr.press %V 121 %W PMLR %X Magnetic Resonance Image (MRI) acquisition, reconstruction and tissue segmentation are usually considered separate problems. This can be limiting when it comes to rapidly extracting relevant clinical parameters. In many applications, availability of reconstructed images with high fidelity may not be a priority as long as biomarker extraction is reliable and feasible. Built upon this concept, we demonstrate that it is possible to perform tissue segmentation directly from highly undersampled \textit{k-}space and obtain quality results comparable to those in fully-sampled scenarios. We propose {\em TB-recon}, a 3D task-based reconstruction framework. {\em TB-recon} simultaneously reconstructs MRIs from raw data and segments tissues of interest. To do so, we devised a network architecture with a shared encoding path and two task-related decoders where features flow among tasks. We deployed {\em TB-recon} on a set of (up to $24\times$) retrospectively undersampled MRIs from the Osteoarthritis Initiative dataset, where we automatically segmented knee cartilage and menisci. An experimental study was conducted showing the superior performance of the proposed method over a combination of a standard MRI reconstruction and segmentation method, as well as alternative deep learning based solutions. In addition, our ablation study highlighted the importance of skip connections among the decoders for the segmentation task. Ultimately, we conducted a reader study, where two musculoskeletal radiologists assessed the proposed model�s reconstruction performance.
APA
Calivá, F., Leynes, A.P., Shah, R., Upadhyay Bharadwaj, U., Majumdar, S., Larson, P.E.Z. & Pedoia, V.. (2020). Breaking Speed Limits with Simultaneous Ultra-Fast MRI Reconstruction and Tissue Segmentation. Proceedings of the Third Conference on Medical Imaging with Deep Learning, in PMLR 121:94-110

Related Material