Endobronchial Ultrasound-Based Support Vector Machine Model for Differentiating between Benign and Malignant Mediastinal and Hilar Lymph Nodes.

IF 3.5 3区医学 Q2 RESPIRATORY SYSTEM

Respiration Pub Date : 2024-01-01 Epub Date: 2024-07-22 DOI:10.1159/000540467

Wenjia Hu, Feifei Wen, Mengyu Zhao, Xiangnan Li, Peiyuan Luo, Guancheng Jiang, Huizhen Yang, Felix J F Herth, Xiaoju Zhang, Quncheng Zhang

{"title":"Endobronchial Ultrasound-Based Support Vector Machine Model for Differentiating between Benign and Malignant Mediastinal and Hilar Lymph Nodes.","authors":"Wenjia Hu, Feifei Wen, Mengyu Zhao, Xiangnan Li, Peiyuan Luo, Guancheng Jiang, Huizhen Yang, Felix J F Herth, Xiaoju Zhang, Quncheng Zhang","doi":"10.1159/000540467","DOIUrl":null,"url":null,"abstract":"Introduction: The aim of the study was to establish an ultrasonographic radiomics machine learning model based on endobronchial ultrasound (EBUS) to assist in diagnosing benign and malignant mediastinal and hilar lymph nodes (LNs).Methods: The clinical and ultrasonographic image data of 197 patients were retrospectively analyzed. The radiomics features extracted by EBUS-based radiomics were analyzed by the least absolute shrinkage and selection operator. Then, we used a support vector machine (SVM) algorithm to establish an EBUS-based radiomics model. A total of 205 lesions were randomly divided into training (n = 143) and validation (n = 62) groups. The diagnostic efficiency was evaluated by receiver operating characteristic (ROC) curve analysis.Results: A total of 13 stable radiomics features with non-zero coefficients were selected. The SVM model exhibited promising performance in both groups. In the training group, the SVM model achieved an ROC area under the curve (AUC) of 0.892 (95% CI: 0.885-0.899), with an accuracy of 85.3%, sensitivity of 93.2%, and specificity of 79.8%. In the validation group, the SVM model had an ROC AUC of 0.906 (95% CI: 0.890-0.923), an accuracy of 74.2%, a sensitivity of 70.3%, and a specificity of 74.1%.Conclusion: The EBUS-based radiomics model can be used to differentiate mediastinal and hilar benign and malignant LNs. The SVM model demonstrated excellent potential as a diagnostic tool in clinical practice.","PeriodicalId":21048,"journal":{"name":"Respiration","volume":null,"pages":null},"PeriodicalIF":3.5000,"publicationDate":"2024-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Respiration","FirstCategoryId":"3","ListUrlMain":"https://doi.org/10.1159/000540467","RegionNum":3,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"2024/7/22 0:00:00","PubModel":"Epub","JCR":"Q2","JCRName":"RESPIRATORY SYSTEM","Score":null,"Total":0}

引用次数: 0

Abstract

Introduction: The aim of the study was to establish an ultrasonographic radiomics machine learning model based on endobronchial ultrasound (EBUS) to assist in diagnosing benign and malignant mediastinal and hilar lymph nodes (LNs).

Methods: The clinical and ultrasonographic image data of 197 patients were retrospectively analyzed. The radiomics features extracted by EBUS-based radiomics were analyzed by the least absolute shrinkage and selection operator. Then, we used a support vector machine (SVM) algorithm to establish an EBUS-based radiomics model. A total of 205 lesions were randomly divided into training (n = 143) and validation (n = 62) groups. The diagnostic efficiency was evaluated by receiver operating characteristic (ROC) curve analysis.

Results: A total of 13 stable radiomics features with non-zero coefficients were selected. The SVM model exhibited promising performance in both groups. In the training group, the SVM model achieved an ROC area under the curve (AUC) of 0.892 (95% CI: 0.885-0.899), with an accuracy of 85.3%, sensitivity of 93.2%, and specificity of 79.8%. In the validation group, the SVM model had an ROC AUC of 0.906 (95% CI: 0.890-0.923), an accuracy of 74.2%, a sensitivity of 70.3%, and a specificity of 74.1%.

Conclusion: The EBUS-based radiomics model can be used to differentiate mediastinal and hilar benign and malignant LNs. The SVM model demonstrated excellent potential as a diagnostic tool in clinical practice.

查看原文本刊更多论文

基于支气管内超声的支持向量机模型，用于区分纵隔和肺门淋巴结的良恶性。

简介：目的建立基于支气管内超声（EBUS）的超声放射组学机器学习模型，以辅助诊断良性和恶性纵隔及肺门淋巴结（LNs）：方法：对197名患者的临床和超声图像数据进行回顾性分析。采用最小绝对收缩和选择算子（LASSO）对基于 EBUS 的放射组学提取的放射组学特征进行分析。然后，我们使用支持向量机（SVM）算法建立了基于 EBUS 的放射组学模型。我们将 205 个病灶随机分为训练组（n=143）和验证组（n=62）。通过接收者操作特征曲线（ROC）分析评估诊断效率：结果：共筛选出 13 个系数不为零的稳定放射组学特征。SVM 模型在两组中均表现出良好的性能。在训练组，SVM 模型的 ROC 曲线下面积（AUC）为 0.892（95% CI：0.885-0.899），准确率为 85.3%，灵敏度为 93.2%，特异性为 79.8%。在验证组中，SVM 模型的 ROC AUC 为 0.906（95% CI：0.890-0.923），准确率为 74.2%，灵敏度为 70.3%，特异性为 74.1%：结论：基于 EBUS 的放射组学模型可用于区分纵隔和肺门良性和恶性 LN。SVM 模型在临床实践中显示出作为诊断工具的巨大潜力。

本文章由计算机程序翻译，如有差异，请以英文原文为准。

求助全文

约1分钟内获得全文求助全文

来源期刊

Respiration 医学-呼吸系统

CiteScore

7.30

自引率

5.40%

发文量

审稿时长

4-8 weeks

期刊介绍： ''Respiration'' brings together the results of both clinical and experimental investigations on all aspects of the respiratory system in health and disease. Clinical improvements in the diagnosis and treatment of chest and lung diseases are covered, as are the latest findings in physiology, biochemistry, pathology, immunology and pharmacology. The journal includes classic features such as editorials that accompany original articles in clinical and basic science research, reviews and letters to the editor. Further sections are: Technical Notes, The Eye Catcher, What’s Your Diagnosis?, The Opinion Corner, New Drugs in Respiratory Medicine, New Insights from Clinical Practice and Guidelines. ''Respiration'' is the official journal of the Swiss Society for Pneumology (SGP) and also home to the European Association for Bronchology and Interventional Pulmonology (EABIP), which occupies a dedicated section on Interventional Pulmonology in the journal. This modern mix of different features and a stringent peer-review process by a dedicated editorial board make ''Respiration'' a complete guide to progress in thoracic medicine.