{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,22]],"date-time":"2026-10-22T19:39:59Z","timestamp":1792697999490,"version":"4.5.0"},"reference-count":23,"publisher":"Springer Science and Business Media LLC","license":[{"start":{"date-parts":[[2026,10,22]],"date-time":"2026-10-22T00:00:00Z","timestamp":1792627200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"},{"start":{"date-parts":[[2026,10,22]],"date-time":"2026-10-22T00:00:00Z","timestamp":1792627200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["J Digit Imaging. Inform. med."],"abstract":"<jats:title>Abstract<\/jats:title>\n                  <jats:p>Spectral geometric methods provide mathematically interpretable representations of tissue morphology, yet their standalone performance in histopathology artificial intelligence has not been systematically evaluated. This study benchmarks purely spectral pipelines across representative digital pathology and spatial omics tasks relative to convolutional baselines. Spectral features derived from graph Laplacians, heat kernel signatures, spectral wavelet energy, Slepian concentrations, fractal descriptors, and persistent homology were extracted from histopathology patches using fixed-grid graphs. Features were processed using spectral neural operators and gradient boosting. Four tasks were evaluated: binary breast cancer classification (BreaKHis), multi-class glioblastoma region-patch classification, spatial transcriptomics prediction (10\u00d7 Visium), and spot-wise denoising. Cross-validation and leave-one-slide-out strategies were applied. Metrics included accuracy, sensitivity, specificity, area under the receiver operating characteristic curve (AUC), mean squared error, and Pearson correlation. Equivalence between spectral and CNN models was not established within the prespecified \u00b10.03 AUC margin. Purely spectral models achieved lower performance than convolutional baselines, with AUC differences of 0.12\u20130.23. The CNN\u2192LGBM model achieved an accuracy of 0.83 \u00b1 0.06, balanced accuracy of 0.73 \u00b1 0.10, and AUC of 0.80 \u00b1 0.13. Equivalence was not established within the prespecified margin. Fusion achieved balanced accuracy of 0.73 \u00b1 0.08, equal to the CNN baseline mean balanced accuracy, without surpassing CNN AUC. Spatial transcriptomics prediction showed limited cross-slide generalization (Pearson correlation 0.06), whereas spot-wise denoising under sparse conditions showed competitive performance. Spectral geometric models do not outperform convolutional methods for classification or segmentation but provide complementary utility in denoising and sparse spatial settings.<\/jats:p>","DOI":"10.1007\/s10278-026-02418-9","type":"journal-article","created":{"date-parts":[[2026,10,22]],"date-time":"2026-10-22T18:51:33Z","timestamp":1792695093000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Performance of Na\u00efve Spectral Geometric Models in Histopathology AI"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0009-0002-0731-9383","authenticated-orcid":false,"given":"Alejandro","family":"Leyva","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"M. Khalid Khan","family":"Niazi","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2026,10,22]]},"reference":[{"key":"2418_CR1","doi-asserted-by":"crossref","unstructured":"Belkin M, Niyogi P. Laplacian eigenmaps and spectral techniques for embedding and clustering. Neural Computation. 2003;15(6):1373\u20131396.","DOI":"10.1162\/089976603321780317"},{"key":"2418_CR2","doi-asserted-by":"crossref","unstructured":"Reuter M, Wolter F-E, Peinecke N. Laplace\u2013Beltrami spectra as Shape-DNA of surfaces and solids. Computer-Aided Design. 2006;38(4):342\u2013366.","DOI":"10.1016\/j.cad.2005.10.011"},{"key":"2418_CR3","doi-asserted-by":"crossref","unstructured":"\u00a0Gurcan MN, Boucheron LE, Can A, Madabhushi A, Rajpoot NM, Yener B. Histopathological image analysis: a review. IEEE Reviews in Biomedical Engineering. 