Journal of Bone Oncology最新文献

{"title":"A multicenter, randomized, double-blind trial comparing LY01011, a biosimilar, with denosumab (Xgeva®) in patients with bone metastasis from solid tumors","authors":"Mingchuan Zhao ,&nbsp;Xichun Hu ,&nbsp;Pengpeng Zhuang ,&nbsp;Aiping Zeng ,&nbsp;Yan Yu ,&nbsp;Zhendong Chen ,&nbsp;Hongmei Sun ,&nbsp;Weihua Yang ,&nbsp;Lili Sheng ,&nbsp;Peijian Peng ,&nbsp;Jingfen Wang ,&nbsp;Tienan Yi ,&nbsp;Minghong Bi ,&nbsp;Huaqiu Shi ,&nbsp;Mingli Ni ,&nbsp;Xiumei Dai ,&nbsp;Changlu Hu ,&nbsp;Hongjie Xu ,&nbsp;Dongqing Lv ,&nbsp;Qingshan Li ,&nbsp;Changlin Dou","doi":"10.1016/j.jbo.2025.100661","DOIUrl":"10.1016/j.jbo.2025.100661","url":null,"abstract":"<div><h3>Introduction</h3><div>Denosumab (Xgeva®) is a standard treatment for the prevention of skeletal-related events (SREs) in patients with bone metastases (BM). This trial was designed to assess the equivalence of LY01011 to denosumab in terms of efficacy and safety.</div></div><div><h3>Materials and methods</h3><div>Eligible patients with BM from solid tumors were randomized at a 1:1 ratio to receive 120 mg of LY01011 or 120 mg of denosumab subcutaneously every four weeks during a 12-week double-blind treatment period, and then all enrolled patients continued to receive LY01011 until week 53. The primary endpoint was the natural logarithm of change of the urinary N-terminal crosslinked telopeptide of type I collagen level normalized to the urine creatinine level (uNTX/uCr) at week 13 from baseline. Other endpoints included the uNTX/uCr ratio, serum bone-specific alkaline phosphatase level alteration, status of anti-drug antibodies and neutralizing antibodies, adverse events and SREs.</div></div><div><h3>Results</h3><div>850 eligible patients were randomized into the LY01011 group (n = 424) or the denosumab group (n = 426). The least-squares means (SEs) of the natural logarithms of the changes in the uNTX/uCr ratios at week 13 from baseline were −1.810 (0.0404) in the LY01011 group and −1.791 (0.0406) in the denosumab group. The LSM difference [90 % CI] between two arms was −0.019 [-0.110, 0.073] within the equivalence margins (−0.135, 0.135) and met the predetermined primary endpoint. The AEs, ADAs and the PK data showed no statistically significant difference.</div></div><div><h3>Conclusions</h3><div>This study demonstrated the equivalent efficacy and safety of LY01011 to denosumab in patients with BM.</div></div>","PeriodicalId":48806,"journal":{"name":"Journal of Bone Oncology","volume":"51 ","pages":"Article 100661"},"PeriodicalIF":3.4,"publicationDate":"2025-01-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143332852","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":"Lipid metabolic reprogramming and associated ferroptosis in osteosarcoma: From molecular mechanisms to potential targets","authors":"Zhiyang Yin ,&nbsp;Guanlu Shen ,&nbsp;Minjie Fan ,&nbsp;Pengfei Zheng","doi":"10.1016/j.jbo.2025.100660","DOIUrl":"10.1016/j.jbo.2025.100660","url":null,"abstract":"<div><div>Osteosarcoma is a common bone tumor in adolescents, which is characterized by lipid metabolism disorders and plays a key role in tumorigenesis and disease progression. Ferroptosis is an iron-dependent form of programmed cell death associated with lipid peroxidation. This review provides an in-depth analysis of the complex relationship between lipid metabolic reprogramming and associated ferroptosis in OS from the perspective of metabolic enzymes and metabolites. We discussed the molecular basis of lipid uptake, synthesis, storage, lipolysis, and the tumor microenvironment, as well as their significance in OS development. Key enzymes such as adenosine triphosphate-citrate lyase (ACLY), acetyl-CoA synthetase 2 (ACSS2), fatty acid synthase (FASN) and stearoyl-CoA desaturase-1 (SCD1) are overexpressed in OS and associated with poor prognosis.</div><div>Based on specific changes in metabolic processes, this review highlights potential therapeutic targets in the lipid metabolism and ferroptosis pathways, and in particular the HMG-CoA reductase inhibitor simvastatin has shown potential in inducing apoptosis and inhibiting OS metastasis. Targeting these pathways provides new strategies for the treatment of OS. However, challenges such as the complexity of drug development and metabolic interactions must be overcome. A comprehensive understanding of the interplay between dysregulation of lipid metabolism and ferroptosis is essential for the development of innovative and effective therapies for OS, with the ultimate goal of improving patient outcomes.