{"doi":"10.3389/fncom.2024.1487877","title":"Multi-stage semi-supervised learning enhances white matter hyperintensity segmentation","abstract":"Introduction White matter hyperintensities (WMHs) are frequently observed on magnetic resonance (MR) images in older adults, commonly appearing as areas of high signal intensity on fluid-attenuated inversion recovery (FLAIR) MR scans. Elevated WMH volumes are associated with a greater risk of dementia and stroke, even after accounting for vascular risk factors. Manual segmentation, while considered the ground truth, is both labor-intensive and time-consuming, limiting the generation of annotated WMH datasets. Un-annotated data are relatively available; however, the requirement of annotated data poses a challenge for developing supervised machine learning models. Methods To address this challenge, we implemented a multi-stage semi-supervised learning (M3SL) approach that first uses un-annotated data segmented by traditional processing methods (“bronze” and “silver” quality data) and then uses a smaller number of “gold”-standard annotations for model refinement. The M3SL approach enabled fine-tuning of the model weights with the gold-standard annotations. This approach was integrated into the training of a U-Net model for WMH segmentation. We used data from three scanner vendors (over more than five scanners) and from both cognitively normal (CN) adult and patients cohorts [with mild cognitive impairment and Alzheimer's disease (AD)]. Results An analysis of WMH segmentation performance across both scanner and clinical stage (CN, MCI, AD) factors was conducted. We compared our results to both conventional and transfer-learning deep learning methods and observed better generalization with M3SL across different datasets. We evaluated several metrics ( F -measure, IoU , and Hausdorff distance) and found significant improvements with our method compared to conventional ( p < 0.001) and transfer-learning ( p < 0.001). Discussion These findings suggest that automated, non-machine learning, tools have a role in a multi-stage learning framework and can reduce the impact of limited annotated data and, thus, enhance model performance.","journal":"Frontiers in Computational Neuroscience","year":2024,"id":477798,"datarank":0.0,"base_score":0.0,"endowment":0.0,"self_citation_contribution":0.0,"citation_network_contribution":0.0,"self_endowment_contribution":0.0,"citer_contribution":0.0,"corpus_percentile":null,"corpus_rank":null,"citation_count":2,"citer_count":0,"citers_with_citation_signal":0,"citers_with_endowment":0,"datacite_reuse_total":0,"is_dataset":false,"is_dataset_confidence":0.9542,"is_data_producer":false,"deposit_databanks":null,"is_oa":true,"file_count":0,"downloads":0,"has_version_chain":false,"published_date":"2024-01-01","fair_score":null,"fair_percentile":null,"algorithm_id":"datarank_citation_only_1hop_v6","ranking_scope":"data_only","authors":[{"id":1316404,"name":"Abhijot S. Sidhu","orcid":null,"position":1,"is_corresponding":false},{"id":1316011,"name":"Murilo Costa de Barros","orcid":"0000-0003-2452-8128","position":2,"is_corresponding":false},{"id":475401,"name":"David G. Gobbi","orcid":"0000-0002-3459-9563","position":3,"is_corresponding":false},{"id":858937,"name":"Cheryl R. McCreary","orcid":"0000-0003-1572-010X","position":4,"is_corresponding":false},{"id":1316012,"name":"Feryal Saad","orcid":"0000-0001-8038-8495","position":5,"is_corresponding":false},{"id":264346,"name":"Richard Camicioli","orcid":"0000-0003-2977-8660","position":6,"is_corresponding":false},{"id":268016,"name":"Eric E. Smith","orcid":"0000-0003-3956-1668","position":7,"is_corresponding":false},{"id":1075036,"name":"Mariana Bento","orcid":"0000-0001-5125-0294","position":8,"is_corresponding":false},{"id":605515,"name":"Richard Frayne","orcid":"0000-0003-0358-1210","position":9,"is_corresponding":false},{"id":1316010,"name":"Kauê Tartarotti Nepomuceno Duarte","orcid":"0000-0002-4074-3672","position":0,"is_corresponding":true}],"reference_count":42,"raw_metadata":null,"created_at":"2026-07-19T02:06:37.812633Z","pmid":"39502452","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":[]}