Journal of Bone Oncology最新文献

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 局部骨肉瘤患者肿瘤坏死的决定因素及其对预后的影响，采用无高剂量甲氨蝶呤的反应适应方案进行统一治疗-回顾性机构分析

IF 3.4 2区医学 Q2 Medicine

Journal of Bone Oncology

Pub Date : 2024-12-01 DOI: 10.1016/j.jbo.2024.100651

Prabhat Gautam Roy , Shuvadeep Ganguly , Archana Sasi , Vivek Kumar , Adarsh Barwad , Asit Ranjan Mridha , Shah Alam Khan , Venkatesan Sampath Kumar , Love Kapoor , Deepam Pushpam , Sameer Bakhshi

Purpose

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.

Methods

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 (<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).

Results

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 (<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).

Conclusions

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.

目的以肿瘤坏死形式对新辅助化疗的反应预测骨肉瘤的预后；尽管在接受高剂量基于甲氨蝶呤（HDMTx）化疗的患者中，适应反应的治疗升级未能改善预后。本研究旨在确定非转移性骨肉瘤患者接受非hdmtx治疗后肿瘤坏死的预测因素及其对生存率的影响。方法对2004-2019年接受新辅助治疗的非转移性骨肉瘤患者进行回顾性单机构研究。患者统一接受三个周期的新辅助顺铂/阿霉素治疗。术后，坏死良好的患者（≥90%）接受顺铂/阿霉素3个周期的治疗，坏死不良的患者（< 90%）接受顺铂/阿霉素与异环磷酰胺/依托泊苷交替治疗6个周期的升级治疗。进行倾向评分匹配（PSM）分析以确定坏死对无事件生存期（EFS）和总生存期（OS）的独立影响。结果在594例登记的骨肉瘤患者中，280例(中位年龄17岁；男性67.1%)纳入分析。73例（26.1%）患者实现了良好的坏死。肿瘤较小（≤10 cm）患者(aOR = 2.28；p = 0.030)，血清碱性磷酸酶（≤450 IU/L）降低(aOR = 2.10；p = 0.035)，较早手术（<；115天）者(aOR = 2.28；P = 0.016)更容易出现良性坏死。在1:2 PSM分析中，未达到有利坏死的患者表现为较差的EFS (HR = 2.68；p = 0.003)和OS (HR = 3.42；p = 0.003)。结论肿瘤小、血清碱性磷酸酶水平低、手术早期的骨肉瘤患者更容易出现良性坏死。肿瘤坏死是骨肉瘤预后的独立预测因素，而非hdmtx为基础的治疗方案中，适应反应的治疗升级无法克服不良坏死的不利影响。

{"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 , Shuvadeep Ganguly , Archana Sasi , Vivek Kumar , Adarsh Barwad , Asit Ranjan Mridha , Shah Alam Khan , Venkatesan Sampath Kumar , Love Kapoor , Deepam Pushpam , 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 (<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 (<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}

引用次数: 0

Novel lipid metabolism factor HIBCH inhibitor synergizes with doxorubicin to suppress osteosarcoma growth and impacts clinical prognosis in osteosarcoma patients 新型脂质代谢因子HIBCH抑制剂与阿霉素协同抑制骨肉瘤生长影响临床预后

IF 3.4 2区医学 Q2 Medicine

Journal of Bone Oncology

Pub Date : 2024-12-01 DOI: 10.1016/j.jbo.2024.100652

Xuhui Yuan , Bo Yu , Haiqi Ding , Hongyan Li , Qijing Wang , Lan Lin , Wenming Zhang , Xinyu Fang

Background

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.

Methods

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 in vitro studies and mouse xenograft models.

Results

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. In vivo experiments demonstrated that the combination of SBF-1 and DOX significantly suppressed tumor growth in mouse xenograft models.

Conclusions

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.

