{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,31]],"date-time":"2026-07-31T08:59:20Z","timestamp":1785488360215,"version":"3.56.0"},"reference-count":28,"publisher":"MDPI AG","issue":"15","license":[{"start":{"date-parts":[[2026,7,31]],"date-time":"2026-07-31T00:00:00Z","timestamp":1785456000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"name":"European Union\u2019s NextGenerationEU","award":["INREIA\/2024\/71"],"award-info":[{"award-number":["INREIA\/2024\/71"]}]},{"name":"European Union\u2019s NextGenerationEU","award":["INREIA\/2024\/161"],"award-info":[{"award-number":["INREIA\/2024\/161"]}]},{"award":["INREIA\/2024\/71"],"award-info":[{"award-number":["INREIA\/2024\/71"]}],"id":[{"id":"https:\/\/ror.org\/019w4f821","id-type":"ROR","asserted-by":"publisher"}]},{"award":["INREIA\/2024\/161"],"award-info":[{"award-number":["INREIA\/2024\/161"]}],"id":[{"id":"https:\/\/ror.org\/019w4f821","id-type":"ROR","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Int. J. Mol. Sci.","IJMS"],"abstract":"<jats:p>Ewing sarcoma is a highly malignant tumor whose histological appearance often overlaps with that of other undifferentiated round-cell and ovoid-cell tumors, making accurate diagnosis challenging. Selecting the most appropriate immunohistochemical and molecular tests is critical, particularly when only limited core biopsy material is available and tissue preservation for additional molecular or biomarker testing is required. Artificial intelligence (AI)-based histopathological image analysis is emerging as a promising diagnostic tool in oncology. This study evaluated the potential of AI-based histopathological analysis to assist pathologists in the morphologic classification of Ewing sarcoma and selected histological mimics using tissue microarrays (TMAs), rather than to identify or predict molecular alterations. We analyzed 1926 digitized histological cores, from 729 patients, assembled into 45 tissue microarrays. The dataset comprised 517 Ewing sarcomas (ESs), 367 rhabdomyosarcomas (RMSs), 187 chondrosarcomas (CHSs), 138 gastrointestinal stromal tumors (GISTs), and 124 synovial sarcomas (SSs). A weakly supervised multiple-instance learning (MIL) framework with transformer-based aggregation was developed using only core-level diagnostic labels. The model achieved classification accuracies of 97.1% for Ewing sarcoma, 80.0% for rhabdomyosarcoma, 85.7% for gastrointestinal stromal tumors, 80.0% for chondrosarcoma, and 76.0% for synovial sarcoma. The overall classification accuracy was 91.6%, with no misclassifications between Ewing sarcoma and rhabdomyosarcoma. These findings highlight the model\u2019s robustness in distinguishing tumor entities that present a well-recognized diagnostic challenge in routine pathology. The AI algorithm demonstrated strong potential as a diagnostic adjunct for assisting pathologists in the morphologic classification of Ewing sarcoma and selected tumor entities based on histopathological features. Although these tumor entities are characterized by specific molecular alterations, the model was not designed to identify or predict molecular alterations directly. Instead, it supports clinical decision-making by recognizing morphologic patterns associated with diagnostically defined tumor entities. The integration of AI-based histopathological analysis with immunohistochemistry and contemporary molecular diagnostic techniques has the potential to improve diagnostic accuracy, optimize the use of ancillary testing, enhance our understanding of genotype\u2013phenotype relationships, and ultimately support more effective patient management.<\/jats:p>","DOI":"10.3390\/ijms27156864","type":"journal-article","created":{"date-parts":[[2026,7,31]],"date-time":"2026-07-31T08:20:18Z","timestamp":1785486018000},"page":"6864","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Artificial Intelligence-Based Histopathological Analysis to Assist Pathologists in Diagnosing Ewing Sarcoma and Selected Tumor Entities Using Tissue Microarrays"],"prefix":"10.3390","volume":"27","author":[{"given":"Francisco","family":"Giner","sequence":"first","affiliation":[{"name":"Pathology Department, University of Valencia, 46010 Valencia, Spain"},{"name":"Pathology Department, Hospital Universitari i Polit\u00e8cnic La Fe, 46026 