{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,18]],"date-time":"2026-08-18T04:24:04Z","timestamp":1787027044102,"version":"build-2736575974"},"reference-count":53,"publisher":"Frontiers Media SA","license":[{"start":{"date-parts":[[2025,8,21]],"date-time":"2025-08-21T00:00:00Z","timestamp":1755734400000},"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>To develop a deep learning radiomics(DLR)model integrating PET\/CT radiomics, deep learning features, and clinical parameters for early prediction of bone oligometastases (\u22645 lesions) in breast cancer.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Methods<\/jats:title>\n                    <jats:p>We retrospectively analyzed 207 breast cancer patients with 312 bone lesions, comprising 107 benign and 205 malignant lesions, including 89 lesions with confirmed bone metastases. Radiomic features were extracted from computed tomography (CT), positron emission tomography (PET), and fused PET\/CT images using PyRadiomics embedded in the uAI Research Portal. Standardized feature extraction and feature selection were performed using the Least Absolute Shrinkage and Selection Operator (LASSO) method. We developed and validated three models: a radiomics-based model, a deep learning model using BasicNet, and a deep learning radiomics (DLR) model incorporating clinical and metabolic parameters. Model performance was assessed using the area under the receiver operating characteristic curve (AUC), accuracy, sensitivity, and specificity. Statistical comparisons were conducted using the DeLong test.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Results<\/jats:title>\n                    <jats:p>Visual assessment of fused PET\/CT images identified 227 (72.8%) abnormal lesions, demonstrating greater sensitivity than CT or PET alone. The complex radiomics model achieved a sensitivity of 98.9% [96.1%\u201399.4%], specificity of 98.2% [88.1%\u201399.6%], accuracy of 98.7% [89.6%\u201399.5%], and area under the curve (AUC) of 0.989. The BasicNet model outperformed other transfer learning models, achieving an AUC of 0.961. The DeLong test confirmed that the AUC of the BasicNet model was significantly higher than the traditional radiomics model. The DLR+Complex model with a random forest classifier achieved the highest overall performance, with an AUC of 0.990, sensitivity of 98.6%, specificity of 90.5%, and accuracy of 99.8%.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Conclusions<\/jats:title>\n                    <jats:p>The BasicNet model significantly outperformed traditional radiomics approaches in predicting bone oligometastases in breast cancer patients. The DLR+Complex model demonstrated the best predictive performance across all metrics. Future strategies for precise diagnosis and treatment should incorporate histologic subtype, advanced imaging, and molecular biomarkers.<\/jats:p>\n                  <\/jats:sec>","DOI":"10.3389\/fonc.2025.1621677","type":"journal-article","created":{"date-parts":[[2025,8,21]],"date-time":"2025-08-21T12:40:57Z","timestamp":1755780057000},"update-policy":"https:\/\/doi.org\/10.3389\/crossmark-policy","source":"Crossref","is-referenced-by-count":2,"title":["Prediction of bone oligometastases in breast cancer using models based on deep learning radiomics of PET\/CT imaging"],"prefix":"10.3389","volume":"15","author":[{"given":"Guoxiu","family":"Lu","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ronghui","family":"Tian","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Wei","family":"Yang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jiayi","family":"Zhao","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Wenjing","family":"Chen","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zijie","family":"Xiang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Shanhu","family":"Hao","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Guoxu","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1965","published-online":{"date-parts":[[2025,8,21]]},"reference":[{"key":"B1","doi-asserted-by":"publisher","DOI":"10.1007\/s10585-023-10230-w","article-title":"Associations