Synthetic Knee MRI T<sub>1p</sub> Maps as an Avenue for Clinical Translation of Quantitative Osteoarthritis Biomarkers
A 2D U-Net was trained to generate synthetic T<sub>1p</sub> maps from T<sub>2</sub> maps for knee MRI to explore the feasibility of domain adaptation for enriching existing datasets and enabling rapid, reliable image reconstruction. The network was developed using 509 healthy...
Main Authors: | , , , , , |
---|---|
Format: | Article |
Language: | English |
Published: |
MDPI AG
2023-12-01
|
Series: | Bioengineering |
Subjects: | |
Online Access: | https://www.mdpi.com/2306-5354/11/1/17 |
_version_ | 1797344653834452992 |
---|---|
author | Michelle W. Tong Aniket A. Tolpadi Rupsa Bhattacharjee Misung Han Sharmila Majumdar Valentina Pedoia |
author_facet | Michelle W. Tong Aniket A. Tolpadi Rupsa Bhattacharjee Misung Han Sharmila Majumdar Valentina Pedoia |
author_sort | Michelle W. Tong |
collection | DOAJ |
description | A 2D U-Net was trained to generate synthetic T<sub>1p</sub> maps from T<sub>2</sub> maps for knee MRI to explore the feasibility of domain adaptation for enriching existing datasets and enabling rapid, reliable image reconstruction. The network was developed using 509 healthy contralateral and injured ipsilateral knee images from patients with ACL injuries and reconstruction surgeries acquired across three institutions. Network generalizability was evaluated on 343 knees acquired in a clinical setting and 46 knees from simultaneous bilateral acquisition in a research setting. The deep neural network synthesized high-fidelity reconstructions of T<sub>1p</sub> maps, preserving textures and local T<sub>1p</sub> elevation patterns in cartilage with a normalized mean square error of 2.4% and Pearson’s correlation coefficient of 0.93. Analysis of reconstructed T<sub>1p</sub> maps within cartilage compartments revealed minimal bias (−0.10 ms), tight limits of agreement, and quantification error (5.7%) below the threshold for clinically significant change (6.42%) associated with osteoarthritis. In an out-of-distribution external test set, synthetic maps preserved T<sub>1p</sub> textures, but exhibited increased bias and wider limits of agreement. This study demonstrates the capability of image synthesis to reduce acquisition time, derive meaningful information from existing datasets, and suggest a pathway for standardizing T<sub>1p</sub> as a quantitative biomarker for osteoarthritis. |
first_indexed | 2024-03-08T11:05:51Z |
format | Article |
id | doaj.art-f5873ad560e04283b9f205a7de5f67e7 |
institution | Directory Open Access Journal |
issn | 2306-5354 |
language | English |
last_indexed | 2024-03-08T11:05:51Z |
publishDate | 2023-12-01 |
publisher | MDPI AG |
record_format | Article |
series | Bioengineering |
spelling | doaj.art-f5873ad560e04283b9f205a7de5f67e72024-01-26T15:06:07ZengMDPI AGBioengineering2306-53542023-12-011111710.3390/bioengineering11010017Synthetic Knee MRI T<sub>1p</sub> Maps as an Avenue for Clinical Translation of Quantitative Osteoarthritis BiomarkersMichelle W. Tong0Aniket A. Tolpadi1Rupsa Bhattacharjee2Misung Han3Sharmila Majumdar4Valentina Pedoia5Department of Radiology and Biomedical Imaging, University of California San Francisco, San Francisco, CA 94143, USADepartment of Radiology and Biomedical Imaging, University of California San Francisco, San Francisco, CA 94143, USADepartment of Radiology and Biomedical Imaging, University of California San Francisco, San Francisco, CA 94143, USADepartment of Radiology and Biomedical Imaging, University of California San Francisco, San Francisco, CA 94143, USADepartment of Radiology and Biomedical Imaging, University of California San Francisco, San Francisco, CA 