骨肉瘤（OS）是一种高度恶性的原发性骨肿瘤，主要影响儿童和青少年。尽管治疗策略有了进步，但骨肉瘤的长期生存率仍然不利，特别是在晚期或复发病例中。新出现的证据表明脂质代谢失调参与了OS的进展，但具体机制尚不清楚。方法建立纳入脂质代谢相关基因的风险模型，将OS患者分为高危组和低危组。通过功能测定来评估3-羟基异丁基辅酶a水解酶（HIBCH）在OS细胞活性中的作用。采用超快速液相色谱-质谱法分析HIBCH对OS细胞代谢的影响。此外，通过体外研究和小鼠异种移植模型评估HIBCH抑制剂SBF-1与阿霉素（DOX）的联合作用。结果shibch是参与OS细胞恶性行为的关键基因。HIBCH的敲除破坏了OS细胞的三羧酸（TCA）循环活性并降低了氧化磷酸化。SBF-1通过调节Akt-mTOR通路，与DOX协同抑制OS细胞的恶性表型。体内实验表明，SBF-1和DOX联合使用可显著抑制小鼠异种移植瘤模型的肿瘤生长。结论本研究揭示了脂质代谢在OS进展中的关键作用，并提出了基于SBF-1与DOX协同联合治疗OS化疗耐药的新策略。

{"title":"Novel lipid metabolism factor HIBCH inhibitor synergizes with doxorubicin to suppress osteosarcoma growth and impacts clinical prognosis in osteosarcoma patients","authors":"Xuhui Yuan , Bo Yu , Haiqi Ding , Hongyan Li , Qijing Wang , Lan Lin , Wenming Zhang , 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}

引用次数: 0

Chinese expert consensus on the diagnosis and clinical management of medication-related osteonecrosis of the jaw 中国专家就药物相关性颌骨坏死的诊断和临床治疗达成共识

IF 3.4 2区医学 Q2 Medicine

Journal of Bone Oncology

Pub Date : 2024-11-19 DOI: 10.1016/j.jbo.2024.100650

Han-Jin Ruan , Heng Chen , Jin-Song Hou , Jin-Gang An , Yu-Xing Guo , Bing Liu , Lei Tian , Jian Pan , Jin-Song Li , Can-Hua Jiang , Zhen Tian , Jie Xu , Ling Zhu , Chang-Fu Sun , Ke-Qian Zhi , Qing Qu , Chun-Lin Zong , Meng-Yu Li , Zhi-Yuan Zhang , Yue He

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.

药物性颌骨坏死（MRONJ）是全身性疾病治疗后出现的一种副作用。然而，目前大多数机构依靠经验方法来制定诊断和治疗方案，国内对MRONJ的分类、分期和治疗缺乏共识或指南。为弥补这一缺陷，改善预后，由国内 11 所知名医学院校及附属医院的代表组成了一个专家组。专家组针对定义、病因和危险因素、诊断、治疗和预防方法等问题，对以往的治疗经验和研究成果进行了全面的文献综述。专家组认为，在排除颌骨转移瘤后，可根据相关用药史和典型的临床表现，结合典型的影像学表现或组织病理学表现，做出MRONJ的诊断。何氏分类法被认为是实用的 MRONJ 临床分期系统。应建议多学科综合治疗，以达到最佳治疗效果。

{"title":"Chinese expert consensus on the diagnosis and clinical management of medication-related osteonecrosis of the jaw","authors":"Han-Jin Ruan , Heng Chen , Jin-Song Hou , Jin-Gang An , Yu-Xing Guo , Bing Liu , Lei Tian , Jian Pan , Jin-Song Li , Can-Hua Jiang , Zhen Tian , Jie Xu , Ling Zhu , Chang-Fu Sun , Ke-Qian Zhi , Qing Qu , Chun-Lin Zong , Meng-Yu Li , Zhi-Yuan Zhang , 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}

引用次数: 0

A patch-based deep learning MRI segmentation model for improving efficiency and clinical examination of the spinal tumor 基于补丁的深度学习磁共振成像分割模型，用于提高脊柱肿瘤的检查效率和临床检查效果

IF 3.4 2区医学 Q2 Medicine

Journal of Bone Oncology

Pub Date : 2024-11-16 DOI: 10.1016/j.jbo.2024.100649

Weimin Chen , Yong Han , Muhammad Awais Ashraf , Junhan Liu , Mu Zhang , Feng Su , Zhiguo Huang , Kelvin K.L. Wong

Background and objective

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.

Methods

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.

Results

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.

Conclusion

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.

