{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,20]],"date-time":"2026-06-20T03:15:27Z","timestamp":1781925327840,"version":"3.54.5"},"reference-count":33,"publisher":"MDPI AG","issue":"2","license":[{"start":{"date-parts":[[2026,1,9]],"date-time":"2026-01-09T00:00:00Z","timestamp":1767916800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"DOI":"10.13039\/501100003710","name":"Korea Health Industry Development Institute","doi-asserted-by":"publisher","award":["RS-2021-KH113822"],"award-info":[{"award-number":["RS-2021-KH113822"]}],"id":[{"id":"10.13039\/501100003710","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100003710","name":"Korea Health Industry Development Institute","doi-asserted-by":"publisher","award":["RS-2022-KH130307"],"award-info":[{"award-number":["RS-2022-KH130307"]}],"id":[{"id":"10.13039\/501100003710","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100003645","name":"National Cancer Center","doi-asserted-by":"publisher","award":["RS-2025-02214710"],"award-info":[{"award-number":["RS-2025-02214710"]}],"id":[{"id":"10.13039\/501100003645","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Cancers"],"abstract":"<jats:p>Background: Previous attempts to classify lymphoma subtypes based on metabolic features extracted from 18F-FDG PET imaging have been hindered by inconsistencies in imaging protocols, scanner types, and inter-institutional variability. To overcome these limitations, we propose a multimodal deep learning framework that integrates harmonized PET imaging features with structured clinical information. The proposed framework is designed to perform hierarchical classification of clinically meaningful lymphoma subtypes through two sequential binary classification tasks. Methods: We collected multi-center data comprising 18F-FDG PET images and structured clinical variables of patients with lymphoma. To mitigate domain shifts caused by different scanner manufacturers, we integrated a Scanner-Conditioned Normalization (SCN) module, which adaptively harmonizes feature distributions using manufacturer-specific parameters. Performance was validated using internal and external cohorts, with the statistical significance of performance gains assessed via DeLong\u2019s test and bootstrap-based CI analysis. Results: The proposed model achieved an area under the curve (AUC) of 0.89 (internal) and 0.84 (external) for Hodgkin lymphoma versus non-Hodgkin lymphoma classification and 0.84 (internal) and 0.76 (external) for diffuse large B-cell lymphoma versus follicular lymphoma classification (p &gt; 0.05). These results were obtained using a multimodal model that integrated anterior and lateral maximum intensity projection (MIP) images with clinical data. Conclusions: This study demonstrates the potential of a deep learning-based approach for lymphoma subtype classification using non-invasive 18F-FDG PET imaging combined with clinical data. While further validation in larger, more diverse cohorts is necessary to address the challenges of rare subtypes and biological heterogeneity, LymphoMAP serves as a meaningful step toward developing assistive tools for early clinical decision-making. These findings underscore the feasibility of using automated pipelines to support, rather than replace, conventional diagnostic workflows in personalized lymphoma management.<\/jats:p>","DOI":"10.3390\/cancers18020210","type":"journal-article","created":{"date-parts":[[2026,1,9]],"date-time":"2026-01-09T09:25:02Z","timestamp":1767950702000},"page":"210","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["Robust Multimodal Deep Learning for Lymphoma Subtype Classification Using 18F-FDG PET Maximum Intensity Projection Images and Clinical Data: A Multi-Center Study"],"prefix":"10.3390","volume":"18","author":[{"given":"Seonhwa","family":"Kim","sequence":"first","affiliation":[{"name":"Department of Radiation Oncology, School of Medicine, Ajou University, Suwon 16499, Republic of Korea"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jun Hyeong","family":"Park","sequence":"additional","affiliation":[{"name":"Department of Biomedical Sciences, Graduate School, Ajou University, Suwon 16499, Republic of Korea"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Chul-Ho","family":"Kim","sequence":"additional","affiliation":[{"name":"Department of Otolaryngology, School of Medicine, Ajou University, Suwon 16499, Republic