Quality assessment of brain MRI scans using a dense neural network model and image metrics. Gupta, A., Sadri, A., Viswanath, S., & Tiwari, P. In Progress in Biomedical Optics and Imaging - Proceedings of SPIE, volume 11312, 2020.
doi  abstract   bibtex   
Structural MRI is the standard-of-care imaging modality for screening and diagnosis of most neurological conditions. However, the ability to reliably evaluate brain MRIs for disease characterization (whether by machines or experts) is often hampered by the presence of artifacts such as magnetic field inhomogeneity, aliasing, or patient motion; some of which may not be visually apparent. Reliable quality assessment of brain MRI scans would allow for excluding noisy acquisitions and reducing errors in subsequent downstream analyses. Since visual inspection is impractical for large volumes of data and subject to inter-observer variability, there is a need for accurate, automated Quality Assessment (QA) of MR images. Previous studies have investigated image quality metrics (IQMs) in order to quantify the effect of specific artifacts and quality degradation in an MR image. There has also been some recent work in developing machine learning models which use IQMs to enable robust QA across multiple sites. We build on this approach by leveraging a total of 64 IQMs (quantifying noise, artifacts, information, and general brain measurements) within a Dense Neural Network (DNN) model for QA of brain MRI scans using the publicly available multi-site ABIDE-I cohort (17 sites, 1102 subjects). In attempting to predict the “mean opinion score” of MR image quality (as assessed by expert radiologists), the DNN model yielded an accuracy of 87.3±2.1% in training (15 sites, 885 subjects) which generalized to a 79.5±1.9% accuracy in validation (2 sites, 246 subjects). This initial DNN model suggests the promise of deep learning to improve automated QA of MRI scans in large multi-site, multi-scanner cohorts.
@inproceedings{
 title = {Quality assessment of brain MRI scans using a dense neural network model and image metrics},
 type = {inproceedings},
 year = {2020},
 keywords = {ABIDE,Deep learning,MRI,Quality assessment,Quality control},
 volume = {11312},
 id = {c5f9af55-31e6-3a15-91f6-1c1161cf418f},
 created = {2023-10-25T08:56:38.653Z},
 file_attached = {false},
 profile_id = {eaba325f-653b-3ee2-b960-0abd5146933e},
 last_modified = {2023-10-25T08:56:38.653Z},
 read = {false},
 starred = {false},
 authored = {true},
 confirmed = {false},
 hidden = {false},
 private_publication = {true},
 abstract = {Structural MRI is the standard-of-care imaging modality for screening and diagnosis of most neurological conditions. However, the ability to reliably evaluate brain MRIs for disease characterization (whether by machines or experts) is often hampered by the presence of artifacts such as magnetic field inhomogeneity, aliasing, or patient motion; some of which may not be visually apparent. Reliable quality assessment of brain MRI scans would allow for excluding noisy acquisitions and reducing errors in subsequent downstream analyses. Since visual inspection is impractical for large volumes of data and subject to inter-observer variability, there is a need for accurate, automated Quality Assessment (QA) of MR images. Previous studies have investigated image quality metrics (IQMs) in order to quantify the effect of specific artifacts and quality degradation in an MR image. There has also been some recent work in developing machine learning models which use IQMs to enable robust QA across multiple sites. We build on this approach by leveraging a total of 64 IQMs (quantifying noise, artifacts, information, and general brain measurements) within a Dense Neural Network (DNN) model for QA of brain MRI scans using the publicly available multi-site ABIDE-I cohort (17 sites, 1102 subjects). In attempting to predict the “mean opinion score” of MR image quality (as assessed by expert radiologists), the DNN model yielded an accuracy of 87.3±2.1% in training (15 sites, 885 subjects) which generalized to a 79.5±1.9% accuracy in validation (2 sites, 246 subjects). This initial DNN model suggests the promise of deep learning to improve automated QA of MRI scans in large multi-site, multi-scanner cohorts.},
 bibtype = {inproceedings},
 author = {Gupta, A. and Sadri, A.R. and Viswanath, S.E. and Tiwari, P.},
 doi = {10.1117/12.2551348},
 booktitle = {Progress in Biomedical Optics and Imaging - Proceedings of SPIE}
}

Downloads: 0