背景和目的磁共振成像（MRI）在诊断脊柱疾病（包括不同类型的脊柱肿瘤）方面发挥着重要作用。然而，传统的分割技术往往耗费大量人力物力，而且容易产生变异。本研究旨在利用卷积-去卷积神经网络和基于补丁的深度学习，提出一种全自动脊柱磁共振成像分割方法。该方法涉及利用卷积神经网络从脊柱数据中自动提取深度学习特征。这样就能有效地表示解剖结构。对网络进行训练，以学习准确分割脊柱磁共振成像数据所需的鉴别特征。此外，还利用卷积神经网络开发了基于斑块提取（PE）的深度神经网络，将特征图还原为原始图像大小。为了提高训练效率，我们结合使用了预训练和增强型随机梯度下降方法。实验结果实验结果表明，所提出的方法在使用钆增强 T1 MRI 进行脊柱图像分割方面非常有效。这种方法不仅准确度高，而且具有实时性。创新模型获得了令人印象深刻的指标，精确度达到 90.6%，召回率达到 91.1%，准确率达到 93.2%，F1 分数达到 91.3%，联合交叉（IoU）达到 83.8%，骰子系数（DC）达到 91.1%。这些结果表明，所提出的方法可以准确分割脊柱肿瘤 CT 图像，解决了传统分割算法的局限性。结论总之，本研究介绍了一种利用卷积神经网络对脊柱 MRI 图像进行全自动分割的方法，并通过应用 PE 模块进行了增强。通过利用基于补丁提取的神经网络（PENN）深度学习技术，所提出的方法有效地解决了传统算法的不足，实现了准确、实时的脊柱 MRI 图像分割。

{"title":"A patch-based deep learning MRI segmentation model for improving efficiency and clinical examination of the spinal tumor","authors":"Weimin Chen , Yong Han , Muhammad Awais Ashraf , Junhan Liu , Mu Zhang , Feng Su , Zhiguo Huang , 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}

引用次数: 0

Auxiliary diagnosis of primary bone tumors based on Machine learning model 基于机器学习模型的原发性骨肿瘤辅助诊断

IF 3.4 2区医学 Q2 Medicine

Journal of Bone Oncology

Pub Date : 2024-11-09 DOI: 10.1016/j.jbo.2024.100648

Sandong Deng , Yugang Huang , Cong Li , Jun Qian , Xiangdong Wang

Objective

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.

Methods

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.

Results

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.

Conclusion

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.

研究原发性骨肿瘤的辅助诊断可以提高诊断的准确性，促进早期发现和个性化治疗，从而减少误诊和漏诊，最终改善患者的预后和生存率。在这项研究中，我们建立了一个包含各类骨肿瘤组织病理学样本的全切片成像（WSI）数据库，并集成了多种神经网络架构的机器学习模型。方法本文将基于深度卷积神经网络（DC-NN）方法的机器学习模型与成像全息分析相结合，分析并探讨其在诊断原发性骨肿瘤中的临床价值。此外，本文还提出了一种差异表达基因的筛选方法。该方法基于配对 T 检验法，首先估计每个样本病例实验数据中的肿瘤纯度，然后评估每个样本病例实验数据的实际基因表达值，最后计算优化的配对 T 检验统计量，并根据阈值筛选差异表达基因。结果所选模型在区分正常图像和肿瘤图像方面表现出了极高的诊断准确性，在使用 DCNN 模型进行的五轮测试中，总体准确率为（99.8 ± 0.4）%，阳性预测值为（100.0 ± 0.0）%，阴性预测值为（99.6 ± 0.8）%。每个数据集的平均曲线下面积（AUC）为（0.998 ± 0.004）。此外，使用 DCNN 模型进行的十轮测试表明，该模型在区分良性和恶性骨肿瘤方面的总体准确率为（71.2 ± 1.6）%，阳性预测值高达（91.9 ± 8.5）%，各数据集的平均 AUC 为（0.62 ± 0.06）。这些发现肯定了骨肿瘤组织病理学诊断的可行性和有效性，为机器学习辅助组织病理学诊断在该领域的应用和进步提供了理论基础。

{"title":"Auxiliary diagnosis of primary bone tumors based on Machine learning model","authors":"Sandong Deng , Yugang Huang , Cong Li , Jun Qian , 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}

引用次数: 0

Deep hashing and attention mechanism-based image retrieval of osteosarcoma scans for diagnosis of bone cancer 基于深度散列和注意力机制的骨肉瘤扫描图像检索，用于骨癌诊断

IF 3.4 2区医学 Q2 Medicine

Journal of Bone Oncology

Pub Date : 2024-11-06 DOI: 10.1016/j.jbo.2024.100645

Taisheng Zeng , Yuguang Ye , Yusi Chen , Daxin Zhu , Yifeng Huang , Ying Huang , Yijie Chen , Jianshe Shi , Bijiao Ding , Jianlong Huang , Mengde Ling

Background

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.