of Korea"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Seulgi","family":"You","sequence":"additional","affiliation":[{"name":"Department of Radiology, School of Medicine, Ajou University, Suwon 16499, Republic of Korea"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9669-2141","authenticated-orcid":false,"given":"Jeong-Seok","family":"Choi","sequence":"additional","affiliation":[{"name":"Department of Otorhinolaryngology\u2014Head and Neck Surgery, College of Medicine, Inha University, Incheon 22212, Republic of Korea"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6596-931X","authenticated-orcid":false,"given":"Jae Won","family":"Chang","sequence":"additional","affiliation":[{"name":"Department of Otolaryngology\u2014Head and Neck Surgery, Chungnam National University Hospital, Daejeon 35015, Republic of Korea"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"In Young","family":"Jo","sequence":"additional","affiliation":[{"name":"Department of Radiation Oncology, Soonchunhyang University Hospital, Cheonan 33019, Republic of Korea"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Byung-Joo","family":"Lee","sequence":"additional","affiliation":[{"name":"Department of Otorhinolaryngology\u2014Head and Neck Surgery, College of Medicine, Pusan National University and Biomedical Research Institute, Pusan National University Hospital, Pusan National University, Busan 49241, Republic of Korea"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8143-8968","authenticated-orcid":false,"given":"Il-Seok","family":"Park","sequence":"additional","affiliation":[{"name":"Department of Otorhinolaryngology\u2014Head and Neck Surgery, Hallym University Dongtan Sacred Heart Hospital, Hallym University College of Medicine, Chuncheon 24252, Republic of Korea"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2239-0225","authenticated-orcid":false,"given":"Han Su","family":"Kim","sequence":"additional","affiliation":[{"name":"Department of Otorhinolaryngology\u2014Head and Neck Surgery, School of Medicine, Ewha Womans University, Seoul 03760, Republic of Korea"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yong-Jin","family":"Park","sequence":"additional","affiliation":[{"name":"Department of Nuclear Medicine, Ajou University Medical Center, School of Medicine, Ajou University, Suwon 16499, Republic of Korea"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2066-9062","authenticated-orcid":false,"given":"Jaesung","family":"Heo","sequence":"additional","affiliation":[{"name":"Department of Radiation Oncology, School of Medicine, Ajou University, Suwon 16499, Republic of Korea"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1968","published-online":{"date-parts":[[2026,1,9]]},"reference":[{"key":"ref_1","doi-asserted-by":"crossref","first-page":"298","DOI":"10.1016\/S0140-6736(16)32407-2","article-title":"Non-Hodgkin lymphoma","volume":"390","author":"Armitage","year":"2017","journal-title":"Lancet"},{"key":"ref_2","first-page":"10","article-title":"Cancer statistics, 2025","volume":"75","author":"Siegel","year":"2025","journal-title":"CA Cancer J. Clin."},{"key":"ref_3","doi-asserted-by":"crossref","first-page":"1720","DOI":"10.1038\/s41375-022-01620-2","article-title":"The 5th edition of the World Health Organization Classification of Haematolymphoid Tumours: Lymphoid Neoplasms","volume":"36","author":"Alaggio","year":"2022","journal-title":"Leukemia"},{"key":"ref_4","doi-asserted-by":"crossref","unstructured":"Kanavos, T., Birbas, E., and Zanos, T.P. (2024). A Systematic Review of the Applications of Deep Learning for the Interpretation of Positron Emission Tomography Images of Patients with Lymphoma. Cancers, 17.","DOI":"10.3390\/cancers17010069"},{"key":"ref_5","doi-asserted-by":"crossref","first-page":"471","DOI":"10.3324\/haematol.12013","article-title":"Investigation of FDG-PET\/CT imaging to guide biopsies in the detection of histological transformation of indolent lymphoma","volume":"93","author":"Moreau","year":"2008","journal-title":"Haematologica"},{"key":"ref_6","first-page":"1535","article-title":"Machine learning in the differentiation of follicular lymphoma from diffuse large B-cell lymphoma with radiomic [18F]FDG PET\/CT features","volume":"49","author":"Yin","year":"2021","journal-title":"Eur. J. Nucl. Med."