</div></div>","PeriodicalId":48806,"journal":{"name":"Journal of Bone Oncology","volume":"51 ","pages":"Article 100660"},"PeriodicalIF":3.4,"publicationDate":"2025-01-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143103134","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":"Predicting bone metastasis risk of colorectal tumors using radiomics and deep learning ViT model","authors":"Guanfeng Chen ,&nbsp;Wenxi Liu ,&nbsp;Yingmin Lin ,&nbsp;Jie Zhang ,&nbsp;Risheng Huang ,&nbsp;Deqiu Ye ,&nbsp;Jing Huang ,&nbsp;Jieyun Chen","doi":"10.1016/j.jbo.2024.100659","DOIUrl":"10.1016/j.jbo.2024.100659","url":null,"abstract":"<div><h3>Background</h3><div>Colorectal cancer is a prevalent malignancy with a significant risk of metastasis, including to bones, which severely impacts patient outcomes. Accurate prediction of bone metastasis risk is crucial for optimizing treatment strategies and improving prognosis.</div></div><div><h3>Purpose</h3><div>This study aims to develop a predictive model combining radiomics and Vision Transformer (ViT) deep learning techniques to assess the risk of bone metastasis in colorectal cancer patients using both plain and contrast-enhanced CT images.</div></div><div><h3>Materials and methods</h3><div>We conducted a retrospective analysis of 155 colorectal cancer patients, including 81 with bone metastasis and 74 without. Radiomic features were extracted from segmented tumors on both plain and contrast-enhanced CT images. LASSO regression was applied to select key features, which were then used to build traditional machine learning models, including Support Vector Machine (SVM), K-Nearest Neighbors (KNN), Random Forest, LightGBM, and XGBoost. Additionally, a dual-modality ViT model was trained on the same CT images, with a late fusion strategy employed to combine outputs from the different modalities. Model performance was evaluated using AUC-ROC, accuracy, sensitivity, and specificity, and differences were statistically assessed using DeLong’s test.</div></div><div><h3>Results</h3><div>The ViT model demonstrated superior predictive performance, achieving an AUC of 0.918 on the test set, significantly outperforming all traditional radiomics-based models. The SVM model, while the best among traditional models, still underperformed compared to the ViT model. The ViT model’s strength lies in its ability to capture complex spatial relationships and long-range dependencies within the imaging data, which are often missed by traditional models. DeLong’s test confirmed the statistical significance of the ViT model’s enhanced performance, highlighting its potential as a powerful tool for predicting bone metastasis risk in colorectal cancer patients.</div></div><div><h3>Conclusion</h3><div>The integration of radiomics with ViT-based deep learning offers a robust and accurate method for predicting bone metastasis risk in colorectal cancer patients. The ViT model’s ability to analyze dual-modality CT imaging data provides greater precision in risk assessment, which can improve clinical decision-making and personalized treatment strategies. These findings underscore the promise of advanced deep learning models in enhancing the accuracy of metastasis prediction. Further validation in larger, multicenter studies is recommended to confirm the generalizability of these results.</div></div>","PeriodicalId":48806,"journal":{"name":"Journal of Bone Oncology","volume":"51 ","pages":"Article 100659"},"PeriodicalIF":3.4,"publicationDate":"2024-12-31","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143103136","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":"Determinants of tumor necrosis and its impact on outcome in patients with Localized osteosarcoma uniformly treated with a response adapted regimen without high dose Methotrexate– A retrospective institutional analysis","authors":"Prabhat Gautam Roy ,&nbsp;Shuvadeep Ganguly ,&nbsp;Archana Sasi ,&nbsp;Vivek Kumar ,&nbsp;Adarsh Barwad ,&nbsp;Asit Ranjan Mridha ,&nbsp;Shah Alam Khan ,&nbsp;Venkatesan Sampath Kumar ,&nbsp;Love Kapoor ,&nbsp;Deepam Pushpam ,&nbsp;Sameer Bakhshi","doi":"10.1016/j.jbo.2024.100651","DOIUrl":"10.1016/j.jbo.2024.100651","url":null,"abstract":"<div><h3>Purpose</h3><div>Response to neoadjuvant chemotherapy in form of tumor necrosis predicts outcome in osteosarcoma; although response-adapted treatment escalation failed to improve outcome among patients treated with high-dose methotrexate-based (HDMTx) chemotherapy. This study aimed to identify factors predicting tumor necrosis and its impact on survival among patients with non-metastatic osteosarcoma treated with a response-adapted non-HDMTx regimen.