Method

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.

Results

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.

Conclusions

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.

背景骨肉瘤的显微图像数据因其错综复杂的性质和巨大的数据量，往往对传统图像检索方法的有效性构成重大障碍。因此，本研究利用先进的深度散列技术和注意力机制，研究了一种新的医学图像检索方法，以更有效地应对这些挑战。方法所提出的算法利用深度散列和注意力机制显著提高了骨肉瘤细胞显微图像检索的效率和准确性。图像预处理包括自适应直方图均衡化和数据集扩增，以提高质量和多样性。特征提取采用 WRN-AM 模型将高维特征映射到低维散列码空间，从而提高检索效率。最后，通过汉明距离进行相似性匹配，可以快速、精确地识别相似图像。结果这项研究取得了显著进展：WRN-AM 模型在使用 64 位散列码的情况下，分类准确率达到 93.2%，mAP 达到 97.09%。结论这种创新方法为骨肉瘤细胞和其他细胞类型的显微数据检索和分类提供了一种强大的解决方案，加快了临床诊断和医学研究的速度。它有助于更快地访问和分析病人的图像数据，提高诊断的准确性，并为医护人员制定治疗计划。同时，它还支持研究人员更有效地利用医学影像数据，促进医学领域的进步和创新。

{"title":"Deep hashing and attention mechanism-based image retrieval of osteosarcoma scans for diagnosis of bone cancer","authors":"Taisheng Zeng , Yuguang Ye , Yusi Chen , Daxin Zhu , Yifeng Huang , Ying Huang , Yijie Chen , Jianshe Shi , Bijiao Ding , Jianlong Huang , 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}

引用次数: 0

AI based diagnostics product design for osteosarcoma cells microscopy imaging of bone cancer patients using CA-MobileNet V3 使用 CA-MobileNet V3 对骨癌患者的骨肉瘤细胞显微成像进行基于人工智能的诊断产品设计

IF 3.4 2区医学 Q2 Medicine

Journal of Bone Oncology

Pub Date : 2024-11-04 DOI: 10.1016/j.jbo.2024.100644

Qian Liu , Xing She , Qian Xia

Objective

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.

Methods

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.

Results

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.

Conclusion

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.

目的骨肉瘤（OS）的发病率很低，但原发性恶性骨肿瘤在 20 岁以下癌症患者的死亡原因中排名第三。目前，通过显微图像分析细胞结构和肿瘤形态仍是诊断骨肉瘤的主要方法之一。方法利用人工智能（AI）在评估和分类图像方面的潜力，本研究探索了一种改进的 CA-MobileNet V3 模型，该模型被嵌入到创新的显微镜产品中，以增强显微镜的特征提取能力，并帮助减少诊断过程中的误分类。结果本文引入的智能识别模型方法在骨肉瘤细胞和其他细胞类型的检索和分类方面具有显著优势。与 ShuffleNet V2、EfficientNet V2、Mobilenet V3（无迁移学习）、TL-MobileNet V3（有迁移学习）等模型相比，模型大小仅为 5.33 MB，属于轻量级模型，改进后模型的准确率达到 98.69 %。结论基于深度学习的 CA-MobileNet V3 自动分类模型的创新方法为骨肉瘤的病理诊断提供了高效可靠的解决方案。这项研究为医学图像分析做出了贡献，为医生提供了准确而有价值的显微诊断工具。同时也推动了人工智能在医学影像技术领域的发展。

{"title":"AI based diagnostics product design for osteosarcoma cells microscopy imaging of bone cancer patients using CA-MobileNet V3","authors":"Qian Liu , Xing She , 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}

引用次数: 0

Clinical decision-making in bone cancer care management and forecast of ICU needs based on computed tomography 骨癌护理管理的临床决策和基于计算机断层扫描的重症监护室需求预测

IF 3.4 2区医学 Q2 Medicine

Journal of Bone Oncology

Pub Date : 2024-11-02 DOI: 10.1016/j.jbo.2024.100646

Huan Xu , Qunfang Zhao , Xiaoyan Miao , Lijun Zhu , Junping Wang

Objective

This study aimed to evaluate the role of computed tomography (CT) imaging in the diagnosis and management of bone cancer during periods of limited access to histopathological testing. We aimed to determine the correlation between CT severity levels and subsequent patient management and care decisions, adhering to established oncological CT reporting guidelines.