},{"key":"ref_7","doi-asserted-by":"crossref","unstructured":"Enke, J.S., Moltz, J.H., D\u2019Anastasi, M., Kunz, W.G., Schmidt, C., Maurus, S., M\u00fchlberg, A., Katzmann, A., S\u00fchling, M., and Hahn, H. (2022). Radiomics Features of the Spleen as Surrogates for CT-Based Lymphoma Diagnosis and Subtype Differentiation. Cancers, 14.","DOI":"10.3390\/cancers14030713"},{"key":"ref_8","first-page":"e114","article-title":"Deep learning for [18F]fluorodeoxyglucose-PET-CT classification in patients with lymphoma: A dual-centre retrospective analysis","volume":"6","author":"Leithner","year":"2023","journal-title":"Lancet Digit. Health"},{"key":"ref_9","doi-asserted-by":"crossref","first-page":"374","DOI":"10.1007\/s00330-023-09937-x","article-title":"Deep convolutional neural network for differentiating between sarcoidosis and lymphoma based on [18F]FDG maximum-intensity projection images","volume":"34","author":"Aoki","year":"2023","journal-title":"Eur. Radiol."},{"key":"ref_10","doi-asserted-by":"crossref","unstructured":"Colliot, O. (2023). Reproducibility in Machine Learning for Medical Imaging. Machine Learning for Brain Disorders, Humana.","DOI":"10.1007\/978-1-0716-3195-9"},{"key":"ref_11","doi-asserted-by":"crossref","first-page":"172","DOI":"10.2967\/jnumed.121.262464","article-title":"A Guide to ComBat Harmonization of Imaging Biomarkers in Multicenter Studies","volume":"63","author":"Orlhac","year":"2021","journal-title":"J. Nucl. Med."},{"key":"ref_12","doi-asserted-by":"crossref","first-page":"4493","DOI":"10.1038\/s41598-022-08412-9","article-title":"Generalized ComBat harmonization methods for radiomic features with multi-modal distributions and multiple batch effects","volume":"12","author":"Horng","year":"2022","journal-title":"Sci. Rep."},{"key":"ref_13","doi-asserted-by":"crossref","first-page":"830","DOI":"10.1016\/j.jbi.2013.06.010","article-title":"Defining and measuring completeness of electronic health records for secondary use","volume":"46","author":"Weiskopf","year":"2013","journal-title":"J. Biomed. Inform."},{"key":"ref_14","first-page":"1860","article-title":"Report of the Committee on Hodgkin\u2019s Disease Staging Classification","volume":"31","author":"Carbone","year":"1971","journal-title":"Cancer Res."},{"key":"ref_15","doi-asserted-by":"crossref","unstructured":"Deng, J., Dong, W., Socher, R., Li, L.-J., Li, K., and Fei-Fei, L. (2009, January 20\u201325). ImageNet: A large-scale hierarchical image database. Proceedings of the 2009 IEEE Conference on Computer Vision and Pattern Recognition, Miami, FL, USA.","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"ref_16","doi-asserted-by":"crossref","unstructured":"Yanar, E., Kutan, F., Ayturan, K., Kutbay, U., Alg\u0131n, O., Hardala\u00e7, F., and A\u011f\u0131ldere, A.M. (2025). A Comparative Analysis of the Mamba, Transformer, and CNN Architectures for Multi-Label Chest X-Ray Anomaly Detection in the NIH ChestX-Ray14 Dataset. Diagnostics, 15.","DOI":"10.3390\/diagnostics15172215"},{"key":"ref_17","doi-asserted-by":"crossref","first-page":"427","DOI":"10.1016\/j.ipm.2009.03.002","article-title":"A systematic analysis of performance measures for classification tasks","volume":"45","author":"Sokolova","year":"2009","journal-title":"Inf. Process. Manag."},{"key":"ref_18","first-page":"325","article-title":"Web-Bootstrap Estimate of Area Under ROC Curve","volume":"35","author":"Freylich","year":"2006","journal-title":"Austrian J. Stat."},{"key":"ref_19","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 2017 IEEE International Conference on Computer Vision (ICCV), Venice, Italy.","DOI":"10.1109\/ICCV.2017.74"},{"key":"ref_20","unstructured":"Izrael, D., Battaglia, A., Hoaglin, D., and Battaglia, M. (2002, January 14\u201317). Use of the ROC curve and the bootstrap in comparing weighted logistic regression models. Proceedings of the Twenty-Seventh Annual SAS Users Group International Conference, Orlando, FL, USA."},{"key":"ref_21","doi-asserted-by":"crossref","unstructured":"Gonz\u00e1lez-Rinc\u00f3n, J., M\u00e9ndez, M., G\u00f3mez, S., Garc\u00eda, J.F., Mart\u00edn, P., Bellas, C., Pedrosa, L., Rodr\u00edguez-Pinilla, S.M., I Camacho, F., and Quero, C. (2019). Unraveling transformation of follicular lymphoma to diffuse large B-cell lymphoma. PLoS ONE, 14.","DOI":"10.1371\/journal.pone.0212813"},{"key":"ref_22","doi-asserted-by":"crossref","first-page":"987","DOI":"10.1056\/NEJM199309303291402","article-title":"International non-Hodgkin\u2019s lymphoma prognostic factors project. A predictive model for aggressive non-Hodgkin\u2019s lymphoma","volume":"329","author":"Shipp","year":"1993","journal-title":"N. Engl. J. Med."