{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,29]],"date-time":"2026-10-29T20:04:35Z","timestamp":1793304275327,"version":"4.5.0"},"reference-count":42,"publisher":"Frontiers Media SA","license":[{"start":{"date-parts":[[2026,7,17]],"date-time":"2026-07-17T00:00:00Z","timestamp":1784246400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":["frontiersin.org"],"crossmark-restriction":true},"short-container-title":["Front. Neurol."],"abstract":"<jats:sec>\n                    <jats:title>Background<\/jats:title>\n                    <jats:p>Accurate assessment of hippocampal volume is of significant clinical value for the early diagnosis and disease monitoring of Alzheimer\u2019s disease (AD). However, automatic segmentation of the hippocampus in MR images remains challenging due to its elongated and irregular morphology, blurred boundaries, low contrast with surrounding tissues, and substantial inter-individual anatomical variability.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Methods<\/jats:title>\n                    <jats:p>We propose an Edge-aware Salient Context Fusion Refinement Network (ESCFR-Net). Built upon a classic U-shaped encoder-decoder architecture, the proposed network employs a Salient Feature Enhancer to suppress background interference and enhance weak feature responses of the hippocampus. A Global Channel Context Attention (GCCA) module is introduced to model long-range spatial dependencies, while a Multi-scale Context Fusion Refinement Module (MCFRM) improves the utilization of multi-scale features. Furthermore, an Edge-Guided Refinement Attention (EGRA) module synergistically enhances edge and semantic features to precisely delineate weak boundaries.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Results<\/jats:title>\n                    <jats:p>\n                      Experimental results on a self-constructed dataset comprising 225 3D-T1 MRI scans demonstrate that ESCFR-Net achieves a Dice coefficient of 0.9004, outperforming state-of-the-art methods such as SwinUNETR and PMFS-Net. Clinical association analysis, conducted on 91 healthy controls (HCs) and 91 patients with mild cognitive impairment (MCI), reveals that bilateral hippocampal volumes in MCI group are significantly smaller than those in HCs (\n                      <jats:italic>p<\/jats:italic>\n                      \u202f&amp;lt;\u202f0.001). Additionally, the total hippocampal volume achieves an area under the curve (AUC) of 0.927 in distinguishing HCs from patients with MCI, with sensitivity and specificity reaching 90.11 and 83.52%, respectively.\n                    <\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Conclusion<\/jats:title>\n                    <jats:p>This study provides a highly accurate and robust automated hippocampal segmentation tool for early diagnosis, disease monitoring, and clinical decision-making in Alzheimer\u2019s disease.<\/jats:p>\n                  <\/jats:sec>","DOI":"10.3389\/fneur.2026.1899123","type":"journal-article","created":{"date-parts":[[2026,7,17]],"date-time":"2026-07-17T04:22:55Z","timestamp":1784262175000},"update-policy":"https:\/\/doi.org\/10.3389\/crossmark-policy","source":"Crossref","is-referenced-by-count":1,"title":["An edge-aware salient context fusion and refinement network for hippocampal segmentation in MR images and its diagnostic value for mild cognitive impairment"],"prefix":"10.3389","volume":"17","author":[{"given":"Limin","family":"Liu","sequence":"first","affiliation":[{"name":"Department of Ultrasound Medicine, The Second Affiliated Hospital, Hengyang Medical School, University of South China","place":["Hengyang, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xiaolong","family":"Chen","sequence":"additional","affiliation":[{"name":"Department of Radiology, The First Affiliated Hospital, Hengyang Medical School, University of South China","place":["Hengyang, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Qiqun","family":"Zeng","sequence":"additional","affiliation":[{"name":"Department of Radiology, The First Affiliated Hospital, Hengyang Medical School, University of South China","place":["Hengyang, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Shili","family":"Zhou","sequence":"additional","affiliation":[{"name":"Department