{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,2]],"date-time":"2026-01-02T09:36:13Z","timestamp":1767346573718,"version":"3.48.0"},"reference-count":45,"publisher":"MDPI AG","issue":"1","license":[{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Diagnostics"],"abstract":"<jats:p>Background\/Objectives: Glioblastoma (GBM) exhibits heterogeneous, nonlinear invasion patterns that challenge conventional modeling and radiomic prediction. Most deep learning approaches describe the morphology but rarely capture the dynamical stability of tumor evolution. We propose an AI framework that approximates a latent attractor landscape of GBM morphodynamics\u2014stable basins in a continuous manifold that are consistent with reproducible morphologic regimes. Methods: Multimodal MRI scans from BraTS 2020 (n = 494) were standardized and embedded with a 3D autoencoder to obtain 128-D latent representations. Unsupervised clustering identified latent basins (\u201cattractors\u201d). A neural ordinary differential equation (neural-ODE) approximated latent dynamics. All dynamics were inferred from cross-sectional population variability rather than longitudinal follow-up, serving as a proof-of-concept approximation of morphologic continuity. Voxel-level perturbation quantified local morphodynamic sensitivity, and proof-of-concept control was explored by adding small inputs to the neural-ODE using both a deterministic controller and a reinforcement learning agent based on soft actor\u2013critic (SAC). Survival analyses (Kaplan\u2013Meier, log-rank, ridge-regularized Cox) assessed associations with outcomes. Results: The learned latent manifold was smooth and clinically organized. Three dominant attractor basins were identified with significant survival stratification (\u03c72 = 31.8, p = 1.3 \u00d7 10\u22127) in the static model. Dynamic attractor basins derived from neural-ODE endpoints showed modest and non-significant survival differences, confirming that these dynamic labels primarily encode the morphodynamic structure rather than fixed prognostic strata. Dynamic basins inferred from neural-ODE flows were not independently prognostic, indicating that the inferred morphodynamic field captures geometric organization rather than additional clinical risk information. The latent stability index showed a weak but borderline significant negative association with survival (\u03c1 = \u22120.13 [\u22120.26, \u22120.01]; p = 0.0499). In multivariable Cox models, age remained the dominant covariate (HR = 1.30 [1.16\u20131.45]; p = 5 \u00d7 10\u22126), with overall C-indices of 0.61\u20130.64. Voxel-level sensitivity maps highlighted enhancing rims and peri-necrotic interfaces as influential regions. In simulation, deterministic control redirected trajectories toward lower-risk basins (\u224857% success; \u224896% terminal distance reduction), while a soft actor\u2013critic (SAC) agent produced smoother trajectories and modest additional reductions in terminal distance, albeit without matching the deterministic controller\u2019s success rate. The learned attractor classes were internally consistent and clinically distinct. Conclusions: Learning a latent attractor landscape links generative AI, dynamical systems theory, and clinical outcomes in GBM. Although limited by the cross-sectional nature of BraTS and modest prognostic gains beyond age, these results provide a mechanistic, controllable framework for tumor morphology in which inferred dynamic attractor-like flows describe latent organization rather than a clinically predictive temporal model, motivating prospective radiogenomic validation and adaptive therapy studies.