{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,15]],"date-time":"2026-08-15T09:29:19Z","timestamp":1786786159528,"version":"build-2736575974"},"reference-count":26,"publisher":"Springer Science and Business Media LLC","issue":"2","license":[{"start":{"date-parts":[[2025,6,27]],"date-time":"2025-06-27T00:00:00Z","timestamp":1750982400000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"},{"start":{"date-parts":[[2025,6,27]],"date-time":"2025-06-27T00:00:00Z","timestamp":1750982400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"}],"funder":[{"DOI":"10.13039\/501100004375","name":"Tel Aviv University","doi-asserted-by":"crossref","id":[{"id":"10.13039\/501100004375","id-type":"DOI","asserted-by":"crossref"}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Virchows Arch"],"published-print":{"date-parts":[[2026,8]]},"abstract":"<jats:title>Abstract<\/jats:title>\n                  <jats:p>\n                    Microscopic images of aggressive and non-aggressive cases of central giant cell granuloma (CGCG) were analyzed by deep learning algorithms in order to assess its potential as a tool in predicting the biological behavior of CGCG. CGCGs with cortical expansion\/perforation, tooth resorption\/displacement, or recurrence were classified as aggressive (A-group;\n                    <jats:italic>N<\/jats:italic>\n                    \u2009=\u200948), CGCGs without these features as non-aggressive (N-group;\n                    <jats:italic>N<\/jats:italic>\n                    \u2009=\u200939). Data on patient age, gender, and jaw location were collected. Hematoxylin\u2013eosin (H&amp;E)\u2013stained sections were scanned at\u2009\u00d7\u200910 magnification, yielding 9982 sections\u00a0(5236 A-group, 4746 N-group). After excluding artifacts, 4272 sections\u00a0(2629 A-group, 1643 N-group) were used to train a ResNet-50 model pre-trained on ImageNet. Data augmentation included random rotation, flipping, and zooming. Model was trained for 100 epochs with an 80\/20 train\/validation split and tested on 100 images (50 A-group, 50 N-group). Receiver Operating Characteristic (ROC) analysis with area under the curve (AUC), sensitivity, and specificity was performed;\n                    <jats:italic>t<\/jats:italic>\n                    -test and chi-square test were used for age and frequency (\n                    <jats:italic>p<\/jats:italic>\n                    \u2009&lt;\u20090.05). AUC was 52%, sensitivity 54%, and specificity 50%. Mean age of patients in A-group was lower than in N-groups (32.6\u2009\u00b1\u200919.98\u00a0years and 42.2\u2009\u00b1\u200921.58\u00a0years, respectively;\n                    <jats:italic>p<\/jats:italic>\n                    \u2009=\u20090.038). F:M ratio was 1:1 in both groups. Mandible was twofold more frequently than maxilla in both groups. This pioneering study to differentiate between aggressive and non-aggressive CGCGs based on whole microscopic sections using a deep machine learning model was not successful, probably due to lack of specific segmentations and technical staining issues. Further investigation with advanced preprocessing is needed to enhance model performance and clinical utility.\u00a0\n                  <\/jats:p>","DOI":"10.1007\/s00428-025-04160-z","type":"journal-article","created":{"date-parts":[[2025,6,26]],"date-time":"2025-06-26T23:38:37Z","timestamp":1750981117000},"page":"353-361","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["Deep learning for classification of aggressive versus non-aggressive central giant cell granuloma using whole-slide histopathology images"],"prefix":"10.1007","volume":"489","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-1187-2333","authenticated-orcid":false,"given":"Marilena","family":"Vered","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Anna","family":"Shnaiderman-Shapiro","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Rozet","family":"Malouf","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ariel","family":"Hirschhorn","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Amos","family":"Buchner","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Shoshana","family":"Reiter","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Lazar","family":"Kats","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2025,6,27]]},"reference":[{"key":"4160_CR1","unstructured":"Jordan