of Ultrasound Medicine, The Second Affiliated Hospital, Hengyang Medical School, University of South China","place":["Hengyang, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xia","family":"Zhang","sequence":"additional","affiliation":[{"name":"Department of Ultrasound Medicine, The Second Affiliated Hospital, Hengyang Medical School, University of South China","place":["Hengyang, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1965","published-online":{"date-parts":[[2026,7,17]]},"reference":[{"key":"ref1","doi-asserted-by":"publisher","first-page":"726","DOI":"10.1016\/S1474-4422(22)00168-5","article-title":"Tau biomarkers in Alzheimer\u2019s disease: towards implementation in clinical practice and trials","volume":"21","author":"Ossenkoppele","year":"2022","journal-title":"Lancet Neurol"},{"key":"ref2","doi-asserted-by":"publisher","first-page":"907","DOI":"10.3233\/JAD-231114","article-title":"The hippocampal subfield volume reduction and plasma biomarker changes in mild cognitive impairment and Alzheimer's disease","volume":"98","author":"Cao","year":"2024","journal-title":"J Alzheimer's Dis"},{"key":"ref3","doi-asserted-by":"publisher","first-page":"270","DOI":"10.1016\/j.jalz.2011.03.008","article-title":"The diagnosis of mild cognitive impairment due to Alzheimer\u2019s disease: recommendations from the National Institute on Aging-Alzheimer\u2019s association workgroups on diagnostic guidelines for Alzheimer\u2019s disease","volume":"7","author":"Albert","year":"2011","journal-title":"Alzheimers Dement"},{"key":"ref4","doi-asserted-by":"publisher","first-page":"5143","DOI":"10.1002\/alz.13859","article-title":"Revised criteria for diagnosis and staging of Alzheimer's disease: Alzheimer's Association workgroup","volume":"20","author":"Jack","year":"2024","journal-title":"Alzheimers Dement"},{"key":"ref5","doi-asserted-by":"publisher","first-page":"1111","DOI":"10.1177\/13872877241296130","article-title":"Identification and cognitive function prediction of Alzheimer\u2019s disease based on multivariate pattern analysis of hippocampal volumes","volume":"102","author":"Gao","year":"2024","journal-title":"J Alzheimer\u2019s Dis: JAD"},{"key":"ref6","doi-asserted-by":"publisher","first-page":"7878","DOI":"10.1038\/s41598-026-38220-4","article-title":"Evaluation of deep learning models for segmentation of hippocampus volumes from MRI images in Alzheimer\u2019s disease","volume":"16","author":"Pusparani","year":"2026","journal-title":"Sci Rep"},{"key":"ref7","doi-asserted-by":"publisher","first-page":"106953","DOI":"10.1016\/j.compbiomed.2023.106953","article-title":"RBS-net: Hippocampus segmentation using multi-layer feature learning with the region, boundary and structure loss","volume":"160","author":"Chen","year":"2023","journal-title":"Comput Biol Med"},{"key":"ref8","doi-asserted-by":"publisher","first-page":"126","DOI":"10.1016\/j.jalz.2014.02.009","article-title":"Delphi definition of the EADC-ADNI harmonized protocol for hippocampal segmentation on magnetic resonance","volume":"11","author":"Boccardi","year":"2015","journal-title":"Alzheimers Dement"},{"key":"ref9","doi-asserted-by":"publisher","first-page":"e70200","DOI":"10.1002\/hbm.70200","article-title":"Evaluating traditional, deep learning and subfield methods for automatically segmenting the Hippocampus from MRI","volume":"46","author":"Sghirripa","year":"2025","journal-title":"Hum Brain Mapp"},{"key":"ref10","doi-asserted-by":"publisher","first-page":"3523","DOI":"10.1109\/TPAMI.2021.3059968","article-title":"Image segmentation using deep learning: a survey","volume":"44","author":"Minaee","year":"2022","journal-title":"IEEE Trans Pattern Anal Mach Intell"},{"key":"ref11","doi-asserted-by":"publisher","first-page":"102444","DOI":"10.1016\/j.media.2022.102444","article-title":"Recent advances and clinical applications of deep learning in medical image analysis","volume":"79","author":"Chen","year":"2022","journal-title":"Med Image Anal"},{"key":"ref12","doi-asserted-by":"publisher","first-page":"255","DOI":"10.1007\/s00330-024-10907-0","article-title":"Deep learning in pulmonary nodule detection and segmentation: a systematic review","volume":"35","author":"Gao","year":"2025","journal-title":"Eur Radiol"},{"key":"ref13","first-page":"1082","volume-title":"2011 