{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,2]],"date-time":"2026-08-02T17:24:20Z","timestamp":1785691460708,"version":"3.56.0"},"reference-count":44,"publisher":"MDPI AG","issue":"12","license":[{"start":{"date-parts":[[2024,12,12]],"date-time":"2024-12-12T00:00:00Z","timestamp":1733961600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["J. Imaging"],"abstract":"<jats:p>Deep learning has shown significant value in automating radiological diagnostics but can be limited by a lack of generalizability to external datasets. Leveraging the geometric principles of non-Euclidean space, certain geometric deep learning approaches may offer an alternative means of improving model generalizability. This study investigates the potential advantages of hyperbolic convolutional neural networks (HCNNs) over traditional convolutional neural networks (CNNs) in neuroimaging tasks. We conducted a comparative analysis of HCNNs and CNNs across various medical imaging modalities and diseases, with a focus on a compiled multi-modality neuroimaging dataset. The models were assessed for their performance parity, robustness to adversarial attacks, semantic organization of embedding spaces, and generalizability. Zero-shot evaluations were also performed with ischemic stroke non-contrast CT images. HCNNs matched CNNs\u2019 performance in less complex settings and demonstrated superior semantic organization and robustness to adversarial attacks. While HCNNs equaled CNNs in out-of-sample datasets identifying Alzheimer\u2019s disease, in zero-shot evaluations, HCNNs outperformed CNNs and radiologists. HCNNs deliver enhanced robustness and organization in neuroimaging data. This likely underlies why, while HCNNs perform similarly to CNNs with respect to in-sample tasks, they confer improved generalizability. Nevertheless, HCNNs encounter efficiency and performance challenges with larger, complex datasets. These limitations underline the need for further optimization of HCNN architectures. HCNNs present promising improvements in generalizability and resilience for medical imaging applications, particularly in neuroimaging. Despite facing challenges with larger datasets, HCNNs enhance performance under adversarial conditions and offer better semantic organization, suggesting valuable potential in generalizable deep learning models in medical imaging and neuroimaging diagnostics.<\/jats:p>","DOI":"10.3390\/jimaging10120319","type":"journal-article","created":{"date-parts":[[2024,12,12]],"date-time":"2024-12-12T03:52:49Z","timestamp":1733975569000},"page":"319","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":4,"title":["Improved Generalizability in Medical Computer Vision: Hyperbolic Deep Learning in Multi-Modality Neuroimaging"],"prefix":"10.3390","volume":"10","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-8347-9173","authenticated-orcid":false,"given":"Cyrus","family":"Ayubcha","sequence":"first","affiliation":[{"name":"Harvard Medical School, Boston, MA 02115, USA"},{"name":"Department of Epidemiology, Harvard T.H. Chan School of Public Health, Boston, MA 02115, USA"},{"name":"Department of Neurosurgery, Cushing Neurosurgical Outcomes Center, Brigham and Women\u2019s Hospital, Harvard Medical School, Boston, MA 02115, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Sulaiman","family":"Sajed","sequence":"additional","affiliation":[{"name":"Department of Neurosurgery, Cushing Neurosurgical Outcomes Center, Brigham and Women\u2019s Hospital, Harvard Medical School, Boston, MA 02115, USA"},{"name":"Department of Medical Science, Boston University, Boston, MA 02118, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5486-8628","authenticated-orcid":false,"given":"Chady","family":"Omara","sequence":"additional","affiliation":[{"name":"Department