{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,26]],"date-time":"2026-06-26T12:51:16Z","timestamp":1782478276346,"version":"3.54.5"},"reference-count":26,"publisher":"Springer Science and Business Media LLC","issue":"1","license":[{"start":{"date-parts":[[2026,6,26]],"date-time":"2026-06-26T00:00:00Z","timestamp":1782432000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"},{"start":{"date-parts":[[2026,6,26]],"date-time":"2026-06-26T00:00:00Z","timestamp":1782432000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"}],"funder":[{"name":"Faculdade Israelita De Ci\u00eancias Da Sa\u00fade Albert Einstein"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Head and Neck Pathol"],"abstract":"<jats:title>Abstract<\/jats:title>\n                  <jats:sec>\n                    <jats:title>Background<\/jats:title>\n                    <jats:p>Peripheral nerve sheath tumors (PNSTs) of the head and neck (H&amp;N) show histopathological overlap. Although convolutional neural networks (CNNs) have demonstrated feasibility in soft tissue tumor classification, limited intra-class variability related to perineurioma remains a critical constraint for rare tumor subtypes.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Methods<\/jats:title>\n                    <jats:p>This retrospective diagnostic accuracy study with internal validation included 30 patients diagnosed with PNSTs. Whole-slide images were digitized at 20\u00d7 magnification and partitioned using a strict patient-wise split. Synthetic perineurioma patches were generated using a modified Pix2Pix-based Generative Adversarial Network (GAN) incorporating a bottleneck architecture and self-attention modules. Two morphology-driven augmentation strategies were evaluated: (1) intra-phenotypic expansion by cross-patient patch pairing within the sclerosing subtype and (2) inter-phenotypic interpolation by cross-phenotype patch pairing between sclerosing and intraneural variants. EfficientNetV2-B0 pre-trained on ImageNet was trained under three configurations: original dataset only, original\u2009+\u2009Experiment A synthetic patches, and original\u2009+\u2009Experiment B synthetic patches. All performance metrics were computed exclusively on an independent yet internal test set composed of original images.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Results<\/jats:title>\n                    <jats:p>GAN-based augmentation improved global classification performance compared with the baseline model trained on original images only (accuracy 0.733). Intra-phenotypic expansion increased accuracy to 0.767 and achieved the highest balanced accuracy (0.750) and macro-F1 (0.740). Inter-phenotypic interpolation yielded the highest overall accuracy and competitive multiclass agreement metrics. Perineurioma recall improved from 0.34 (baseline) to 0.51 with intra-phenotypic augmentation and 0.47 with inter-phenotypic interpolation, while specificity remained\u2009\u2265\u20090.999 across all strategies.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Conclusions<\/jats:title>\n                    <jats:p>Structured, pathology-informed GAN augmentation improved CNN classification of PNSTs, particularly for the morphologically heterogeneous perineurioma class. Intra-phenotypic expansion primarily improved rare-class sensitivity, whereas inter-phenotypic interpolation improved multiclass agreement and global robustness. These findings support morphology-driven synthetic enrichment as a clinically meaningful strategy to improve AI performance in underrepresented tumor entities and potentially support diagnostic decision-making in digital pathology environments.