{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,24]],"date-time":"2026-03-24T21:17:55Z","timestamp":1774387075196,"version":"3.50.1"},"reference-count":20,"publisher":"Springer Science and Business Media LLC","issue":"2","license":[{"start":{"date-parts":[[2025,10,6]],"date-time":"2025-10-06T00:00:00Z","timestamp":1759708800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"},{"start":{"date-parts":[[2025,10,6]],"date-time":"2025-10-06T00:00:00Z","timestamp":1759708800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"}],"funder":[{"DOI":"10.13039\/501100005610","name":"Fukuoka University","doi-asserted-by":"publisher","award":["No.GW2402"],"award-info":[{"award-number":["No.GW2402"]}],"id":[{"id":"10.13039\/501100005610","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100009619","name":"Japan Agency for Medical Research and Development","doi-asserted-by":"publisher","award":["JP19dm0307101"],"award-info":[{"award-number":["JP19dm0307101"]}],"id":[{"id":"10.13039\/100009619","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100000646","name":"Japan Society for the Promotion of Science London","doi-asserted-by":"publisher","award":["JP21K19898"],"award-info":[{"award-number":["JP21K19898"]}],"id":[{"id":"10.13039\/501100000646","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Int J CARS"],"abstract":"<jats:title>Abstract<\/jats:title>\n                  <jats:sec>\n                    <jats:title>Purpose<\/jats:title>\n                    <jats:p>A fully automated segmentation of substantia nigra (SN) is an essential task for the development of an explainable computer-aided diagnosis system of Parkinson\u2019s disease (PD). Since anatomical alterations of SN are vital information in PD diagnosis, a precise segmentation model should have generalization ability against spatiotemporal changes. To satisfy these requirements, we propose a fully automated pipeline with several new techniques for a volumetric image obtained by neuromelanin magnetic resonance imaging.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Methods<\/jats:title>\n                    <jats:p>We develop a pipeline by integrating SN-prior probability estimation into the decision of the SN-contained region of interest. An estimated SN-prior probability is further fed into a new priority attention mechanism as a gating signal in our segmentation model. Furthermore, we introduce test-time dropout to improve a segmentation model\u2019s accuracy and generalization ability. To evaluate the model\u2019s generalization ability, we collected principal and external datasets with longitudinal scans of the same PD patients.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Results<\/jats:title>\n                    <jats:p>Our segmentation model achieved averaged Dice scores of 0.845 and 0.851 for SN hyperintense regions in the principal and external datasets, respectively. These results demonstrated the best generalization ability in our comparative evaluations. Thresholding the number of voxels in the SN hyperintense regions, we also evaluated the segmentation results in automated PD identification. The PD identification achieved the areas under the receiver operating characteristic curves of 0.755 and 0.726 by our pipeline\u2019s output and the ground truth, respectively.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Conclusions<\/jats:title>\n                    <jats:p>The proposed pipeline, where we integrated SN-prior probability estimation, priority attention mechanism and test-time dropout to our segmentation model, achieved accurate SN segmentation with high generalization ability for our longitudinal data: the principal and external datasets. As demonstrated in the validation with the automated PD identification, our pipeline has the potential for improving the performance of PD diagnosis via further large-scale longitudinal analysis.