Journal of Bone Oncology最新文献

{"title":"Editors' introduction: The microenvironment in bone metastasis – New dimensions","authors":"Ingunn Holen , Claire Edwards","doi":"10.1016/j.jbo.2024.100633","DOIUrl":"10.1016/j.jbo.2024.100633","url":null,"abstract":"","PeriodicalId":48806,"journal":{"name":"Journal of Bone Oncology","volume":"48 ","pages":"Article 100633"},"PeriodicalIF":3.4,"publicationDate":"2024-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142417933","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Automated segmentation and source prediction of bone tumors using ConvNeXtv2 Fusion based Mask R-CNN to identify lung cancer metastasis","authors":"Ketong Zhao ,&nbsp;Ping Dai ,&nbsp;Ping Xiao ,&nbsp;Yuhang Pan ,&nbsp;Litao Liao ,&nbsp;Junru Liu ,&nbsp;Xuemei Yang ,&nbsp;Zhenxing Li ,&nbsp;Yanjun Ma ,&nbsp;Jianxi Liu ,&nbsp;Zhengbo Zhang ,&nbsp;Shupeng Li ,&nbsp;Hailong Zhang ,&nbsp;Sheng Chen ,&nbsp;Feiyue Cai ,&nbsp;Zhen Tan","doi":"10.1016/j.jbo.2024.100637","DOIUrl":"10.1016/j.jbo.2024.100637","url":null,"abstract":"<div><div>Lung cancer, which is a leading cause of cancer-related deaths worldwide, frequently metastasizes to the bones, significantly diminishing patients’ quality of life and complicating treatment strategies. This study aims to develop an advanced 3D Mask R-CNN model, enhanced with the ConvNeXt-V2 backbone, for the automatic segmentation of bone tumors and identification of lung cancer metastasis to support personalized treatment planning. Data were collected from two hospitals: Center A (106 patients) and Center B (265 patients). The data from Center B were used for training, while Center A’s dataset served as an independent external validation set. High-resolution CT scans with 1 mm slice thickness and no inter-slice gaps were utilized, and the regions of interest (ROIs) were manually segmented and validated by two experienced radiologists. The 3D Mask R-CNN model achieved a Dice Similarity Coefficient (DSC) of 0.856, a sensitivity of 0.921, and a specificity of 0.961 on the training set. On the test set, it achieved a DSC of 0.849, a sensitivity of 0.911, and a specificity of 0.931. For the classification task, the model attained an AUC of 0.865, an accuracy of 0.866, a sensitivity of 0.875, and a specificity of 0.835 on the training set, while achieving an AUC of 0.842, an accuracy of 0.836, a sensitivity of 0.847, and a specificity of 0.819 on the test set. These results highlight the model’s potential in improving the accuracy of bone tumor segmentation and lung cancer metastasis detection, paving the way for enhanced diagnostic workflows and personalized treatment strategies in clinical oncology.</div></div>","PeriodicalId":48806,"journal":{"name":"Journal of Bone Oncology","volume":"48 ","pages":"Article 100637"},"PeriodicalIF":3.4,"publicationDate":"2024-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142417934","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"AI diagnostics in bone oncology for predicting bone metastasis in lung cancer patients using DenseNet-264 deep learning model and radiomics","authors":"Taisheng Zeng ,&nbsp;Yusi Chen ,&nbsp;Daxin Zhu ,&nbsp;Yifeng Huang ,&nbsp;Ying Huang ,&nbsp;Yijie Chen ,&nbsp;Jianshe Shi ,&nbsp;Bijiao Ding ,&nbsp;Jianlong Huang","doi":"10.1016/j.jbo.2024.100640","DOIUrl":"10.1016/j.jbo.2024.100640","url":null,"abstract":"<div><div>This study aims to predict bone metastasis in lung cancer patients using radiomics and deep learning. Early prediction of bone metastasis is crucial for timely intervention and personalized treatment plans. This can improve patient outcomes and quality of life. By integrating advanced imaging techniques with artificial intelligence, this study seeks to enhance predictive accuracy and clinical decision-making.</div></div><div><h3>Methods</h3><div>We included 189 lung cancer patients, comprising 89 with non-bone metastasis and 100 with confirmed bone metastasis. Radiomic features were extracted from CT images, and feature selection was performed using Minimum Redundancy Maximum Relevance (mRMR) and Least Absolute Shrinkage and Selection Operator (LASSO). We developed and validated a radiomics model and a deep learning model using DenseNet-264. Model performance was evaluated using the area under the receiver operating characteristic curve (AUC), accuracy, sensitivity, and specificity. Statistical comparisons were made using the DeLong test.