{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,19]],"date-time":"2026-06-19T20:44:55Z","timestamp":1781901895586,"version":"3.54.5"},"reference-count":37,"publisher":"Frontiers Media SA","license":[{"start":{"date-parts":[[2023,5,15]],"date-time":"2023-05-15T00:00:00Z","timestamp":1684108800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"DOI":"10.13039\/501100004829","name":"Department of Science and Technology of Sichuan Province","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100004829","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["frontiersin.org"],"crossmark-restriction":true},"short-container-title":["Front. Neurosci."],"abstract":"<jats:sec><jats:title>Background<\/jats:title><jats:p>Hippocampal sclerosis (HS) is the most common pathological type of temporal lobe epilepsy (TLE) and one of the important surgical markers. Currently, HS is mainly diagnosed manually by radiologists based on visual inspection of MRI, which greatly relies on MRI quality and physician experience. In clinical practice, non-thin MRI scans are often used due to the time and efficiency needed for the acquisition. However, these scans can be difficult for junior physicians to interpret accurately. Thus, the rapid and accurate diagnosis of HS using real-world MRI images in clinical settings is a challenging task.<\/jats:p><\/jats:sec><jats:sec><jats:title>Objective<\/jats:title><jats:p>Our aim was to explore the feasibility of using computer vision methods to diagnose HS on real-world clinical MRI images and to provide a reference for future clinical applications of artificial intelligence methods to aid in detecting HS.<\/jats:p><\/jats:sec><jats:sec><jats:title>Methods<\/jats:title><jats:p>We proposed a deep learning algorithm called \u201cHS-Net\u201d to discriminate HS using real-world clinical MRI images. First, we delineated and segmented a region of interest (ROI) around the hippocampus. Then, we utilized the fractional differential (FD) method to enhance the textures of the ROIs. Finally, we used a small-sample image classification method based on transfer learning to fine-tune the feature extraction part of a pretrained model and added two fully connected layers and an output layer. In the study, 96 TLE patients with HS confirmed by postoperative pathology and 89 healthy controls were retrospectively enrolled. All subjects were cross-validated, and models were evaluated for performance, robustness, and clinical utility.<\/jats:p><\/jats:sec><jats:sec><jats:title>Results<\/jats:title><jats:p>The HS-Net model achieved an area under the curve (AUC) of 0.894, an accuracy of 82.88%, an F1-score of 84.08% in the test cohort based on real, routine, clinical T2-weighted fluid attenuated inversion recovery (FLAIR) sequence MRI images. Additionally, the AUC, accuracy and F1 scores of our model all increased by around 3 percentage points when the inputs were augmented with the ROIs of the textures enhanced using the FD method.<\/jats:p><\/jats:sec><jats:sec><jats:title>Conclusions<\/jats:title><jats:p>Our computational model has the potential to be used for the diagnosis of HS in real clinical MRI images, which could assist physicians, particularly junior physicians, in improving the accuracy of discrimination.<\/jats:p><\/jats:sec>","DOI":"10.3389\/fnins.2023.1180679","type":"journal-article","created":{"date-parts":[[2023,5,15]],"date-time":"2023-05-15T13:36:03Z","timestamp":1684157763000},"update-policy":"https:\/\/doi.org\/10.3389\/crossmark-policy","source":"Crossref","is-referenced-by-count":6,"title":["Automated detection of hippocampal sclerosis using real-world clinical MRI images"],"prefix":"10.3389","volume":"17","author":[{"given":"Jingwen","family":"Jiang","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jiajun","family":"Qiu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jin","family":"Yin","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Junren","family":"Wang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xinyue","family":"Jiang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zuo","family":"Yi","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yang","family":"Chen","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xiaobo","family":"Zhou","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xiutian","family":"Sima","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1965","published-online":{"date-parts":[[2023,5,15]]},"reference":[{"key":"B1","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2301.01241","article-title":"Developing and deploying deep learning models in brain mri: a review","author":"Aggarwal","year":"2023","journal-title":"arXiv preprint arXiv:2301.01241"},{"key":"B2","doi-asserted-by":"publisher","first-page":"1400","DOI":"10.3174\/ajnr.A4313","article-title":"Mesial temporal sclerosis: accuracy of neuroquant versus neuroradiologist","volume":"36","author":"Azab","year":"2015","journal-title":"Am. J. Neuroradiol."