Valencia, Spain"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"\u00c1lvaro","family":"Pastor-Naranjo","sequence":"additional","affiliation":[{"name":"Instituto Universitario de Investigaci\u00f3n e Innovaci\u00f3n en Tecnolog\u00eda Centrada en el Ser Humano (HUMAN-Tech), Universitat Polit\u00e8cnica de Val\u00e8ncia (UPV), 46026 Valencia, Spain"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7821-6168","authenticated-orcid":false,"given":"Pablo","family":"Meseguer","sequence":"additional","affiliation":[{"name":"Instituto Universitario de Investigaci\u00f3n e Innovaci\u00f3n en Tecnolog\u00eda Centrada en el Ser Humano (HUMAN-Tech), Universitat Polit\u00e8cnica de Val\u00e8ncia (UPV), 46026 Valencia, Spain"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Roc\u00edo","family":"Del Amor","sequence":"additional","affiliation":[{"name":"Instituto Universitario de Investigaci\u00f3n e Innovaci\u00f3n en Tecnolog\u00eda Centrada en el Ser Humano (HUMAN-Tech), Universitat Polit\u00e8cnica de Val\u00e8ncia (UPV), 46026 Valencia, Spain"},{"name":"Artikode Intelligence S.L., 46022 Valencia, Spain"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8080-4484","authenticated-orcid":false,"given":"Marco","family":"Gambarotti","sequence":"additional","affiliation":[{"name":"Department of Pathology, IRCCS Rizzoli Orthopaedic Institute, 40136 Bologna, Italy"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1074-0155","authenticated-orcid":false,"given":"Alberto","family":"Righi","sequence":"additional","affiliation":[{"name":"Department of Pathology, IRCCS Rizzoli Orthopaedic Institute, 40136 Bologna, Italy"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7369-8388","authenticated-orcid":false,"given":"Jos\u00e9 Antonio","family":"L\u00f3pez-Guerrero","sequence":"additional","affiliation":[{"name":"Molecular Biology Department, Instituto Valenciano de Oncolog\u00eda, 46009 Valencia, Spain"},{"name":"Department of Pathology, Catholic University of Valencia, 46001 Valencia, Spain"},{"name":"Joint Cancer Research Unit, Centro de Investigaci\u00f3n Pr\u00edncipe Felipe (CIPF), 46024 Valencia, Spain"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5016-5653","authenticated-orcid":false,"given":"Samuel","family":"Navarro","sequence":"additional","affiliation":[{"name":"Pathology Department, University of Valencia, 46010 Valencia, Spain"},{"name":"Pathology Department, Hospital Cl\u00ednic Universitari, 46010 Valencia, Spain"},{"name":"Centro de Investigaci\u00f3n Biom\u00e9dica en Red de C\u00e1ncer (CIBERONC), 28029 Madrid, Spain"},{"name":"Instituto de Investigaci\u00f3n Sanitaria, Instituto de Investigaci\u00f3n Sanitaria del Hospital Cl\u00ednico Universitario de Valencia (INCLIVA), 46010 Valencia, Spain"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Empar","family":"Mayordomo-Aranda","sequence":"additional","affiliation":[{"name":"Pathology Department, University of Valencia, 46010 Valencia, Spain"},{"name":"Pathology Department, Hospital Universitari i Polit\u00e8cnic La Fe, 46026 Valencia, Spain"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9205-103X","authenticated-orcid":false,"given":"Antonio","family":"Llombart-Bosch","sequence":"additional","affiliation":[{"name":"Pathology Department, University of Valencia, 46010 Valencia, Spain"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Valery","family":"Naranjo","sequence":"additional","affiliation":[{"name":"Instituto Universitario de Investigaci\u00f3n e Innovaci\u00f3n en Tecnolog\u00eda Centrada en el Ser Humano (HUMAN-Tech), Universitat Polit\u00e8cnica de Val\u00e8ncia (UPV), 46026 Valencia, Spain"},{"name":"Artikode Intelligence S.L., 46022 Valencia, Spain"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7318-1330","authenticated-orcid":false,"given":"Isidro","family":"Machado","sequence":"additional","affiliation":[{"name":"Pathology Department, University of Valencia, 46010 Valencia, Spain"},{"name":"Centro de Investigaci\u00f3n Biom\u00e9dica en Red de C\u00e1ncer (CIBERONC), 28029 Madrid, Spain"},{"name":"Instituto de Investigaci\u00f3n Sanitaria, Instituto de Investigaci\u00f3n Sanitaria del Hospital Cl\u00ednico Universitario de Valencia (INCLIVA), 46010 Valencia, Spain"},{"name":"Pathology Department, Instituto Valenciano de Oncolog\u00eda, 46009 Valencia, Spain"},{"name":"Patologika Laboratory Hospital Quir\u00f3nsalud, 46010 Valencia, Spain"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1968","published-online":{"date-parts":[[2026,7,31]]},"reference":[{"key":"ref_1","doi-asserted-by":"crossref","first-page":"5","DOI":"10.1038\/s41572-018-0003-x","article-title":"Ewing sarcoma","volume":"4","author":"CidreAranaz","year":"2018","journal-title":"Nat. Rev. Dis. Prim."