</div></div><div><h3>Results</h3><div>The radiomics model achieved an AUC of 0.815 on the training set and 0.778 on the validation set. The DenseNet-264 model demonstrated superior performance with an AUC of 0.990 on the training set and 0.971 on the validation set. The DeLong test confirmed that the AUC of the DenseNet-264 model was significantly higher than that of the radiomics model (p &lt; 0.05).</div></div><div><h3>Conclusions</h3><div>The DenseNet-264 model significantly outperforms the radiomics model in predicting bone metastasis in lung cancer patients. The early and accurate prediction provided by the deep learning model can facilitate timely interventions and personalized treatment planning, potentially improving patient outcomes. Future studies should focus on validating these findings in larger, multi-center cohorts and integrating clinical data to further enhance predictive accuracy.</div></div>","PeriodicalId":48806,"journal":{"name":"Journal of Bone Oncology","volume":"48 ","pages":"Article 100640"},"PeriodicalIF":3.4,"publicationDate":"2024-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142358183","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Diagnosis of newly developed multiple myeloma without bone disease detectable on conventional computed tomography (CT) scan by using dual-energy CT","authors":"Nan Jiang ,&nbsp;Yu Xia ,&nbsp;Mingcong Luo ,&nbsp;Jianhua Chen ,&nbsp;Zongjian Qiu ,&nbsp;Jianfang Liu","doi":"10.1016/j.jbo.2024.100636","DOIUrl":"10.1016/j.jbo.2024.100636","url":null,"abstract":"<div><h3>Objective</h3><div>To evaluate the diagnostic utility of fat (hydroxyapatite) density [D_{Fat (HAP)}] on dual-energy computed tomography (DECT) for identifying clinical diagnosed multiple myeloma without bone disease (MNBD) that is not visible on conventional CT scans.</div></div><div><h3>Material and Methods</h3><div>In this age-gender-examination sites matched case control prospective study, Chest and/or abdominal images on Revolution CT of MNBDs and control subjects were consecutive enrolled in a 1:2 ratio from October 2022 to November 2023. Multiple myeloma was clinical diagnosed according to criteria of the International Myeloma Working Group. Regions of interest (ROIs) were drawn separately for all thoracolumbar vertebrae in the scanning range by two radiologists. Additionally, a radiologist specializing in musculoskeletal imaging supervised the process. D_{Fat (HAP)} was extracted from each ROI. The spine was divided into upper thoracic (UPT), middle and lower thoracic (MLT), thoracolumbar (TL), and middle and lower lumbar (MLL) vertebrae. The area under the receiver operating characteristic curve (AUC) was calculated to evaluate the diagnostic performance of D_{Fat (HAP)} in diagnosing multiple myeloma, and the sensitivity, specificity, and accuracy under the optimal cut-off were determined by Youden index (sensitivity + specificity −1).</div></div><div><h3>Results</h3><div>A total of 32 and MNBD patients and 64 control patients were included. The total number of ROIs outlined included MNBD group (n = 493) and control group (n = 986). For all vertebrae, D_Fat(HAP) got average performance in the diagnosis of MNBD (AUC = 0.733, <em>p</em> &lt; 0.001) with a cut-off value of 958 (mg/cm³); the sensitivity, specificity, and accuracy were 58.8 %, 77.8 %, and 71.7 %, respectively. Regarding segment analysis, the diagnostic performance was good for all (AUC, 0.803–0.837; <em>p</em> &lt; 0.001) but the UPT segment (AUC = 0.692, <em>p</em> = 0.002). The optimal diagnostic cut-off values for the MLT, TL, and MLL vertebrae were 955 mg/cm³, 947 mg/cm³, and 947 mg/cm³, respectively; the sensitivity, specificity, and accuracy were 80.0 %-87.5 %, 71.9 %-82.6 %, and 77.1 %-81.6 %, respectively.</div></div><div><h3>Conclusion</h3><div>DECT was effective for detecting MNBD, and better diagnostic results can be obtained by grouping different spine segments.</div></div>","PeriodicalId":48806,"journal":{"name":"Journal of Bone Oncology","volume":"48 ","pages":"Article 100636"},"PeriodicalIF":3.4,"publicationDate":"2024-09-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142327283","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"The efficacy and applicability of chimeric antigen receptor (CAR) T cell-based regimens for primary bone tumors: A comprehensive review of current evidence","authors":"Atefeh Barzegari ,&nbsp;Fateme Salemi ,&nbsp;Amirhossein Kamyab ,&nbsp;Adarsh Aratikatla ,&nbsp;Negar Nejati ,&nbsp;Mojgan Valizade ,&nbsp;Ehab Eltouny ,&nbsp;Alireza Ebrahimi","doi":"10.1016/j.jbo.2024.100635","DOIUrl":"10.1016/j.jbo.2024.100635","url":null,"abstract":"<div><div>Primary bone tumors (PBT), although rare, could pose significant mortality