},{"key":"B3","doi-asserted-by":"publisher","first-page":"185","DOI":"10.1159\/000503831","article-title":"The epidemiology of epilepsy","volume":"54","author":"Beghi","year":"2020","journal-title":"Neuroepidemiology"},{"key":"B4","doi-asserted-by":"publisher","first-page":"2785","DOI":"10.1093\/brain\/awp187","article-title":"Frequency, prognosis and surgical treatment of structural abnormalities seen with magnetic resonance imaging in childhood epilepsy","volume":"132","author":"Berg","year":"2009","journal-title":"Brain"},{"key":"B5","doi-asserted-by":"publisher","first-page":"348","DOI":"10.1111\/epi.13319","article-title":"International recommendation for a comprehensive neuropathologic workup of epilepsy surgery brain tissue: a consensus task force report from the ilae commission on diagnostic methods","volume":"57","author":"Bl\u00fcmcke","year":"2016","journal-title":"Epilepsia"},{"key":"B6","doi-asserted-by":"publisher","first-page":"1648","DOI":"10.1056\/NEJMoa1703784","article-title":"Histopathological findings in brain tissue obtained during epilepsy surgery","volume":"377","author":"Blumcke","year":"2017","journal-title":"N. Engl. J. Med."},{"key":"B7","doi-asserted-by":"crossref","first-page":"258","DOI":"10.1007\/978-3-030-87589-3_27","article-title":"\u201cDiagnosis of hippocampal sclerosis from clinical routine head MR images using structure-constrained super-resolution network,\u201d","volume-title":"International Workshop on Machine Learning in Medical Imaging","author":"Cao","year":"2021"},{"key":"B8","doi-asserted-by":"publisher","first-page":"77","DOI":"10.3174\/ajnr.A3640","article-title":"3t MRI quantification of hippocampal volume and signal in mesial temporal lobe epilepsy improves detection of hippocampal sclerosis","volume":"35","author":"Coan","year":"2014","journal-title":"Am. J. Neuroradiol."},{"key":"B9","doi-asserted-by":"publisher","first-page":"2003","DOI":"10.1111\/epi.12828","article-title":"7 t MRI features in control human hippocampus and hippocampal sclerosis: an ex vivo study with histologic correlations","volume":"55","author":"Coras","year":"2014","journal-title":"Epilepsia"},{"key":"B10","doi-asserted-by":"publisher","DOI":"10.1155\/2014\/238459","article-title":"A review of definitions for fractional derivatives and integral","author":"De Oliveira","year":"2014","journal-title":"Math. Probl. Eng."},{"key":"B11","doi-asserted-by":"crossref","first-page":"248","DOI":"10.1109\/CVPR.2009.5206848","article-title":"\u201cImageNet: a large-scale hierarchical image database,\u201d","volume-title":"2009 IEEE Conference on Computer Vision and Pattern Recognition","author":"Deng","year":"2009"},{"key":"B12","doi-asserted-by":"publisher","first-page":"420","DOI":"10.1016\/S1474-4422(15)00383-X","article-title":"Brain imaging in the assessment for epilepsy surgery","volume":"15","author":"Duncan","year":"2016","journal-title":"Lancet Neurol."},{"key":"B13","doi-asserted-by":"publisher","first-page":"1639","DOI":"10.1056\/NEJMoa1615335","article-title":"Surgery for drug-resistant epilepsy in children","volume":"377","author":"Dwivedi","year":"2017","journal-title":"N. Engl. J. Med."},{"key":"B14","doi-asserted-by":"publisher","first-page":"922","DOI":"10.1001\/jama.2012.220","article-title":"Early surgical therapy for drug-resistant temporal lobe epilepsy: a randomized trial","volume":"307","author":"Engel","year":"2012","journal-title":"JAMA"},{"key":"B15","doi-asserted-by":"publisher","first-page":"459","DOI":"10.1016\/S1474-4422(18)30499-X","article-title":"Global, regional, and national burden of neurological disorders, 1990\u20132016: a systematic analysis for the global burden of disease study 2016","volume":"18","author":"Feigin","year":"2019","journal-title":"Lancet Neurol."},{"key":"B16","doi-asserted-by":"publisher","first-page":"296","DOI":"10.1212\/WNL.0000000000003509","article-title":"Prevalence and incidence of epilepsy: a systematic review and meta-analysis of international studies","volume":"88","author":"Fiest","year":"2017","journal-title":"Neurology"},{"key":"B17","doi-asserted-by":"publisher","first-page":"1103","DOI":"10.1002\/hbm.23090","article-title":"In vivo MRI signatures of hippocampal subfield pathology in intractable epilepsy","volume":"37","author":"Goubran","year":"2016","journal-title":"Hum. Brain Mapp."},{"key":"B18","doi-asserted-by":"publisher","first-page":"50","DOI":"10.1177\/1971400917731301","article-title":"Diagnosis of mesial temporal sclerosis: sensitivity, specificity and predictive values of the quantitative analysis of magnetic resonance imaging","volume":"31","author":"Granados Sanchez","year":"2018","journal-title":"Neuroradiol. J."},{"key":"B19","doi-asserted-by":"publisher","first-page":"920","DOI":"10.1212\/WNL.0b013e3182a35193","article-title":"MRI-identified pathology in adults with new-onset seizures","volume":"81","author":"Hakami","year":"2013","journal-title":"Neurology"},{"key":"B20","first-page":"770","article-title":"\u201cDeep residual learning for image recognition,\u201d","volume-title":"Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition","author":"He","year":"2016"},{"key":"B21","doi-asserted-by":"publisher","DOI":"10.1155\/2020\/2761627","article-title":"Identification of pancreaticoduodenectomy resection for pancreatic head adenocarcinoma: a preliminary study of radiomics","author":"Hui","year":"2020","journal-title":"Comput. Math Methods Med."