{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,11,4]],"date-time":"2025-11-04T12:57:08Z","timestamp":1762261028297,"version":"build-2065373602"},"reference-count":43,"publisher":"MDPI AG","issue":"11","license":[{"start":{"date-parts":[[2025,11,4]],"date-time":"2025-11-04T00:00:00Z","timestamp":1762214400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Algorithms"],"abstract":"<jats:p>Schizophrenia is challenging to identify from resting-state functional MRI (rs-fMRI) due to subtle, distributed changes and the clinical need for transparent models. We build on the Swin 4D fMRI Transformer (SwiFT) to classify schizophrenia vs. controls and explain predictions with Transformer Layer-wise Relevance Propagation (TransLRP). We further introduce Swarm-LRP, a particle swarm optimization (PSO) scheme that tunes Layer-wise Relevance Propagation (LRP) rules against model-agnostic explainability (XAI) metrics from Quantus. On the COBRE dataset, TransLRP yields higher faithfulness and lower sensitivity\/complexity than Integrated Gradients, and highlights physiologically plausible regions. Swarm-LRP improves single-subject explanation quality over baseline LRP by optimizing (\u03b1,\u03b3,\u03f5) values and discrete layer-rule assignments. These results suggest that architecture-aware explanations can recover spatiotemporal patterns of rs-fMRI relevant to schizophrenia while improving attribution robustness. This feasibility study indicates a path toward clinically interpretable neuroimaging models.<\/jats:p>","DOI":"10.3390\/a18110701","type":"journal-article","created":{"date-parts":[[2025,11,4]],"date-time":"2025-11-04T12:13:08Z","timestamp":1762258388000},"page":"701","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Explainable Schizophrenia Classification from rs-fMRI Using SwiFT and TransLRP"],"prefix":"10.3390","volume":"18","author":[{"given":"Julian","family":"Weaver","sequence":"first","affiliation":[{"name":"Department of Biomedical Engineering, The University of Texas at Austin, Austin, TX 78712, USA"}]},{"given":"Emerald","family":"Zhang","sequence":"additional","affiliation":[{"name":"Department of Biomedical Engineering, The University of Texas at Austin, Austin, TX 78712, USA"}]},{"given":"Nihita","family":"Sarma","sequence":"additional","affiliation":[{"name":"Department of Biomedical Engineering, The University of Texas at Austin, Austin, TX 78712, USA"}]},{"given":"Alaa","family":"Melek","sequence":"additional","affiliation":[{"name":"Department of Biomedical Engineering, The University of Texas at Austin, Austin, TX 78712, USA"}]},{"given":"Edward","family":"Castillo","sequence":"additional","affiliation":[{"name":"Department of Biomedical Engineering, The University of Texas at Austin, Austin, TX 78712, USA"}]}],"member":"1968","published-online":{"date-parts":[[2025,11,4]]},"reference":[{"key":"ref_1","first-page":"9804836","article-title":"From Onset and Prodromal Stage to a Life-Long Course of Schizophrenia and Its Symptom Dimensions: How Sex, Age, and Other Risk Factors Influence Incidence and Course of Illness","volume":"2019","year":"2019","journal-title":"Psychiatry J."},{"key":"ref_2","doi-asserted-by":"crossref","first-page":"271","DOI":"10.31887\/DCNS.2010.12.3\/ajablensky","article-title":"The diagnostic concept of schizophrenia: Its history, evolution, and future prospects","volume":"12","author":"Jablensky","year":"2010","journal-title":"Dialogues Clin. Neurosci."},{"key":"ref_3","first-page":"638","article-title":"Schizophrenia: Overview and treatment options","volume":"39","author":"Patel","year":"2014","journal-title":"Pharm. Ther."