{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,1]],"date-time":"2026-09-01T15:19:12Z","timestamp":1788275952166,"version":"build-2803163510"},"reference-count":38,"publisher":"Ovid Technologies (Wolters Kluwer Health)","issue":"7","funder":[{"name":"Hallym University Research Fund, 2023","award":["HURF-2023-46"],"award-info":[{"award-number":["HURF-2023-46"]}]}],"content-domain":{"domain":["lww.com","ovid.com"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2025,7]]},"abstract":"<jats:sec>\n            <jats:title>Purpose:<\/jats:title>\n            <jats:p>Convolutional neural networks (CNNs) have been studied for detecting bone metastases on bone scans; however, the application of ConvNeXt and transformer models has not yet been explored. This study aims to evaluate the performance of various deep learning models, including the ConvNeXt and transformer models, in diagnosing metastatic lesions from bone scans.<\/jats:p>\n          <\/jats:sec>\n          <jats:sec>\n            <jats:title>Materials and Methods:<\/jats:title>\n            <jats:p>We retrospectively analyzed bone scans from patients with cancer obtained at 2 institutions: the training and validation sets (n=4626) were from Hospital 1 and the test set (n=1428) was from Hospital 2. The deep learning models evaluated included ResNet18, the Data-Efficient Image Transformer (DeiT), the Vision Transformer (ViT Large 16), the Swin Transformer (Swin Base), and ConvNeXt Large. Gradient-weighted class activation mapping (Grad-CAM) was used for visualization.<\/jats:p>\n          <\/jats:sec>\n          <jats:sec>\n            <jats:title>Results:<\/jats:title>\n            <jats:p>Both the validation set and the test set demonstrated that the ConvNeXt large model (0.969 and 0.885, respectively) exhibited the best performance, followed by the Swin Base model (0.965 and 0.840, respectively), both of which significantly outperformed ResNet (0.892 and 0.725, respectively). Subgroup analyses revealed that all the models demonstrated greater diagnostic accuracy for patients with polymetastasis compared with those with oligometastasis. Grad-CAM visualization revealed that the ConvNeXt Large model focused more on identifying local lesions, whereas the Swin Base model focused on global areas such as the axial skeleton and pelvis.<\/jats:p>\n          <\/jats:sec>\n          <jats:sec>\n            <jats:title>Conclusions:<\/jats:title>\n            <jats:p>Compared with traditional CNN and transformer models, the ConvNeXt model demonstrated superior diagnostic performance in detecting bone metastases from bone scans, especially in cases of polymetastasis, suggesting its potential in medical image analysis.<\/jats:p>\n          <\/jats:sec>","DOI":"10.1097\/rlu.0000000000005898","type":"journal-article","created":{"date-parts":[[2025,4,16]],"date-time":"2025-04-16T13:00:08Z","timestamp":1744808408000},"page":"596-604","update-policy":"https:\/\/doi.org\/10.1097\/lww.0000000000001000","source":"Crossref","is-referenced-by-count":5,"title":["Comparison of CNNs and Transformer Models in Diagnosing Bone Metastases in Bone Scans Using Grad-CAM"],"prefix":"10.1097","volume":"50","author":[{"given":"Sehyun","family":"Pak","sequence":"first","affiliation":[{"name":"Department of Medicine, Hallym University College of Medicine, Chuncheon, Gangwon, Republic of Korea"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1290-0949","authenticated-orcid":false,"given":"Hye Joo","family":"Son","sequence":"additional","affiliation":[{"name":"Department of Nuclear Medicine, Dankook University Medical Center, Cheonan, Chungnam, Republic of Korea"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Dongwoo","family":"Kim","sequence":"additional","affiliation":[{"name":"Department of Nuclear Medicine, Hallym University Sacred Heart Hospital, Hallym University College of Medicine, Anyang, Gyeonggi, Republic of Korea"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6200-0159","authenticated-orcid":false,"given":"Ji Young","family":"Woo","sequence":"additional","affiliation":[{"name":"Department of Radiology, Hallym University Kangnam Sacred Heart Hospital, Hallym University College of Medicine, Seoul, Republic of Korea"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9606-4556","authenticated-orcid":false,"given":"Ik","family":"Yang","sequence":"additional","affiliation":[{"name":"Department of Radiology, Hallym University Kangnam Sacred Heart Hospital, Hallym University College of Medicine, Seoul, Republic of