</div></div><div><h3>Methods</h3><div>A retrospective single-institutional study was conducted among non-metastatic osteosarcoma patients treated with neoadjuvant therapy between 2004–2019. Patients were treated uniformly with three cycles of neoadjuvant cisplatin/doxorubicin. Post-operatively, patients with favourable necrosis (≥90 %) received 3 cycles of cisplatin/doxorubicin, while patients with poor necrosis (&lt;90 %) received escalated treatment with alternating six cycles of cisplatin/doxorubicin and ifosfamide/etoposide. Propensity score matching (PSM) analyses were conducted to ascertain independent impact of necrosis on event-free survival (EFS) and overall survival (OS).</div></div><div><h3>Results</h3><div>Of 594 registered osteosarcoma patients, 280 patients (median age 17 years; male 67.1 %) were included for analysis. 73 patients (26.1 %) achieved favourable necrosis. Patients with smaller tumor size (≤10 cm) (aOR = 2.28; p = 0.030), lower serum alkaline phosphatase (≤450 IU/L) (aOR = 2.10; p = 0.035), and who had surgery earlier (&lt;115 days) (aOR = 2.28; p = 0.016) were more likely to have favourable necrosis. On 1:2 PSM analysis, patients not achieving favourable necrosis demonstrated inferior EFS (HR = 2.68; p = 0.003) and OS (HR = 3.42; p = 0.003).</div></div><div><h3>Conclusions</h3><div>Patients of osteosarcoma with smaller tumor, lower serum alkaline phosphatase and earlier surgery are more likely to achieve favourable necrosis. Tumor necrosis independently predicts outcome in osteosarcoma, and response-adapted treatment escalation fails to overcome the adverse impact of poor necrosis in non-HDMTx based regimen.</div></div>","PeriodicalId":48806,"journal":{"name":"Journal of Bone Oncology","volume":"49 ","pages":"Article 100651"},"PeriodicalIF":3.4,"publicationDate":"2024-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142748553","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":"Novel lipid metabolism factor HIBCH inhibitor synergizes with doxorubicin to suppress osteosarcoma growth and impacts clinical prognosis in osteosarcoma patients","authors":"Xuhui Yuan ,&nbsp;Bo Yu ,&nbsp;Haiqi Ding ,&nbsp;Hongyan Li ,&nbsp;Qijing Wang ,&nbsp;Lan Lin ,&nbsp;Wenming Zhang ,&nbsp;Xinyu Fang","doi":"10.1016/j.jbo.2024.100652","DOIUrl":"10.1016/j.jbo.2024.100652","url":null,"abstract":"<div><h3>Background</h3><div>Osteosarcoma (OS) is a highly malignant primary bone tumor primarily affecting children and adolescents. Despite advancements in therapeutic strategies, long-term survival rates for OS remain unfavorable, especially in advanced or recurrent cases. Emerging evidence has noted the involvement of lipid metabolism dysregulation in OS progression, but the specific mechanisms remain unclear.</div></div><div><h3>Methods</h3><div>A risk model incorporating lipid metabolism-related genes was established to stratify OS patients into high-risk and low-risk groups. Functional assays were conducted to assess the role of 3-hydroxyisobutyryl-CoA hydrolase (HIBCH) in OS cell activities. Ultra-fast liquid chromatography-mass spectrometry was adopted to analyze the impact of HIBCH on OS cell metabolism. Moreover, the combined effect of HIBCH inhibitor SBF-1 with doxorubicin (DOX) was evaluated through <em>in vitro</em> studies and mouse xenograft models.</div></div><div><h3>Results</h3><div>HIBCH was identified as a key gene involved in the malignant behaviors of OS cells. HIBCH knockdown disrupted tricarboxylic acid (TCA) cycle activity and reduced oxidative phosphorylation in OS cells. SBF-1 showed synergistic effects with DOX in inhibiting malignant phenotypes of OS cells by modulating the Akt-mTOR pathway. <em>In vivo</em> experiments demonstrated that the combination of SBF-1 and DOX significantly suppressed tumor growth in mouse xenograft models.</div></div><div><h3>Conclusions</h3><div>This study reveals the critical role of lipid metabolism in OS progression and suggests a new therapeutic strategy against chemotherapy resistance in OS based on the synergistic combination of SBF-1 with DOX.