and morbidity risks due to their high incidence of lung metastasis. Survival rates of patients with PBTs may vary based on the tumor type, therapeutic interventions, and the time of diagnosis. Despite advances in the management of patients with these tumors over the past four decades, the survival rates seem not to have improved significantly, implicating the need for novel therapeutic interventions. Surgical resection with wide margins, radiotherapy, and systemic chemotherapy are the main lines of treatment for PBTs. Neoadjuvant and adjuvant chemotherapy, along with emerging immunotherapeutic approaches such as chimeric antigen receptor (CAR)-T cell therapy, have the potential to improve the treatment outcomes for patients with PBTs. CAR-T cell therapy has been introduced as an option in hematologic malignancies, with FDA approval for several CD19-targeting CAR-T cell products. This review aims to highlight the potential of immunotherapeutic strategies, specifically CAR T cell therapy, in managing PBTs.</div></div>","PeriodicalId":48806,"journal":{"name":"Journal of Bone Oncology","volume":"48 ","pages":"Article 100635"},"PeriodicalIF":3.4,"publicationDate":"2024-09-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142319813","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Synergistic effect between denosumab and immune checkpoint inhibitors (ICI)? A retrospective study of 268 patients with ICI and bone metastases","authors":"E. Mabrut ,&nbsp;S. Mainbourg ,&nbsp;J. Peron ,&nbsp;D. Maillet ,&nbsp;S. Dalle ,&nbsp;C. Fontaine Delaruelle ,&nbsp;E. Grolleau ,&nbsp;P. Clezardin ,&nbsp;E. Bonnelye ,&nbsp;C.B. Confavreux ,&nbsp;E. Massy","doi":"10.1016/j.jbo.2024.100634","DOIUrl":"10.1016/j.jbo.2024.100634","url":null,"abstract":"<div><h3>Background</h3><div>Bone metastasis is a significant concern in advanced solid tumors, contributing to diminished patient survival and quality of life due to skeletal-related events (SREs). Denosumab (DMAB), a monoclonal antibody targeting the receptor activator of nuclear factor kappa-B ligand (RANKL), is used to prevent SREs in such cases. The RANK/RANKL axis, crucial in immunological processes, has garnered attention, especially with the expanding use of immune checkpoint inhibitors (ICI) in modern oncology.</div></div><div><h3>Objective</h3><div>Our study aims to explore the potential synergistic antitumor effects of combining immunotherapy with denosumab, as suggested by anecdotal evidence, small cohort studies, and preclinical research.</div></div><div><h3>Methods</h3><div>We conducted a retrospective analysis using the IMMUCARE database, encompassing patients receiving ICI treatment since 2014 and diagnosed with bone metastases. We examined overall survival (OS), progression-free survival (PFS) and switch of treatment line based on denosumab usage. Patients were stratified into groups: without denosumab, ICI followed by denosumab, and denosumab followed by ICI. Survival curves and multivariate Cox regression analyses were performed.</div></div><div><h3>Results</h3><div>Among the 268 patients with bone metastases, 154 received treatment with ICI alone, while 114 received ICI in combination with denosumab at some point during their oncological history. No significant differences were observed in overall survival (OS) or progression-free survival (PFS) between patients receiving ICI monotherapy and those receiving ICI with denosumab (p = 0.29 and p = 0.79, respectively). However, upon analyzing patients who received denosumab following ICI initiation (17 patients), a notable difference emerged. The group receiving ICI followed by denosumab exhibited a significant advantage compared to those without denosumab (154 patients) or those receiving denosumab before ICI initiation (72 patients) (p = 0.022).</div></div><div><h3>Conclusion</h3><div>This retrospective investigation supports the notion of potential benefits associated with sequential administration of ICI and denosumab, although statistical significance was not achieved. Future studies, including prospective trials or updated retrospective analyses, focusing on cancers treated with first-line immunotherapy, could provide further insights into this therapeutic approach.