},{"key":"ref_4","doi-asserted-by":"crossref","first-page":"8437260","DOI":"10.1155\/2021\/8437260","article-title":"Diagnosis of Schizophrenia Based on Deep Learning Using fMRI","volume":"2021","author":"Zheng","year":"2021","journal-title":"Comput. Math. Methods Med."},{"key":"ref_5","doi-asserted-by":"crossref","first-page":"22","DOI":"10.1162\/netn_a_00281","article-title":"A transformer model for learning spatiotemporal contextual representation in fMRI data","volume":"7","author":"Asadi","year":"2023","journal-title":"Netw. Neurosci."},{"key":"ref_6","unstructured":"Bengs, M., Gessert, N., and Schlaefer, A. (2020). 4D Spatio-Temporal Deep Learning with 4D fMRI Data for Autism Spectrum Disorder Classification. arXiv."},{"key":"ref_7","doi-asserted-by":"crossref","unstructured":"B\u00f6hle, M., Eitel, F., Weygandt, M., and Ritter, K. (2019). Layer-Wise Relevance Propagation for Explaining Deep Neural Network Decisions in MRI-Based Alzheimer\u2019s Disease Classification. Front. Aging Neurosci., 11.","DOI":"10.3389\/fnagi.2019.00194"},{"key":"ref_8","doi-asserted-by":"crossref","unstructured":"Liu, Z., Lin, Y., Cao, Y., Hu, H., Wei, Y., Zhang, Z., Lin, S., and Guo, B. (2021). Swin Transformer: Hierarchical Vision Transformer using Shifted Windows. arXiv.","DOI":"10.1109\/ICCV48922.2021.00986"},{"key":"ref_9","unstructured":"Kim, P.Y., Kwon, J., Joo, S., Bae, S., Lee, D., Jung, Y., Yoo, S., Cha, J., and Moon, T. (2023). SwiFT: Swin 4D fMRI Transformer. arXiv."},{"key":"ref_10","unstructured":"Montavon, G., Binder, A., Lapuschkin, S., Samek, W., and M\u00fcller, K. (2023). Layer-Wise Relevance Propagation: An Overview. Explainable AI: Interpreting, Explaining and Visualizing Deep Learning, Springer."},{"key":"ref_11","doi-asserted-by":"crossref","unstructured":"Bach, S., Binder, A., Montavon, G., Klauschen, F., M\u00fcller, K.R., and Samek, W. (2015). On Pixel-Wise Explanations for Non-Linear Classifier Decisions by Layer-Wise Relevance Propagation. PLoS ONE, 10.","DOI":"10.1371\/journal.pone.0130140"},{"key":"ref_12","doi-asserted-by":"crossref","unstructured":"Komorowski, P., Baniecki, H., and Biecek, P. (2023, January 17\u201324). Towards Evaluating Explanations of Vision Transformers for Medical Imaging. Proceedings of the 2023 IEEE\/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW), Vancouver, BC, Canada.","DOI":"10.1109\/CVPRW59228.2023.00383"},{"key":"ref_13","doi-asserted-by":"crossref","unstructured":"Chefer, H., Gur, S., and Wolf, L. (2021). Transformer Interpretability Beyond Attention Visualization. arXiv.","DOI":"10.1109\/CVPR46437.2021.00084"},{"key":"ref_14","doi-asserted-by":"crossref","unstructured":"Abnar, S., and Zuidema, W. (2020). Quantifying Attention Flow in Transformers. arXiv.","DOI":"10.18653\/v1\/2020.acl-main.385"},{"key":"ref_15","unstructured":"Hedstr\u00f6m, A., Weber, L., Bareeva, D., Krakowczyk, D., Motzkus, F., Samek, W., Lapuschkin, S., and H\u00f6hne, M.M.C. (2023). Quantus: An Explainable AI Toolkit for Responsible Evaluation of Neural Network Explanations and Beyond. arXiv."},{"key":"ref_16","doi-asserted-by":"crossref","first-page":"330","DOI":"10.1016\/j.schres.2021.06.011","article-title":"Structural and diffusion MRI based schizophrenia classification using 2D pretrained and 3D naive Convolutional Neural Networks","volume":"243","author":"Hu","year":"2022","journal-title":"Schizophr. Res."},{"key":"ref_17","doi-asserted-by":"crossref","first-page":"451","DOI":"10.1109\/TCDS.2019.2916916","article-title":"Four-Dimensional Modeling of fMRI Data via Spatio\u2013Temporal Convolutional Neural Networks (ST-CNNs)","volume":"12","author":"Zhao","year":"2020","journal-title":"IEEE Trans. Cogn. Dev. Syst."