amongst genes, molecules, cells, and organs in breast cancer\u00a0metastasis","volume":"41","author":"Nathanson","year":"2024","journal-title":"Clin Exp metastasis"},{"key":"B2","doi-asserted-by":"publisher","DOI":"10.1002\/cac2.12207","article-title":"Global patterns of breast\u00a0cancer incidence and mortality: A population-based cancer registry data analysis from 2000 to 2020","volume":"41","author":"Lei","year":"2021","journal-title":"Cancer Commun (Lond)"},{"key":"B3","doi-asserted-by":"publisher","first-page":"2094","DOI":"10.3390\/diagnostics12092094","article-title":"Percutaneous CT-guided bone lesion biopsy for confirmation of bone metastases in patients with breast cancer","volume":"12","author":"Kovacevic","year":"2022","journal-title":"Diagnostics (Basel)"},{"key":"B4","doi-asserted-by":"publisher","first-page":"4124","DOI":"10.3390\/ijms21114124","article-title":"Switching homes: how cancer moves to bone","volume":"21","author":"Ponzetti","year":"2020","journal-title":"Int J Mol Sci"},{"key":"B5","doi-asserted-by":"publisher","DOI":"10.1200\/GO.23.00275","article-title":"Second chance for cure: stereotactic ablative radiotherapy in oligometastatic disease","volume":"10","author":"Salim","year":"2024","journal-title":"JCO Global Oncol"},{"key":"B6","doi-asserted-by":"publisher","DOI":"10.1016\/S1052-3359(25)00556-3","article-title":"The management of non-small-cell lung cancer with oligometastases","volume":"11","author":"Downey","year":"2001","journal-title":"Chest Surg Clin N Am"},{"key":"B7","doi-asserted-by":"publisher","DOI":"10.1016\/s0360-3016(03)01442-1","article-title":"Is there a favorable subset of patients with prostate cancer who develop oligometastases","volume":"58","author":"Singh","year":"2004","journal-title":"Int J Radiat oncology biology Phys"},{"key":"B8","doi-asserted-by":"publisher","DOI":"10.1016\/j.semradonc.2005.12.004","article-title":"Physics and imaging for targeting of oligometastases","volume":"16","author":"Yin","year":"2006","journal-title":"Semin Radiat Oncol"},{"key":"B9","doi-asserted-by":"publisher","first-page":"125704","DOI":"10.1016\/j.ijpharm.2025.125704","article-title":"Enhancing YOLOv8n with Mamba-like linear attention for defect detection and coating thickness analysis of irregular film tablet","volume":"678","author":"Wang","year":"2025","journal-title":"Int J pharmaceutics"},{"key":"B10","doi-asserted-by":"publisher","first-page":"23","DOI":"10.1002\/path.4288","article-title":"Metastatic progression of breast cancer: insights from 50 years of autopsies","volume":"232","author":"Cummings","year":"2014","journal-title":"J Pathol"},{"key":"B11","doi-asserted-by":"publisher","DOI":"10.1007\/s12032-007-9027-x","article-title":"Diagnostic value of magnetic resonance imaging and scintigraphy in patients with metastatic breast cancer of the axial skeleton: a comparative study","volume":"25","author":"Yilmaz","year":"2008","journal-title":"Med Oncol"},{"key":"B12","doi-asserted-by":"publisher","DOI":"10.1200\/JCO.2006.09.2940","article-title":"Magnetic resonance imaging of the axial skeleton for detecting bone metastases in patients with high-risk prostate cancer: diagnostic and cost-effectiveness and comparison with current detection strategies","volume":"25","author":"Lecouvet","year":"2007","journal-title":"J Clin Oncol"},{"key":"B13","doi-asserted-by":"publisher","DOI":"10.1016\/j.ejca.2017.12.012","article-title":"Strategies and technical challenges for imaging oligometastatic disease: Recommendations from the European Organisation for Research and Treatment of Cancer imaging group","volume":"91","author":"deSouza","year":"2018","journal-title":"Eur J Cancer (Oxford England: 1990)"},{"key":"B14","doi-asserted-by":"publisher","DOI":"10.1097\/CORR.0000000000001681","article-title":"What is the comparative ability of 18F-FDG PET\/CT, 99mTc-MDP skeletal scintigraphy, and whole-body MRI as a staging investigation to detect skeletal metastases in patients with osteosarcoma and ewing sarcoma","volume":"479","author":"Aryal","year":"2021","journal-title":"Clin Orthop Relat