</div></div>","PeriodicalId":48806,"journal":{"name":"Journal of Bone Oncology","volume":"49 ","pages":"Article 100652"},"PeriodicalIF":3.4,"publicationDate":"2024-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142748609","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":"Chinese expert consensus on the diagnosis and clinical management of medication-related osteonecrosis of the jaw","authors":"Han-Jin Ruan ,&nbsp;Heng Chen ,&nbsp;Jin-Song Hou ,&nbsp;Jin-Gang An ,&nbsp;Yu-Xing Guo ,&nbsp;Bing Liu ,&nbsp;Lei Tian ,&nbsp;Jian Pan ,&nbsp;Jin-Song Li ,&nbsp;Can-Hua Jiang ,&nbsp;Zhen Tian ,&nbsp;Jie Xu ,&nbsp;Ling Zhu ,&nbsp;Chang-Fu Sun ,&nbsp;Ke-Qian Zhi ,&nbsp;Qing Qu ,&nbsp;Chun-Lin Zong ,&nbsp;Meng-Yu Li ,&nbsp;Zhi-Yuan Zhang ,&nbsp;Yue He","doi":"10.1016/j.jbo.2024.100650","DOIUrl":"10.1016/j.jbo.2024.100650","url":null,"abstract":"<div><div>Medication-related osteonecrosis of the jaw (MRONJ) is a side effect that occurs after treatment for systemic diseases. However, most institutions currently rely on empirical methods to make diagnosis and treatment plans, and there is a lack of consensus or guidelines for the classification, staging and treatment of MRONJ in China. To address this gap and improve prognosis, an expert panel representing 11 renowned domestic medical colleges and affiliated hospitals in China was convened. The panel made a comprehensive literature review of previous treatment experiences and research findings to address issues of definitions, etiology and risk factors, diagnosis, treatment and prevention methods. The panel concluded that the diagnosis of MRONJ can be made on the basis of a history of related medications and typical clinical manifestations, with either typical radiographic manifestations or histopathological manifestations, after excluding jaw metastasis. Surgical treatment should be considered for symptomatic patients with sequestrum or bone abnormalities accompanied by recurrent infections, and He’s classification was considered a practical clinical MRONJ staging system. Multidisciplinary comprehensive treatment should be proposed to achieve optimal treatment outcomes.</div></div>","PeriodicalId":48806,"journal":{"name":"Journal of Bone Oncology","volume":"49 ","pages":"Article 100650"},"PeriodicalIF":3.4,"publicationDate":"2024-11-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142701503","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":"A patch-based deep learning MRI segmentation model for improving efficiency and clinical examination of the spinal tumor","authors":"Weimin Chen ,&nbsp;Yong Han ,&nbsp;Muhammad Awais Ashraf ,&nbsp;Junhan Liu ,&nbsp;Mu Zhang ,&nbsp;Feng Su ,&nbsp;Zhiguo Huang ,&nbsp;Kelvin K.L. Wong","doi":"10.1016/j.jbo.2024.100649","DOIUrl":"10.1016/j.jbo.2024.100649","url":null,"abstract":"<div><h3>Background and objective</h3><div>Magnetic resonance imaging (MRI) plays a vital role in diagnosing spinal diseases, including different types of spinal tumors. However, conventional segmentation techniques are often labor-intensive and susceptible to variability. This study aims to propose a full-automatic segmentation method for spine MRI images, utilizing a convolutional-deconvolution neural network and patch-based deep learning. The objective is to improve segmentation efficiency, meeting clinical needs for accurate diagnoses and treatment planning.</div></div><div><h3>Methods</h3><div>The methodology involved the utilization of a convolutional neural network to automatically extract deep learning features from spine data. This allowed for the effective representation of anatomical structures. The network was trained to learn discriminative features necessary for accurate segmentation of the spine MRI data. Furthermore, a patch extraction (PE) based deep neural network was developed using a convolutional neural network to restore the feature maps to their original image size. To improve training efficiency, a combination of pre-training and an enhanced stochastic gradient descent method was utilized.</div></div><div><h3>Results</h3><div>The experimental results highlight the effectiveness of the proposed method for spine image segmentation using Gadolinium-enhanced T1 MRI. This approach not only delivers high accuracy but also offers real-time performance. The innovative model attained impressive metrics, achieving 90.6% precision, 91.1% recall, 93.2% accuracy, 91.3% F1-score, 83.8% Intersection over Union (IoU), and 91.1% Dice Coefficient (DC). These results indicate that the proposed method can accurately segment spine tumors CT images, addressing the limitations of traditional segmentation algorithms.