{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,12]],"date-time":"2026-08-12T05:27:55Z","timestamp":1786512475274,"version":"build-2736575974"},"reference-count":44,"publisher":"Frontiers Media SA","license":[{"start":{"date-parts":[[2026,8,12]],"date-time":"2026-08-12T00:00:00Z","timestamp":1786492800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":["frontiersin.org"],"crossmark-restriction":true},"short-container-title":["Front. Oncol."],"abstract":"<jats:sec>\n                    <jats:title>Objective<\/jats:title>\n                    <jats:p>\n                      To evaluate the predictive value of tabular deep learning models trained on handcrafted\n                      <jats:sup>18<\/jats:sup>\n                      F-FDG PET\/CT PyRadiomics features and clinical data for cancer-related cognitive impairment (CRCI) among patients with diffuse large B-cell lymphoma without central nervous system involvement (non-CNS DLBCL).\n                    <\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Material and methods<\/jats:title>\n                    <jats:p>\n                      We retrospectively analyzed 112 non-CNS DLBCL patients who underwent brain\n                      <jats:sup>18<\/jats:sup>\n                      F-fluorodeoxyglucose (\n                      <jats:sup>18<\/jats:sup>\n                      F-FDG)PET\/CT. Based on Montreal Cognitive Assessment (MoCA) and Functional Assessment of Cancer Therapy-Cognitive Function (FACT-Cog) scores, patients were classified into the CRCI group (n = 73) and the non-CRCI group (n = 39) and randomly partitioned into training (n=89) and test (n=23) sets at an 8:2 ratio. Five-fold cross-validation was performed within the training set for model development, and bootstrap resampling was used to estimate 95% confidence intervals for AUC. Radiomic features were extracted with PyRadiomics from automatically segmented brain regions using MOOSE120 software. These handcrafted PET\/CT radiomic features and clinical variables were organized as structured tabular datasets; raw PET\/CT images were not used as direct model inputs. Feature selection was performed using correlation coefficients. The performance of seven tabular deep learning models was evaluated using receiver operating characteristic (ROC) curves and decision curve analysis (DCA), and different input modalities (clinical, PET, CT, and combined) were compared. Shapley additive explanations (SHAP) were applied to interpret feature contributions.\n                    <\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Results<\/jats:title>\n                    <jats:p>The AutoInt and Neural Oblivious Decision Ensembles (NODE) models showed the best predictive performance, achieving training areas under the curve (AUCs) of 0.905 and 0.904, and test AUCs of 0.858 and 0.808, respectively. DCA suggested potential clinical utility. In the modality-specific analysis, the AutoInt model integrating CT, PET, and clinical features achieved a training AUC of 0.905 and a test AUC of 0.858, representing the most favorable test-set performance among the evaluated AutoInt input modalities. A CT texture feature from the left occipital lobe emerged as the highest-ranked model contributor in SHAP analysis, with a mean absolute attribution score of approximately 0.0078.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Conclusions<\/jats:title>\n                    <jats:p>Tabular deep learning models based on handcrafted PET\/CT PyRadiomics features showed preliminary potential for predicting CRCI in patients with non-CNS DLBCL. Among the evaluated models, AutoInt achieved the most favorable performance in the exploratory internal test set. Multimodal integration of PET, CT, and clinical tabular features may provide complementary information for CRCI prediction. SHAP analysis identified a left occipital CT texture feature as the top-ranked model contributor; however, this finding should be regarded as exploratory rather than a validated biomarker.<\/jats:p>\n                  <\/jats:sec>","DOI":"10.3389\/fonc.2026.1861773","type":"journal-article","created":{"date-parts":[[2026,8,12]],"date-time":"2026-08-12T04:40:25Z","timestamp":1786509625000},"update-policy":"https:\/\/doi.org\/10.3389\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["Predictive value of 18F-FDG PET\/CT PyRadiomics features using a tabular deep learning model for cancer-related cognitive impairment in patients with DLBCL without CNS involvement"],"prefix":"10.3389","volume":"16","author":[{"given":"Jing","family":"Wang","sequence":"first","affiliation":[{"name":"General Hospital of Ningxia Medical University","place":["Yinchuan, Ningxia Hui Autonomous Region, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yiyuan","family":"Dong","sequence":"additional","affiliation":[{"name":"General