{"doi":"10.1148/radiol.220522","title":"Quantitative Brain Morphometry of Portable Low-Field-Strength MRI Using Super-Resolution Machine Learning","abstract":"Background Portable, low-field-strength (0.064-T) MRI has the potential to transform neuroimaging but is limited by low spatial resolution and low signal-to-noise ratio. Purpose To implement a machine learning super-resolution algorithm that synthesizes higher spatial resolution images (1-mm isotropic) from lower resolution T1-weighted and T2-weighted portable brain MRI scans, making them amenable to automated quantitative morphometry. Materials and Methods An external high-field-strength MRI data set (1-mm isotropic scans from the Open Access Series of Imaging Studies data set) and segmentations for 39 regions of interest (ROIs) in the brain were used to train a super-resolution convolutional neural network (CNN). Secondary analysis of an internal test set of 24 paired low- and high-field-strength clinical MRI scans in participants with neurologic symptoms was performed. These were part of a prospective observational study (August 2020 to December 2021) at Massachusetts General Hospital (exclusion criteria: inability to lay flat, body habitus preventing low-field-strength MRI, presence of MRI contraindications). Three well-established automated segmentation tools were applied to three sets of scans: high-field-strength (1.5–3 T, reference standard), low-field-strength (0.064 T), and synthetic high-field-strength images generated from the low-field-strength data with the CNN. Statistical significance of correlations was assessed with Student t tests. Correlation coefficients were compared with Steiger Z tests. Results Eleven participants (mean age, 50 years ± 14; seven men) had full cerebrum coverage in the images without motion artifacts or large stroke lesion with distortion from mass effect. Direct segmentation of low-field-strength MRI yielded nonsignificant correlations with volumetric measurements from high field strength for most ROIs (P > .05). Correlations largely improved when segmenting the synthetic images: P values were less than .05 for all ROIs (eg, for the hippocampus [r = 0.85; P < .001], thalamus [r = 0.84; P = .001], and whole cerebrum [r = 0.92; P < .001]). Deviations from the model (z score maps) visually correlated with pathologic abnormalities. Conclusion This work demonstrated proof-of-principle augmentation of portable MRI with a machine learning super-resolution algorithm, which yielded highly correlated brain morphometric measurements to real higher resolution images. © RSNA, 2022 Online supplemental material is available for this article. See also the editorial by Ertl-Wagner amd Wagner in this issue. An earlier incorrect version appeared online. This article was corrected on February 1, 2023.","journal":"Radiology","year":2022,"id":234369,"datarank":0.6966586348712059,"base_score":4.6443908991413725,"endowment":4.6443908991413725,"self_citation_contribution":0.6966586348712059,"citation_network_contribution":0.0,"self_endowment_contribution":0.6966586348712059,"citer_contribution":0.0,"corpus_percentile":null,"corpus_rank":null,"citation_count":103,"citer_count":0,"citers_with_citation_signal":0,"citers_with_endowment":0,"datacite_reuse_total":0,"is_dataset":false,"is_dataset_confidence":0.9472,"is_data_producer":false,"deposit_databanks":null,"is_oa":true,"file_count":0,"downloads":0,"has_version_chain":false,"published_date":"2022-01-01","fair_score":null,"fair_percentile":null,"algorithm_id":"datarank_citation_only_1hop_v6","ranking_scope":"data_only","authors":[{"id":646279,"name":"Riana Schleicher","orcid":"0000-0002-3743-7922","position":1,"is_corresponding":false},{"id":849892,"name":"Sonia Laguna","orcid":"0000-0003-3504-2051","position":2,"is_corresponding":false},{"id":242308,"name":"Benjamin Billot","orcid":"0000-0002-3018-1282","position":3,"is_corresponding":false},{"id":307822,"name":"Pamela W. Schaefer","orcid":"0000-0002-4222-6134","position":4,"is_corresponding":false},{"id":89085,"name":"Brenna McKaig","orcid":"0009-0009-7185-762X","position":5,"is_corresponding":false},{"id":256551,"name":"Joshua N. Goldstein","orcid":"0000-0002-6406-1828","position":6,"is_corresponding":false},{"id":256547,"name":"Kevin N. Sheth","orcid":"0000-0003-2003-5473","position":7,"is_corresponding":false},{"id":241416,"name":"Matthew S. Rosen","orcid":"0000-0002-7194-002X","position":8,"is_corresponding":false},{"id":350022,"name":"W. Taylor Kimberly","orcid":"0000-0002-2519-8530","position":9,"is_corresponding":false},{"id":242311,"name":"Juan Eugenio Iglesias","orcid":"0000-0001-7569-173X","position":0,"is_corresponding":true}],"reference_count":23,"raw_metadata":{"citation_network_status":"fetched"},"created_at":"2026-07-19T00:21:36.529874Z","pmid":"36346311","pmcid":null,"fwci":null,"citation_percentile":null,"influential_citations":0,"oa_status":null,"license":null,"views":0,"total_file_size_bytes":0,"version_count":0,"fair_f":null,"fair_a":null,"fair_i":null,"fair_r":null,"fair_zscore":null,"fair_rationale":null,"fair_model":null,"fair_agent_version":null,"fair_fulltext_source":null,"fair_has_llm":null,"fair_computed_at":null,"clinical_trials":[],"software_tools":[],"db_accessions":[],"linked_datasets":[],"topics":[]}