</div></div><div><h3>Conclusion</h3><div>In conclusion, this study introduces a fully automated segmentation method for spine MRI images utilizing a convolutional neural network, enhanced by the application of the PE-module. By utilizing a patch extraction based neural network (PENN) deep learning techniques, the proposed method effectively addresses the deficiencies of traditional algorithms and achieves accurate and real-time spine MRI image segmentation.</div></div>","PeriodicalId":48806,"journal":{"name":"Journal of Bone Oncology","volume":"49 ","pages":"Article 100649"},"PeriodicalIF":3.4,"publicationDate":"2024-11-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142701505","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":"Auxiliary diagnosis of primary bone tumors based on Machine learning model","authors":"Sandong Deng ,&nbsp;Yugang Huang ,&nbsp;Cong Li ,&nbsp;Jun Qian ,&nbsp;Xiangdong Wang","doi":"10.1016/j.jbo.2024.100648","DOIUrl":"10.1016/j.jbo.2024.100648","url":null,"abstract":"<div><h3>Objective</h3><div>Research on auxiliary diagnosis of primary bone tumors can enhance diagnostic accuracy, facilitate early detection, and enable personalized treatment, thereby reducing misdiagnosis and missed cases, ultimately leading to improved patient prognosis and survival rates. In this study, we established a whole slide imaging (WSI) database comprising histopathological samples from all categories of bone tumors and integrated multiple neural network architectures for machine learning models. We then evaluated the accuracy of these models in diagnosing primary bone tumors.</div></div><div><h3>Methods</h3><div>In this paper, the machine learning model based on the deep convolutional neural network (DC-NN) method was combined with imaging omics analysis to analyze and discuss its clinical value in diagnosing primary bone tumors. In addition, this paper proposed a screening method for differentially expressed genes. Based on the paired T-test method, the process first estimated the tumor purity in the experimental data of each sample case, then assessed the actual gene expression value of the experimental data of each sample case, and finally calculated the optimized paired T-test statistics, and screened differentially expressed genes according to the threshold value.</div></div><div><h3>Results</h3><div>The selected model demonstrated excellent diagnostic accuracy in distinguishing between normal and tumor images, with overall accuracy of (99.8 ± 0.4) % for five rounds of testing using the DCNN model and positive and negative predictive values of (100.0 ± 0.0) % and (99.6 ± 0.8) %, respectively. The mean area under each dataset’s curve (AUC) was (0.998 ± 0.004). Further, ten rounds of testing using the DCNN model showed an overall accuracy of (71.2 ± 1.6) % and a substantial positive predictive value of (91.9 ± 8.5) % in distinguishing benign from malignant bone tumors, with an average AUC of (0.62 ± 0.06) across datasets.</div></div><div><h3>Conclusion</h3><div>The deep learning model accurately classifies bone tumor histopathology based on the degree of infiltration, achieving diagnostic performance comparable to that of senior pathologists. These findings affirm the feasibility and effectiveness of histopathological diagnosis in bone tumors, providing a theoretical foundation for the application and advancement of machine learning-assisted histopathological diagnosis in this field.</div></div>","PeriodicalId":48806,"journal":{"name":"Journal of Bone Oncology","volume":"49 ","pages":"Article 100648"},"PeriodicalIF":3.4,"publicationDate":"2024-11-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142656668","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":"Deep hashing and attention mechanism-based image retrieval of osteosarcoma scans for diagnosis of bone cancer","authors":"Taisheng Zeng ,&nbsp;Yuguang Ye ,&nbsp;Yusi Chen ,&nbsp;Daxin Zhu ,&nbsp;Yifeng Huang ,&nbsp;Ying Huang ,&nbsp;Yijie Chen ,&nbsp;Jianshe Shi ,&nbsp;Bijiao Ding ,&nbsp;Jianlong Huang ,&nbsp;Mengde Ling","doi":"10.1016/j.jbo.2024.100645","DOIUrl":"10.1016/j.jbo.2024.100645","url":null,"abstract":"<div><h3>Background</h3><div>Due to its intricate nature and substantial data size, microscopic image data of osteosarcoma often present a significant obstacle to the effectiveness of conventional image retrieval methods. Therefore, this study investigates a new approach for medical image retrieval using advanced deep hashing techniques and attention mechanisms to address these challenges more effectively.