<\/jats:p>","DOI":"10.3390\/diagnostics16010139","type":"journal-article","created":{"date-parts":[[2026,1,2]],"date-time":"2026-01-02T09:18:56Z","timestamp":1767345536000},"page":"139","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["AI-Guided Inference of Morphodynamic Attractor-like States in Glioblastoma"],"prefix":"10.3390","volume":"16","author":[{"given":"Simona Ruxandra","family":"Volov\u0103\u021b","sequence":"first","affiliation":[{"name":"Department of Oncology-Radiotherapy, University of Medicine and Pharmacy \u201cGrigore T. Popa\u201d Ia\u0219i, 700115 Ia\u0219i, Romania"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0007-7650-7798","authenticated-orcid":false,"given":"Diana Ioana","family":"Panaite","sequence":"additional","affiliation":[{"name":"Department of Oncology-Radiotherapy, University of Medicine and Pharmacy \u201cGrigore T. Popa\u201d Ia\u0219i, 700115 Ia\u0219i, Romania"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"M\u0103d\u0103lina Raluca","family":"Ostafe","sequence":"additional","affiliation":[{"name":"Department of Oncology-Radiotherapy, University of Medicine and Pharmacy \u201cGrigore T. Popa\u201d Ia\u0219i, 700115 Ia\u0219i, Romania"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2791-3400","authenticated-orcid":false,"given":"C\u0103lin Gheorghe","family":"Buzea","sequence":"additional","affiliation":[{"name":"National Institute of Research and Development for Technical Physics, IFT Ia\u0219i, 700050 Ia\u0219i, Romania"},{"name":"Clinical Emergency Hospital \u201cProf. Dr. Nicolae Oblu\u201d Ia\u0219i, 700309 Ia\u0219i, Romania"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Drago\u0219 Teodor","family":"Iancu","sequence":"additional","affiliation":[{"name":"Regional Institute of Oncology, IRO Ia\u0219i, 700483 Ia\u0219i, Romania"},{"name":"Faculty of Medicine, University of Medicine and Pharmacy \u201cGrigore T. Popa\u201d Ia\u0219i, 700115 Ia\u0219i, Romania"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Maricel","family":"Agop","sequence":"additional","affiliation":[{"name":"Department of Environmental Engineering, Mechanical Engineering and Agritourism, Faculty of Engineering, \u201cVasile Alecsandri\u201d University of Bac\u0103u, 600115 Bac\u0103u, Romania"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6447-0958","authenticated-orcid":false,"given":"L\u0103cr\u0103mioara","family":"Ochiuz","sequence":"additional","affiliation":[{"name":"Faculty of Medicine, University of Medicine and Pharmacy \u201cGrigore T. Popa\u201d Ia\u0219i, 700115 Ia\u0219i, Romania"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5485-0620","authenticated-orcid":false,"given":"Drago\u0219 Ioan","family":"Rusu","sequence":"additional","affiliation":[{"name":"Department of Environmental Engineering, Mechanical Engineering and Agritourism, Faculty of Engineering, \u201cVasile Alecsandri\u201d University of Bac\u0103u, 600115 Bac\u0103u, Romania"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Cristian Constantin","family":"Volov\u0103\u021b","sequence":"additional","affiliation":[{"name":"Department of Radiology, University of Medicine and Pharmacy \u201cGrigore T. Popa\u201d Ia\u0219i, 700115 Ia\u0219i, Romania"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"1968","published-online":{"date-parts":[[2026,1,1]]},"reference":[{"key":"ref_1","doi-asserted-by":"crossref","first-page":"987","DOI":"10.1056\/NEJMoa043330","article-title":"Radiotherapy plus concomitant and adjuvant temozolomide for glioblastoma","volume":"352","author":"Stupp","year":"2005","journal-title":"N. Engl. J. Med."},{"key":"ref_2","doi-asserted-by":"crossref","first-page":"vi1","DOI":"10.1093\/neuonc\/noae145","article-title":"CBTRUS statistical report: Primary brain and other central nervous system tumors diagnosed in the United States in 2017\u20132021","volume":"26","author":"Price","year":"2024","journal-title":"Neuro-Oncol"},{"key":"ref_3","doi-asserted-by":"crossref","first-page":"4006","DOI":"10.1038\/ncomms5006","article-title":"Decoding tumour phenotype by noninvasive imaging using a quantitative radiomics approach","volume":"5","author":"Aerts","year":"2014","journal-title":"Nat. Commun."