2009;2:147\u2013171.","DOI":"10.1109\/RBME.2009.2034865"},{"key":"2418_CR4","doi-asserted-by":"crossref","unstructured":"Lu G, Fei B. Medical hyperspectral imaging: a review. Journal of Biomedical Optics. 2014;19(1):010901.","DOI":"10.1117\/1.JBO.19.1.010901"},{"issue":"5","key":"2418_CR5","first-page":"1260","volume":"30","author":"E Vorontsov","year":"2024","unstructured":"Vorontsov E, et al. Virchow: a foundation model for clinical-grade computational pathology. Nature Medicine. 2024;30(5):1260\u20131270.","journal-title":"Nature Medicine."},{"issue":"1","key":"2418_CR6","doi-asserted-by":"crossref","first-page":"46","DOI":"10.1186\/s13634-022-00877-0","volume":"2022","author":"Z Zhang","year":"2022","unstructured":"Zhang Z, Bourennane S, Fossati C. Hyperspectral image denoising and destriping based on mixed noise modeling. EURASIP Journal on Advances in Signal Processing. 2022;2022(1):46.","journal-title":"EURASIP Journal on Advances in Signal Processing."},{"key":"2418_CR7","doi-asserted-by":"crossref","first-page":"1915","DOI":"10.1016\/j.csbj.2020.07.006","volume":"18","author":"S Ortega","year":"2020","unstructured":"Ortega S, Fabelo H, Iakovidis DK, Koulaouzidis A, Callico GM. Hyperspectral and multispectral imaging in digital and computational pathology: A systematic review. Computer and Structural Biotechnology Journal. 2020;18:1915\u20131928.","journal-title":"Computer and Structural Biotechnology Journal."},{"key":"2418_CR8","volume":"111","author":"B Hu","year":"2019","unstructured":"Hu B, Sun D, Wang Y, Liu H, Ma P. Tumor tissue classification based on micro-hyperspectral imaging using convolutional neural networks. Computers in Biology and Medicine. 2019;111:103352.","journal-title":"Computers in Biology and Medicine."},{"key":"2418_CR9","doi-asserted-by":"publisher","unstructured":"Ortega, Samuel, et al. \u201cHyperspectral Imaging and Deep Learning for the Detection of Breast Cancer Cells in Digitized Histological Images.\u201d Proceedings of SPIE, 2020. https:\/\/doi.org\/10.1117\/12.2548","DOI":"10.1117\/12.2548"},{"key":"2418_CR10","unstructured":"L\u00e9vy B. Laplace\u2013Beltrami eigenfunctions toward an algorithm that understands geometry. Proceedings of Shape Modeling International. 2006."},{"issue":"5","key":"2418_CR11","doi-asserted-by":"publisher","first-page":"1383","DOI":"10.1111\/j.1467-8659.2009.01515.x","volume":"28","author":"J Sun","year":"2009","unstructured":"Sun J, Ovsjanikov M, Guibas L. A concise and provably informative multi-scale signature based on heat diffusion (HKS). Computer Graphics Forum. 2009;28(5):1383\u20131392.","journal-title":"Computer Graphics Forum."},{"issue":"4","key":"2418_CR12","doi-asserted-by":"publisher","first-page":"342","DOI":"10.1016\/j.cad.2005.10.011","volume":"38","author":"M Reuter","year":"2006","unstructured":"Reuter M, Wolter F-E, Peinecke N. Laplace\u2013Beltrami spectra as \u201cShape-DNA\u201d. Computer-Aided Design. 2006;38(4):342\u2013366.","journal-title":"Computer-Aided Design."},{"key":"2418_CR13","doi-asserted-by":"crossref","unstructured":"Reuter M. Discrete Laplace\u2013Beltrami operators for shape analysis and segmentation. Proceedings of Vision, Modeling, and Visualization (VMV). 2009.","DOI":"10.1016\/j.cag.2009.03.005"},{"key":"2418_CR14","unstructured":"Li Z, Kovachki N, Azizzadenesheli K, et al. Fourier Neural Operator for Parametric PDEs. arXiv preprint arXiv:2010.08895. 2020."},{"key":"2418_CR15","unstructured":"Fanaskov V, Oseledets I. Spectral Neural Operators. arXiv preprint arXiv:2205.10573. 2022. Wang X, Zhang M. How Powerful Are Spectral Graph Neural Networks? Proceedings of the 39th International Conference on Machine Learning (ICML). 2022."},{"key":"2418_CR16","doi-asserted-by":"publisher","DOI":"10.1016\/j.media.2024.103444","volume":"101","author":"S Brussee","year":"2025","unstructured":"Brussee S, Buzzanca G, Schrader AMR, Kers J (2025) Graph neural networks in histopathology: Emerging trends and future directions. Medical Image Analysis. 101:103444. https:\/\/doi.org\/10.1016\/j.media.2024.103444","journal-title":"Medical Image Analysis."