},{"key":"ref_18","doi-asserted-by":"crossref","unstructured":"Hu, M., Sim, K., Zhou, J.H., Jiang, X., and Guan, C. (2020, January 20\u201324). Brain MRI-based 3D Convolutional Neural Networks for Classification of Schizophrenia and Controls. Proceedings of the 2020 42nd Annual International Conference of the IEEE Engineering in Medicine & Biology Society (EMBC), Online.","DOI":"10.1109\/EMBC44109.2020.9176610"},{"key":"ref_19","doi-asserted-by":"crossref","first-page":"110786","DOI":"10.1016\/j.ejrad.2023.110786","article-title":"Explainable AI in medical imaging: An overview for clinical practitioners\u2014Beyond saliency-based XAI approaches","volume":"162","author":"Borys","year":"2023","journal-title":"Eur. J. Radiol."},{"key":"ref_20","doi-asserted-by":"crossref","unstructured":"Singh, A., Sengupta, S., and Lakshminarayanan, V. (2020). Explainable deep learning models in medical image analysis. arXiv.","DOI":"10.3390\/jimaging6060052"},{"key":"ref_21","doi-asserted-by":"crossref","unstructured":"Suara, S., Jha, A., Sinha, P., and Sekh, A.A. (2023). Is Grad-CAM Explainable in Medical Images?. arXiv.","DOI":"10.1007\/978-3-031-58181-6_11"},{"key":"ref_22","doi-asserted-by":"crossref","unstructured":"Zhang, J., Rao, V.M., Tian, Y., Yang, Y., Acosta, N., Wan, Z., Lee, P.Y., Zhang, C., Kegeles, L.S., and Small, S.A. (2023). Detecting schizophrenia with 3D structural brain MRI using deep learning. Sci. Rep., 13.","DOI":"10.1038\/s41598-023-41359-z"},{"key":"ref_23","unstructured":"Sundararajan, M., Taly, A., and Yan, Q. (2017). Axiomatic Attribution for Deep Networks. arXiv."},{"key":"ref_24","unstructured":"Yeh, C.K., Hsieh, C.Y., Suggala, A.S., Inouye, D.I., and Ravikumar, P. (2019). On the (In)fidelity and Sensitivity for Explanations. arXiv."},{"key":"ref_25","unstructured":"Munoz, C., da Costa, K., Modenesi, B., and Koshiyama, A. (2014). Evaluating explainability for machine learning predictions using model-agnostic metrics. arXiv."},{"key":"ref_26","doi-asserted-by":"crossref","unstructured":"Stoyanov, D., Taylor, D., Kia, S.M., Oguz, I., Reyes, M., Martel, A., Maier-Hein, L., Marquand, A.F., Duchesnay, E., and L\u00f6fstedt, T. (2018). Towards Complementary Explanations Using Deep Neural Networks. Understanding and Interpreting Machine Learning in Medical Image Computing Applications, Springer. Lecture Notes in Computer Science.","DOI":"10.1007\/978-3-030-02628-8"},{"key":"ref_27","doi-asserted-by":"crossref","unstructured":"Ribeiro, M.T., Singh, S., and Guestrin, C. (2016). \u201cWhy Should I Trust You?\u201d: Explaining the Predictions of Any Classifier. arXiv.","DOI":"10.1145\/2939672.2939778"},{"key":"ref_28","doi-asserted-by":"crossref","unstructured":"Ahmed, A.M.A., and Ali, L.A.M. (2021). Explainable Medical Image Segmentation via Generative Adversarial Networks and Layer-wise Relevance Propagation. arXiv.","DOI":"10.5617\/nmi.9126"},{"key":"ref_29","doi-asserted-by":"crossref","first-page":"291","DOI":"10.1038\/s41467-023-44371-z","article-title":"Improving deep neural network generalization and robustness to background bias via layer-wise relevance propagation optimization","volume":"15","author":"Bassi","year":"2024","journal-title":"Nat. Commun."},{"key":"ref_30","doi-asserted-by":"crossref","first-page":"343","DOI":"10.1007\/s12021-017-9338-9","article-title":"Multimodal Neuroimaging in Schizophrenia: Description and Dissemination","volume":"15","author":"Aine","year":"2017","journal-title":"Neuroinformatics"},{"key":"ref_31","first-page":"13","article-title":"DPARSF: A MATLAB Toolbox for \"Pipeline\" Data Analysis of Resting-State fMRI","volume":"4","year":"2010","journal-title":"Front. Syst. Neurosci."