},{"key":"ref_4","doi-asserted-by":"crossref","first-page":"880","DOI":"10.1148\/radiol.2016160845","article-title":"Radiomic profiling of glioblastoma: Identifying an imaging predictor of patient survival with improved performance over established clinical and radiologic risk models","volume":"280","author":"Kickingereder","year":"2016","journal-title":"Radiology"},{"key":"ref_5","doi-asserted-by":"crossref","first-page":"10353","DOI":"10.1038\/s41598-017-10649-8","article-title":"A deep learning\u2013based radiomics model for prediction of survival in glioblastoma multiforme","volume":"7","author":"Lao","year":"2017","journal-title":"Sci. Rep."},{"key":"ref_6","doi-asserted-by":"crossref","first-page":"166","DOI":"10.1016\/j.radonc.2019.06.031","article-title":"Deep learning derived tumor infiltration maps for personalized target definition in glioblastoma radiotherapy","volume":"138","author":"Peeken","year":"2019","journal-title":"Radiother. Oncol."},{"key":"ref_7","unstructured":"Bakas, S., Reyes, M., Jakab, A., Bauer, S., Rempfler, M., Crimi, A., Shinohara, R.T., Berger, C., Ha, S.M., and Rozycki, M. (2018). Identifying the best machine learning algorithms for brain tumor segmentation, progression assessment, and overall survival prediction in the BraTS challenge. arXiv."},{"key":"ref_8","doi-asserted-by":"crossref","first-page":"98","DOI":"10.1016\/j.media.2017.10.002","article-title":"A deep learning model integrating FCNNs and CRFs for brain tumor segmentation","volume":"43","author":"Zhao","year":"2018","journal-title":"Med. Image Anal."},{"key":"ref_9","doi-asserted-by":"crossref","first-page":"203","DOI":"10.1038\/s41592-020-01008-z","article-title":"nnU-Net: A self-configuring method for deep learning\u2013based biomedical image segmentation","volume":"18","author":"Isensee","year":"2021","journal-title":"Nat. Methods"},{"key":"ref_10","first-page":"6840","article-title":"Denoising diffusion probabilistic models","volume":"33","author":"Ho","year":"2020","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"ref_11","doi-asserted-by":"crossref","unstructured":"Kazerouni, A., Khodapanah Aghdam, E., Heidari, M., Azad, R., Fayyaz, M., Hacihaliloglu, I., and Merhof, D. (2022). Diffusion models for medical image analysis: A comprehensive survey. arXiv.","DOI":"10.1016\/j.media.2023.102846"},{"key":"ref_12","unstructured":"Kingma, D.P., and Welling, M. (2013). Auto-encoding variational Bayes. arXiv."},{"key":"ref_13","unstructured":"Higgins, I., Matthey, L., Pal, A., Burgess, C.P., Glorot, X., Botvinick, M., Mohamed, S., and Lerchner, A. (2017, January 24\u201326). beta-VAE: Learning Basic Visual Concepts with a Constrained Variational Framework. Proceedings of the International Conference on Learning Representations, Toulon, France. Available online: https:\/\/openreview.net\/forum?id=Sy2fzU9gl."},{"key":"ref_14","doi-asserted-by":"crossref","unstructured":"Selvaraju, R.R., Cogswell, M., Das, A., Vedantam, R., Parikh, D., and Batra, D. (2017, January 22\u201329). Grad-CAM: Visual explanations from deep networks via gradient-based localization. Proceedings of the IEEE International Conference on Computer Vision (ICCV), Venice, Italy.","DOI":"10.1109\/ICCV.2017.74"},{"key":"ref_15","unstructured":"Simonyan, K., Vedaldi, A., and Zisserman, A. (2014). Deep inside convolutional networks: Visualising image classification models and saliency maps. arXiv."},{"key":"ref_16","doi-asserted-by":"crossref","first-page":"102141","DOI":"10.1016\/j.media.2021.102141","article-title":"Adversarial attack vulnerability of medical image analysis systems: Unexplored factors","volume":"73","author":"Bortsova","year":"2021","journal-title":"Med. Image Anal."},{"key":"ref_17","doi-asserted-by":"crossref","first-page":"546","DOI":"10.1002\/bies.200800189","article-title":"Reprogramming cell fates: Reconciling rarity with robustness","volume":"31","author":"Huang","year":"2009","journal-title":"BioEssays"},{"key":"ref_18","doi-asserted-by":"crossref","first-page":"3539","DOI":"10.1098\/rsif.2012.0434","article-title":"Quasi-potential landscape in complex multi-stable systems","volume":"9","author":"Zhou","year":"2012","journal-title":"J. R. Soc. Interface"},{"key":"ref_19","doi-asserted-by":"crossref","unstructured":"Kauffman, S.A. (1993). The Origins of Order: Self-Organization and Selection in Evolution, Oxford University Press.","DOI":"10.1093\/oso\/9780195079517.001.0001"},{"key":"ref_20","doi-asserted-by":"crossref","first-page":"183","DOI":"10.1016\/j.semcancer.2011.05.003","article-title":"On the intrinsic inevitability of cancer: From foetal to fatal attraction","volume":"21","author":"Huang","year":"2011","journal-title":"Semin. Cancer Biol."