Methodology

A retrospective analysis was conducted on 60 symptomatic patients from January 2021 to January 2024. The cohort included patients aged between 50 and 86 years, with a mean age of 68 years, and 75 % were male. All patients had their bone cancer diagnosis confirmed through histopathological examination, and CT imaging was used as the reference method. The analysis involved assessing the correlation between CT severity scores and patient management, including ICU admissions.

Results

The study found that CT imaging demonstrated a sensitivity of 92.6% in diagnosing bone cancer, with accuracy increasing to 97.6% in cases with high-probability CT characteristics. CT specificity also showed a consistent rise. Osteolytic lesions were the predominant finding, detected in 85.9% of cases. Among these, 88% exhibited engagement across multiple skeletal regions, 92.8% showed bilateral distribution, and 92.8% presented with peripheral involvement. In ICU patients, bone consolidation was observed in 81.5% of cases and was predominant in 66.7% of the ICU cohort. Additionally, ICU patients had significantly higher CT severity scores, with scores exceeding 14 being notably prevalent.

Conclusions

During the management period of bone cancer at our hospital, characteristic features on CT imaging facilitated swift and sensitive investigation. Two distinct CT phenotypes, associated with the primary osteolytic phenotype and severity score, emerged as valuable indicators for assessing the severity of the disease, particularly during ICU care. These findings highlight the diverse manifestations and severity levels encountered in bone cancer patients and underscore the importance of CT imaging in their diagnosis and management.

本研究旨在评估计算机断层扫描（CT）成像在组织病理学检测受限期间骨癌诊断和管理中的作用。我们旨在确定 CT 严重程度与后续患者管理和护理决策之间的相关性，同时遵守既定的肿瘤 CT 报告指南。患者年龄在 50 至 86 岁之间，平均年龄为 68 岁，其中 75% 为男性。所有患者均通过组织病理学检查确诊为骨癌，并以 CT 成像作为参考方法。结果研究发现，CT 成像在诊断骨癌方面的灵敏度为 92.6%，在具有高概率 CT 特征的病例中，准确率上升到 97.6%。CT 特异性也呈持续上升趋势。溶骨性病变是最主要的发现，在 85.9% 的病例中被检测到。其中，88%的病例表现为多个骨骼区域受累，92.8%的病例表现为双侧分布，92.8%的病例表现为外周受累。在重症监护室患者中，81.5%的病例观察到骨质增生，66.7%的重症监护室患者以骨质增生为主。此外，ICU 患者的 CT 严重程度评分明显较高，超过 14 分的患者明显增多。两种不同的 CT 表型与原发性溶骨表型和严重程度评分相关，是评估疾病严重程度的重要指标，尤其是在重症监护室护理期间。这些发现突显了骨癌患者的不同表现和严重程度，并强调了 CT 成像在诊断和管理中的重要性。

{"title":"Clinical decision-making in bone cancer care management and forecast of ICU needs based on computed tomography","authors":"Huan Xu , Qunfang Zhao , Xiaoyan Miao , Lijun Zhu , Junping Wang","doi":"10.1016/j.jbo.2024.100646","DOIUrl":"10.1016/j.jbo.2024.100646","url":null,"abstract":"<div><h3>Objective</h3><div>This study aimed to evaluate the role of computed tomography (CT) imaging in the diagnosis and management of bone cancer during periods of limited access to histopathological testing. We aimed to determine the correlation between CT severity levels and subsequent patient management and care decisions, adhering to established oncological CT reporting guidelines.</div></div><div><h3>Methodology</h3><div>A retrospective analysis was conducted on 60 symptomatic patients from January 2021 to January 2024. The cohort included patients aged between 50 and 86 years, with a mean age of 68 years, and 75 % were male. All patients had their bone cancer diagnosis confirmed through histopathological examination, and CT imaging was used as the reference method. The analysis involved assessing the correlation between CT severity scores and patient management, including ICU admissions.</div></div><div><h3>Results</h3><div>The study found that CT imaging demonstrated a sensitivity of 92.6% in diagnosing bone cancer, with accuracy increasing to 97.6% in cases with high-probability CT characteristics. CT specificity also showed a consistent rise. Osteolytic lesions were the predominant finding, detected in 85.9% of cases. Among these, 88% exhibited engagement across multiple skeletal regions, 92.8% showed bilateral distribution, and 92.8% presented with peripheral involvement. In ICU patients, bone consolidation was observed in 81.5% of cases and was predominant in 66.7% of the ICU cohort. Additionally, ICU patients had significantly higher CT severity scores, with scores exceeding 14 being notably prevalent.</div></div><div><h3>Conclusions</h3><div>During the management period of bone cancer at our hospital, characteristic features on CT imaging facilitated swift and sensitive investigation. Two distinct CT phenotypes, associated with the primary osteolytic phenotype and severity score, emerged as valuable indicators for assessing the severity of the disease, particularly during ICU care. These findings highlight the diverse manifestations and severity levels encountered in bone cancer patients and underscore the importance of CT imaging in their diagnosis and management.</div></div>","PeriodicalId":48806,"journal":{"name":"Journal of Bone Oncology","volume":"49 ","pages":"Article 100646"},"PeriodicalIF":3.4,"publicationDate":"2024-11-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142594102","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}