of Neurosurgery, Cushing Neurosurgical Outcomes Center, Brigham and Women\u2019s Hospital, Harvard Medical School, Boston, MA 02115, USA"},{"name":"Department of Neurosurgery, Leiden University Medical Center, 2333 ZA Leiden, The Netherlands"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5385-4729","authenticated-orcid":false,"given":"Anna B.","family":"Veldman","sequence":"additional","affiliation":[{"name":"Department of Neurosurgery, Cushing Neurosurgical Outcomes Center, Brigham and Women\u2019s Hospital, Harvard Medical School, Boston, MA 02115, USA"},{"name":"Department of Neurosurgery, Leiden University Medical Center, 2333 ZA Leiden, The Netherlands"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Shashi B.","family":"Singh","sequence":"additional","affiliation":[{"name":"Stanford University School of Medicine, Stanford, CA 94305, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3397-4309","authenticated-orcid":false,"given":"Yashas Ullas","family":"Lokesha","sequence":"additional","affiliation":[{"name":"Department of Radiology, Sri Devaraj Urs Medical College, Kolar 563101, India"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Alex","family":"Liu","sequence":"additional","affiliation":[{"name":"Department of Computer and Information Sciences, Temple University, Philadelphia, PA 19122, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Mohammad Ali","family":"Aziz-Sultan","sequence":"additional","affiliation":[{"name":"Department of Neurosurgery, Cushing Neurosurgical Outcomes Center, Brigham and Women\u2019s Hospital, Harvard Medical School, Boston, MA 02115, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Timothy R.","family":"Smith","sequence":"additional","affiliation":[{"name":"Department of Neurosurgery, Cushing Neurosurgical Outcomes Center, Brigham and Women\u2019s Hospital, Harvard Medical School, Boston, MA 02115, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Andrew","family":"Beam","sequence":"additional","affiliation":[{"name":"Department of Epidemiology, Harvard T.H. Chan School of Public Health, Boston, MA 02115, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1968","published-online":{"date-parts":[[2024,12,12]]},"reference":[{"key":"ref_1","doi-asserted-by":"crossref","unstructured":"Ren, B., Liu, M., Ding, R., and Liu, H. (2024). A Survey on 3D Skeleton-Based Action Recognition Using Learning Method. Cyborg Bionic Syst., 5.","DOI":"10.34133\/cbsystems.0100"},{"key":"ref_2","doi-asserted-by":"crossref","unstructured":"Qian, K., Bao, Z., Zhao, Z., Koike, T., Dong, F., Schmitt, M., Dong, Q., Shen, J., Jiang, W., and Jiang, Y. (2024). Learning Representations from Heart Sound: A Comparative Study on Shallow and Deep Models. Cyborg Bionic Syst., 5.","DOI":"10.34133\/cbsystems.0075"},{"key":"ref_3","doi-asserted-by":"crossref","unstructured":"Han, Z., Tian, H., Han, X., Wu, J., Zhang, W., Li, C., Qiu, L., Duan, X., and Tian, W. (2024). A Respiratory Motion Prediction Method Based on LSTM-AE with Attention Mechanism for Spine Surgery. Cyborg Bionic Syst., 5.","DOI":"10.34133\/cbsystems.0063"},{"key":"ref_4","first-page":"3094","article-title":"A Universal Approximation Theorem of Deep Neural Networks for Expressing Probability Distributions","volume":"33","author":"Lu","year":"2020","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"ref_5","first-page":"5350","article-title":"Hyperbolic Neural Networks","volume":"31","author":"Ganea","year":"2018","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"ref_6","unstructured":"Sala, F., Sa, C.D., Gu, A., and Re, C. (2018, January 10\u201315). Representation Tradeoffs for Hyperbolic Embeddings. Proceedings of the 35th International Conference on Machine Learning, Stockholm, Sweden. Available online: https:\/\/proceedings.mlr.press\/v80\/sala18a.html."