• 文献检索
  • 文档翻译
  • 深度研究
  • 学术资讯
  • Suppr Zotero 插件Zotero 插件
  • 邀请有礼
  • 套餐&价格
  • 历史记录
应用&插件
Suppr Zotero 插件Zotero 插件浏览器插件Mac 客户端Windows 客户端微信小程序
定价
高级版会员购买积分包购买API积分包
服务
文献检索文档翻译深度研究API 文档MCP 服务
关于我们
关于 Suppr公司介绍联系我们用户协议隐私条款
关注我们

Suppr 超能文献

核心技术专利:CN118964589B侵权必究
粤ICP备2023148730 号-1Suppr @ 2026

文献检索

告别复杂PubMed语法,用中文像聊天一样搜索,搜遍4000万医学文献。AI智能推荐,让科研检索更轻松。

立即免费搜索

文件翻译

保留排版,准确专业,支持PDF/Word/PPT等文件格式,支持 12+语言互译。

免费翻译文档

深度研究

AI帮你快速写综述,25分钟生成高质量综述,智能提取关键信息,辅助科研写作。

立即免费体验

基于机器学习的儿童肾母细胞瘤分期CT影像组学方法

Machine Learning-Based CT Radiomics Method for Identifying the Stage of Wilms Tumor in Children.

作者信息

Ma Xiao-Hui, Shu Liqi, Jia Xuan, Zhou Hai-Chun, Liu Ting-Ting, Liang Jia-Wei, Ding Yu-Shuang, He Min, Shu Qiang

机构信息

The Children's Hospital, Zhejiang University School of Medicine, National Clinical Research Center for Child Health, Hangzhou, China.

Department of Neurology, Warren Alpert Medical School of Brown University, Providence, RI, United States.

出版信息

Front Pediatr. 2022 May 23;10:873035. doi: 10.3389/fped.2022.873035. eCollection 2022.

DOI:10.3389/fped.2022.873035
PMID:35676904
原文链接:https://pmc.ncbi.nlm.nih.gov/articles/PMC9168275/
Abstract

PURPOSE

To develop and validate a machine learning-based CT radiomics method for preoperatively predicting the stages (stage I and non-stage I) of Wilms tumor (WT) in pediatric patients.

METHODS

A total of 118 patients with WT, who underwent contrast-enhanced computed tomography (CT) scans in our center between 2014 and 2021, were studied retrospectively and divided into two groups: stage I and non-stage I disease. Patients were randomly divided into training cohorts ( = 94) and test cohorts ( = 24). A total of 1,781 radiomic features from seven feature classes were extracted from preoperative portal venous-phase images of abdominal CT. Synthetic Minority Over-Sampling Technique (SMOTE) was used to handle imbalanced datasets, followed by a -test and Least Absolute Shrinkage and Selection Operator (LASSO) regularization for feature selection. Support Vector Machine (SVM) was deployed using the selected informative features to develop the predicting model. The performance of the model was evaluated according to its accuracy, sensitivity, and specificity. The receiver operating characteristic curve (ROC) and the area under the ROC curve (AUC) was also arranged to assess the model performance.

RESULTS

The SVM model was fitted with 15 radiomic features obtained by -test and LASSO concerning WT staging in the training dataset and demonstrated favorable performance in the testing dataset. Cross-validated AUC on the training dataset was 0.79 with a 95 percent confidence interval (CI) of 0.773-0.815 and a coefficient of variation of 3.76%, while AUC on the test dataset was 0.81, and accuracy, sensitivity, and specificity were 0.79, 0.87, and 0.69, respectively.

CONCLUSIONS

The machine learning model of SVM based on radiomic features extracted from CT images accurately predicted WT stage I and non-stage I disease in pediatric patients preoperatively, which provided a rapid and non-invasive way for investigation of WT stages.