Korea"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Hee Sung","family":"Hwang","sequence":"additional","affiliation":[{"name":"Department of Nuclear Medicine, Hallym University Sacred Heart Hospital, Hallym University College of Medicine, Anyang, Gyeonggi, Republic of Korea"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2022-6333","authenticated-orcid":false,"given":"Dohyoung","family":"Rim","sequence":"additional","affiliation":[{"name":"Rowan, Seoul, Republic of Korea"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Min Seok","family":"Choi","sequence":"additional","affiliation":[{"name":"PE Data Solution, SK hynix, Icheon, Gyeonggi, Republic of Korea"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4580-3918","authenticated-orcid":false,"given":"Suk Hyun","family":"Lee","sequence":"additional","affiliation":[{"name":"Department of Radiology, Hallym University Kangnam Sacred Heart Hospital, Hallym University College of Medicine, Seoul, Republic of Korea"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"276","published-online":{"date-parts":[[2025,4,16]]},"reference":[{"key":"R1-20250619","doi-asserted-by":"crossref","first-page":"347","DOI":"10.1053\/j.semnuclmed.2015.02.002","article-title":"Pitfalls and limitations of radionuclide planar and hybrid bone imaging","volume":"45","author":"Agrawal","year":"2015","journal-title":"Semin Nucl Med"},{"key":"R2-20250619","doi-asserted-by":"crossref","first-page":"44","DOI":"10.1186\/s12885-017-3922-0","article-title":"Incidence of bone metastases in patients with solid tumors: analysis of oncology electronic medical records in the United States","volume":"18","author":"Hernandez","year":"2018","journal-title":"BMC Cancer"},{"key":"R3-20250619","doi-asserted-by":"crossref","first-page":"482","DOI":"10.21037\/atm.2020.03.55","article-title":"Incidence of patients with bone metastases at diagnosis of solid tumors in adults: a large population-based study","volume":"8","author":"Huang","year":"2020","journal-title":"Ann Transl Med"},{"key":"R4-20250619","doi-asserted-by":"crossref","first-page":"782","DOI":"10.1016\/j.urology.2009.12.050","article-title":"Diagnosis of bone metastases in urological malignancies--an update","volume":"76","author":"Rajarubendra","year":"2010","journal-title":"Urology"},{"key":"R5-20250619","doi-asserted-by":"crossref","first-page":"51","DOI":"10.1007\/s13139-021-00733-3","article-title":"Preparing for the artificial intelligence revolution in nuclear cardiology","volume":"57","author":"Garcia","year":"2023","journal-title":"Nucl Med Mol Imaging"},{"key":"R6-20250619","doi-asserted-by":"crossref","first-page":"216","DOI":"10.1007\/s13139-023-00802-9","article-title":"Deep learning-based feature extraction from whole-body PET\/CT employing maximum intensity projection images: preliminary results of lung cancer Data","volume":"57","author":"Gil","year":"2023","journal-title":"Nucl Med Mol Imaging"},{"key":"R7-20250619","doi-asserted-by":"crossref","first-page":"94","DOI":"10.1007\/s13139-022-00769-z","article-title":"Voxel-based internal dosimetry for (177)Lu-labeled radiopharmaceutical therapy using deep residual learning","volume":"57","author":"Kim","year":"2023","journal-title":"Nucl Med Mol Imaging"},{"key":"R8-20250619","doi-asserted-by":"crossref","first-page":"86","DOI":"10.1007\/s13139-022-00745-7","article-title":"Automatic lung cancer segmentation in [(18)F]FDG PET\/CT using a two-stage deep learning approach","volume":"57","author":"Park","year":"2023","journal-title":"Nucl Med Mol Imaging"},{"key":"R9-20250619","doi-asserted-by":"crossref","first-page":"73","DOI":"10.1007\/s13139-022-00772-4","article-title":"MR template-based individual brain PET volumes-of-interest generation neither using MR nor using spatial normalization","volume":"57","author":"Seo","year":"2023","journal-title":"Nucl Med Mol Imaging"},{"key":"R10-20250619","doi-asserted-by":"crossref","first-page":"2793","DOI":"10.1007\/s11831-023-09898-w","article-title":"Convolutional neural network in medical image analysis: a review","volume":"30","author":"Kshatri","year":"2023","journal-title":"Arch Comput Methods Eng"},{"key":"R11-20250619","doi-asserted-by":"crossref","first-page":"107660","DOI":"10.1016\/j.cmpb.2023.107660","article-title":"ResNet and its application to medical image processing: research progress and challenges","volume":"240","author":"Xu","year":"2023","journal-title":"Comput Methods Programs Biomed"},{"key":"R12-20250619","doi-asserted-by":"crossref","first-page":"103000","DOI":"10.1016\/j.media.2023.103000","article-title":"Advances