<\/jats:p>\n                  <\/jats:sec>","DOI":"10.1007\/s12105-026-01939-7","type":"journal-article","created":{"date-parts":[[2026,6,26]],"date-time":"2026-06-26T12:37:28Z","timestamp":1782477448000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Pathology-informed Generative Adversarial Network Augmentation Improves Classification of Peripheral Nerve Sheath Tumors by Modeling Morphological Variability: A Pilot Investigation"],"prefix":"10.1007","volume":"20","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-0895-7125","authenticated-orcid":false,"given":"Giovanna Calabrese dos","family":"Santos","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0006-8472-3047","authenticated-orcid":false,"given":"Hyago Vieira Lemes Barbosa","family":"Silva","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3725-8051","authenticated-orcid":false,"given":"Anna Lu\u00edza Damaceno","family":"Ara\u00fajo","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0004-1040-8058","authenticated-orcid":false,"given":"Tha\u00eds Cerqueira Reis","family":"Nakamura","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0007-8016-6551","authenticated-orcid":false,"given":"Micael Gil Scholl","family":"Santos","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2704-1908","authenticated-orcid":false,"given":"Anderson Faria","family":"Claret","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2167-7286","authenticated-orcid":false,"given":"Felipe Augusto Pereira","family":"de Figueiredo","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8890-8723","authenticated-orcid":false,"given":"Sebasti\u00e3o Silv\u00e9rio","family":"de Sousa-Neto","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7150-3025","authenticated-orcid":false,"given":"Daniela","family":"Giraldo-Rold\u00e1n","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0006-3668-6800","authenticated-orcid":false,"given":"Leonardo Marcello Rener","family":"de Freitas","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0481-156X","authenticated-orcid":false,"given":"Luiz Paulo","family":"Kowalski","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2040-6617","authenticated-orcid":false,"given":"Alan Roger","family":"Santos-Silva","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6677-0065","authenticated-orcid":false,"given":"Marcio Ajudarte","family":"Lopes","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1840-4911","authenticated-orcid":false,"given":"Pablo Agustin","family":"Vargas","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6019-6653","authenticated-orcid":false,"given":"Matheus Cardoso","family":"Moraes","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2026,6,26]]},"reference":[{"key":"1939_CR1","unstructured":"WHO Classification of Tumours Editorial Board Head and Neck Tumours [Internet]. 5th ed. WHO Classification of Tumours Editorial Board, editor. Lyon (France): International Agency for Research on Cancer; 2022 [cited 2025 Jun 18]. https:\/\/publications.iarc.fr\/. Accessed 18 Jun 2025"},{"key":"1939_CR2","doi-asserted-by":"publisher","first-page":"2","DOI":"10.1111\/his.12267","volume":"64","author":"CDM Fletcher","year":"2014","unstructured":"Fletcher CDM (2014) The evolving classification of soft tissue tumours \u2013 an update based on the new 2013\u2009<\u2009scp\u2009>\u2009WHO classification. Histopathology 64:2\u201311. https:\/\/doi.org\/10.1111\/his.12267","journal-title":"Histopathology"},{"key":"1939_CR3","doi-asserted-by":"publisher","first-page":"i40","DOI":"10.1093\/noajnl\/vdz047","volume":"2","author":"BC Prudner","year":"2020","unstructured":"Prudner BC, Ball T, Rathore R, Hirbe AC (2020) Diagnosis and management of malignant peripheral nerve sheath tumors: Current practice and future perspectives. Neurooncol Adv 2:i40\u2013i49. https:\/\/doi.org\/10.1093\/noajnl\/vdz047","journal-title":"Neurooncol Adv"},{"key":"1939_CR4","doi-asserted-by":"publisher","first-page":"253","DOI":"10.1016\/j.hoc.2021.08.010","volume":"36","author":"JT Jordan","year":"2022","unstructured":"Jordan JT, Plotkin SR (2022) Neurofibromatoses. Hematol Oncol Clin North Am 36:253\u2013267. https:\/\/doi.org\/10.1016\/j.hoc.2021.08.010","journal-title":"Hematol