引用次数: 0

A novel adjunctive diagnostic method for bone cancer: Osteosarcoma cell segmentation based on Twin Swin Transformer with multi-scale feature fusion 一种新型骨癌辅助诊断方法：基于双斯温变换器和多尺度特征融合的骨肉瘤细胞分割技术

IF 3.4 2区医学 Q2 Medicine

Journal of Bone Oncology

Pub Date : 2024-11-01 DOI: 10.1016/j.jbo.2024.100647

Tingxi Wen, Binbin Tong, Yuqing Fu, Yunfeng Li, Mengde Ling, Xinwen Chen

Background

Osteosarcoma, the most common primary bone tumor originating from osteoblasts, poses a significant challenge in medical practice, particularly among adolescents. Conventional diagnostic methods heavily rely on manual analysis of magnetic resonance imaging (MRI) scans, which often fall short in providing accurate and timely diagnosis. This underscores the critical need for advancements in medical imaging technologies to improve the detection and characterization of osteosarcoma.

Methods

In this study, we sought to address the limitations of current diagnostic approaches by leveraging Hoechst-stained images of osteosarcoma cells obtained via fluorescence microscopy. Our primary objective was to enhance the segmentation of osteosarcoma cells, a crucial step in precise diagnosis and treatment planning. Recognizing the shortcomings of existing feature extraction networks in capturing detailed cellular structures, we propose a novel approach utilizing a twin swin transformer architecture for osteosarcoma cell segmentation, with a focus on multi-scale feature fusion.

Results

The experimental findings demonstrate the effectiveness of the proposed Twin Swin Transformer with multi-scale feature fusion in significantly improving osteosarcoma cell segmentation. Compared to conventional techniques, our method achieves superior segmentation performance, highlighting its potential utility in clinical settings.

Conclusion

The development of our Twin Swin Transformer with multi-scale feature fusion method represents a significant advancement in medical imaging technology, particularly in the field of osteosarcoma diagnosis. By harnessing advanced computational techniques and leveraging high-resolution imaging data, our approach offers enhanced accuracy and efficiency in osteosarcoma cell segmentation, ultimately facilitating better patient care and clinical decision-making.

背景骨肉瘤是起源于成骨细胞的最常见的原发性骨肿瘤，是医疗实践中的一大挑战，尤其是在青少年中。传统的诊断方法严重依赖于对磁共振成像（MRI）扫描的人工分析，往往无法提供准确及时的诊断。方法在这项研究中，我们试图利用通过荧光显微镜获得的骨肉瘤细胞的 Hoechst 染色图像来解决当前诊断方法的局限性。我们的主要目标是加强骨肉瘤细胞的分割，这是精确诊断和治疗计划的关键步骤。认识到现有特征提取网络在捕捉详细细胞结构方面的不足，我们提出了一种利用双漩涡变换器架构进行骨肉瘤细胞分割的新方法，重点是多尺度特征融合。与传统技术相比，我们的方法实现了更优越的分割性能，凸显了其在临床环境中的潜在用途。结论我们开发的多尺度特征融合 Twin Swin Transformer 方法代表了医学成像技术的重大进步，尤其是在骨肉瘤诊断领域。通过利用先进的计算技术和高分辨率成像数据，我们的方法提高了骨肉瘤细胞分割的准确性和效率，最终促进了更好的患者护理和临床决策。