<\/jats:p>\n                  <\/jats:sec>","DOI":"10.1007\/s11548-025-03451-9","type":"journal-article","created":{"date-parts":[[2025,10,6]],"date-time":"2025-10-06T14:37:34Z","timestamp":1759761454000},"page":"343-354","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Fully automated segmentation of substantia nigra toward longitudinal analysis of Parkinson\u2019s disease"],"prefix":"10.1007","volume":"21","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-7667-1666","authenticated-orcid":false,"given":"Tao","family":"Hu","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1410-1078","authenticated-orcid":false,"given":"Hayato","family":"Itoh","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7714-422X","authenticated-orcid":false,"given":"Masahiro","family":"Oda","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9732-8488","authenticated-orcid":false,"given":"Shinji","family":"Saiki","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5028-218X","authenticated-orcid":false,"given":"Koji","family":"Kamagata","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2305-301X","authenticated-orcid":false,"given":"Kei-ichi","family":"Ishikawa","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Wataru","family":"Sako","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2034-2556","authenticated-orcid":false,"given":"Nobutaka","family":"Hattori","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8491-0698","authenticated-orcid":false,"given":"Shigeki","family":"Aoki","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0100-4797","authenticated-orcid":false,"given":"Kensaku","family":"Mori","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2025,10,6]]},"reference":[{"issue":"5","key":"3451_CR1","doi-asserted-by":"publisher","first-page":"384","DOI":"10.1212\/01.wnl.0000247740.47667.03","volume":"68","author":"ER Dorsey","year":"2007","unstructured":"Dorsey ER, Constantinescu R, Thompson J, Biglan K, Holloway R, Kieburtz K, Marshall F, Ravina B, Schifitto G, Siderowf A, Tanner CM (2007) Projected number of people with Parkinson disease in the most populous nations, 2005 through 2030. Neurology 68(5):384\u2013386","journal-title":"Neurology"},{"issue":"7","key":"3451_CR2","doi-asserted-by":"publisher","first-page":"1592","DOI":"10.1002\/mds.28531","volume":"36","author":"R Gaurav","year":"2021","unstructured":"Gaurav R, Yahia-Cherif L, Pyatigorskaya N, Mangone G, Biondetti E, Valabr\u00e8gue R, Ewenczyk C, Hutchison RM, Cedarbaum JM, Corvol J, Vidailhet M (2021) Longitudinal changes in neuromelanin MRI signal in Parkinson\u2019s disease: a progression marker. Mov Disord 36(7):1592\u20131602","journal-title":"Mov Disord"},{"issue":"9","key":"3451_CR3","doi-asserted-by":"publisher","first-page":"2757","DOI":"10.1093\/brain\/awaa216","volume":"143","author":"E Biondetti","year":"2020","unstructured":"Biondetti E, Gaurav R, Yahia-Cherif L, Mangone G, Pyatigorskaya N, Valabr\u00e8gue R, Ewenczyk C, Hutchison M, Fran\u00e7ois C, Arnulf I, Corvol J, Vidailhet M, Leh\u00e8ricy S (2020) Spatiotemporal changes in substantia nigra neuromelanin content in Parkinson\u2019s Disease. Brain 143(9):2757\u20132770","journal-title":"Brain"},{"key":"3451_CR4","doi-asserted-by":"publisher","first-page":"1387","DOI":"10.1007\/s00234-019-02279-w","volume":"61","author":"BA Le","year":"2019","unstructured":"Le BA, Kamagata K, Otsuka Y, Andica C, Hatano T, Saccenti L, Ogawa T, Takeshige-Amano H, Wada A, Michimasa S, Hagiwara A, Irie R, Hori M, Oyama G, Shimo Y, Umemura A, Hattori N, Aoki S (2019) Convolutional neural network-based segmentation can help in assessing the substantia nigra in neuromelanin MRI. Neuroradiology 61:1387\u20131395","journal-title":"Neuroradiology"},{"issue":"7","key":"3451_CR5","doi-asserted-by":"publisher","first-page":"945","DOI":"10.1002\/mds.26201","volume":"30","author":"G Castellanos","year":"2015","unstructured":"Castellanos