},{"key":"ref_7","doi-asserted-by":"crossref","unstructured":"van Kreveld, M., and Speckmann, B. (2012). Low Distortion Delaunay Embedding of Trees in Hyperbolic Plane. Graph Drawing, Springer. Lecture Notes in Computer Science.","DOI":"10.1007\/978-3-642-25878-7"},{"key":"ref_8","doi-asserted-by":"crossref","first-page":"10023","DOI":"10.1109\/TPAMI.2021.3136921","article-title":"Hyperbolic Deep Neural Networks: A Survey","volume":"44","author":"Peng","year":"2022","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"ref_9","doi-asserted-by":"crossref","unstructured":"Khrulkov, V., Mirvakhabova, L., Ustinova, E., Oseledets, I., and Lempitsky, V. (2020, January 13\u201319). Hyperbolic Image Embeddings. Proceedings of the 2020 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), Seattle, WA, USA.","DOI":"10.1109\/CVPR42600.2020.00645"},{"key":"ref_10","unstructured":"Shimizu, R., Mukuta, Y., and Harada, T. (2021). Hyperbolic Neural Networks++. arXiv."},{"key":"ref_11","doi-asserted-by":"crossref","unstructured":"Chen, W., Han, X., Lin, Y., Zhao, H., Liu, Z., Li, P., Sun, M., and Zhou, J. (2022, January 22\u201327). Fully Hyperbolic Neural Networks. Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), Dublin, Ireland.","DOI":"10.18653\/v1\/2022.acl-long.389"},{"key":"ref_12","doi-asserted-by":"crossref","unstructured":"Guo, Y., Wang, X., Chen, Y., and Yu, S.X. (2022, January 18\u201324). Clipped Hyperbolic Classifiers Are Super-Hyperbolic Classifiers. Proceedings of the 2022 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), New Orleans, LA, USA.","DOI":"10.1109\/CVPR52688.2022.00010"},{"key":"ref_13","unstructured":"Mishne, G., Wan, Z., Wang, Y., and Yang, S. (2023, January 23\u201329). The Numerical Stability of Hyperbolic Representation Learning. Proceedings of the 40th International Conference on Machine Learning, Honolulu, HI, USA."},{"key":"ref_14","doi-asserted-by":"crossref","unstructured":"van Spengler, M., Berkhout, E., and Mettes, P. (2023, January 1\u20136). Poincar\u00e9 ResNet. Proceedings of the 2023 IEEE\/CVF International Conference on Computer Vision (ICCV), Paris, France.","DOI":"10.1109\/ICCV51070.2023.00499"},{"key":"ref_15","doi-asserted-by":"crossref","first-page":"26731","DOI":"10.1007\/s11042-022-14305-w","article-title":"Machine learning and deep learning approach for medical image analysis: Diagnosis to detection","volume":"82","author":"Rana","year":"2023","journal-title":"Multimed. Tools Appl."},{"key":"ref_16","doi-asserted-by":"crossref","unstructured":"Yu, Z., Nguyen, T., Gal, Y., Ju, L., Chandra, S.S., Zhang, L., Bonnington, P., Mar, V., Wang, Z., and Ge, Z. (2022). Skin Lesion Recognition with Class-Hierarchy Regularized Hyperbolic Embeddings. Medical Image Computing and Computer Assisted Intervention\u2014MICCAI 2022, Springer.","DOI":"10.1007\/978-3-031-16437-8_57"},{"key":"ref_17","doi-asserted-by":"crossref","first-page":"102889","DOI":"10.1016\/j.media.2023.102889","article-title":"BayeSeg: Bayesian modeling for medical image segmentation with interpretable generalizability","volume":"89","author":"Gao","year":"2023","journal-title":"Med. Image Anal."},{"key":"ref_18","doi-asserted-by":"crossref","unstructured":"Chaddad, A., Hu, Y., Wu, Y., Wen, B., and Kateb, R. (2024). Generalizable and explainable deep learning for medical image computing: An overview. Curr. Opin. Biomed. Eng., 33.","DOI":"10.1016\/j.cobme.2024.100567"},{"key":"ref_19","doi-asserted-by":"crossref","first-page":"60","DOI":"10.1016\/j.media.2017.07.005","article-title":"A survey on deep learning in medical image analysis","volume":"42","author":"Litjens","year":"2017","journal-title":"Med. Image Anal."