IEEE International Symposium on Biomedical Imaging: From Nano To Macro","author":"Gray","year":"2021"},{"key":"ref14","first-page":"3431","author":"Long","year":"2015"},{"key":"ref15","doi-asserted-by":"crossref","DOI":"10.1007\/978-3-319-24574-4_28","article-title":"U-net: convolutional networks for biomedical image segmentation, MICCAI","author":"Ronneberger","year":"2015"},{"key":"ref16","first-page":"192","author":"Chen","year":"2017"},{"key":"ref17","doi-asserted-by":"publisher","first-page":"893","DOI":"10.1007\/s10278-022-00613-y","article-title":"Hippocampus segmentation using U-net convolutional network from brain magnetic resonance imaging (MRI)","volume":"35","author":"Hazarika","year":"2022","journal-title":"J Digit Imaging"},{"key":"ref18","doi-asserted-by":"publisher","first-page":"68","DOI":"10.26599\/tst.2020.9010056","article-title":"Combining residual attention mechanisms and generative adversarial networks for hippocampus segmentation","volume":"27","author":"Deng","year":"2022","journal-title":"Tsinghua Sci Technol"},{"key":"ref19","doi-asserted-by":"publisher","first-page":"120608","DOI":"10.1016\/j.neuroimage.2024.120608","article-title":"Light3DHS: a lightweight 3D hippocampus segmentation method using multiscale convolution attention and vision transformer","volume":"292","author":"Xiao","year":"2024","journal-title":"NeuroImage"},{"key":"ref20","doi-asserted-by":"publisher","first-page":"108611","DOI":"10.1016\/j.cmpb.2025.108611","article-title":"PMFSNet: polarized multi-scale feature self-attention network for lightweight medical image segmentation","volume":"261","author":"Zhong","year":"2025","journal-title":"Comput Methods Prog Biomed"},{"key":"ref21","doi-asserted-by":"publisher","first-page":"98","DOI":"10.1007\/s44443-025-00109-z","article-title":"MWFNet: a multi-level wavelet fusion network for hippocampal subfield segmentation","volume":"37","author":"Li","year":"2025","journal-title":"J King Saud Univ Comput Inf Sci"},{"key":"ref22","doi-asserted-by":"publisher","first-page":"5155","DOI":"10.3390\/s25165155","article-title":"FED-UNet++: an improved nested UNet for Hippocampus segmentation in Alzheimer\u2019s disease diagnosis","volume":"25","author":"Yang","year":"2025","journal-title":"Sensors"},{"key":"ref23","doi-asserted-by":"publisher","first-page":"101274","DOI":"10.1016\/j.jrras.2024.101274","article-title":"A comparative study of automatic hippocampal segmentation in whole-brain radiotherapy applying DPNU-net, mask-RCNN, and nnU-net models","volume":"18","author":"Liu","year":"2025","journal-title":"J Radiat Res Appl Sci"},{"key":"ref24","doi-asserted-by":"crossref","first-page":"205","DOI":"10.1007\/978-3-031-25066-8_9","volume-title":"Computer Vision \u2013 ECCV 2022 Workshops","author":"Cao","year":"2023"},{"key":"ref25","first-page":"1748","author":"Hatamizadeh","year":"2022"},{"key":"ref26","article-title":"TransUNet: transformers make strong encoders for medical image segmentation","author":"Chen","year":"2021"},{"key":"ref27","doi-asserted-by":"crossref","first-page":"109","DOI":"10.1007\/978-3-030-87193-2_11","volume-title":"Medical Image Computing and Computer Assisted Intervention \u2013 MICCAI 2021","author":"Wang","year":"2021"},{"key":"ref28","doi-asserted-by":"crossref","first-page":"171","DOI":"10.1007\/978-3-030-87199-4_16","volume-title":"Medical Image Computing and Computer Assisted Intervention \u2013 MICCAI 2021","author":"Xie","year":"2021"},{"key":"ref29","doi-asserted-by":"crossref","first-page":"235","DOI":"10.1007\/978-3-031-16443-9_23","volume-title":"Medical Image Computing and Computer Assisted Intervention \u2013 MICCAI 2022","author":"Liu","year":"2022"},{"key":"ref30","doi-asserted-by":"publisher","first-page":"15317","DOI":"10.1038\/s41598-024-66415-0","article-title":"DSnet: a new dual-branch network for hippocampus subfield segmentation","volume":"14","author":"Zhu","year":"2024","journal-title":"Sci Rep"},{"key":"ref31","doi-asserted-by":"publisher","first-page":"311","DOI":"10.3390\/jimaging11090311","article-title":"Cascaded spatial and depth attention UNet for Hippocampus segmentation","volume":"11","author":"Wei","year":"2025","journal-title":"J Imaging"},{"key":"ref32","doi-asserted-by":"publisher","first-page":"207","DOI":"10.1002\/hbm.25326","article-title":"FreeSurfer-based