</div></div><div><h3>Method</h3><div>The proposed algorithm significantly improves osteosarcoma cell microscopic image retrieval efficiency and accuracy using deep hashing and attention mechanisms. Image preprocessing includes adaptive histogram equalization and dataset augmentation to enhance quality and diversity. Feature extraction employs the WRN-AM model to map high-dimensional features to a low-dimensional hash code space, improving retrieval efficiency. Finally, similarity matching via Hamming distance allows rapid and precise identification of similar images.</div></div><div><h3>Results</h3><div>The study shows notable advancements: the WRN-AM model achieves 93.2% classification accuracy and 97.09% mAP using 64-bit hash codes. These findings underscore the technique’s effective performance in extracting and categorizing diverse microscopic cell data efficiently and reliably.</div></div><div><h3>Conclusions</h3><div>This innovative approach provides a robust solution for retrieving and classifying microscopic data of osteosarcoma cells and other cell types, speeding up clinical diagnosis and medical research. It facilitates quicker access and analysis of patient image data, enhancing diagnostic precision and treatment planning for healthcare professionals. Concurrently, it supports researchers in leveraging medical image data more efficiently, fostering progress and innovation in the medical field.</div></div>","PeriodicalId":48806,"journal":{"name":"Journal of Bone Oncology","volume":"49 ","pages":"Article 100645"},"PeriodicalIF":3.4,"publicationDate":"2024-11-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142656669","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 based diagnostics product design for osteosarcoma cells microscopy imaging of bone cancer patients using CA-MobileNet V3","authors":"Qian Liu ,&nbsp;Xing She ,&nbsp;Qian Xia","doi":"10.1016/j.jbo.2024.100644","DOIUrl":"10.1016/j.jbo.2024.100644","url":null,"abstract":"<div><h3>Objective</h3><div>The incidence of osteosarcoma (OS) is low, but primary malignant bone tumors rank third among the causes of death in cancer patients under the age of 20. Currently, analysis of cellular structure and tumor morphology through microscopic images remains one of the main diagnostic methods for osteosarcoma. However, this completely manual approach is tedious, time-consuming, and difficult to diagnose accurately due to the similarities in certain characteristics of malignant and benign tumors.</div></div><div><h3>Methods</h3><div>Leveraging the potential of artificial intelligence (AI) in assessing and classifying images, this study explored a modified CA-MobileNet V3 model that was embedded into innovative microscope products to enhance the microscope’s feature extraction capabilities and help reduce misclassification during diagnosis.</div></div><div><h3>Results</h3><div>The intelligent recognition model method introduced in this paper has significant advantages in retrieval and classification of osteosarcoma cells and other cell types. Compared with models such as ShuffleNet V2, EfficientNet V2, Mobilenet V3 (without transfer learning), TL-MobileNet V3 (with transfer learning), etc., the model size is only 5.33 MB, is a lightweight model, and the accuracy of the improved model reached 98.69 %. In addition, the artificial intelligence microscope (AIM) with integrated design based on this model can also help improve diagnostic efficiency.</div></div><div><h3>Conclusion</h3><div>The innovative method of the CA-MobileNet V3 automatic classification model based on deep learning provides an efficient and reliable solution for the pathological diagnosis of osteosarcoma. This study contributes to medical image analysis and provides doctors with an accurate and valuable tool for microscopic diagnosis. It also promotes the advancement of artificial intelligence in medical imaging technology.</div></div>","PeriodicalId":48806,"journal":{"name":"Journal of Bone Oncology","volume":"49 ","pages":"Article 100644"},"PeriodicalIF":3.4,"publicationDate":"2024-11-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142656666","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}