},{"key":"ref_20","doi-asserted-by":"crossref","unstructured":"Shi, P., Qiu, J., Abaxi, S.M.D., Wei, H., Lo, F.P.-W., and Yuan, W. (2023). Generalist Vision Foundation Models for Medical Imaging: A Case Study of Segment Anything Model on Zero-Shot Medical Segmentation. Diagnostics, 13.","DOI":"10.3390\/diagnostics13111947"},{"key":"ref_21","doi-asserted-by":"crossref","unstructured":"Li, X., Zhang, L., Wu, Z., Liu, Z., Zhao, L., Yuan, Y., Liu, J., Li, G., Zhu, D., and Yan, P. (2023). Artificial General Intelligence for Medical Imaging. arXiv.","DOI":"10.1109\/RBME.2024.3493775"},{"key":"ref_22","doi-asserted-by":"crossref","unstructured":"Hirano, H., Minagi, A., and Takemoto, K. (2021). Universal adversarial attacks on deep neural networks for medical image classification. BMC Med. Imaging, 21.","DOI":"10.1186\/s12880-020-00530-y"},{"key":"ref_23","doi-asserted-by":"crossref","unstructured":"Tasci, B., and Tasci, I. (2022). Deep feature extraction based brain image classification model using preprocessed images: PDRNet. Biomed. Signal Process. Control, 78.","DOI":"10.1016\/j.bspc.2022.103948"},{"key":"ref_24","unstructured":"Hssayeni, M. (2019). Computed Tomography Images for Intracranial Hemorrhage Detection and Segmentation. PhysioNet."},{"key":"ref_25","doi-asserted-by":"crossref","first-page":"175","DOI":"10.1002\/jmri.26766","article-title":"Deep learning enables automatic detection and segmentation of brain metastases on multisequence MRI","volume":"51","author":"Yi","year":"2020","journal-title":"J. Magn. Reson. Imaging"},{"key":"ref_26","unstructured":"(2024, July 24). Brain Tumor MRI Images 17 Classes. Available online: https:\/\/www.kaggle.com\/datasets\/fernando2rad\/brain-tumor-mri-images-17-classes."},{"key":"ref_27","unstructured":"Ashish, N., and Ambite, J.-L. (2015). SchizConnect: Virtual Data Integration in Neuroimaging. Data Integration in the Life Sciences, Springer International Publishing."},{"key":"ref_28","doi-asserted-by":"crossref","unstructured":"Hernandez, R.M., Sison, D.K., Nolasco, N.C., Melo, J., and Castillo, R. (2023, January 24\u201325). Application of Machine Learning on MRI Scans for Alzheimer\u2019s Disease Early Detection. Proceedings of the 8th International Conference on Sustainable Information Engineering and Technology, Bali, Indonesia.","DOI":"10.1145\/3626641.3627609"},{"key":"ref_29","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1016\/S0920-9964(01)00163-3","article-title":"A review of MRI findings in schizophrenia","volume":"49","author":"Shenton","year":"2001","journal-title":"Schizophr. Res."},{"key":"ref_30","doi-asserted-by":"crossref","first-page":"1122","DOI":"10.1016\/j.cell.2018.02.010","article-title":"Identifying Medical Diagnoses and Treatable Diseases by Image-Based Deep Learning","volume":"172","author":"Kermany","year":"2018","journal-title":"Cell"},{"key":"ref_31","doi-asserted-by":"crossref","unstructured":"Li, N., Li, T., Hu, C., Wang, K., and Kang, H. (2021). A Benchmark of Ocular Disease Intelligent Recognition: One Shot for Multi-disease Detection. arXiv.","DOI":"10.1007\/978-3-030-71058-3_11"},{"key":"ref_32","doi-asserted-by":"crossref","unstructured":"Pogorelov, K., Randel, K.R., Griwodz, C., Eskeland, S.L., de Lange, T., Johansen, D., Spampinato, C., Dang-Nguyen, D.