},{"key":"ref_2","doi-asserted-by":"crossref","unstructured":"Ye, C., Dai, M., and Zhang, B. (2019). Risk Factors for Metastasis at Initial Diagnosis With Ewing Sarcoma. Front. Oncol., 9.","DOI":"10.3389\/fonc.2019.01043"},{"key":"ref_3","doi-asserted-by":"crossref","unstructured":"Z\u00f6llner, S.K., Amatruda, J.F., Bauer, S., Collaud, S., de \u00c1lava, E., DuBois, S.G., Hardes, J., Hartmann, W., Kovar, H., and Metzler, M. (2021). Ewing Sarcoma Diagnosis, Treatment, Clinical Challenges and Future Perspectives. J. Clin. Med., 10.","DOI":"10.3390\/jcm10081685"},{"key":"ref_4","doi-asserted-by":"crossref","first-page":"26","DOI":"10.1111\/his.12281","article-title":"Round cell sarcomas beyond Ewing: Emerging entities","volume":"64","author":"Antonescu","year":"2014","journal-title":"Histopathology"},{"key":"ref_5","doi-asserted-by":"crossref","first-page":"31","DOI":"10.1016\/j.path.2023.07.001","article-title":"Sarcomas with EWSR1::NonETS Fusion (EWSR1::NFATC2 and EWSR1::PATZ1)","volume":"17","author":"Machado","year":"2024","journal-title":"Surg. Pathol. Clin."},{"key":"ref_6","doi-asserted-by":"crossref","first-page":"100368","DOI":"10.1016\/j.jpi.2024.100368","article-title":"Utility of artificial intelligence in a binary classification of soft tissue tumors","volume":"15","author":"Di","year":"2024","journal-title":"J. Pathol. Inform."},{"key":"ref_7","doi-asserted-by":"crossref","first-page":"e7252","DOI":"10.1002\/cam4.7252","article-title":"Prediction of prognosis using artificial intelligencebased histopathological image analysis in patients with soft tissue sarcomas","volume":"13","author":"Hagi","year":"2024","journal-title":"Cancer Med."},{"key":"ref_8","doi-asserted-by":"crossref","first-page":"1193","DOI":"10.1038\/s41379-022-01075-x","article-title":"Machine learning for rhabdomyosarcoma histopathology","volume":"35","author":"Frankel","year":"2022","journal-title":"Mod. Pathol."},{"key":"ref_9","doi-asserted-by":"crossref","first-page":"365","DOI":"10.1158\/1078-0432.CCR-24-2599","article-title":"Quantitative and Morphology-Based Deep Convolutional Neural Network Approaches for Osteosarcoma Survival Prediction in the Neoadjuvant and Metastatic Settings","volume":"31","author":"Coudray","year":"2025","journal-title":"Clin. Cancer Res."},{"key":"ref_10","doi-asserted-by":"crossref","first-page":"38","DOI":"10.1055\/s-0039-3400266","article-title":"Pattern Recognition in Musculoskeletal Imaging Using Artificial Intelligence","volume":"24","author":"Gorelik","year":"2020","journal-title":"Semin. Musculoskelet. Radiol."},{"key":"ref_11","doi-asserted-by":"crossref","first-page":"567","DOI":"10.1016\/j.diii.2023.09.005","article-title":"Radiomics and artificial intelligence for softtissue sarcomas: Current status and perspectives","volume":"104","author":"Spinnato","year":"2023","journal-title":"Diagn. Interv. Imaging"},{"key":"ref_12","doi-asserted-by":"crossref","first-page":"75","DOI":"10.1016\/j.semcancer.2023.07.003","article-title":"Artificial intelligencebased radiomics in bone tumors: Technical advances and clinical application","volume":"95","author":"Meng","year":"2023","journal-title":"Semin. Cancer Biol."},{"key":"ref_13","doi-asserted-by":"crossref","first-page":"136","DOI":"10.1097\/PAP.0000000000000425","article-title":"Artificial IntelligenceEnabled Prostate Cancer Diagnosis and Prognosis: Current State and Future Implications","volume":"31","author":"Satturwar","year":"2024","journal-title":"Adv. Anat. Pathol."},{"key":"ref_14","doi-asserted-by":"crossref","first-page":"2307","DOI":"10.1038\/s41591-023-02504-3","article-title":"A visuallanguage foundation model for pathology image analysis using medical Twitter","volume":"29","author":"Huang","year":"2023","journal-title":"Nat. Med."},{"key":"ref_15","doi-asserted-by":"crossref","first-page":"213502","DOI":"10.1109\/ACCESS.2020.3040106","article-title":"Detection of breast cancer from whole slide histopathological images using deep multiple instance cnn","volume":"8","author":"Das","year":"2020","journal-title":"IEEE Access"},{"key":"ref_16","doi-asserted-by":"crossref","first-page":"3094","DOI":"10.1109\/JBHI.2021.3061457","article-title":"Selflearning for weakly supervised gleason grading of local patterns","volume":"8","author":"SilvaRodriguez","year":"2021","journal-title":"IEEE J. Biomed. Health Inform."