{"title":"A novel adjunctive diagnostic method for bone cancer: Osteosarcoma cell segmentation based on Twin Swin Transformer with multi-scale feature fusion","authors":"Tingxi Wen, Binbin Tong, Yuqing Fu, Yunfeng Li, Mengde Ling, Xinwen Chen","doi":"10.1016/j.jbo.2024.100647","DOIUrl":"10.1016/j.jbo.2024.100647","url":null,"abstract":"<div><h3>Background</h3><div>Osteosarcoma, the most common primary bone tumor originating from osteoblasts, poses a significant challenge in medical practice, particularly among adolescents. Conventional diagnostic methods heavily rely on manual analysis of magnetic resonance imaging (MRI) scans, which often fall short in providing accurate and timely diagnosis. This underscores the critical need for advancements in medical imaging technologies to improve the detection and characterization of osteosarcoma.</div></div><div><h3>Methods</h3><div>In this study, we sought to address the limitations of current diagnostic approaches by leveraging Hoechst-stained images of osteosarcoma cells obtained via fluorescence microscopy. Our primary objective was to enhance the segmentation of osteosarcoma cells, a crucial step in precise diagnosis and treatment planning. Recognizing the shortcomings of existing feature extraction networks in capturing detailed cellular structures, we propose a novel approach utilizing a twin swin transformer architecture for osteosarcoma cell segmentation, with a focus on multi-scale feature fusion.</div></div><div><h3>Results</h3><div>The experimental findings demonstrate the effectiveness of the proposed Twin Swin Transformer with multi-scale feature fusion in significantly improving osteosarcoma cell segmentation. Compared to conventional techniques, our method achieves superior segmentation performance, highlighting its potential utility in clinical settings.</div></div><div><h3>Conclusion</h3><div>The development of our Twin Swin Transformer with multi-scale feature fusion method represents a significant advancement in medical imaging technology, particularly in the field of osteosarcoma diagnosis. By harnessing advanced computational techniques and leveraging high-resolution imaging data, our approach offers enhanced accuracy and efficiency in osteosarcoma cell segmentation, ultimately facilitating better patient care and clinical decision-making.</div></div>","PeriodicalId":48806,"journal":{"name":"Journal of Bone Oncology","volume":"49 ","pages":"Article 100647"},"PeriodicalIF":3.4,"publicationDate":"2024-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142656667","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}

引用次数: 0

Progression of vertebral fractures in metastatic melanoma and non-small cell lung cancer patients given immune checkpoint inhibitors 服用免疫检查点抑制剂的转移性黑色素瘤和非小细胞肺癌患者椎体骨折的进展情况

IF 3.4 2区医学 Q2 Medicine

Journal of Bone Oncology

Pub Date : 2024-10-11 DOI: 10.1016/j.jbo.2024.100642

Marco Meazza Prina , Andrea Alberti , Valeria Tovazzi , Marco Ravanelli , Greta Schivardi , Alice Baggi , Luca Ammoni , Lucilla Guarneri , Francesca Salvotti , Manuel Zamparini , Davide Farina , Margherita Parolise , Salvatore Grisanti , Alfredo Berruti

Introduction

The immune system mediates important effects on bone metabolism, but little has been done to understand immunotherapy’s role in this interaction. This study aims to describe and identify risk factors for the occurrence and/or exacerbation of vertebral fractures (vertebral fracture progression) during immune checkpoint inhibitors (ICIs).

Methods

We conducted an observational, retrospective, monocentric study. We collected data on melanoma and NSCLC patients, treated with first-line ICIs at the Medical Oncology Department ASST Spedali Civili of Brescia, between January 2015 and November 2021, and with a median follow-up of 20.1 (6–36) months. We collected data on patients, diseases, immune-related adverse events, and cortico-steroid therapy initiated on concomitant ICIs.

Results

We identified 135 patients, 65 (48.2 %) with locally advanced/metastatic melanoma and 70 (51.8 %) with locally advanced/metastatic non-small cell lung cancer (NSCLC). Twenty-one (15.6 %) patients already had an asymptomatic vertebral fracture at baseline before starting ICIs in monotherapy. A total of ten patients, or 7.4 %, had a vertebra fracture progression defined as a new vertebral fracture or a worsening of a previous fracture. There was a strong relation between the steroid therapy and irAEs with vertebra fracture progression [OR (95 % CI) 8.1 (3.7–17.8) p-value < 0.001] in univariable analysis. However, only steroid therapy resulted to be an independent risk factor [8.260 (95 % CI 0.909–75.095); p-value 0.061] at the multivariable analysis.