},{"key":"ref_23","first-page":"127","article-title":"Artificial intelligence in cancer imaging: Clinical challenges and applications","volume":"69","author":"Bi","year":"2019","journal-title":"CA Cancer J. Clin."},{"key":"ref_24","doi-asserted-by":"crossref","unstructured":"Ortega, C., Eshet, Y., Prica, A., Anconina, R., Johnson, S., Constantini, D., Keshavarzi, S., Kulanthaivelu, R., Metser, U., and Veit-Haibach, P. (2023). Combination of FDG PET\/CT Radiomics and Clinical Parameters for Outcome Prediction in Patients with Hodgkin\u2019s Lymphoma. Cancers, 15.","DOI":"10.3390\/cancers15072056"},{"key":"ref_25","doi-asserted-by":"crossref","first-page":"1543","DOI":"10.1093\/annonc\/mdp030","article-title":"High SUV uptake on FDG\u2013PET\/CT predicts for an aggressive B-cell lymphoma in a prospective study of primary FDG\u2013PET\/CT staging in lymphoma","volume":"20","author":"Ngeow","year":"2009","journal-title":"Ann. Oncol."},{"key":"ref_26","doi-asserted-by":"crossref","first-page":"4643","DOI":"10.1200\/JCO.2005.12.072","article-title":"Intensity of18Fluorodeoxyglucose Uptake in Positron Emission Tomography Distinguishes Between Indolent and Aggressive Non-Hodgkin\u2019s Lymphoma","volume":"23","author":"Noy","year":"2005","journal-title":"J. Clin. Oncol."},{"key":"ref_27","doi-asserted-by":"crossref","first-page":"108461","DOI":"10.1016\/j.compbiomed.2024.108461","article-title":"A multi-instance tumor subtype classification method for small PET datasets using RA-DL attention module guided deep feature extraction with radiomics features","volume":"174","author":"Diao","year":"2024","journal-title":"Comput. Biol. Med."},{"key":"ref_28","doi-asserted-by":"crossref","first-page":"107872","DOI":"10.1016\/j.cmpb.2023.107872","article-title":"A hybrid few-shot multiple-instance learning model predicting the aggressiveness of lymphoma in PET\/CT images","volume":"243","author":"Xu","year":"2023","journal-title":"Comput. Methods Programs Biomed."},{"key":"ref_29","doi-asserted-by":"crossref","first-page":"127","DOI":"10.1038\/s41746-021-00497-2","article-title":"Low-count whole-body PET with deep learning in a multicenter and externally validated study","volume":"4","author":"Chaudhari","year":"2021","journal-title":"npj Digit. Med."},{"key":"ref_30","doi-asserted-by":"crossref","first-page":"e26708","DOI":"10.1002\/hbm.26708","article-title":"DeepComBat: A statistically motivated, hyperparameter-robust, deep learning approach to harmonization of neuroimaging data","volume":"45","author":"Hu","year":"2024","journal-title":"Hum. Brain Mapp."},{"key":"ref_31","doi-asserted-by":"crossref","unstructured":"Su, H., Maji, S., Kalogerakis, E., and Learned-Miller, E. (2015, January 7\u201313). Multi-view Convolutional Neural Networks for 3D Shape Recognition. Proceedings of the IEEE International Conference on Computer Vision (ICCV), Santiago, Chile.","DOI":"10.1109\/ICCV.2015.114"},{"key":"ref_32","doi-asserted-by":"crossref","first-page":"3","DOI":"10.1111\/ejh.13863","article-title":"The diagnosis and management of suspected lymphoma in general practice","volume":"110","author":"Paquin","year":"2022","journal-title":"Eur. J. Haematol."},{"key":"ref_33","doi-asserted-by":"crossref","first-page":"102088","DOI":"10.1016\/j.compmedimag.2022.102088","article-title":"Bridging 2D and 3D segmentation networks for computation-efficient volumetric medical image segmentation: An empirical study of 2.5D solutions","volume":"99","author":"Zhang","year":"2022","journal-title":"Comput. Med Imaging Graph."}],"container-title":["Cancers"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/2072-6694\/18\/2\/210\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,1,9]],"date-time":"2026-01-09T09:29:22Z","timestamp":1767950962000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/2072-6694\/18\/2\/210"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,1,9]]},"references-count":33,"journal-issue":{"issue":"2","published-online":{"date-parts":[[2026,1]]}},"alternative-id":["cancers18020210"],"URL":"https:\/\/doi.org\/10.3390\/cancers18020210","relation":{},"ISSN":["2072-6694"],"issn-type":[{"value":"2072-6694","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,1,9]]}}}