</div></div>","PeriodicalId":48806,"journal":{"name":"Journal of Bone Oncology","volume":"48 ","pages":"Article 100634"},"PeriodicalIF":3.4,"publicationDate":"2024-09-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142319812","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Preliminary discrimination and evaluation of clinical application value of ChatGPT4o in bone tumors","authors":"Leiyun Huang ,&nbsp;Jinghan Hu ,&nbsp;Qingjin Cai ,&nbsp;Aoran Ye ,&nbsp;Yanxiong Chen ,&nbsp;Zha Yang Xiao-zhi ,&nbsp;Yongzhen Liu ,&nbsp;Ji Zheng ,&nbsp;Zengdong Meng","doi":"10.1016/j.jbo.2024.100632","DOIUrl":"10.1016/j.jbo.2024.100632","url":null,"abstract":"","PeriodicalId":48806,"journal":{"name":"Journal of Bone Oncology","volume":"48 ","pages":"Article 100632"},"PeriodicalIF":3.4,"publicationDate":"2024-09-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.sciencedirect.com/science/article/pii/S221213742400112X/pdfft?md5=023e585e4c330a169d903e280b897588&pid=1-s2.0-S221213742400112X-main.pdf","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142162347","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Groenlandicine enhances cisplatin sensitivity in cisplatin-resistant osteosarcoma cells through the BAX/Bcl-2/Caspase-9/Caspase-3 pathway","authors":"Zihao Zhao ,&nbsp;Qihong Wu ,&nbsp;Yangyang Xu ,&nbsp;Yuhuan Qin ,&nbsp;Runsang Pan ,&nbsp;Qingqi Meng ,&nbsp;Siming Li","doi":"10.1016/j.jbo.2024.100631","DOIUrl":"10.1016/j.jbo.2024.100631","url":null,"abstract":"<div><p>Groenlandicine is a protoberberine alkaloid isolated from <em>Coptidis Rhizoma</em>, a widely used traditional Chinese medicine known for its various biological activities. This study aims to validate groenlandicine’s effect on both cisplatin-sensitive and cisplatin-resistant osteosarcoma (OS) cells, along with exploring its potential molecular mechanism.</p><p>The ligand-based virtual screening (LBVS) method and molecular docking were employed to screen drugs. CCK-8 and FCM were used to measure the effect of groenlandicine on the OS cells transfected by lentivirus with over-expression or low-expression of TOP1. Cell scratch assay, CCK-8, FCM, and the EdU assay were utilized to evaluate the effect of groenlandicine on cisplatin-resistant cells. WB, immunofluorescence, and PCR were conducted to measure the levels of TOP1, Bcl-2, BAX, Caspase-9, and Caspase-3. Additionally, a subcutaneous tumor model was established in nude mice to verify the efficacy of groenlandicine.</p><p>Groenlandicine reduced the migration and proliferation while promoting apoptosis in OS cells, effectively damaging them. Meanwhile, groenlandicine exhibited weak cytotoxicity in 293T cells. Combination with cisplatin enhanced tumor-killing activity, markedly activating BAX, cleaved-Caspase-3, and cleaved-Caspase-9, while inhibiting the Bcl2 pathway in cisplatin-resistant OS cells. Moreover, the level of TOP1, elevated in cisplatin-resistant OS cells, was down-regulated by groenlandicine both <em>in vitro</em> and <em>in vivo</em>. Animal experiments confirmed that groenlandicine combined with cisplatin suppressed OS growth with lower nephrotoxicity.</p><p>Groenlandicine induces apoptosis and enhances the sensitivity of drug-resistant OS cells to cisplatin via the BAX/Bcl-2/Caspase-9/Caspase-3 pathway. Groenlandicine inhibits OS cells growth by down-regulating TOP1 level.Therefore, groenlandicine holds promise as a potential agent for reversing cisplatin resistance in OS treatment.</p></div>","PeriodicalId":48806,"journal":{"name":"Journal of Bone Oncology","volume":"48 ","pages":"Article 100631"},"PeriodicalIF":3.4,"publicationDate":"2024-08-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.sciencedirect.com/science/article/pii/S2212137424001118/pdfft?md5=41394f38e1dad067a9c2e0bb78fbea8b&pid=1-s2.0-S2212137424001118-main.pdf","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142058032","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Improved localization and segmentation of spinal bone metastases in MRI with nnUNet radiomics","authors":"Yong Xu ,&nbsp;Chengjie Meng ,&nbsp;Dan Chen ,&nbsp;Yongsheng Cao ,&nbsp;Xin Wang ,&nbsp;Peng Ji","doi":"10.1016/j.jbo.2024.100630","DOIUrl":"10.1016/j.jbo.2024.100630","url":null,"abstract":"<div><h3>Objective</h3><p>Variability exists in the subjective delineation of tumor areas in MRI scans of patients with spinal bone metastases. This research aims to investigate the efficacy of the nnUNet radiomics model for automatic segmentation and identification of spinal bone metastases.</p></div><div><h3>Methods</h3><p>A cohort of 118 patients diagnosed with spinal bone metastases at our institution between January 2020 and December 2023 was enrolled. They were randomly divided into a training set (n = 78) and a test set (n = 40). The nnUNet radiomics segmentation model was developed, employing manual delineations of tumor areas by physicians as the reference standard. Both methods were utilized to compute tumor area measurements, and the segmentation performance and consistency of the nnUNet model were assessed.