},{"key":"ref_32","unstructured":"Ashburner, J., Barnes, G., Chen, C.C., Daunizeau, J., Flandin, G., Friston, K., Gitelman, D., Glauche, V., Henson, R., and Hutton, C. (2021). SPM12 Manual, UCL Queen Square Institute of Neurology."},{"key":"ref_33","doi-asserted-by":"crossref","first-page":"401","DOI":"10.1136\/jamia.2001.0080401","article-title":"A four-dimensional probabilistic atlas of the human brain","volume":"8","author":"Mazziotta","year":"2001","journal-title":"J. Am. Med. Inform. Assoc."},{"key":"ref_34","doi-asserted-by":"crossref","unstructured":"Bhatt, U., Weller, A., and Moura, J.M.F. (2020). Evaluating and Aggregating Feature-based Model Explanations. arXiv.","DOI":"10.24963\/ijcai.2020\/417"},{"key":"ref_35","unstructured":"phi Nguyen, A., and Mart\u00ednez, M.R. (2020). On quantitative aspects of model interpretability. arXiv."},{"key":"ref_36","doi-asserted-by":"crossref","unstructured":"Li, C., Jiang, J., Zhao, Y., Li, R., Wang, E., Zhang, X., and Zhao, K. (2021). Genetic Algorithm based hyper-parameters optimization for transfer Convolutional Neural Network. arXiv.","DOI":"10.1117\/12.2637170"},{"key":"ref_37","unstructured":"Kennedy, J., and Eberhart, R. (December, January 27). Particle swarm optimization. Proceedings of the ICNN\u201995-International Conference on Neural Networks, Perth, WA, Australia."},{"key":"ref_38","doi-asserted-by":"crossref","first-page":"155","DOI":"10.1016\/j.schres.2005.11.020","article-title":"Decreased volume of left and total anterior insular lobule in schizophrenia","volume":"83","author":"Makris","year":"2006","journal-title":"Schizophr. Res."},{"key":"ref_39","doi-asserted-by":"crossref","first-page":"214","DOI":"10.1097\/WNR.0000000000001881","article-title":"Functional connectivity of sub-cortical brain regions: Disparities and similarities","volume":"34","author":"Alahmadi","year":"2023","journal-title":"Neuroreport"},{"key":"ref_40","doi-asserted-by":"crossref","first-page":"108","DOI":"10.1016\/j.neubiorev.2015.12.007","article-title":"Cognition and resting-state functional connectivity in schizophrenia","volume":"61","author":"Sheffield","year":"2016","journal-title":"Neurosci. Biobehav. Rev."},{"key":"ref_41","doi-asserted-by":"crossref","first-page":"e25376","DOI":"10.1002\/jnr.25376","article-title":"Alterations in amygdala subregions\u2013Default mode network connectivity after treatment in patients with schizophrenia","volume":"102","author":"Xu","year":"2024","journal-title":"J. Neurosci. Res."},{"key":"ref_42","doi-asserted-by":"crossref","unstructured":"Cao, X., Li, Q., Liu, S., Li, Z., Wang, Y., Cheng, L., Yang, C., and Xu, Y. (2022). Enhanced Resting-State Functional Connectivity of the Nucleus Accumbens in First-Episode, Medication-Na\u00efve Patients With Early Onset Schizophrenia. Front. Neurosci., 16.","DOI":"10.3389\/fnins.2022.844519"},{"key":"ref_43","doi-asserted-by":"crossref","first-page":"S208","DOI":"10.1016\/j.neuroimage.2004.07.051","article-title":"Advances in functional and structural MR image analysis and implementation as FSL","volume":"23","author":"Smith","year":"2004","journal-title":"NeuroImage"}],"container-title":["Algorithms"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/1999-4893\/18\/11\/701\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,11,4]],"date-time":"2025-11-04T12:30:29Z","timestamp":1762259429000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/1999-4893\/18\/11\/701"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,11,4]]},"references-count":43,"journal-issue":{"issue":"11","published-online":{"date-parts":[[2025,11]]}},"alternative-id":["a18110701"],"URL":"https:\/\/doi.org\/10.3390\/a18110701","relation":{},"ISSN":["1999-4893"],"issn-type":[{"value":"1999-4893","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,11,4]]}}}