94143, USADepartment of Radiology and Biomedical Imaging, University of California San Francisco, San Francisco, CA 94143, USAA 2D U-Net was trained to generate synthetic T<sub>1p</sub> maps from T<sub>2</sub> maps for knee MRI to explore the feasibility of domain adaptation for enriching existing datasets and enabling rapid, reliable image reconstruction. The network was developed using 509 healthy contralateral and injured ipsilateral knee images from patients with ACL injuries and reconstruction surgeries acquired across three institutions. Network generalizability was evaluated on 343 knees acquired in a clinical setting and 46 knees from simultaneous bilateral acquisition in a research setting. The deep neural network synthesized high-fidelity reconstructions of T<sub>1p</sub> maps, preserving textures and local T<sub>1p</sub> elevation patterns in cartilage with a normalized mean square error of 2.4% and Pearson’s correlation coefficient of 0.93. Analysis of reconstructed T<sub>1p</sub> maps within cartilage compartments revealed minimal bias (−0.10 ms), tight limits of agreement, and quantification error (5.7%) below the threshold for clinically significant change (6.42%) associated with osteoarthritis. In an out-of-distribution external test set, synthetic maps preserved T<sub>1p</sub> textures, but exhibited increased bias and wider limits of agreement. This study demonstrates the capability of image synthesis to reduce acquisition time, derive meaningful information from existing datasets, and suggest a pathway for standardizing T<sub>1p</sub> as a quantitative biomarker for osteoarthritis.https://www.mdpi.com/2306-5354/11/1/17T<sub>1p</sub> mapT<sub>2</sub> mapkneeMRIosteoarthritissynthesis |
spellingShingle | Michelle W. Tong Aniket A. Tolpadi Rupsa Bhattacharjee Misung Han Sharmila Majumdar Valentina Pedoia Synthetic Knee MRI T<sub>1p</sub> Maps as an Avenue for Clinical Translation of Quantitative Osteoarthritis Biomarkers Bioengineering T<sub>1p</sub> map T<sub>2</sub> map knee MRI osteoarthritis synthesis |
title | Synthetic Knee MRI T<sub>1p</sub> Maps as an Avenue for Clinical Translation of Quantitative Osteoarthritis Biomarkers |
title_full | Synthetic Knee MRI T<sub>1p</sub> Maps as an Avenue for Clinical Translation of Quantitative Osteoarthritis Biomarkers |
title_fullStr | Synthetic Knee MRI T<sub>1p</sub> Maps as an Avenue for Clinical Translation of Quantitative Osteoarthritis Biomarkers |
title_full_unstemmed | Synthetic Knee MRI T<sub>1p</sub> Maps as an Avenue for Clinical Translation of Quantitative Osteoarthritis Biomarkers |
title_short | Synthetic Knee MRI T<sub>1p</sub> Maps as an Avenue for Clinical Translation of Quantitative Osteoarthritis Biomarkers |
title_sort | synthetic knee mri t sub 1p sub maps as an avenue for clinical translation of quantitative osteoarthritis biomarkers |
topic | T<sub>1p</sub> map T<sub>2</sub> map knee MRI osteoarthritis synthesis |
url | https://www.mdpi.com/2306-5354/11/1/17 |
work_keys_str_mv | AT michellewtong synthetickneemritsub1psubmapsasanavenueforclinicaltranslationofquantitativeosteoarthritisbiomarkers AT aniketatolpadi synthetickneemritsub1psubmapsasanavenueforclinicaltranslationofquantitativeosteoarthritisbiomarkers AT rupsabhattacharjee synthetickneemritsub1psubmapsasanavenueforclinicaltranslationofquantitativeosteoarthritisbiomarkers AT misunghan synthetickneemritsub1psubmapsasanavenueforclinicaltranslationofquantitativeosteoarthritisbiomarkers AT sharmilamajumdar synthetickneemritsub1psubmapsasanavenueforclinicaltranslationofquantitativeosteoarthritisbiomarkers AT valentinapedoia synthetickneemritsub1psubmapsasanavenueforclinicaltranslationofquantitativeosteoarthritisbiomarkers |