in medical image analysis with vision Transformers: A comprehensive review","volume":"91","author":"Azad","year":"2024","journal-title":"Med Image Anal"},{"key":"R13-20250619","first-page":"11976","article-title":"A convnet for the 2020s","author":"Liu","year":"2022","journal-title":"Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition"},{"key":"R14-20250619","doi-asserted-by":"crossref","first-page":"1384","DOI":"10.3390\/diagnostics11081384","article-title":"TransMed: Transformers advance multi-modal medical image classification","volume":"11","author":"Dai","year":"2021","journal-title":"Diagnostics (Basel)"},{"key":"R15-20250619","first-page":"10012","article-title":"Swin transformer: hierarchical vision transformer using shifted windows","author":"Liu","year":"2021","journal-title":"Proceedings of the IEEE\/CVF international conference on computer vision"},{"key":"R16-20250619","doi-asserted-by":"crossref","first-page":"2559","DOI":"10.1007\/s10278-024-01086-x","article-title":"A comparative analysis of deep learning-based approaches for classifying dental implants decision support system","volume":"37","author":"Lubbad","year":"2024","journal-title":"J Imaging Inform Med"},{"key":"R17-20250619","doi-asserted-by":"crossref","first-page":"239","DOI":"10.3390\/dermatopathology11030026","article-title":"Enhancing melanoma diagnosis with advanced deep learning models focusing on Vision Transformer, Swin Transformer, and ConvNeXt","volume":"11","author":"Aksoy","year":"2024","journal-title":"Dermatopathology (Basel)"},{"key":"R18-20250619","doi-asserted-by":"crossref","first-page":"1578","DOI":"10.3390\/brainsci13111578","article-title":"Multi-slice generation sMRI and fMRI for autism spectrum disorder diagnosis using 3D-CNN and vision transformers","volume":"13","author":"Alharthi","year":"2023","journal-title":"Brain Sci"},{"key":"R19-20250619","doi-asserted-by":"crossref","first-page":"102809","DOI":"10.1016\/j.media.2023.102809","article-title":"From modern CNNs to vision transformers: Assessing the performance, robustness, and classification strategies of deep learning models in histopathology","volume":"87","author":"Springenberg","year":"2023","journal-title":"Med Image Anal"},{"key":"R20-20250619","doi-asserted-by":"crossref","first-page":"1098893","DOI":"10.3389\/fphys.2023.1098893","article-title":"Deep learning for the screening of primary ciliary dyskinesia based on cranial computed tomography","volume":"14","author":"Duan","year":"2023","journal-title":"Front Physiol"},{"key":"R21-20250619","doi-asserted-by":"crossref","first-page":"585","DOI":"10.1007\/s00259-021-05481-2","article-title":"Diagnostic performance of deep learning models for detecting bone metastasis on whole-body bone scan in prostate cancer","volume":"49","author":"Han","year":"2022","journal-title":"Eur J Nucl Med Mol Imaging"},{"key":"R22-20250619","doi-asserted-by":"crossref","first-page":"e22409","DOI":"10.1016\/j.heliyon.2023.e22409","article-title":"ChatGPT-assisted deep learning for diagnosing bone metastasis in bone scans: bridging the AI gap for clinicians","volume":"9","author":"Son","year":"2023","journal-title":"Heliyon"},{"key":"R23-20250619","doi-asserted-by":"crossref","first-page":"1248","DOI":"10.3390\/jpm11121248","article-title":"Detection of bone metastases on bone scans through image classification with contrastive learning","volume":"11","author":"Hsieh","year":"2021","journal-title":"J Pers Med"},{"key":"R24-20250619","doi-asserted-by":"crossref","first-page":"101784","DOI":"10.1016\/j.media.2020.101784","article-title":"Automated diagnosis of bone metastasis based on multi-view bone scans using attention-augmented deep neural networks","volume":"65","author":"Pi","year":"2020","journal-title":"Med Image Anal"},{"key":"R25-20250619","doi-asserted-by":"crossref","first-page":"242","DOI":"10.1016\/j.zemedi.2023.01.008","article-title":"Artificial intelligence-based analysis of whole-body bone scintigraphy: the quest for the optimal deep learning algorithm and comparison with human observer performance","volume":"34","author":"Hajianfar","year":"2024","journal-title":"Z Med Phys"},{"key":"R26-20250619","doi-asserted-by":"crossref","first-page":"25627","DOI":"10.1038\/s41598-024-73991-8","article-title":"Bone scintigraphy based on deep learning model and modified growth optimizer","volume":"14","author":"Magdy","year":"2024","journal-title":"Sci Rep"},{"key":"R27-20250619","doi-asserted-by":"crossref","first-page":"449","DOI":"10.1007\/s00432-024-05969-y","article-title":"Deep