Oncol Clin North Am"},{"key":"1939_CR5","doi-asserted-by":"publisher","first-page":"781","DOI":"10.1097\/PAI.0000000000000960","volume":"29","author":"ALD de Ara\u00fajo","year":"2021","unstructured":"Ara\u00fajo ALD, Fons\u00eaca JM, do, Amaral-Silva GK, de Lima Morais TM, Mariz BALA, Fonseca FP et al (2021) The Role of Immunohistochemistry for Primary Oral Diagnosis in a Brazilian Oral Pathology Service. Appl Immunohistochem Mol Morphology 29:781\u2013790. https:\/\/doi.org\/10.1097\/PAI.0000000000000960","journal-title":"Appl Immunohistochem Mol Morphology"},{"key":"1939_CR6","doi-asserted-by":"publisher","first-page":"1153","DOI":"10.1109\/TMI.2016.2553401","volume":"35","author":"H Greenspan","year":"2016","unstructured":"Greenspan H, van Ginneken B, Summers RM (2016) Guest Editorial Deep Learning in Medical Imaging: Overview and Future Promise of an Exciting New Technique. IEEE Trans Med Imaging 35:1153\u20131159. https:\/\/doi.org\/10.1109\/TMI.2016.2553401","journal-title":"IEEE Trans Med Imaging"},{"key":"1939_CR7","doi-asserted-by":"publisher","first-page":"351","DOI":"10.1007\/s11036-020-01672-7","volume":"26","author":"J Wang","year":"2021","unstructured":"Wang J, Zhu H, Wang S-H, Zhang Y-DA (2021) Review of deep learning on medical image analysis. Mob Networks Appl 26:351\u2013380. https:\/\/doi.org\/10.1007\/s11036-020-01672-7","journal-title":"Mob Networks Appl"},{"key":"1939_CR8","doi-asserted-by":"publisher","first-page":"2039","DOI":"10.3390\/cancers16112039","volume":"16","author":"CYMN Jansma","year":"2024","unstructured":"Jansma CYMN, Wan X, Acem I, Spaanderman DJ, Visser JJ, Hanff D et al (2024) Preoperative Classification of Peripheral Nerve Sheath Tumors on MRI Using Radiomics. Cancers (Basel) 16:2039. https:\/\/doi.org\/10.3390\/cancers16112039","journal-title":"Cancers (Basel)"},{"key":"1939_CR9","doi-asserted-by":"publisher","first-page":"444","DOI":"10.1111\/jop.13560","volume":"53","author":"GC dos Santos","year":"2024","unstructured":"dos Santos GC, Ara\u00fajo ALD, de Amorim HA, Giraldo-Rold\u00e1n D, de Sousa-Neto SS, Vargas PA et al (2024) Feasibility study of ResNet-50 in the distinction of intraoral neural tumors using histopathological images. J Oral Pathol Med John Wiley Sons Inc 53:444\u2013450. https:\/\/doi.org\/10.1111\/jop.13560","journal-title":"J Oral Pathol Med John Wiley Sons Inc"},{"key":"1939_CR10","doi-asserted-by":"publisher","unstructured":"Cruz-Roa AA, Arevalo Ovalle JE, Madabhushi A, Gonz\u00e1lez Osorio FA (2013) A deep learning architecture for image representation, visual interpretability and automated basal-cell carcinoma cancer detection. https:\/\/doi.org\/10.1007\/978-3-642-40763-5_50","DOI":"10.1007\/978-3-642-40763-5_50"},{"key":"1939_CR11","doi-asserted-by":"publisher","first-page":"2450","DOI":"10.3390\/rs13132450","volume":"13","author":"AE Maxwell","year":"2021","unstructured":"Maxwell AE, Warner TA, Guill\u00e9n LA (2021) Accuracy assessment in convolutional neural network-based deep learning remote sensing studies\u2014Part 1: literature review. Remote Sens 13:2450. https:\/\/doi.org\/10.3390\/rs13132450","journal-title":"Remote Sens"},{"key":"1939_CR12","doi-asserted-by":"publisher","first-page":"1785","DOI":"10.3390\/diagnostics13101785","volume":"13","author":"HH Al-nakhle","year":"2023","unstructured":"Al-nakhle HH, Khateb AM (2023) Comprehensive In Silico characterization of the coding and non-coding snps in human dectin-1 gene with the potential of high-risk pathogenicity associated with fungal infections. Diagnostics 13:1785. https:\/\/doi.org\/10.3390\/diagnostics13101785","journal-title":"Diagnostics"},{"key":"1939_CR13","doi-asserted-by":"publisher","first-page":"231","DOI":"10.1038\/s41597-023-02125-y","volume":"10","author":"K Ding","year":"2023","unstructured":"Ding K, Zhou M, Wang H, Gevaert O, Metaxas D, Zhang S (2023) A large-scale synthetic pathological dataset