},{"key":"ref_17","doi-asserted-by":"crossref","unstructured":"Zhao, Y., Yang, F., Fang, Y., Liu, H., Zhou, N., Zhang, J., Sun, J., Yang, S., Menze, B., and Fan, X. (2020, January 14\u201319). Predicting lymph node metastasis using histopathological images based on multiple instance learning with deep graph convolution. Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, Seattle, WA, USA.","DOI":"10.1109\/CVPR42600.2020.00489"},{"key":"ref_18","doi-asserted-by":"crossref","first-page":"854","DOI":"10.1109\/TMI.2019.2936244","article-title":"Classification of Volumetric Images Using MultiInstance Learning and Extreme Value Theorem","volume":"39","author":"Tennakoon","year":"2020","journal-title":"IEEE Trans. Med. Imaging"},{"key":"ref_19","unstructured":"Ilse, M., Tomczak, J.M., and Welling, M. (2018, January 10\u201315). Attentionbased deep multiple instance learning. Proceedings of the 35th International Conference on Machine Learning (ICML), Stockholm, Sweden."},{"key":"ref_20","first-page":"2136","article-title":"Transmil: Transformer based correlated multiple instance learning for whole slide image classification","volume":"34","author":"Shao","year":"2021","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"ref_21","doi-asserted-by":"crossref","first-page":"102197","DOI":"10.1016\/j.artmed.2021.102197","article-title":"An attentionbased weakly supervised framework for spitzoid melanocytic lesion diagnosis in whole slide images","volume":"121","author":"Launet","year":"2021","journal-title":"Artif. Intell. Med."},{"key":"ref_22","doi-asserted-by":"crossref","first-page":"102337","DOI":"10.1016\/j.compmedimag.2024.102337","article-title":"Multiple instance learning for digital pathology: A review of the stateoftheart, limitations & future potential","volume":"112","author":"Gadermayr","year":"2024","journal-title":"Comput. Med. Imaging Graph"},{"key":"ref_23","unstructured":"(2026, January 01). DeepAI Glossary. Multiple Instance Learning. Available online: https:\/\/deepai.tn\/glossary\/."},{"key":"ref_24","doi-asserted-by":"crossref","first-page":"1301","DOI":"10.1038\/s41591-019-0508-1","article-title":"Clinicalgrade computational pathology using weakly supervised deep learning on whole slide images","volume":"25","author":"Campanella","year":"2019","journal-title":"Nat. Med."},{"key":"ref_25","unstructured":"Jia, C., Yang, Y., Xia, Y., Chen, Y.T., Parekh, Z., Pham, H., Le, Q., Sung, Y.H., Li, Z., and Duerig, T. (2021). Scaling up Visual and Visionlanguage Representation Learning with Noisy Text Supervision in International Conference on Machine Learning, PMLR."},{"key":"ref_26","doi-asserted-by":"crossref","first-page":"863","DOI":"10.1038\/s41591-024-02856-4","article-title":"A visuallanguage foundation model for computational pathology","volume":"30","author":"Lu","year":"2024","journal-title":"Nat. Med."},{"key":"ref_27","doi-asserted-by":"crossref","first-page":"108491","DOI":"10.1016\/j.cmpb.2024.108491","article-title":"Positional encodingguided transformerbased multiple instance learning for histopathology whole slide images classification","volume":"258","author":"Shi","year":"2025","journal-title":"Comput. Methods Programs Biomed."},{"key":"ref_28","first-page":"2579","article-title":"Visualizing data using tSNE","volume":"9","author":"Maaten","year":"2008","journal-title":"J. Mach. Learn. Res."}],"container-title":["International Journal of Molecular Sciences"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/1422-0067\/27\/15\/6864\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,7,31]],"date-time":"2026-07-31T08:23:11Z","timestamp":1785486191000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/1422-0067\/27\/15\/6864"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,7,31]]},"references-count":28,"journal-issue":{"issue":"15","published-online":{"date-parts":[[2026,8]]}},"alternative-id":["ijms27156864"],"URL":"https:\/\/doi.org\/10.3390\/ijms27156864","relation":{},"ISSN":["1422-0067"],"issn-type":[{"value":"1422-0067","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,7,31]]}}}