Res"},{"key":"B15","doi-asserted-by":"publisher","first-page":"356","DOI":"10.1053\/j.semnuclmed.2023.11.005","article-title":"SPECT\/CT, PET\/CT, and PET\/MRI for Response Assessment of Bone Metastases","volume":"54","author":"Zamani-Siahkali","year":"2024","journal-title":"Semin Nucl Med"},{"key":"B16","doi-asserted-by":"publisher","DOI":"10.1007\/s00330-017-4994-6","article-title":"Comparison of hybrid 68Ga-PSMA-PET\/CT and 99mTc-DPD-SPECT\/CT for the detection of bone metastases in prostate cancer patients: Additional value of morphologic information from low dose CT","volume":"28","author":"Janssen","year":"2018","journal-title":"Eur Radiol"},{"key":"B17","doi-asserted-by":"publisher","DOI":"10.1093\/noajnl\/vdad175","article-title":"Stereotactic body radiotherapy for treatment of spinal metastasis: A systematic review of the literature","volume":"6","author":"McVeigh","year":"2024","journal-title":"Neurooncol Adv"},{"key":"B18","doi-asserted-by":"publisher","DOI":"10.1002\/ijc.31793","article-title":"A risk-based approach to identifying oligometastatic disease on imaging","volume":"144","author":"deSouza","year":"2019","journal-title":"Int J Cancer"},{"key":"B19","doi-asserted-by":"publisher","first-page":"107811","DOI":"10.1016\/j.cmpb.2023.107811","article-title":"Computer-aided diagnosis of skeletal metastases in multi-parametric whole-body MRI","volume":"242","author":"Ceranka","year":"2023","journal-title":"Comput\u00a0Methods programs biomedicine"},{"key":"B20","doi-asserted-by":"publisher","DOI":"10.1016\/j.acra.2024.11.018","article-title":"BMSMM-net: A bone metastasis segmentation framework based on mamba and multiperspective extraction","volume":"32","author":"Shang","year":"2025","journal-title":"Acad Radiol"},{"key":"B21","doi-asserted-by":"publisher","DOI":"10.1109\/EMBC44109.2020.9175904","article-title":"Deep learning approaches for bone and bone lesion segmentation on 18FDG PET\/CT imaging in the context of metastatic breast cancer","volume":"2020","author":"Moreau","year":"2020","journal-title":"Annu Int Conf IEEE Eng Med Biol Soc"},{"key":"B22","doi-asserted-by":"publisher","first-page":"101","DOI":"10.3390\/cancers14010101","article-title":"Automatic segmentation of metastatic breast cancer lesions on (18)F-FDG PET\/CT longitudinal acquisitions for treatment response assessment","volume":"14","author":"Moreau","year":"2021","journal-title":"Cancers"},{"key":"B23","doi-asserted-by":"publisher","DOI":"10.1097\/SCS.0000000000011360","article-title":"Moving to 3D: quantifying virtual surgical planning accuracy using geometric morphometrics and cephalometrics in facial feminization surgery","author":"Hu","year":"2025","journal-title":"J Craniofac Surg"},{"key":"B24","doi-asserted-by":"publisher","DOI":"10.3760\/cma.j.cn121430-20201012-00667","article-title":"Design and development of analysis software for acid-base balance disorder based on Visual Basic.NET","volume":"33","author":"Ma","year":"2021","journal-title":"Zhonghua Wei Zhong Bing Ji Jiu Yi Xue"},{"key":"B25","doi-asserted-by":"publisher","DOI":"10.1245\/s10434-012-2307-5","article-title":"Clinicopathologic risk factors for the local recurrence of phyllodes tumors of the breast","volume":"19","author":"Jang","year":"2012","journal-title":"Ann Surg Oncol"},{"key":"B26","doi-asserted-by":"publisher","DOI":"10.1016\/j.jos.2019.02.014","article-title":"Effects of anterior boundary of the necrotic lesion on the progressive collapse after\u00a0varus osteotomy for osteonecrosis of the femoral head","volume":"25","author":"Kubo","year":"2020","journal-title":"J orthopaedic Sci"},{"key":"B27","doi-asserted-by":"publisher","DOI":"10.1007\/s11517-025-03320-2","article-title":"Improved segmentation of hepatic vascular networks in ultrasound volumes using 3D U-Net with intensity transformation-based data augmentation","volume":"63","author":"Takahashi","year":"2025","journal-title":"Med Biol Eng Comput"},{"key":"B28","doi-asserted-by":"publisher","DOI":"10.1053\/j.semnuclmed.2024.11.005","article-title":"Radiomics and artificial intelligence landscape for [18F]FDG PET\/CT in multiple myeloma","volume":"55","author":"Sachpekidis","year":"2024","journal-title":"Semin