segmentation of hippocampal subfields: a review of methods and applications, with a novel quality control procedure for ENIGMA studies and other collaborative efforts","volume":"43","author":"S\u00e4mann","year":"2022","journal-title":"Hum Brain Mapp"},{"key":"ref33","doi-asserted-by":"publisher","first-page":"4785","DOI":"10.1016\/j.acra.2025.04.038","article-title":"Artificial intelligence-assisted hippocampal segmentation and its diagnostic value for Alzheimer\u2019s disease: a Meta-analysis","volume":"32","author":"Wu","year":"2025","journal-title":"Acad Radiol"},{"key":"ref34","doi-asserted-by":"publisher","first-page":"3716","DOI":"10.1007\/s00330-017-4768-1","article-title":"The effect of hippocampal function, volume and connectivity on posterior cingulate cortex functioning during episodic memory fMRI in mild cognitive impairment","volume":"27","author":"Papma","year":"2017","journal-title":"Eur Radiol"},{"key":"ref35","doi-asserted-by":"publisher","first-page":"e663","DOI":"10.1097\/MAO.0000000000003540","article-title":"Changes in measures of vestibular and balance function and Hippocampus volume in Alzheimer\u2019s disease and mild cognitive impairment","volume":"43","author":"Cohen","year":"2022","journal-title":"Otol Neurotol"},{"key":"ref36","doi-asserted-by":"publisher","first-page":"1381","DOI":"10.1007\/s13760-023-02235-9","article-title":"Volume changes of hippocampal and amygdala subfields in patients with mild cognitive impairment and Alzheimer\u2019s disease","volume":"123","author":"Qu","year":"2023","journal-title":"Acta Neurol Belg"},{"key":"ref37","doi-asserted-by":"publisher","first-page":"125","DOI":"10.1080\/0361073X.2024.2313940","article-title":"Hippocampal subregions volume and texture for the diagnosis of mild cognitive impairment","volume":"51","author":"Chu","year":"2025","journal-title":"Exp Aging Res"},{"key":"ref38","doi-asserted-by":"publisher","first-page":"1106","DOI":"10.1126\/science.abl5163","article-title":"Impact of neurodegenerative diseases on human adult hippocampal neurogenesis","volume":"374","author":"Terreros-Roncal","year":"2021","journal-title":"Science"},{"key":"ref39","doi-asserted-by":"publisher","first-page":"173673","DOI":"10.1016\/j.scitotenv.2024.173673","article-title":"Neurodegenerative pathways and metabolic changes in the hippocampus and cortex of mice exposed to urban particulate matter: insights from an integrated interactome analysis","volume":"945","author":"Kim","year":"2024","journal-title":"Sci Total Environ"},{"key":"ref40","doi-asserted-by":"publisher","first-page":"1347682","DOI":"10.3389\/fneur.2024.1347682","article-title":"Associations between renal function, hippocampal volume, and cognitive impairment in 544 outpatients","volume":"15","author":"Wu","year":"2024","journal-title":"Front Neurol"},{"key":"ref41","doi-asserted-by":"publisher","first-page":"191","DOI":"10.1177\/13872877251314785","article-title":"Association of hippocampal atrophy with tau pathology of temporal regions in preclinical Alzheimer\u2019s disease","volume":"104","author":"Pan","year":"2025","journal-title":"J Alzheimer\u2019s Dis: JAD"},{"key":"ref42","doi-asserted-by":"publisher","first-page":"380","DOI":"10.21037\/qims-2025-1-2553","article-title":"Multimodal magnetic resonance imaging (MRI) quantification of hippocampal injury in acute carbon monoxide poisoning: reduced hippocampal volume as a sensitive biomarker linked to cognitive impairment and prognosis","volume":"16","author":"Li","year":"2026","journal-title":"Quant Imaging Med Surg"}],"container-title":["Frontiers in Neurology"],"original-title":[],"link":[{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fneur.2026.1899123\/full","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,7,17]],"date-time":"2026-07-17T04:22:57Z","timestamp":1784262177000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fneur.2026.1899123\/full"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,7,17]]},"references-count":42,"alternative-id":["10.3389\/fneur.2026.1899123"],"URL":"https:\/\/doi.org\/10.3389\/fneur.2026.1899123","relation":{},"ISSN":["1664-2295"],"issn-type":[{"value":"1664-2295","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,7,17]]},"article-number":"1899123"}}