G, Fern\u00e1ndez-Seara MA, Lorenzo-Betancor O, Ortega-Cubero S, Puigvert M, Uranga J, Vidorreta M, Irigoyen J, Lorenzo E, Mu\u00f1oz-Barrutia A, Carlos O, Pastor P, Pastor MA (2015) Automated Neuromelanin Imaging as a Diagnostic Biomarker for Parkinson\u2019s Disease. Mov Disord 30(7):945\u2013952","journal-title":"Mov Disord"},{"issue":"8","key":"3451_CR6","doi-asserted-by":"publisher","first-page":"1266","DOI":"10.1109\/TMI.2009.2014372","volume":"28","author":"X Artaechevarria","year":"2009","unstructured":"Artaechevarria X, Munoz-Barrutia A, Ortiz-de-Solorzano C (2009) Combination strategies in multi-atlas image segmentation: application to brain MR data. IEEE Trans Med Imaging 28(8):1266\u20131277","journal-title":"IEEE Trans Med Imaging"},{"key":"3451_CR7","doi-asserted-by":"publisher","first-page":"324","DOI":"10.1016\/j.neuroimage.2016.06.039","volume":"139","author":"E Visser","year":"2016","unstructured":"Visser E, Keuken MC, Forstmann BU, Jenkinson M (2016) Automated segmentation of the substantia nigra, subthalamic nucleus and red nucleus in 7 T data at young and old age. Neuroimage 139:324\u2013336","journal-title":"Neuroimage"},{"issue":"3","key":"3451_CR8","doi-asserted-by":"publisher","first-page":"813","DOI":"10.1109\/TMI.2018.2872852","volume":"38","author":"M Ariz","year":"2018","unstructured":"Ariz M, Abad RC, Castellanos G, Mart\u00ednez M, Mu\u00f1oz-Barrutia A, Fern\u00e1ndez-Seara MA, Pastor P, Pastor MA, Ortiz-de-Sol\u00f3rzano C (2018) Dynamic atlas-based segmentation and quantification of neuromelanin-rich brainstem structures in Parkinson disease. IEEE Trans Med Imaging 38(3):813\u2013823","journal-title":"IEEE Trans Med Imaging"},{"key":"3451_CR9","doi-asserted-by":"crossref","unstructured":"Basukala D, Mukundan R, Melzer T, Keenan R (2018) Segmentation of substantia nigra for the automated characterization of Parkinson\u2019s disease. In: 2018 IEEE international conference on image processing, applications and systems (IPAS), pp 85\u201390","DOI":"10.1109\/IPAS.2018.8708886"},{"issue":"4","key":"3451_CR10","doi-asserted-by":"publisher","first-page":"1112","DOI":"10.1002\/jmri.26023","volume":"48","author":"T Guo","year":"2018","unstructured":"Guo T, Song Y, Li J, Fan M, Yan X, He A, Huang D, Shen C, Zhang G, Yang G (2018) Seed point discontinuity-based segmentation method for the substantia nigra and the red nucleus in quantitative susceptibility maps. J Magn Reson Imaging 48(4):1112\u20131119","journal-title":"J Magn Reson Imaging"},{"key":"3451_CR11","doi-asserted-by":"crossref","unstructured":"Ronneberger O, Fischer P, Brox T (2015) U-Net: convolutional networks for biomedical image segmentation. In: Proceedings of the medical image computing and computer assisted intervention, pp 234\u2013241","DOI":"10.1007\/978-3-319-24574-4_28"},{"key":"3451_CR12","doi-asserted-by":"publisher","first-page":"S453","DOI":"10.33549\/physiolres.934380","volume":"68","author":"R Krupi\u010dka","year":"2019","unstructured":"Krupi\u010dka R, Mare\u010dek S, Mal\u00e1 C, Lang M, Klemp\u00ed\u0159 O, Duspivov\u00e1 T, \u0160irok\u00e1 R, Jaro\u0161\u00edkov\u00e1 T, Keller J, \u0160onka K, Ru\u017ei\u010dka E (2019) Automatic substantia nigra segmentation in neuromelanin-sensitive MRI by deep neural network in patients with prodromal and manifest synucleinopathy. Physiol Res 68:S453\u2013S458","journal-title":"Physiol Res"},{"key":"3451_CR13","unstructured":"Yu F, Koltun V (2016) Multi-scale context aggregation by dilated convolutions. In: International conference on learning representations"},{"key":"3451_CR14","doi-asserted-by":"publisher","DOI":"10.1016\/j.nicl.2022.103250","volume":"36","author":"R Gaurav","year":"2022","unstructured":"Gaurav R, Romain V, Lydia YC, Graziella M, Sridar N, Isabelle A, Marie V, Jean-Christophe C, St\u00e9phane L (2022) NigraNet: an automatic framework to assess nigral neuromelanin content in early Parkinson\u2019s