Nucl Med"},{"key":"B29","doi-asserted-by":"publisher","DOI":"10.7717\/peerj-cs.454","article-title":"AresB-Net: accurate residual binarized neural networks using shortcut concatenation and shuffled grouped convolution","volume":"7","author":"Kim","year":"2021","journal-title":"PeerJ Comput Sci"},{"key":"B30","doi-asserted-by":"publisher","DOI":"10.3389\/fonc.2024.1489973","article-title":"Value of radiomics and deep learning feature fusion models based on dce-mri in distinguishing sinonasal squamous cell carcinoma from lymphoma","volume":"14","author":"Zhang","year":"2024","journal-title":"Front Oncol"},{"key":"B31","doi-asserted-by":"publisher","DOI":"10.1016\/j.heliyon.2024.e37345","article-title":"Radiomic features based on pyradiomics predict CD276 expression associated with breast cancer prognosis","volume":"10","author":"Li","year":"2024","journal-title":"Heliyon"},{"key":"B32","doi-asserted-by":"publisher","DOI":"10.4103\/ijnm.ijnm_111_21","article-title":"Radiomic analysis of positron-emission tomography and computed tomography images to differentiate between multiple myeloma and skeletal metastases","volume":"37","author":"Mannam","year":"2022","journal-title":"Indian J Nucl Med"},{"key":"B33","doi-asserted-by":"publisher","DOI":"10.1016\/j.acra.2024.06.040","article-title":"Combined quantitative amyloid-\u03b2 PET and structural MRI features improve alzheimer\u2019s disease classification in random forest model - A multicenter study","volume":"31","author":"Bao","year":"2024","journal-title":"Acad Radiol"},{"key":"B34","doi-asserted-by":"publisher","DOI":"10.3389\/fonc.2025.1510386","article-title":"Prediction of EGFR mutations in non-small cell lung cancer: a nomogram based on 18F-FDG PET and thin-section CT radiomics with machine learning","volume":"15","author":"Li","year":"2025","journal-title":"Front Oncol"},{"key":"B35","doi-asserted-by":"publisher","first-page":"484","DOI":"10.1007\/s00432-024-05987-w","article-title":"Intratumoral and peritumoral radiomics for preoperative prediction of neoadjuvant chemotherapy effect in breast cancer based on 18F-FDG PET\/CT","volume":"150","author":"Hou","year":"2024","journal-title":"J Cancer Res Clin Oncol"},{"key":"B36","doi-asserted-by":"publisher","DOI":"10.3389\/fnins.2025.1576931","article-title":"Alzheimer\u2019s disease recognition via long-range state space model using multi-modal brain images","volume":"19","author":"Ren","year":"2025","journal-title":"Front Neurosci"},{"key":"B37","doi-asserted-by":"publisher","DOI":"10.1002\/cam4.70826","article-title":"Delta-he as a novel predictive and prognostic biomarker in patients with NSCLC treated with PD-1\/PD-L1 inhibitors","volume":"14","author":"Hong","year":"2025","journal-title":"Cancer Med"},{"key":"B38","doi-asserted-by":"publisher","DOI":"10.1007\/s00259-023-06108-4","article-title":"Automated quantification of PET\/CT skeletal tumor burden in prostate cancer using artificial intelligence: The PET index","volume":"50","author":"Lindgren Belal","year":"2023","journal-title":"Eur J Nucl Med Mol Imaging"},{"key":"B39","doi-asserted-by":"publisher","first-page":"225019","DOI":"10.1088\/1361-6560\/aaebd0","article-title":"Automated classification of benign and Malignant lesions in 18F-NaF PET\/CT images using machine learning","volume":"63","author":"Perk","year":"2018","journal-title":"Phys Med Biol"},{"key":"B40","doi-asserted-by":"publisher","first-page":"51","DOI":"10.1186\/s40658-020-00316-9","article-title":"RECOMIA-a cloud-based platform for artificial intelligence research in nuclear medicine and radiology","volume":"7","author":"Tr\u00e4g\u00e5rdh","year":"2020","journal-title":"EJNMMI Phys"},{"key":"B41","doi-asserted-by":"publisher","DOI":"10.3389\/fnagi.2021.764872","article-title":"Deep-learning radiomics for discrimination conversion of alzheimer\u2019s disease in patients with mild cognitive impairment: A study based on 18F-FDG PET imaging","volume":"13","author":"Zhou","year":"2021","journal-title":"Front Aging Neurosci"},{"key":"B42","doi-asserted-by":"publisher","DOI":"10.3389\/fmed.2023.1157000","article-title":"Prediction of the COVID disease