摘要

目的

开发并验证一种基于机器学习的CT影像组学方法,用于术前预测小儿患者肾母细胞瘤(WT)的分期(I期和非I期)。

方法

回顾性研究了2014年至2021年期间在本中心接受增强计算机断层扫描(CT)的118例WT患者,并将其分为两组:I期疾病组和非I期疾病组。患者被随机分为训练队列(n = 94)和测试队列(n = 24)。从腹部CT术前门静脉期图像中提取了来自七个特征类别的总共1781个影像组学特征。采用合成少数过采样技术(SMOTE)处理不平衡数据集,随后进行t检验和最小绝对收缩和选择算子(LASSO)正则化进行特征选择。使用选定的信息性特征部署支持向量机(SVM)来开发预测模型。根据模型的准确性、敏感性和特异性评估模型性能。还绘制了受试者工作特征曲线(ROC)和ROC曲线下面积(AUC)来评估模型性能。

结果

SVM模型拟合了训练数据集中通过t检验和LASSO获得的15个与WT分期相关的影像组学特征,并在测试数据集中表现出良好性能。训练数据集上的交叉验证AUC为0.79,95%置信区间(CI)为0.773 - 0.815,变异系数为3.76%,而测试数据集上的AUC为0.81,准确性、敏感性和特异性分别为0.79、0.87和0.69。

结论

基于CT图像提取的影像组学特征的SVM机器学习模型能够准确术前预测小儿患者WT的I期和非I期疾病,为WT分期研究提供了一种快速、无创的方法。

https://cdn.ncbi.nlm.nih.gov/pmc/blobs/f040/9168275/4d9ec00184c9/fped-10-873035-g0002.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/f040/9168275/c52e4651fb38/fped-10-873035-g0001.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/f040/9168275/4d9ec00184c9/fped-10-873035-g0002.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/f040/9168275/c52e4651fb38/fped-10-873035-g0001.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/f040/9168275/4d9ec00184c9/fped-10-873035-g0002.jpg

相似文献

1
Machine Learning-Based CT Radiomics Method for Identifying the Stage of Wilms Tumor in Children.基于机器学习的儿童肾母细胞瘤分期CT影像组学方法
Front Pediatr. 2022 May 23;10:873035. doi: 10.3389/fped.2022.873035. eCollection 2022.
2
Computed Tomography-Based Radiomics Model to Predict Central Cervical Lymph Node Metastases in Papillary Thyroid Carcinoma: A Multicenter Study.基于计算机断层扫描的影像组学模型预测甲状腺乳头状癌中央颈部淋巴结转移:一项多中心研究。
Front Endocrinol (Lausanne). 2021 Oct 21;12:741698. doi: 10.3389/fendo.2021.741698. eCollection 2021.
3
Non-Contrasted CT Radiomics for SAH Prognosis Prediction.用于蛛网膜下腔出血预后预测的非增强CT影像组学
Bioengineering (Basel). 2023 Aug 16;10(8):967. doi: 10.3390/bioengineering10080967.
4
Optimizing the radiomics-machine-learning model based on non-contrast enhanced CT for the simplified risk categorization of thymic epithelial tumors: A large cohort retrospective study.基于非增强CT优化放射组学-机器学习模型用于胸腺瘤简化风险分类:一项大型队列回顾性研究
Lung Cancer. 2022 Apr;166:150-160. doi: 10.1016/j.lungcan.2022.03.007. Epub 2022 Mar 8.
5
Preoperative prediction of vessel invasion in locally advanced gastric cancer based on computed tomography radiomics and machine learning.基于计算机断层扫描影像组学和机器学习的局部进展期胃癌血管侵犯术前预测
Oncol Lett. 2023 May 22;26(1):293. doi: 10.3892/ol.2023.13879. eCollection 2023 Jul.
6
Multiphasic CT-Based Radiomics Analysis for the Differentiation of Benign and Malignant Parotid Tumors.基于多期CT的影像组学分析用于鉴别腮腺良恶性肿瘤
Front Oncol. 2022 Jun 30;12:913898. doi: 10.3389/fonc.2022.913898. eCollection 2022.
7
Machine learning for differentiation of lipid-poor adrenal adenoma and subclinical pheochromocytoma based on multiphase CT imaging radiomics.基于多期 CT 成像影像组学的机器学习在鉴别乏脂性肾上腺腺瘤与亚临床嗜铬细胞瘤中的应用。
BMC Med Imaging. 2023 Oct 16;23(1):159. doi: 10.1186/s12880-023-01106-2.
8
Computed Tomography-Based Radiomic Features Could Potentially Predict Microsatellite Instability Status in Stage II Colorectal Cancer: A Preliminary Study.基于计算机断层扫描的放射组学特征可能有助于预测 II 期结直肠癌的微卫星不稳定性状态:一项初步研究。
Acad Radiol. 2019 Dec;26(12):1633-1640. doi: 10.1016/j.acra.2019.02.009. Epub 2019 Mar 28.
9
Machine learning-based CT radiomics approach for predicting WHO/ISUP nuclear grade of clear cell renal cell carcinoma: an exploratory and comparative study.基于机器学习的CT影像组学方法预测透明细胞肾细胞癌的WHO/ISUP核分级:一项探索性和比较性研究
Insights Imaging. 2021 Nov 20;12(1):170. doi: 10.1186/s13244-021-01107-1.
10
CT-Based Radiomics Signature With Machine Learning Predicts MYCN Amplification in Pediatric Abdominal Neuroblastoma.基于CT的影像组学特征结合机器学习预测小儿腹部神经母细胞瘤中的MYCN扩增
Front Oncol. 2021 May 24;11:687884. doi: 10.3389/fonc.2021.687884. eCollection 2021.