},{"key":"ref_21","doi-asserted-by":"crossref","first-page":"58","DOI":"10.1038\/s41540-023-00317-1","article-title":"Explainable deep learning for tumor dynamic modeling and overall survival prediction using Neural-ODE","volume":"9","author":"Laurie","year":"2023","journal-title":"npj Syst. Biol. Appl."},{"key":"ref_22","unstructured":"Bazgir, O., Wang, Z., Park, J.W., Hafner, M., and Lu, J. (2024). Integration of Graph Neural Network and Neural-ODEs for tumor dynamics prediction. arXiv."},{"key":"ref_23","doi-asserted-by":"crossref","first-page":"105376","DOI":"10.1016\/j.biosystems.2024.105376","article-title":"Understanding cancer from a biophysical, developmental and systems biology perspective using the landscapes-attractor model","volume":"247","author":"Grunt","year":"2025","journal-title":"BioSystems"},{"key":"ref_24","doi-asserted-by":"crossref","unstructured":"Strogatz, S.H. (2018). Nonlinear Dynamics and Chaos: With Applications to Physics, Biology, Chemistry, and Engineering, CRC Press.","DOI":"10.1201\/9780429399640"},{"key":"ref_25","doi-asserted-by":"crossref","unstructured":"Hirsch, M.W., Smale, S., and Devaney, R.L. (2012). Differential Equations, Dynamical Systems, and an Introduction to Chaos, Academic Press. [3rd ed.].","DOI":"10.1016\/B978-0-12-382010-5.00015-4"},{"key":"ref_26","doi-asserted-by":"crossref","first-page":"469","DOI":"10.1007\/s001099900023","article-title":"Gene expression profiling, genetic networks, and cellular states: An integrating concept for tumorigenesis and drug discovery","volume":"77","author":"Huang","year":"1999","journal-title":"J. Mol. Med."},{"key":"ref_27","doi-asserted-by":"crossref","first-page":"128701","DOI":"10.1103\/PhysRevLett.94.128701","article-title":"Cell fates as high-dimensional attractor states of gene regulatory networks","volume":"94","author":"Huang","year":"2005","journal-title":"Phys. Rev. Lett."},{"key":"ref_28","doi-asserted-by":"crossref","first-page":"8257","DOI":"10.1073\/pnas.1017017108","article-title":"Quantifying the Waddington landscape and biological paths for development and differentiation","volume":"108","author":"Wang","year":"2011","journal-title":"Proc. Natl. Acad. Sci. USA"},{"key":"ref_29","doi-asserted-by":"crossref","first-page":"104179","DOI":"10.1016\/j.isci.2022.104179","article-title":"Algorithmic reconstruction of glioblastoma network complexity","volume":"25","author":"Uthamacumaran","year":"2022","journal-title":"iScience"},{"key":"ref_30","doi-asserted-by":"crossref","first-page":"110971","DOI":"10.1016\/j.compbiomed.2025.110971","article-title":"Deep learning-based feature discovery for decoding phenotypic plasticity in pediatric high-grade gliomas single-cell transcriptomics","volume":"197","author":"Uthamacumaran","year":"2025","journal-title":"Comput. Biol. Med."},{"key":"ref_31","doi-asserted-by":"crossref","first-page":"015001","DOI":"10.1088\/1478-3975\/8\/1\/015001","article-title":"Cancer tumors as Metazoa 1.0: Tapping genes of ancient ancestors","volume":"8","author":"Davies","year":"2011","journal-title":"Phys. Biol."},{"key":"ref_32","doi-asserted-by":"crossref","unstructured":"Lopes, F., Pires, B.R.B., Lima, A.A.B., Binato, R., and Abdelhay, E. (2024). NF-\u03baB epigenetic attractor landscape drives breast cancer heterogeneity. bioRxiv.","DOI":"10.1101\/2024.07.10.602798"},{"key":"ref_33","doi-asserted-by":"crossref","first-page":"31","DOI":"10.1038\/s41540-025-00512-2","article-title":"Modeling the dynamics of EMT reveals genes associated with pan-cancer intermediate states and plasticity","volume":"11","author":"McDermott","year":"2025","journal-title":"NPJ Syst. Biol. Appl."