Hospital of Ningxia Medical University","place":["Yinchuan, Ningxia Hui Autonomous Region, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ningjun","family":"Xu","sequence":"additional","affiliation":[{"name":"Division of Chinese Medicine, School of Pharmacy, Macau University of Science and Technology","place":["Macau, Macau SAR, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xiaowei","family":"Ma","sequence":"additional","affiliation":[{"name":"General Hospital of Ningxia Medical University","place":["Yinchuan, Ningxia Hui Autonomous Region, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ying","family":"Liu","sequence":"additional","affiliation":[{"name":"General Hospital of Ningxia Medical University","place":["Yinchuan, Ningxia Hui Autonomous Region, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Qian","family":"Zhao","sequence":"additional","affiliation":[{"name":"General Hospital of Ningxia Medical University","place":["Yinchuan, Ningxia Hui Autonomous Region, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1965","published-online":{"date-parts":[[2026,8,12]]},"reference":[{"key":"B1","doi-asserted-by":"publisher","DOI":"10.3390\/medsci9010005","article-title":"Epidemiology of non-Hodgkin's lymphoma","volume":"9","author":"Thandra","year":"2021","journal-title":"Med Sci (Basel)"},{"key":"B2","doi-asserted-by":"publisher","first-page":"54","DOI":"10.1080\/10428194.2021.1975188","article-title":"Epidemiology of diffuse large B-cell lymphoma (DLBCL) and follicular lymphoma (FL) in the United States and Western Europe: population-level projections for 2020-2025","volume":"63","author":"Kanas","year":"2022","journal-title":"Leuk Lymphoma"},{"key":"B3","doi-asserted-by":"publisher","DOI":"10.3389\/fnins.2022.914556","article-title":"Altered regional brain glucose metabolism in diffuse large B-cell lymphoma patients treated with cyclophosphamide, epirubicin, vincristine, and prednisone: an fluorodeoxyglucose positron emission tomography study of 205 cases","volume":"16","author":"Hu","year":"2022","journal-title":"Front Neurosci"},{"key":"B4","doi-asserted-by":"publisher","first-page":"819","DOI":"10.1186\/s13063-022-06731-w","article-title":"Effectiveness of the Unified Barlow Protocol (UP) and neuropsychological treatment in cancer survivors for cognitive impairments: study protocol for a randomized controlled trial","volume":"23","author":"Garc\u00eda-Torres","year":"2022","journal-title":"Trials"},{"key":"B5","doi-asserted-by":"publisher","DOI":"10.1111\/j.1532-5415.2005.53221.x","article-title":"The Montreal Cognitive Assessment, MoCA: a brief screening tool for mild cognitive impairment","volume":"53","author":"Nasreddine","year":"2005","journal-title":"J Am Geriatr Soc"},{"key":"B6","doi-asserted-by":"publisher","DOI":"10.1016\/s1474-4422(12)70191-6","article-title":"Cognitive reserve in ageing and Alzheimer's disease","volume":"11","author":"Stern","year":"2012","journal-title":"Lancet Neurol"},{"key":"B7","doi-asserted-by":"publisher","DOI":"10.1007\/s11910-019-0917-z","article-title":"Defining cognitive reserve and implications for cognitive aging","volume":"19","author":"Pettigrew","year":"2019","journal-title":"Curr Neurol Neurosci Rep"},{"key":"B8","doi-asserted-by":"publisher","first-page":"298","DOI":"10.1002\/cncr.31777","article-title":"Cognitive performance in survivors of breast cancer and markers of biological aging","volume":"125","author":"Carroll","year":"2019","journal-title":"Cancer"},{"key":"B9","doi-asserted-by":"publisher","DOI":"10.2217\/fon-2022-0438","article-title":"Psychometric properties of the 37-item Functional Assessment of Cancer Therapy-Cognitive Function (FACT-Cog) scale","volume":"18","author":"Hajj","year":"2022","journal-title":"Future Oncol"},{"key":"B10","doi-asserted-by":"publisher","DOI":"10.3390\/bioengineering12050442","article-title":"Neuromodulation of cerebral blood flow: a physiological mechanism and methodological review of neurovascular coupling","volume":"12","author":"Zhong","year":"2025","journal-title":"Bioengineering (Basel)"},{"key":"B11","doi-asserted-by":"publisher","DOI":"10.3389\/fncel.2022.1006797","article-title":"Decreased integration of default-mode network during a working memory task in schizophrenia with severe attention deficits","volume":"16","author":"Cheng","year":"2022","journal-title":"Front Cell Neurosci"},{"key":"B12","doi-asserted-by":"publisher","DOI":"10.3390\/cells12091220","article-title":"Basal ganglia compensatory white matter changes on DTI in Alzheimer's disease","volume":"12","author":"Wurst","year":"2023","journal-title":"Cells"},{"key":"B13","doi-asserted-by":"publisher","DOI":"10.1016\/j.nbd.2021.105534","article-title":"TRPM2 contributes to neuroinflammation and cognitive