for deep learning-enabled segmentation of breast cancer. Sci Data 10:231. https:\/\/doi.org\/10.1038\/s41597-023-02125-y","journal-title":"Sci Data"},{"issue":"12","key":"1939_CR14","doi-asserted-by":"publisher","first-page":"3777","DOI":"10.3390\/s24123777","volume":"24","author":"JL Ruiz-Casado","year":"2024","unstructured":"Ruiz-Casado JL, Molina-Cabello MA, Luque-Baena RM (2024) Enhancing histopathological image classification performance through synthetic data generation with generative adversarial networks. Sensors 24(12):3777. https:\/\/doi.org\/10.3390\/s24123777","journal-title":"Sensors"},{"key":"1939_CR15","doi-asserted-by":"publisher","first-page":"101816","DOI":"10.1016\/j.media.2020.101816","volume":"67","author":"Y Xue","year":"2021","unstructured":"Xue Y, Ye J, Zhou Q, Long LR, Antani S, Xue Z et al (2021) Selective synthetic augmentation with HistoGAN for improved histopathology image classification. Med Image Anal 67:101816. https:\/\/doi.org\/10.1016\/j.media.2020.101816","journal-title":"Med Image Anal"},{"key":"1939_CR16","doi-asserted-by":"publisher","first-page":"43","DOI":"10.4103\/jpi.jpi_103_20","volume":"12","author":"L Jose","year":"2021","unstructured":"Jose L, Liu S, Russo C, Nadort A, Di Ieva A (2021) Generative adversarial networks in digital pathology and histopathological image processing: a review. J Pathol Inf 12:43. https:\/\/doi.org\/10.4103\/jpi.jpi_103_20","journal-title":"J Pathol Inf"},{"key":"1939_CR17","doi-asserted-by":"publisher","first-page":"1185","DOI":"10.1007\/s11831-024-10174-8","volume":"32","author":"M Ali","year":"2025","unstructured":"Ali M, Ali M, Hussain M, Koundal D (2025) Generative adversarial networks (gans) for medical image processing: recent advancements. Arch Comput Methods Eng 32:1185\u20131198. https:\/\/doi.org\/10.1007\/s11831-024-10174-8","journal-title":"Arch Comput Methods Eng"},{"key":"1939_CR18","doi-asserted-by":"publisher","first-page":"321","DOI":"10.1016\/j.neucom.2018.09.013","volume":"321","author":"M Frid-Adar","year":"2018","unstructured":"Frid-Adar M, Diamant I, Klang E, Amitai M, Goldberger J, Greenspan H (2018) GAN-based synthetic medical image augmentation for increased CNN performance in liver lesion classification. Neurocomputing 321:321\u2013331. https:\/\/doi.org\/10.1016\/j.neucom.2018.09.013","journal-title":"Neurocomputing"},{"key":"1939_CR19","unstructured":"Tan M, Le QV (2021) EfficientNetV2: Smaller Models and Faster Training"},{"key":"1939_CR20","doi-asserted-by":"crossref","unstructured":"Isola P, Zhu J-Y, Zhou T, Efros AA (2018) Image-to-Image Translation with Conditional Adversarial Networks","DOI":"10.1109\/CVPR.2017.632"},{"key":"1939_CR21","unstructured":"Zhang H, Goodfellow I, Metaxas D, Odena A (2019) Self-attention generative adversarial networks"},{"key":"1939_CR22","doi-asserted-by":"publisher","DOI":"10.5555\/1390681.1390684","author":"L Van Der Maaten","year":"2008","unstructured":"Van Der Maaten L, Hinton G (2008) Visualizing Data using t-SNE. J Mach Learn Res [Internet]. [cited 2026 Apr 7];2579\u2013605 https:\/\/doi.org\/10.5555\/1390681.1390684","journal-title":"J Mach Learn Res [Internet]"},{"key":"1939_CR23","doi-asserted-by":"publisher","unstructured":"Deng J, Dong W, Socher R, Li L-J, Li K (2009) Li Fei-Fei. ImageNet: a large-scale hierarchical image database. 2009 ieee conference on computer vision and pattern recognition. IEEE; pp. 248\u201355. https:\/\/doi.org\/10.1109\/CVPR.2009.5206848","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"1939_CR24","doi-asserted-by":"publisher","first-page":"79","DOI":"10.1016\/j.oooo.2025.01.004","volume":"140","author":"ALD Ara\u00fajo","year":"2025","unstructured":"Ara\u00fajo ALD, Sperandio M, Calabrese G, Faria SS, Cardenas DAC, Martins MD et al (2025) Artificial intelligence in healthcare applications targeting cancer diagnosis\u2014part I: data structure, preprocessing and data organization. Oral Surg