</p></div><div><h3>Results</h3><p>The nnUNet model demonstrated effective localization and segmentation of metastases, including smaller lesions. The Dice coefficients for the training and test sets were 0.926 and 0.824, respectively. Within the test set, the Dice coefficients for lumbar and thoracic vertebrae were 0.838 and 0.785, respectively. Strong linear correlation was observed between the nnUNet model segmentation and physician-delineated tumor areas in 40 patients (<em>R</em>² = 0.998, <em>P</em> &lt; 0.001).</p></div><div><h3>Conclusions</h3><p>The nnUNet model exhibits efficacy in automatically localizing and segmenting spinal bone metastases in MRI scans.</p></div>","PeriodicalId":48806,"journal":{"name":"Journal of Bone Oncology","volume":"48 ","pages":"Article 100630"},"PeriodicalIF":3.4,"publicationDate":"2024-08-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.sciencedirect.com/science/article/pii/S2212137424001106/pdfft?md5=1821d5886af7299365cde372beac3007&pid=1-s2.0-S2212137424001106-main.pdf","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142089723","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Radiographic imaging and diagnosis of spinal bone tumors: AlexNet and ResNet for the classification of tumor malignancy","authors":"Chengquan Guo ,&nbsp;Yan Chen ,&nbsp;Jianjun Li","doi":"10.1016/j.jbo.2024.100629","DOIUrl":"10.1016/j.jbo.2024.100629","url":null,"abstract":"<div><h3>Objective</h3><p>This study aims to explore the application of radiographic imaging and image recognition algorithms, particularly AlexNet and ResNet, in classifying malignancies for spinal bone tumors.</p></div><div><h3>Methods</h3><p>We selected a cohort of 580 patients diagnosed with primary spinal osseous tumors who underwent treatment at our hospital between January 2016 and December 2023, whereby 1532 images (679 images of benign tumors, 853 images of malignant tumors) were extracted from this imaging dataset. Training and validation follow a ratio of 2:1. All patients underwent X-ray examinations as part of their diagnostic workup. This study employed convolutional neural networks (CNNs) to categorize spinal bone tumor images according to their malignancy. AlexNet and ResNet models were employed for this classification task. These models were fine-tuned through training, which involved the utilization of a database of bone tumor images representing different categories.</p></div><div><h3>Results</h3><p>Through rigorous experimentation, the performance of AlexNet and ResNet in classifying spinal bone tumor malignancy was extensively evaluated. The models were subjected to an extensive dataset of bone tumor images, and the following results were observed. AlexNet: This model exhibited commendable efficiency during training, with each epoch taking an average of 3 s. Its classification accuracy was found to be approximately 95.6 %. ResNet: The ResNet model showed remarkable accuracy in image classification. After an extended training period, it achieved a striking 96.2 % accuracy rate, signifying its proficiency in distinguishing the malignancy of spinal bone tumors. However, these results illustrate the clear advantage of AlexNet in terms of proficiency despite a lower classification accuracy. The robust performance of the ResNet model is auspicious when accuracy is more favored in the context of diagnosing spinal bone tumor malignancy, albeit at the cost of longer training times, with each epoch taking an average of 32 s.</p></div><div><h3>Conclusion</h3><p>Integrating deep learning and CNN-based image recognition technology offers a promising solution for qualitatively classifying bone tumors. This research underscores the potential of these models in enhancing the diagnosis and treatment processes for patients, benefiting both patients and medical professionals alike. The study highlights the significance of selecting appropriate models, such as ResNet, to improve accuracy in image recognition tasks.</p></div>","PeriodicalId":48806,"journal":{"name":"Journal of Bone Oncology","volume":"48 ","pages":"Article 100629"},"PeriodicalIF":3.4,"publicationDate":"2024-08-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.sciencedirect.com/science/article/pii/S221213742400109X/pdfft?md5=c94f1dae2cfd227a4fe0e1942824e827&pid=1-s2.0-S221213742400109X-main.pdf","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142020916","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}