deficits in a cuprizone-induced multiple sclerosis model via NLRP3 inflammasome","volume":"160","author":"Shao","year":"2021","journal-title":"Neurobiol Dis"},{"key":"B14","first-page":"118","article-title":"Associations between breast cancer survivorship and adverse mental health outcomes: A systematic review","volume":"112","author":"Carreira","year":"2020","journal-title":"J Natl Cancer Inst"},{"key":"B15","doi-asserted-by":"publisher","DOI":"10.21037\/qims.2018.11.02","article-title":"Brain morphological alteration and cognitive dysfunction in multiple system atrophy","volume":"8","author":"Zhang","year":"2018","journal-title":"Quant Imaging Med Surg"},{"key":"B16","doi-asserted-by":"publisher","DOI":"10.1088\/0031-9155\/61\/13\/r150","article-title":"Applications and limitations of radiomics","volume":"61","author":"Yip","year":"2016","journal-title":"Phys Med Biol"},{"key":"B17","doi-asserted-by":"publisher","DOI":"10.1158\/0008-5472.can-17-0339","article-title":"Computational radiomics system to decode the radiographic phenotype","volume":"77","author":"van Griethuysen","year":"2017","journal-title":"Cancer Res"},{"key":"B18","doi-asserted-by":"publisher","first-page":"91","DOI":"10.1186\/s13244-020-00887-2","article-title":"Radiomics in medical imaging-\"how-to\" guide and critical reflection","volume":"11","author":"van Timmeren","year":"2020","journal-title":"Insights Imaging"},{"key":"B19","doi-asserted-by":"publisher","DOI":"10.1109\/tnnls.2022.3229161","article-title":"Deep neural networks and tabular data: a survey","volume":"35","author":"Borisov","year":"2024","journal-title":"IEEE Trans Neural Netw Learn Syst"},{"key":"B20","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1097\/rlu.0000000000004433","article-title":"Machine learning model to predict diagnosis of mild cognitive impairment by using radiomic and amyloid brain PET","volume":"48","author":"Ciarmiello","year":"2023","journal-title":"Clin Nucl Med"},{"key":"B21","doi-asserted-by":"publisher","DOI":"10.3390\/diagnostics12040933","article-title":"Radiomics analysis of brain [18F]FDG PET\/CT to predict Alzheimer's disease in patients with amyloid PET positivity: a preliminary report on the application of SPM cortical segmentation, PyRadiomics and machine-learning analysis","volume":"12","author":"Alongi","year":"2022","journal-title":"Diagnostics (Basel)"},{"key":"B22","doi-asserted-by":"publisher","DOI":"10.1016\/j.acra.2022.12.033","article-title":"18F-FDG-PET radiomics based on white matter predicts the progression of mild cognitive impairment to Alzheimer disease: a machine learning study","volume":"30","author":"Peng","year":"2023","journal-title":"Acad Radiol"},{"key":"B23","doi-asserted-by":"publisher","first-page":"56","DOI":"10.1038\/s42256-019-0138-9","article-title":"From local explanations to global understanding with explainable AI for trees","volume":"2","author":"Lundberg","year":"2020","journal-title":"Nat Mach Intell"},{"key":"B24","doi-asserted-by":"publisher","DOI":"10.2174\/1871527320666210512014505","article-title":"An insight into the role of artificial intelligence in the early diagnosis of Alzheimer's disease","volume":"21","author":"Verma","year":"2022","journal-title":"CNS Neurol Disord Drug Targets"},{"key":"B25","doi-asserted-by":"publisher","DOI":"10.1177\/2058460121990296","article-title":"Reviewing the relationship between machines and radiology: the application of artificial intelligence","volume":"10","author":"Ahmad","year":"2021","journal-title":"Acta Radiol Open"},{"key":"B26","doi-asserted-by":"publisher","DOI":"10.1093\/bjrai\/ubae011","article-title":"Artificial intelligence-driven radiomics: developing valuable radiomics signatures with the use of artificial intelligence","volume":"1","author":"Vrettos","year":"2024","journal-title":"BJR Artif Intell"},{"key":"B27","doi-asserted-by":"publisher","DOI":"10.1016\/j.jbi.2020.103671","article-title":"Deep representation learning of patient data from Electronic Health Records (EHR): a systematic review","volume":"115","author":"Si","year":"2021","journal-title":"J BioMed Inform"},{"key":"B28","doi-asserted-by":"crossref","DOI":"10.1145\/3357384.3357925","article-title":"AutoInt: automatic feature interaction learning via self-attentive neural networks","author":"Song","year":"2019"},{"key":"B29","doi-asserted-by":"crossref","DOI":"10.1609\/aaai.v35i8.16826","article-title":"TabNet: attentive interpretable tabular learning","author":"Arik","year":"2021"},{"key":"B30","doi-asserted-by":"publisher","DOI":"10.1148\/ryai.210064","article-title":"External validation of deep learning algorithms for radiologic diagnosis: a systematic review","volume":"4","author":"Yu","year":"2022","journal-title":"Radiol Artif Intell"},{"key":"B31","doi-asserted-by":"crossref","DOI":"10.1371\/journal.pone.0256152","article-title":"Radiomics