disease using convolutional neural network. NeuroImage Cli 36:103250","journal-title":"NeuroImage Cli"},{"key":"3451_CR15","doi-asserted-by":"crossref","unstructured":"Hu T, Itoh H, Oda M, Hayashi Y, Lu Z, Saiki S, Hattori N, Kamagata K, Aoki S, Kumamaru KK, Akashi T, Mori K (2022) Enhancing model generalization for substantia nigra segmentation using a test-time normalization-based method. In: Proceedings of the medical image computing and computer assisted intervention, pp 736\u2013744","DOI":"10.1007\/978-3-031-16449-1_70"},{"key":"3451_CR16","doi-asserted-by":"crossref","unstructured":"Schlemper J, Oktay O, Schaap M, Heinrich M, Kainz B, Glocker B, Rueckert D (2019) Attention gated networks: learning to leverage salient regions in medical images. Med Image Anal 53:197\u2013207","DOI":"10.1016\/j.media.2019.01.012"},{"key":"3451_CR17","doi-asserted-by":"crossref","unstructured":"Hu T, Itoh H, Oda M, Saiki S, Hattori N, Kamagata K, Aoki S, Mori K (2023) Priority attention network with Bayesian learning for fully automatic segmentation of substantia nigra from neuromelanin MRI. In: Proceedings of the SPIE medical imaging 2023: image processing, SPIE12464, pp 786\u2013791","DOI":"10.1117\/12.2655112"},{"key":"3451_CR18","unstructured":"Gal Y, Ghahramani Z (2016) Dropout as a bayesian approximation: representing model uncertainty in deep learning. In: Proceedings of the 33rd international conference on machine learning, pp 1050\u20131059"},{"issue":"3","key":"3451_CR19","doi-asserted-by":"publisher","first-page":"181","DOI":"10.1136\/jnnp.55.3.181","volume":"55","author":"AJ Hughes","year":"1992","unstructured":"Hughes AJ, Susan ED, Linda K, Andrew JL (1992) Accuracy of clinical diagnosis of idiopathic Parkinson\u2019s disease: a clinico-pathological study of 100 cases. J Neurol Neurosurg 55(3):181\u2013184","journal-title":"J Neurol Neurosurg"},{"key":"3451_CR20","doi-asserted-by":"publisher","first-page":"1721","DOI":"10.1109\/ACCESS.2018.2886371","volume":"7","author":"SR Hashemi","year":"2018","unstructured":"Hashemi SR, Salehi S, Erdogmus D, Prabhu SP, Warfield SK, Gholipour A (2018) Asymmetric loss functions and deep densely-connected networks for highly-imbalanced medical image segmentation: Application to multiple sclerosis lesion detection. IEEE Access 7:1721\u20131735","journal-title":"IEEE Access"}],"container-title":["International Journal of Computer Assisted Radiology and Surgery"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11548-025-03451-9.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s11548-025-03451-9","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11548-025-03451-9.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,3,24]],"date-time":"2026-03-24T18:02:54Z","timestamp":1774375374000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s11548-025-03451-9"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,6]]},"references-count":20,"journal-issue":{"issue":"2","published-online":{"date-parts":[[2026,2]]}},"alternative-id":["3451"],"URL":"https:\/\/doi.org\/10.1007\/s11548-025-03451-9","relation":{},"ISSN":["1861-6429"],"issn-type":[{"value":"1861-6429","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,10,6]]},"assertion":[{"value":"20 February 2025","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"28 May 2025","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"6 October 2025","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"No Conflict of interest.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Conflict of interest"}},{"value":"All the procedures performed in studies involving human participants were in accordance with the ethical committee of Nagoya University (No. 382), and Juntendo University (H19-179), and the 1964 Helsinki Declaration and subsequent amendments or comparable ethical standards.","order":3,"name":"Ethics","group":{"name":"EthicsHeading","label":"Ethical Approval"}}]}}