Oral Med Oral Pathol Oral Radiol [Internet] 140:79\u201388. https:\/\/doi.org\/10.1016\/j.oooo.2025.01.004","journal-title":"Oral Surg Oral Med Oral Pathol Oral Radiol [Internet]"},{"key":"1939_CR25","doi-asserted-by":"publisher","first-page":"89","DOI":"10.1016\/j.oooo.2025.01.002","volume":"140","author":"ALD Ara\u00fajo","year":"2025","unstructured":"Ara\u00fajo ALD, Sperandio M, Calabrese G, Faria SS, Cardenas DAC, Martins MD et al (2025) Artificial intelligence in healthcare applications targeting cancer diagnosis\u2014part II: interpreting the model outputs and spotlighting the performance metrics. Oral Surg Oral Med Oral Pathol Oral Radiol [Internet] 140:89\u201399. https:\/\/doi.org\/10.1016\/j.oooo.2025.01.002","journal-title":"Oral Surg Oral Med Oral Pathol Oral Radiol [Internet]"},{"key":"1939_CR26","doi-asserted-by":"publisher","first-page":"442","DOI":"10.1016\/0005-2795(75)90109-9","volume":"405","author":"BW Matthews","year":"1975","unstructured":"Matthews BW (1975) Comparison of the predicted and observed secondary structure of T4 phage lysozyme. Biochimica et Biophysica Acta (BBA) - Protein Structure. 405:442\u2013451. https:\/\/doi.org\/10.1016\/0005-2795(75)90109-9","journal-title":"Biochimica et Biophysica Acta (BBA) - Protein Struct"}],"container-title":["Head and Neck Pathology"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s12105-026-01939-7.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s12105-026-01939-7","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s12105-026-01939-7.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,6,26]],"date-time":"2026-06-26T12:37:34Z","timestamp":1782477454000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s12105-026-01939-7"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,6,26]]},"references-count":26,"journal-issue":{"issue":"1","published-online":{"date-parts":[[2026,12]]}},"alternative-id":["1939"],"URL":"https:\/\/doi.org\/10.1007\/s12105-026-01939-7","relation":{},"ISSN":["1936-0568"],"issn-type":[{"value":"1936-0568","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,6,26]]},"assertion":[{"value":"3 May 2026","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"9 June 2026","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"26 June 2026","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"All authors declare that they have no conflicts of interest.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Conflict of interest"}},{"value":"This study was performed in accordance with the Declaration of Helsinki and was approved on November 14, 2023, by the Faculdade de Odontologia de Piracicaba Ethical Committee (Registration number: 70281123.8.0000.5418), which also comprised Material Transfer Agreements between co-participant Institutions to share digital slides.","order":3,"name":"Ethics","group":{"name":"EthicsHeading","label":"Ethics Approval"}},{"value":"Due to the retrospective nature of the study, the free and informed consent form was waived for carrying out the study.","order":4,"name":"Ethics","group":{"name":"EthicsHeading","label":"Informed Consent"}},{"value":"For this type of study consent for publication is not required.","order":5,"name":"Ethics","group":{"name":"EthicsHeading","label":"Consent for Publication"}},{"value":"During the preparation of this work the authors used ChatGPT (Mar 14 version) from OpenAI (https:\/\/chat.openai.com\/chat) to specifically review grammar and spelling. After utilizing this tool\/service, the authors thoroughly reviewed and edited the content as necessary. The authors assume full responsibility for the content of the publication. No large language models\/tools\/ service were used to analyze and draw insights from data as part of the research process.","order":6,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declaration of Generative AI and AI-assisted technologies in the writing process"}}],"article-number":"75"}}