RC, Gomes CC, Gomez RS (2024) Central giant cell granuloma. In: Muller S, Odell EW, Tilakaratne WM (eds) WHO Classification of head and neck tumours. Odontogenic and maxillofacial bone tumours, 5th edn. IARC Press, Lyon, pp 379\u2013380"},{"key":"4160_CR2","doi-asserted-by":"publisher","first-page":"792","DOI":"10.1002\/hed.20069","volume":"26","author":"J de Lange","year":"2004","unstructured":"de Lange J, van den Akker HP, Klip H (2004) Incidence and disease-free survival after surgical therapy of central giant cell granulomas of the jaw in The Netherlands: 1990\u20131995. Head Neck 26:792\u2013795. https:\/\/doi.org\/10.1002\/hed.20069","journal-title":"Head Neck"},{"key":"4160_CR3","doi-asserted-by":"publisher","unstructured":"Vered M, Buchner A, Dayan D (2008) Central giant cell granuloma of the jawbones--new insights into molecular biology with clinical implications on treatment approaches. Histol Histopathol 23:1151\u20131160. https:\/\/doi.org\/10.14670\/HH-23.1151","DOI":"10.14670\/HH-23.1151"},{"key":"4160_CR4","doi-asserted-by":"publisher","first-page":"731","DOI":"10.1111\/jop.12730","volume":"47","author":"BR Chrcanovic","year":"2018","unstructured":"Chrcanovic BR, Gomes CC, Gomez RS (2018) Central giant cell lesion of the jaws: an updated analysis of 2270 cases reported in the literature. J Oral Pathol Med 47:731\u2013739. https:\/\/doi.org\/10.1111\/jop.12730","journal-title":"J Oral Pathol Med"},{"key":"4160_CR5","doi-asserted-by":"publisher","first-page":"708","DOI":"10.1016\/0278-2391(86)90040-6","volume":"44","author":"R Chuong","year":"1986","unstructured":"Chuong R, Kaban LB, Kozakewich H, Perez-Atayde A (1986) Central giant cell lesions of the jaws: a clinicopathologic study. J Oral Maxillofac Surg 44:708\u2013713. https:\/\/doi.org\/10.1016\/0278-2391(86)90040-6","journal-title":"J Oral Maxillofac Surg"},{"key":"4160_CR6","doi-asserted-by":"publisher","first-page":"1103","DOI":"10.1053\/joms.2002.34975","volume":"60","author":"LB Kaban","year":"2002","unstructured":"Kaban LB, Troulis MJ, Ebb D, August M, Hornicek FJ, Dodson TB (2002) Antiangiogenic therapy with interferon alpha for giant cell lesions of the jaws. J Oral Maxillofac Surg 60:1103\u20131111. https:\/\/doi.org\/10.1053\/joms.2002.34975","journal-title":"J Oral Maxillofac Surg"},{"key":"4160_CR7","doi-asserted-by":"publisher","unstructured":"Torabinia N, Razavi SM, Shokrolahi Z (2011) A comparative immunohistochemical evaluation of CD68 and TRAP protein expression in central and peripheral giant cell granulomas of the jaws. J Oral Pathol Med 40:334\u2013337. https:\/\/doi.org\/10.1111\/j.1600-0714.2010.00944.x","DOI":"10.1111\/j.1600-0714.2010.00944.x"},{"key":"4160_CR8","doi-asserted-by":"publisher","first-page":"445","DOI":"10.1007\/s12105-014-0589-6","volume":"8","author":"AM Flanagan","year":"2014","unstructured":"Flanagan AM, Speight PM (2014) Giant cell lesions of the craniofacial bones. Head Neck Pathol 8:445\u2013453. https:\/\/doi.org\/10.1007\/s12105-014-0589-6","journal-title":"Head Neck Pathol"},{"key":"4160_CR9","doi-asserted-by":"publisher","first-page":"151526","DOI":"10.1016\/j.anndiagpath.2020.151526","volume":"46","author":"VRV Melo-Muniz","year":"2020","unstructured":"Melo-Muniz VRV, Nunes FD, Cangussu MCT et al (2020) Central giant cell granuloma: a clinicopathological and immunohistochemical study of macrophages, blood vessels, lymphatic vessels and regulatory proteins. Ann Diagn Pathol 46:151526. https:\/\/doi.org\/10.1016\/j.anndiagpath.2020.151526","journal-title":"Ann Diagn Pathol"},{"key":"4160_CR10","doi-asserted-by":"publisher","unstructured":"de Oliveira Filho SA, Martins AFL, Mosconi C, de Paula HM, Mendon\u00e7a EF (2021) Angiogenesis pattern and H3.3 histone mutation in aggressive and non-aggressive central giant cell lesions. Arch Oral Biol 130:105218.