machine learning study with a small sample size: single random training-test set split may lead to unreliable results","volume":"16","author":"An","year":"2021","journal-title":"PloS One"},{"key":"B32","doi-asserted-by":"publisher","DOI":"10.1109\/tpami.2026.3657217","article-title":"Representation learning for tabular data: a comprehensive survey","volume":"48","author":"Jiang","year":"2026","journal-title":"IEEE Trans Pattern Anal Mach Intell"},{"key":"B33","doi-asserted-by":"publisher","DOI":"10.1016\/j.artmed.2024.102804","article-title":"Prognostic prediction of sepsis patient using transformer with skip connected token for tabular data","volume":"149","author":"Choi","year":"2024","journal-title":"Artif Intell Med"},{"key":"B34","doi-asserted-by":"publisher","DOI":"10.3390\/diagnostics12123215","article-title":"Ensemble learning based on hybrid deep learning model for heart disease early prediction","volume":"12","author":"Almulihi","year":"2022","journal-title":"Diagnostics (Basel)"},{"key":"B35","doi-asserted-by":"publisher","DOI":"10.1109\/tbcas.2023.3348844","article-title":"Population-specific glucose prediction in diabetes care with transformer-based deep learning on the edge","volume":"18","author":"Zhu","year":"2024","journal-title":"IEEE Trans BioMed Circuits Syst"},{"key":"B36","doi-asserted-by":"publisher","first-page":"149","DOI":"10.1038\/s41746-022-00689-4","article-title":"Integrated multimodal artificial intelligence framework for healthcare applications","volume":"5","author":"Soenksen","year":"2022","journal-title":"NPJ Digit Med"},{"key":"B37","doi-asserted-by":"publisher","DOI":"10.3390\/life12020241","article-title":"A multi-center study of CT-based neck nodal radiomics for predicting an adaptive radiotherapy trigger of ill-fitted thermoplastic masks in patients with nasopharyngeal carcinoma","volume":"12","author":"Lam","year":"2022","journal-title":"Life (Basel)"},{"key":"B38","doi-asserted-by":"publisher","first-page":"614","DOI":"10.1038\/s41598-018-36938-4","article-title":"Assessing robustness of radiomic features by image perturbation","volume":"9","author":"Zwanenburg","year":"2019","journal-title":"Sci Rep"},{"key":"B39","doi-asserted-by":"publisher","DOI":"10.21037\/qims-21-86","article-title":"Radiomics feature reliability assessed by intraclass correlation coefficient: a systematic review","volume":"11","author":"Xue","year":"2021","journal-title":"Quantitative Imaging Med Surg"},{"key":"B40","doi-asserted-by":"publisher","DOI":"10.1016\/j.crad.2025.106921","article-title":"Radiomics across modalities: a comprehensive review of neurodegenerative diseases","volume":"85","author":"Inglese","year":"2025","journal-title":"Clin Radiol"},{"key":"B41","doi-asserted-by":"publisher","first-page":"Article 171","DOI":"10.1145\/3770684","article-title":"Beyond the clock: exploring multimodal behavior markers of mild cognitive impairment in older adults during clock drawing test","volume":"9","author":"Fan","year":"2025","journal-title":"Proc ACM Interact Mob Wearable Ubiquitous Technol"},{"key":"B42","doi-asserted-by":"publisher","DOI":"10.1093\/gerona\/glaf158","article-title":"Accelerometer-measured multidimensional physical activity patterns and physical functional decline: a prospective national cohort study of aging","volume":"80","author":"Fan","year":"2025","journal-title":"J Gerontol A Biol Sci Med Sci"},{"key":"B43","doi-asserted-by":"publisher","DOI":"10.1186\/s12966-025-01706-x","article-title":"From physical activity patterns to cognitive status: development and validation of novel digital biomarkers for cognitive assessment in older adults","volume":"22","author":"Fan","year":"2025","journal-title":"Int J Behav Nutr Phys Act"},{"key":"B44","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1109\/tim.2024.3470051","article-title":"PFIMPA: a multimodal approach to predict physical function impairment in older adults using physical activity from wrist-worn accelerometer","volume":"73","author":"Fan","year":"2024","journal-title":"IEEE Trans Instrum Meas"}],"container-title":["Frontiers in Oncology"],"original-title":[],"link":[{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fonc.2026.1861773\/full","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,8,12]],"date-time":"2026-08-12T04:40:40Z","timestamp":1786509640000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fonc.2026.1861773\/full"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,8,12]]},"references-count":44,"alternative-id":["10.3389\/fonc.2026.1861773"],"URL":"https:\/\/doi.org\/10.3389\/fonc.2026.1861773","relation":{},"ISSN":["2234-943X"],"issn-type":[{"value":"2234-943X","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,8,12]]},"article-number":"1861773"}}