Conclusion

Concurrent steroid therapy in patients receiving immunotherapy exposes them to a high risk of fractures due to skeletal fragility. The use of bone resorption inhibitors should be considered in these patients to prevent these adverse events.

导言免疫系统对骨代谢有重要影响，但人们对免疫疗法在这种相互作用中的作用了解甚少。本研究旨在描述和识别在使用免疫检查点抑制剂（ICIs）期间发生和/或加重椎体骨折（椎体骨折进展）的风险因素。我们收集了2015年1月至2021年11月期间在布雷西亚ASST Spedali Civili肿瘤内科接受一线ICIs治疗的黑色素瘤和NSCLC患者的数据，中位随访时间为20.1（6-36）个月。我们收集了有关患者、疾病、免疫相关不良事件以及在使用 ICIs 的同时开始皮质类固醇治疗的数据。结果我们发现了 135 名患者，其中 65 人（48.2%）患有局部晚期/转移性黑色素瘤，70 人（51.8%）患有局部晚期/转移性非小细胞肺癌（NSCLC）。21名患者（15.6%）在开始接受 ICIs 单药治疗前，基线已有无症状脊椎骨折。共有 10 名患者（占 7.4%）出现了脊椎骨折进展，即新的脊椎骨折或之前的骨折恶化。在单变量分析中，类固醇治疗和irAEs与椎体骨折进展之间存在密切关系[OR (95 % CI) 8.1 (3.7-17.8) p-value<0.001]。然而，在多变量分析中，只有类固醇治疗是一个独立的风险因素[8.260 (95 % CI 0.909-75.095)；p-value 0.061]。这些患者应考虑使用骨吸收抑制剂来预防这些不良事件的发生。

{"title":"Progression of vertebral fractures in metastatic melanoma and non-small cell lung cancer patients given immune checkpoint inhibitors","authors":"Marco Meazza Prina , Andrea Alberti , Valeria Tovazzi , Marco Ravanelli , Greta Schivardi , Alice Baggi , Luca Ammoni , Lucilla Guarneri , Francesca Salvotti , Manuel Zamparini , Davide Farina , Margherita Parolise , Salvatore Grisanti , Alfredo Berruti","doi":"10.1016/j.jbo.2024.100642","DOIUrl":"10.1016/j.jbo.2024.100642","url":null,"abstract":"<div><h3>Introduction</h3><div>The immune system mediates important effects on bone metabolism, but little has been done to understand immunotherapy’s role in this interaction. This study aims to describe and identify risk factors for the occurrence and/or exacerbation of vertebral fractures (vertebral fracture progression) during immune checkpoint inhibitors (ICIs).</div></div><div><h3>Methods</h3><div>We conducted an observational, retrospective, monocentric study. We collected data on melanoma and NSCLC patients, treated with first-line ICIs at the Medical Oncology Department ASST Spedali Civili of Brescia, between January 2015 and November 2021, and with a median follow-up of 20.1 (6–36) months. We collected data on patients, diseases, immune-related adverse events, and cortico-steroid therapy initiated on concomitant ICIs.</div></div><div><h3>Results</h3><div>We identified 135 patients, 65 (48.2 %) with locally advanced/metastatic melanoma and 70 (51.8 %) with locally advanced/metastatic non-small cell lung cancer (NSCLC). Twenty-one (15.6 %) patients already had an asymptomatic vertebral fracture at baseline before starting ICIs in monotherapy. A total of ten patients, or 7.4 %, had a vertebra fracture progression defined as a new vertebral fracture or a worsening of a previous fracture. There was a strong relation between the steroid therapy and irAEs with vertebra fracture progression [OR (95 % CI) 8.1 (3.7–17.8) p-value < 0.001] in univariable analysis. However, only steroid therapy resulted to be an independent risk factor [8.260 (95 % CI 0.909–75.095); p-value 0.061] at the multivariable analysis.</div></div><div><h3>Conclusion</h3><div>Concurrent steroid therapy in patients receiving immunotherapy exposes them to a high risk of fractures due to skeletal fragility. The use of bone resorption inhibitors should be considered in these patients to prevent these adverse events.</div></div>","PeriodicalId":48806,"journal":{"name":"Journal of Bone Oncology","volume":"49 ","pages":"Article 100642"},"PeriodicalIF":3.4,"publicationDate":"2024-10-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142434051","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}

引用次数: 0