using lung CT images by Deep Learning algorithm: DETS-optimized Resnet 101 classifier","volume":"10","author":"Haennah","year":"2023","journal-title":"Front In Med"},{"key":"B43","doi-asserted-by":"publisher","first-page":"100654","DOI":"10.1016\/j.jbo.2024.100654","article-title":"Mixed reality infrastructure based on deep learning medical image segmentation and 3D visualization for bone tumors using DCU-Net","volume":"50","author":"Wang","year":"2025","journal-title":"J Bone Oncol"},{"key":"B44","doi-asserted-by":"publisher","first-page":"108730","DOI":"10.1016\/j.cmpb.2025.108730","article-title":"S-Net: A novel shallow network for enhanced detail retention in medical image segmentation","volume":"265","author":"Shang","year":"2025","journal-title":"Comput Methods Programs BioMed"},{"key":"B45","doi-asserted-by":"publisher","DOI":"10.1093\/jbmr\/zjaf054","article-title":"Dive into the bone: new insights into molecular mechanisms\u00a0of\u00a0cancer bone invasion","volume":"40","author":"Tsukasaki","year":"2025","journal-title":"J Bone Miner Res"},{"key":"B46","doi-asserted-by":"publisher","first-page":"221","DOI":"10.3892\/ol.2025.14967","article-title":"Cancer metastasis to the bone: Mechanisms and animal models (Review)","volume":"29","author":"Deng","year":"2025","journal-title":"Oncol Lett"},{"key":"B47","doi-asserted-by":"publisher","DOI":"10.1007\/s00259-016-3415-4","article-title":"The EANM practice guidelines for bone scintigraphy","volume":"43","author":"Van den Wyngaert","year":"2016","journal-title":"Eur J Nucl Med Mol Imaging"},{"key":"B48","doi-asserted-by":"publisher","first-page":"100659","DOI":"10.1016\/j.jbo.2024.100659","article-title":"Predicting bone metastasis risk of colorectal tumors using radiomics and deep learning ViT model","volume":"51","author":"Chen","year":"2025","journal-title":"J Bone Oncol"},{"key":"B49","doi-asserted-by":"publisher","DOI":"10.3389\/fonc.2024.1298516","article-title":"A semi-automatic deep learning model based on biparametric MRI scanning strategy to predict bone metastases in newly diagnosed prostate cancer patients","volume":"14","author":"Xinyang","year":"2024","journal-title":"Front Oncol"},{"key":"B50","doi-asserted-by":"publisher","first-page":"103079","DOI":"10.1016\/j.inffus.2025.103079","article-title":"TSCMamba: mamba meets multi-view learning for time\u00a0series classification","volume":"120","author":"Ahamed","year":"2025","journal-title":"Int J Inf fusion"},{"key":"B51","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2025.3556561","article-title":"Rethinking efficient and\u00a0effective point-based networks for event camera classification and regression","volume":"47","author":"Ren","year":"2025","journal-title":"IEEE\u00a0Trans Pattern Anal Mach Intell"},{"key":"B52","doi-asserted-by":"publisher","DOI":"10.1016\/j.ijrobp.2022.06.067","article-title":"Completeness of\u00a0reporting oligometastatic disease characteristics in the literature and influence on\u00a0oligometastatic disease classification using the ESTRO\/EORTC nomenclature","volume":"114","author":"Nevens","year":"2022","journal-title":"Int\u00a0J Radiat oncology biology Phys"},{"key":"B53","doi-asserted-by":"publisher","first-page":"117","DOI":"10.1186\/s12943-025-02322-w","article-title":"Correction: Targeting SOST using a small\u2212molecule compound retards breast cancer bone metastasis","volume":"24","author":"Sun","year":"2025","journal-title":"Mol Cancer"}],"container-title":["Frontiers in Oncology"],"original-title":[],"link":[{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fonc.2025.1621677\/full","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,8,21]],"date-time":"2025-08-21T12:40:59Z","timestamp":1755780059000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fonc.2025.1621677\/full"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,8,21]]},"references-count":53,"alternative-id":["10.3389\/fonc.2025.1621677"],"URL":"https:\/\/doi.org\/10.3389\/fonc.2025.1621677","relation":{},"ISSN":["2234-943X"],"issn-type":[{"value":"2234-943X","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,8,21]]},"article-number":"1621677"}}