},{"key":"ref_34","doi-asserted-by":"crossref","first-page":"1993","DOI":"10.1109\/TMI.2014.2377694","article-title":"The multimodal brain tumor image segmentation benchmark (BRATS)","volume":"34","author":"Menze","year":"2015","journal-title":"IEEE Trans. Med. Imaging"},{"key":"ref_35","doi-asserted-by":"crossref","first-page":"170117","DOI":"10.1038\/sdata.2017.117","article-title":"Advancing The Cancer Genome Atlas glioma MRI collections with expert segmentation labels and radiomic features","volume":"4","author":"Bakas","year":"2017","journal-title":"Nat. Sci. Data"},{"key":"ref_36","doi-asserted-by":"crossref","first-page":"2247","DOI":"10.1098\/rstb.2011.0008","article-title":"Systems biology of stem cells: Three useful perspectives to help overcome the paradigm of linear pathways","volume":"366","author":"Huang","year":"2011","journal-title":"Philos. Trans. R. Soc. Lond. B Biol. Sci."},{"key":"ref_37","doi-asserted-by":"crossref","first-page":"869","DOI":"10.1016\/j.semcdb.2009.07.003","article-title":"Cancer attractors: A systems view of tumors from a gene network dynamics perspective","volume":"20","author":"Huang","year":"2009","journal-title":"Semin. Cell Dev. Biol."},{"key":"ref_38","doi-asserted-by":"crossref","first-page":"85","DOI":"10.1038\/s41540-025-00565-3","article-title":"Dynamical systems theory as an organizing principle for single-cell biology","volume":"11","author":"Islam","year":"2025","journal-title":"npj Syst. Biol. Appl."},{"key":"ref_39","doi-asserted-by":"crossref","first-page":"147","DOI":"10.1016\/j.trecan.2023.10.006","article-title":"Big data and artificial intelligence in cancer research","volume":"10","author":"Wu","year":"2024","journal-title":"Trends Cancer"},{"key":"ref_40","doi-asserted-by":"crossref","first-page":"7366","DOI":"10.1158\/0008-5472.CAN-11-1399","article-title":"Quantifying the role of angiogenesis in malignant progression of gliomas: In silico modeling integrates imaging and histology","volume":"71","author":"Swanson","year":"2011","journal-title":"Cancer Res."},{"key":"ref_41","doi-asserted-by":"crossref","first-page":"907","DOI":"10.1148\/radiol.2016161382","article-title":"Radiogenomics of Glioblastoma: Machine Learning-based Classification of Molecular Characteristics by Using Multiparametric and Multiregional MR Imaging Features","volume":"281","author":"Kickingereder","year":"2016","journal-title":"Radiology"},{"key":"ref_42","doi-asserted-by":"crossref","unstructured":"Chaddad, A., Kucharczyk, M.J., Daniel, P., Sabri, S., Jean-Claude, B.J., Niazi, T., and Abdulkarim, B. (2019). Radiomics in Glioblastoma: Current Status and Challenges Facing Clinical Implementation. Front. Oncol., 9.","DOI":"10.3389\/fonc.2019.00374"},{"key":"ref_43","unstructured":"Hu, Z., Yang, Z., Zhang, H., Vaios, E., Lafata, K., Yin, F.-F., and Wang, C. (2022). A deep learning model with radiomics analysis integration for glioblastoma post-resection survival prediction. arXiv."},{"key":"ref_44","doi-asserted-by":"crossref","first-page":"eaai8478","DOI":"10.1126\/science.aai8478","article-title":"Decoupling genetics, lineages, and microenvironment in IDH-mutant gliomas by single-cell RNA-seq","volume":"355","author":"Venteicher","year":"2017","journal-title":"Science"},{"key":"ref_45","doi-asserted-by":"crossref","first-page":"835","DOI":"10.1016\/j.cell.2019.06.024","article-title":"An integrative model of cellular states, plasticity, and genetics for glioblastoma","volume":"178","author":"Neftel","year":"2019","journal-title":"Cell"}],"container-title":["Diagnostics"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/2075-4418\/16\/1\/139\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,1,2]],"date-time":"2026-01-02T09:34:34Z","timestamp":1767346474000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/2075-4418\/16\/1\/139"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,1,1]]},"references-count":45,"journal-issue":{"issue":"1","published-online":{"date-parts":[[2026,1]]}},"alternative-id":["diagnostics16010139"],"URL":"https:\/\/doi.org\/10.3390\/diagnostics16010139","relation":{},"ISSN":["2075-4418"],"issn-type":[{"value":"2075-4418","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,1,1]]}}}