learning model using planar whole-body bone scintigraphy for diagnosis of skull base invasion in patients with nasopharyngeal carcinoma","volume":"150","author":"Mu","year":"2024","journal-title":"J Cancer Res Clin Oncol"},{"key":"R28-20250619","doi-asserted-by":"crossref","first-page":"2","DOI":"10.2214\/AJR.15.15895","article-title":"How sure are you, doctor? A standardized lexicon to describe the radiologist\u2019s level of certainty","volume":"207","author":"Panicek","year":"2016","journal-title":"AJR Am J Roentgenol"},{"key":"R29-20250619","doi-asserted-by":"crossref","first-page":"178","DOI":"10.3390\/diagnostics13020178","article-title":"Vision-Transformer-based transfer learning for mammogram classification","volume":"13","author":"Ayana","year":"2023","journal-title":"Diagnostics (Basel)"},{"key":"R30-20250619","doi-asserted-by":"crossref","first-page":"1549","DOI":"10.3390\/diagnostics12071549","article-title":"Transformers improve breast cancer diagnosis from unregistered multi-view mammograms","volume":"12","author":"Chen","year":"2022","journal-title":"Diagnostics"},{"key":"R31-20250619","doi-asserted-by":"crossref","first-page":"1024104","DOI":"10.3389\/fmicb.2022.1024104","article-title":"A deep ensemble learning-based automated detection of COVID-19 using lung CT images and Vision Transformer and ConvNeXt","volume":"13","author":"Tian","year":"2022","journal-title":"Front Microbiol"},{"key":"R32-20250619","doi-asserted-by":"crossref","first-page":"109228","DOI":"10.1016\/j.patcog.2022.109228","article-title":"An effective CNN and Transformer complementary network for medical image segmentation","volume":"136","author":"Yuan","year":"2023","journal-title":"Pattern Recognit"},{"key":"R34-20250619","doi-asserted-by":"crossref","first-page":"341","DOI":"10.1007\/s13534-023-00341-4","article-title":"CI-UNet: melding convnext and cross-dimensional attention for robust medical image segmentation","volume":"14","author":"Zhang","year":"2024","journal-title":"Biomed Eng Lett"},{"key":"R35-20250619","doi-asserted-by":"crossref","first-page":"102470","DOI":"10.1016\/j.media.2022.102470","article-title":"Explainable artificial intelligence (XAI) in deep learning-based medical image analysis","volume":"79","author":"van der Velden","year":"2022","journal-title":"Med Image Anal"},{"key":"R36-20250619","doi-asserted-by":"crossref","first-page":"e0267642","DOI":"10.1371\/journal.pone.0267642","article-title":"Differential immune landscapes in appendicular versus axial skeleton","volume":"17","author":"Ahmed","year":"2022","journal-title":"PLoS One"},{"key":"R37-20250619","doi-asserted-by":"crossref","first-page":"336","DOI":"10.1007\/s11263-019-01228-7","article-title":"Grad-CAM: visual explanations from deep networks via gradient-based localization","volume":"128","author":"Selvaraju","year":"2020","journal-title":"Int J Comput Vis"},{"key":"R38-20250619","doi-asserted-by":"crossref","first-page":"52","DOI":"10.3390\/jimaging6060052","article-title":"Explainable deep learning models in medical image analysis","volume":"6","author":"Singh","year":"2020","journal-title":"J Imaging"},{"key":"R39-20250619","doi-asserted-by":"crossref","first-page":"707","DOI":"10.1016\/j.survophthal.2024.05.008","article-title":"Diabetic retinopathy screening through artificial intelligence algorithms: a systematic review","volume":"69","author":"Farahat","year":"2024","journal-title":"Surv Ophthalmol"}],"container-title":["Clinical Nuclear Medicine"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/journals.lww.com\/10.1097\/RLU.0000000000005898","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,19]],"date-time":"2025-06-19T14:00:24Z","timestamp":1750341624000},"score":1,"resource":{"primary":{"URL":"https:\/\/journals.lww.com\/10.1097\/RLU.0000000000005898"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,4,16]]},"references-count":38,"journal-issue":{"issue":"7","published-print":{"date-parts":[[2025]]}},"URL":"https:\/\/doi.org\/10.1097\/rlu.0000000000005898","relation":{},"ISSN":["0363-9762","1536-0229"],"issn-type":[{"value":"0363-9762","type":"print"},{"value":"1536-0229","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,4,16]]},"assertion":[{"value":"2025-01-02","name":"received","label":"Received","group":{"name":"publication_history","label":"Publication History"}},{"value":"2025-03-09","name":"accepted","label":"Accepted","group":{"name":"publication_history","label":"Publication History"}}]}}