},{"key":"B22","doi-asserted-by":"publisher","DOI":"10.1155\/2013\/618536","article-title":"Texture enhancement for medical images based on fractional differential masks","author":"Jalab","year":"2013","journal-title":"Discrete Dyn. Nat. Soc."},{"key":"B23","doi-asserted-by":"publisher","first-page":"324","DOI":"10.1016\/j.compeleceng.2015.02.013","article-title":"Adaptive fractional differential approach and its application to medical image enhancement","volume":"45","author":"Li","year":"2015","journal-title":"Comput. Electr. Eng."},{"key":"B24","doi-asserted-by":"publisher","first-page":"440","DOI":"10.3174\/ajnr.A5966","article-title":"Improved detection of subtle mesial temporal sclerosis: validation of a commercially available software for automated segmentation of hippocampal volume","volume":"40","author":"Mettenburg","year":"2019","journal-title":"Am. J. Neuroradiol."},{"key":"B25","doi-asserted-by":"publisher","first-page":"2519","DOI":"10.1111\/epi.16392","article-title":"Automated detection of hippocampal sclerosis using clinically empirical and radiomics features","volume":"60","author":"Mo","year":"2019","journal-title":"Epilepsia"},{"key":"B26","doi-asserted-by":"publisher","first-page":"220","DOI":"10.1111\/j.1528-1167.2006.00916.x","article-title":"Voxel-based t2 relaxation rate measurements in temporal lobe epilepsy (tle) with and without mesial temporal sclerosis","volume":"48","author":"Mueller","year":"2007","journal-title":"Epilepsia"},{"key":"B27","doi-asserted-by":"publisher","first-page":"1669","DOI":"10.1111\/epi.13492","article-title":"Cost-effectiveness analysis of epilepsy surgery in a controlled cohort of adult patients with intractable partial epilepsy: a 5-year follow-up study","volume":"57","author":"Picot","year":"2016","journal-title":"Epilepsia"},{"key":"B28","doi-asserted-by":"publisher","first-page":"1114","DOI":"10.1016\/S1474-4422(14)70156-5","article-title":"Epilepsy surgery in children and adults","volume":"13","author":"Ryvlin","year":"2014","journal-title":"Lancet Neurol."},{"key":"B29","first-page":"4510","article-title":"\u201cMobileNetV2: inverted residuals and linear bottlenecks,\u201d","volume-title":"Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition","author":"Sandler","year":"2018"},{"key":"B30","first-page":"618","article-title":"\u201cGrad-CAM: visual explanations from deep networks via gradient-based localization,\u201d","volume-title":"Proceedings of the IEEE International Conference on Computer Vision","author":"Selvaraju","year":"2017"},{"key":"B31","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1186\/s40537-019-0197-0","article-title":"A survey on image data augmentation for deep learning","volume":"6","author":"Shorten","year":"2019","journal-title":"J. Big Data"},{"key":"B32","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1409.1556","article-title":"Very deep convolutional networks for large-scale image recognition","author":"Simonyan","year":"2014","journal-title":"arXiv preprint arXiv:1409.1556"},{"key":"B33","doi-asserted-by":"publisher","first-page":"689","DOI":"10.1016\/S0140-6736(18)32596-0","article-title":"Epilepsy in adults","volume":"393","author":"Thijs","year":"2019","journal-title":"Lancet"},{"key":"B34","doi-asserted-by":"publisher","first-page":"437","DOI":"10.15585\/mmwr.mm6715a1","article-title":"Active epilepsy and seizure control in adults\u2013United States, 2013 and 2015","volume":"67","author":"Tian","year":"2018","journal-title":"Morb. Mort. Wkly Rep."},{"key":"B35","doi-asserted-by":"publisher","first-page":"7","DOI":"10.1111\/epi.14458","article-title":"Epilepsy in Asia: disease burden, management barriers, and challenges","volume":"60","author":"Trinka","year":"2019","journal-title":"Epilepsia"},{"key":"B36","doi-asserted-by":"publisher","first-page":"917","DOI":"10.1166\/jmihi.2019.2682","article-title":"CT and MRI image diagnosis of cystic renal cell carcinoma based on a fractional-order differential texture enhancement algorithm","volume":"9","author":"Wang","year":"2019","journal-title":"J. Med. Imaging Health Inform."},{"key":"B37","doi-asserted-by":"publisher","first-page":"311","DOI":"10.1056\/NEJM200108023450501","article-title":"A randomized, controlled trial of surgery for temporal-lobe epilepsy","volume":"345","author":"Wiebe","year":"2001","journal-title":"N. Engl. J. Med."}],"container-title":["Frontiers in Neuroscience"],"original-title":[],"link":[{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fnins.2023.1180679\/full","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,5,15]],"date-time":"2023-05-15T13:36:16Z","timestamp":1684157776000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fnins.2023.1180679\/full"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,5,15]]},"references-count":37,"alternative-id":["10.3389\/fnins.2023.1180679"],"URL":"https:\/\/doi.org\/10.3389\/fnins.2023.1180679","relation":{},"ISSN":["1662-453X"],"issn-type":[{"value":"1662-453X","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023,5,15]]},"article-number":"1180679"}}