\u00a0https:\/\/doi.org\/10.1016\/j.archoralbio.2021.105218","DOI":"10.1016\/j.archoralbio.2021.105218"},{"key":"4160_CR11","doi-asserted-by":"publisher","first-page":"495","DOI":"10.1111\/j.1600-0714.2007.00541.x","volume":"36","author":"M Vered","year":"2007","unstructured":"Vered M, Nasrallah W, Buchner A, Dayan D (2007) Stromal myofibroblasts in central giant cell granuloma of the jaws cannot distinguish between non-aggressive and aggressive lesions. J Oral Pathol Med 36:495\u2013500. https:\/\/doi.org\/10.1111\/j.1600-0714.2007.00541.x","journal-title":"J Oral Pathol Med"},{"key":"4160_CR12","doi-asserted-by":"publisher","first-page":"1414","DOI":"10.1016\/j.joms.2017.01.001","volume":"75","author":"A Kahn","year":"2017","unstructured":"Kahn A, Chaushu G, Ginene L, Vered M (2017) Age and expression of CD163 and colony-stimulating factor 1 receptor (CD115) are associated with the biological behavior of central giant cell granuloma. J Oral Maxillofac Surg 75:1414\u20131424. https:\/\/doi.org\/10.1016\/j.joms.2017.01.001","journal-title":"J Oral Maxillofac Surg"},{"key":"4160_CR13","doi-asserted-by":"publisher","first-page":"126","DOI":"10.1002\/path.5365","volume":"250","author":"CC Gomes","year":"2020","unstructured":"Gomes CC, Diniz MG, Bastos VC, Bernardes VF, Gomez RS (2020) Making sense of giant cell lesions of the jaws (GCLJ): lessons learned from next-generation sequencing. J Pathol 250:126\u2013133. https:\/\/doi.org\/10.1002\/path.5365","journal-title":"J Pathol"},{"key":"4160_CR14","doi-asserted-by":"publisher","first-page":"4572","DOI":"10.1038\/s41467-018-06690-4","volume":"9","author":"CC Gomes","year":"2018","unstructured":"Gomes CC, Gayden T, Bajic A et al (2018) TRPV4 and KRAS and FGFR1 gain-of-function mutations drive giant cell lesions of the jaw. Nat Commun 9:4572. https:\/\/doi.org\/10.1038\/s41467-018-06690-4","journal-title":"Nat Commun"},{"key":"4160_CR15","doi-asserted-by":"publisher","unstructured":"Gomes CC, Diniz MG, Amaral FR, Antonini Guimar\u00e3es BV, Gomez RS (2014) The highly prevalent H3F3A mutation in giant cell tumours of bone is not shared by sporadic central giant cell lesion of the jaws. Oral Surg Oral Med Oral Pathol Oral Radiol 118:583\u2013585. https:\/\/doi.org\/10.1016\/j.oooo.2014.07.011","DOI":"10.1016\/j.oooo.2014.07.011"},{"key":"4160_CR16","doi-asserted-by":"publisher","unstructured":"Egger J, Gsaxner C, Pepe A, Pomykala KL, Jonske F, Kurz M, Li J, Kleesiek J (2022) Medical deep learning-a systematic meta-review. Comput Methods Programs Biomed 221:106874. https:\/\/doi.org\/10.1016\/j.cmpb.2022.106874","DOI":"10.1016\/j.cmpb.2022.106874"},{"key":"4160_CR17","doi-asserted-by":"publisher","first-page":"508","DOI":"10.1016\/j.jds.2020.06.019","volume":"16","author":"SB Khanagar","year":"2021","unstructured":"Khanagar SB, Al-Ehaideb A, Maganur PC, Vishwanathaiah S, Patil S, Baeshen HA, Sarode SC, Bhandi S (2021) Developments, application, and performance of artificial intelligence in dentistry - a systematic review. J Dent Sci 16:508\u2013522. https:\/\/doi.org\/10.1016\/j.jds.2020.06.019","journal-title":"J Dent Sci"},{"key":"4160_CR18","doi-asserted-by":"publisher","unstructured":"Liu Z, Jin L, Chen J, Fang Q, Ablameyko S, Yin Z, Xu Y (2021) A survey on applications of deep learning in microscopy image analysis. Comput Biol Med 134:104523.\u00a0https:\/\/doi.org\/10.1016\/j.compbiomed.2021","DOI":"10.1016\/j.compbiomed.2021"},{"key":"4160_CR19","doi-asserted-by":"publisher","unstructured":"Fuyong Xing, Yuanpu Xie, Hai Su, Fujun Liu, Lin Yang (2018) Deep learning in microscopy image analysis: a survey. IEEE Trans Neural Netw Learn Syst 29:4550\u20134568. https:\/\/doi.org\/10.1109\/TNNLS.2017.2766168","DOI":"10.1109\/TNNLS.2017.2766168"},{"key":"4160_CR20","doi-asserted-by":"publisher","first-page":"104885","DOI":"10.1016\/j.oraloncology.2020.104885","volume":"110","author":"H Mahmood","year":"2020","unstructured":"Mahmood H, Shaban M, Indave BI, Santos-Silva AR, Rajpoot N, Khurram SA (2020) Use of artificial intelligence in diagnosis of head and neck precancerous and cancerous lesions: a systematic review. Oral Oncol 110:104885. https:\/\/doi.org\/10.1016\/j.oraloncology.2020.104885","journal-title":"Oral Oncol"},{"key":"4160_CR21","doi-asserted-by":"publisher","first-page":"e200029","DOI":"10.1148\/ryai.2020200029","volume":"2","author":"J Mongan","year":"2020","unstructured":"Mongan J, Moy L, Kahn CE Jr (2020) Checklist for Artificial Intelligence in Medical Imaging (CLAIM): a guide for authors and reviewers. Radiol Artif Intell 2:e200029. https:\/\/doi.org\/10.1148\/ryai.2020200029","journal-title":"Radiol