-T., Lux, M., and Schmidt, P.T. (2017, January 20\u201323). KVASIR: A Multi-Class Image Dataset for Computer Aided Gastrointestinal Disease Detection. Proceedings of the 8th ACM on Multimedia Systems Conference, Taipei, Taiwan.","DOI":"10.1145\/3083187.3083212"},{"key":"ref_33","doi-asserted-by":"crossref","first-page":"521","DOI":"10.1038\/s41597-023-02432-4","article-title":"FracAtlas: A Dataset for Fracture Classification, Localization and Segmentation of Musculoskeletal Radiographs","volume":"10","author":"Abedeen","year":"2023","journal-title":"Sci. Data"},{"key":"ref_34","doi-asserted-by":"crossref","first-page":"180161","DOI":"10.1038\/sdata.2018.161","article-title":"The HAM10000 dataset, a large collection of multi-source dermatoscopic images of common pigmented skin lesions","volume":"5","author":"Tschandl","year":"2018","journal-title":"Sci. Data"},{"key":"ref_35","doi-asserted-by":"crossref","unstructured":"Codella, N.C.F., Gutman, D., Celebi, M.E., Helba, B., Marchetti, M.A., Dusza, S.W., Kalloo, A., Liopyris, K., Mishra, N., and Kittler, H. (2018, January 4\u20137). Skin Lesion Analysis Toward Melanoma Detection: A Challenge at the 2017 International Symposium on Biomedical Imaging (ISBI), Hosted by the International Skin Imaging Collaboration (ISIC). Proceedings of the 2018 IEEE 15th International Symposium on Biomedical Imaging (ISBI 2018), Washington, DC, USA.","DOI":"10.1109\/ISBI.2018.8363547"},{"key":"ref_36","unstructured":"Combalia, M., Codella, N.C.F., Rotemberg, V., Helba, B., Vilaplana, V., Reiter, O., Carrera, C., Barreiro, A., Halpern, A.C., and Puig, S. (2019). BCN20000: Dermoscopic Lesions in the Wild. arXiv."},{"key":"ref_37","doi-asserted-by":"crossref","first-page":"1498","DOI":"10.1162\/jocn.2007.19.9.1498","article-title":"Open Access Series of Imaging Studies (OASIS): Cross-sectional MRI Data in Young, Middle Aged, Nondemented, and Demented Older Adults","volume":"19","author":"Marcus","year":"2007","journal-title":"J. Cogn. Neurosci."},{"key":"ref_38","unstructured":"Bdeir, A., Schwethelm, K., and Landwehr, N. (2024). Fully Hyperbolic Convolutional Neural Networks for Computer Vision. arXiv."},{"key":"ref_39","unstructured":"Sorzano, C.O.S., Vargas, J., and Montano, A.P. (2014). A survey of dimensionality reduction techniques. arXiv."},{"key":"ref_40","doi-asserted-by":"crossref","first-page":"1287","DOI":"10.1126\/science.aaw4399","article-title":"Adversarial attacks on medical machine learning","volume":"363","author":"Finlayson","year":"2019","journal-title":"Science"},{"key":"ref_41","doi-asserted-by":"crossref","unstructured":"Apostolidis, K.D., and Papakostas, G.A. (2021). A Survey on Adversarial Deep Learning Robustness in Medical Image Analysis. Electronics, 10.","DOI":"10.3390\/electronics10172132"},{"key":"ref_42","doi-asserted-by":"crossref","first-page":"108923","DOI":"10.1016\/j.patcog.2022.108923","article-title":"Robust convolutional neural networks against adversarial attacks on medical images","volume":"132","author":"Shi","year":"2022","journal-title":"Pattern Recognit."},{"key":"ref_43","doi-asserted-by":"crossref","first-page":"e220126","DOI":"10.1148\/ryai.220126","article-title":"Moving from ImageNet to RadImageNet for improved transfer learning and generalizability","volume":"4","year":"2022","journal-title":"Radiol. Artif. Intell."},{"key":"ref_44","doi-asserted-by":"crossref","first-page":"21","DOI":"10.1007\/s10462-024-10969-y","article-title":"Federated learning design and functional models: A survey","volume":"58","author":"Ayeelyan","year":"2024","journal-title":"Artif. Intell. Rev."}],"container-title":["Journal of Imaging"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/2313-433X\/10\/12\/319\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,10]],"date-time":"2025-10-10T16:53:17Z","timestamp":1760115197000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/2313-433X\/10\/12\/319"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,12,12]]},"references-count":44,"journal-issue":{"issue":"12","published-online":{"date-parts":[[2024,12]]}},"alternative-id":["jimaging10120319"],"URL":"https:\/\/doi.org\/10.3390\/jimaging10120319","relation":{},"ISSN":["2313-433X"],"issn-type":[{"value":"2313-433X","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,12,12]]}}}