},{"issue":"11","key":"2418_CR17","doi-asserted-by":"publisher","first-page":"3749","DOI":"10.1038\/s41591-025-03982-3","volume":"31","author":"T Ding","year":"2025","unstructured":"Ding T, Wagner SJ, Song AH, Chen RJ, Lu MY, Zhang A et al (2025) A multimodal whole-slide foundation model for pathology. Nature Medicine. 31(11):3749\u20133761. https:\/\/doi.org\/10.1038\/s41591-025-03982-3","journal-title":"Nature Medicine."},{"issue":"9","key":"2418_CR18","doi-asserted-by":"publisher","first-page":"1900","DOI":"10.1038\/s41592-025-02795-z","volume":"22","author":"X Fu","year":"2025","unstructured":"Fu X, Cao Y, Bian B, Wang C, Graham D, Pathmanathan N et al (2025) Spatial gene expression at single-cell resolution from histology using deep learning with GHIST. Nature Methods. 22(9):1900\u20131910. https:\/\/doi.org\/10.1038\/s41592-025-02795-z","journal-title":"Nature Methods."},{"key":"2418_CR19","doi-asserted-by":"publisher","unstructured":"Wu Y, Xie J, Nie J, Cao J, Zeng Y, Wang Z. DANet: Spatial gene expression prediction from H&E histology images through dynamic alignment. Briefings in Bioinformatics. 2025;26(4):bbaf422. https:\/\/doi.org\/10.1093\/bib\/bbaf422.","DOI":"10.1093\/bib\/bbaf422"},{"key":"2418_CR20","doi-asserted-by":"publisher","unstructured":"Caple, Jodi, et al. \u201cElliptical Fourier Analysis: Fundamentals, Applications, and Value for Forensic Anthropology.\u201d International Journal of Legal Medicine, vol. 131, no. 6, 2017, pp. 1675\u20131690. https:\/\/doi.org\/10.1007\/s00414-017-1555-0.","DOI":"10.1007\/s00414-017-1555-0"},{"issue":"3","key":"2418_CR21","first-page":"85","volume":"10","author":"V Vadori","year":"2024","unstructured":"Vadori V, et al. Automated classification of cell shapes: a comparative evaluation of shape descriptors. Journal of Imaging. 2024;10(3):85.","journal-title":"Journal of Imaging."},{"key":"2418_CR22","unstructured":"Ohio Supercomputer Center. Ascend Supercomputer. Columbus (OH): Ohio Supercomputer Center; 2022. Available from: http:\/\/osc.edu\/ark:\/19495\/hpc3ww9d"},{"key":"2418_CR23","doi-asserted-by":"crossref","unstructured":"Song et al., \u201cGene-DML: Dual-Pathway Multi-Level Discrimination for Gene Expression Prediction from Histopathology Images.\u201d WACV 2026 \/ arXiv:2507.14670","DOI":"10.1109\/WACV61042.2026.00494"}],"container-title":["Journal of Imaging Informatics in Medicine"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s10278-026-02418-9.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s10278-026-02418-9","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s10278-026-02418-9.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,10,22]],"date-time":"2026-10-22T18:51:40Z","timestamp":1792695100000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s10278-026-02418-9"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,10,22]]},"references-count":23,"alternative-id":["2418"],"URL":"https:\/\/doi.org\/10.1007\/s10278-026-02418-9","relation":{},"ISSN":["2948-2933"],"issn-type":[{"value":"2948-2933","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,10,22]]},"assertion":[{"value":"11 May 2026","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"5 October 2026","order":2,"name":"revised","label":"Revised","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"6 October 2026","order":3,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"22 October 2026","order":4,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"The authors declare no competing interests.","order":1,"name":"Ethics","label":"Competing interests","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"All datasets used in this study are publicly available and fully anonymized.","order":2,"name":"Ethics","label":"Ethics Approval","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"Not applicable; public, anonymized datasets were used.","order":3,"name":"Ethics","label":"Consent to Participate","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"All authors agree to publication in this journal.","order":4,"name":"Ethics","label":"Consent for Publication","group":{"name":"EthicsHeading","label":"Declarations"}}]}}