Cargando…
Exercise‐induced calf muscle hyperemia: Rapid mapping of magnetic resonance imaging using deep learning approach
Exercise‐induced hyperemia in calf muscles was recently shown to be quantifiable with high‐resolution magnetic resonance imaging (MRI). However, processing of the MRI data to obtain muscle‐perfusion maps is time‐consuming. This study proposes to substantially accelerate the mapping of muscle perfusi...
Autores principales: | , , , , , , |
---|---|
Formato: | Online Artículo Texto |
Lenguaje: | English |
Publicado: |
John Wiley and Sons Inc.
2020
|
Materias: | |
Acceso en línea: | https://www.ncbi.nlm.nih.gov/pmc/articles/PMC7435025/ https://www.ncbi.nlm.nih.gov/pubmed/32812401 http://dx.doi.org/10.14814/phy2.14563 |
_version_ | 1783572260358979584 |
---|---|
author | Zhang, Jeff L. Conlin, Christopher C. Li, Xiaowan Layec, Gwenael Chang, Ken Kalpathy‐Cramer, Jayashree Lee, Vivian S. |
author_facet | Zhang, Jeff L. Conlin, Christopher C. Li, Xiaowan Layec, Gwenael Chang, Ken Kalpathy‐Cramer, Jayashree Lee, Vivian S. |
author_sort | Zhang, Jeff L. |
collection | PubMed |
description | Exercise‐induced hyperemia in calf muscles was recently shown to be quantifiable with high‐resolution magnetic resonance imaging (MRI). However, processing of the MRI data to obtain muscle‐perfusion maps is time‐consuming. This study proposes to substantially accelerate the mapping of muscle perfusion using a deep‐learning method called artificial neural network (NN). Forty‐eight MRI scans were acquired from 21 healthy subjects and patients with peripheral artery disease (PAD). For optimal training of NN, different training‐data sets were compared, investigating the effect of data diversity and reference perfusion accuracy. Reference perfusion was estimated by tracer kinetic model fitting initialized with multiple values (multigrid model fitting). Result: The NN method was much faster than tracer kinetic model fitting. To generate a perfusion map of matrix 128 × 128 on a same computer, multigrid model fitting took about 80 min, single‐grid or regular model fitting about 3 min, while the NN method took about 1 s. Compared to the reference values, NN trained with a diverse group gave estimates with mean absolute error (MAE) of 15.9 ml/min/100g and correlation coefficient (R) of 0.949, significantly more accurate than regular model fitting (MAE 22.3 ml/min/100g, R 0.889, p < .001). Conclusion: the NN method enables rapid perfusion mapping, and if properly trained, estimates perfusion with accuracy comparable to multigrid model fitting. |
format | Online Article Text |
id | pubmed-7435025 |
institution | National Center for Biotechnology Information |
language | English |
publishDate | 2020 |
publisher | John Wiley and Sons Inc. |
record_format | MEDLINE/PubMed |
spelling | pubmed-74350252020-08-20 Exercise‐induced calf muscle hyperemia: Rapid mapping of magnetic resonance imaging using deep learning approach Zhang, Jeff L. Conlin, Christopher C. Li, Xiaowan Layec, Gwenael Chang, Ken Kalpathy‐Cramer, Jayashree Lee, Vivian S. Physiol Rep Original Research Exercise‐induced hyperemia in calf muscles was recently shown to be quantifiable with high‐resolution magnetic resonance imaging (MRI). However, processing of the MRI data to obtain muscle‐perfusion maps is time‐consuming. This study proposes to substantially accelerate the mapping of muscle perfusion using a deep‐learning method called artificial neural network (NN). Forty‐eight MRI scans were acquired from 21 healthy subjects and patients with peripheral artery disease (PAD). For optimal training of NN, different training‐data sets were compared, investigating the effect of data diversity and reference perfusion accuracy. Reference perfusion was estimated by tracer kinetic model fitting initialized with multiple values (multigrid model fitting). Result: The NN method was much faster than tracer kinetic model fitting. To generate a perfusion map of matrix 128 × 128 on a same computer, multigrid model fitting took about 80 min, single‐grid or regular model fitting about 3 min, while the NN method took about 1 s. Compared to the reference values, NN trained with a diverse group gave estimates with mean absolute error (MAE) of 15.9 ml/min/100g and correlation coefficient (R) of 0.949, significantly more accurate than regular model fitting (MAE 22.3 ml/min/100g, R 0.889, p < .001). Conclusion: the NN method enables rapid perfusion mapping, and if properly trained, estimates perfusion with accuracy comparable to multigrid model fitting. John Wiley and Sons Inc. 2020-08-18 /pmc/articles/PMC7435025/ /pubmed/32812401 http://dx.doi.org/10.14814/phy2.14563 Text en © 2020 The Authors. Physiological Reports published by Wiley Periodicals LLC on behalf of The Physiological Society and the American Physiological Society This is an open access article under the terms of the http://creativecommons.org/licenses/by/4.0/ License, which permits use, distribution and reproduction in any medium, provided the original work is properly cited. |
spellingShingle | Original Research Zhang, Jeff L. Conlin, Christopher C. Li, Xiaowan Layec, Gwenael Chang, Ken Kalpathy‐Cramer, Jayashree Lee, Vivian S. Exercise‐induced calf muscle hyperemia: Rapid mapping of magnetic resonance imaging using deep learning approach |
title | Exercise‐induced calf muscle hyperemia: Rapid mapping of magnetic resonance imaging using deep learning approach |
title_full | Exercise‐induced calf muscle hyperemia: Rapid mapping of magnetic resonance imaging using deep learning approach |
title_fullStr | Exercise‐induced calf muscle hyperemia: Rapid mapping of magnetic resonance imaging using deep learning approach |
title_full_unstemmed | Exercise‐induced calf muscle hyperemia: Rapid mapping of magnetic resonance imaging using deep learning approach |
title_short | Exercise‐induced calf muscle hyperemia: Rapid mapping of magnetic resonance imaging using deep learning approach |
title_sort | exercise‐induced calf muscle hyperemia: rapid mapping of magnetic resonance imaging using deep learning approach |
topic | Original Research |
url | https://www.ncbi.nlm.nih.gov/pmc/articles/PMC7435025/ https://www.ncbi.nlm.nih.gov/pubmed/32812401 http://dx.doi.org/10.14814/phy2.14563 |
work_keys_str_mv | AT zhangjeffl exerciseinducedcalfmusclehyperemiarapidmappingofmagneticresonanceimagingusingdeeplearningapproach AT conlinchristopherc exerciseinducedcalfmusclehyperemiarapidmappingofmagneticresonanceimagingusingdeeplearningapproach AT lixiaowan exerciseinducedcalfmusclehyperemiarapidmappingofmagneticresonanceimagingusingdeeplearningapproach AT layecgwenael exerciseinducedcalfmusclehyperemiarapidmappingofmagneticresonanceimagingusingdeeplearningapproach AT changken exerciseinducedcalfmusclehyperemiarapidmappingofmagneticresonanceimagingusingdeeplearningapproach AT kalpathycramerjayashree exerciseinducedcalfmusclehyperemiarapidmappingofmagneticresonanceimagingusingdeeplearningapproach AT leevivians exerciseinducedcalfmusclehyperemiarapidmappingofmagneticresonanceimagingusingdeeplearningapproach |