Artif Intell"},{"key":"4160_CR22","doi-asserted-by":"publisher","unstructured":"Kruse-L\u00f6sler B, Diallo R, Gaertner C, Mischke KL, Joos U, Kleinheinz J (2006) Central giant cell granuloma of the jaws: a clinical, radiologic, and histopathologic study of 26 cases. Oral Surg Oral Med Oral Pathol Oral Radiol Endod 101:346\u2013354. https:\/\/doi.org\/10.1016\/j.tripleo.2005.02.060","DOI":"10.1016\/j.tripleo.2005.02.060"},{"key":"4160_CR23","doi-asserted-by":"publisher","first-page":"1841","DOI":"10.1007\/s00330-018-5730-6","volume":"29","author":"P Yin","year":"2019","unstructured":"Yin P, Mao N, Zhao C, Wu J, Sun C, Chen L, Hong N (2019) Comparison of radiomics machine-learning classifiers and feature selection for differentiation of sacral chordoma and sacral giant cell tumour based on 3D computed tomography features. Eur Radiol 29:1841\u20131847. https:\/\/doi.org\/10.1007\/s00330-018-5730-6","journal-title":"Eur Radiol"},{"key":"4160_CR24","doi-asserted-by":"publisher","unstructured":"Lau CPY, Ma W, Law KY, Lacambra MD, Wong KC, Lee CW, Lee OK, Dou Q, Kumta SM (2022) Development of deep learning algorithms to discriminate giant cell tumors of bone from adjacent normal tissues by confocal Raman spectroscopy. Analyst 147:1425\u20131439. https:\/\/doi.org\/10.1039\/d1an01554k","DOI":"10.1039\/d1an01554k"},{"key":"4160_CR25","doi-asserted-by":"publisher","unstructured":"Yin P, Mao N, Zhao C, Wu J, Chen L, Hong N (2019) A triple-classification radiomics model for the differentiation of primary chordoma, giant cell tumor, and metastatic tumor of sacrum based on T2-weighted and contrast-enhanced T1-weighted MRI. J Magn Reson Imaging 49:752\u2013759. https:\/\/doi.org\/10.1002\/jmri.26238","DOI":"10.1002\/jmri.26238"},{"key":"4160_CR26","doi-asserted-by":"publisher","first-page":"111496","DOI":"10.1016\/j.ejrad.2024.111496","volume":"176","author":"Z Xie","year":"2024","unstructured":"Xie Z, Zhao H, Song L, Ye Q, Zhong L, Li S, Zhang R, Wang M, Chen X, Lu Z, Yang W, Zhao Y (2024) A radiograph-based deep learning model improves radiologists\u2019 performance for classification of histological types of primary bone tumors: a multicenter study. Eur J Radiol 176:111496. https:\/\/doi.org\/10.1016\/j.ejrad.2024.111496","journal-title":"Eur J Radiol"}],"container-title":["Virchows Archiv"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s00428-025-04160-z.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s00428-025-04160-z","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s00428-025-04160-z.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,8,15]],"date-time":"2026-08-15T09:25:12Z","timestamp":1786785912000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s00428-025-04160-z"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,6,27]]},"references-count":26,"journal-issue":{"issue":"2","published-print":{"date-parts":[[2026,8]]}},"alternative-id":["4160"],"URL":"https:\/\/doi.org\/10.1007\/s00428-025-04160-z","relation":{},"ISSN":["0945-6317","1432-2307"],"issn-type":[{"value":"0945-6317","type":"print"},{"value":"1432-2307","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,6,27]]},"assertion":[{"value":"9 May 2025","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"12 June 2025","order":2,"name":"revised","label":"Revised","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"17 June 2025","order":3,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"27 June 2025","order":4,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"All procedures performed in studies involving human participants were in accordance with the ethical standards of the institutional and\/or national research committee and with the 1964 Helsinki declaration and its later amendments or comparable ethical standards.","order":1,"name":"Ethics","label":"Ethics approval","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"This study has obtained approval from the Ethics Committee of Tel Aviv University and the need for informed consent was waived.","order":2,"name":"Ethics","label":"Consent","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"The authors declare no competing interests.","order":3,"name":"Ethics","label":"Competing interests","group":{"name":"EthicsHeading","label":"Declarations"}}]}}