引用本文的文献

1
Computed tomography radiomics prediction of survival in hepatocellular carcinoma and is associated with ADH1A expression of the retinol metabolism pathway.计算机断层扫描影像组学对肝细胞癌生存的预测及其与视黄醇代谢途径中ADH1A表达的相关性。
Medicine (Baltimore). 2025 Jun 13;104(24):e42792. doi: 10.1097/MD.0000000000042792.
2
Artificial intelligence can help individualize Wilms tumor treatment by predicting tumor response to preoperative chemotherapy.人工智能可以通过预测肿瘤对术前化疗的反应来帮助实现肾母细胞瘤治疗的个体化。
Investig Clin Urol. 2025 Jan;66(1):47-55. doi: 10.4111/icu.20240135.
3
A review on optimization of Wilms tumour management using radiomics.

本文引用的文献

1
Integrating tumor and nodal radiomics to predict lymph node metastasis in gastric cancer.整合肿瘤和淋巴结影像组学以预测胃癌中的淋巴结转移
Radiother Oncol. 2020 Sep;150:89-96. doi: 10.1016/j.radonc.2020.06.004. Epub 2020 Jun 10.
2
Radiomics and deep learning in lung cancer.肺癌的放射组学和深度学习。
Strahlenther Onkol. 2020 Oct;196(10):879-887. doi: 10.1007/s00066-020-01625-9. Epub 2020 May 4.
3
Introduction to Radiomics.放射组学简介。
关于使用放射组学优化肾母细胞瘤治疗的综述。
BJR Open. 2024 Oct 8;6(1):tzae034. doi: 10.1093/bjro/tzae034. eCollection 2024 Jan.
4
Insights into Personalized Care Strategies for Wilms Tumor: A Narrative Literature Review.肾母细胞瘤个性化护理策略的见解:一篇叙述性文献综述
Biomedicines. 2024 Jun 30;12(7):1455. doi: 10.3390/biomedicines12071455.
5
Applications of Artificial Intelligence for Pediatric Cancer Imaging.人工智能在儿科癌症成像中的应用。
AJR Am J Roentgenol. 2024 Aug;223(2):e2431076. doi: 10.2214/AJR.24.31076. Epub 2024 May 23.
6
Automated segmentation and volume prediction in pediatric Wilms' tumor CT using nnu-net.使用 nnu-net 进行小儿肾母细胞瘤 CT 的自动分割和体积预测。
BMC Pediatr. 2024 May 9;24(1):321. doi: 10.1186/s12887-024-04775-2.
7
The application of machine learning based on computed tomography images in the identification of renal tumors in children.基于计算机断层扫描图像的机器学习在儿童肾肿瘤识别中的应用。
Transl Pediatr. 2024 Mar 27;13(3):417-426. doi: 10.21037/tp-23-508. Epub 2024 Mar 11.
8
Radiomics in differential diagnosis of Wilms tumor and neuroblastoma with adrenal location in children.放射组学在儿童肾上腺部位肾母细胞瘤与神经母细胞瘤鉴别诊断中的应用
Eur Radiol. 2024 Aug;34(8):5016-5027. doi: 10.1007/s00330-024-10589-8. Epub 2024 Feb 5.
9
CT radiomics to differentiate between Wilms tumor and clear cell sarcoma of the kidney in children.基于 CT 影像组学鉴别儿童肾母细胞瘤和肾透明细胞肉瘤。
BMC Med Imaging. 2024 Jan 5;24(1):13. doi: 10.1186/s12880-023-01184-2.
10
Promoting the application of pediatric radiomics via an integrated medical engineering approach.通过综合医学工程方法促进儿科放射组学的应用。
Cancer Innov. 2023 Feb 19;2(4):302-311. doi: 10.1002/cai2.44. eCollection 2023 Aug.
J Nucl Med. 2020 Apr;61(4):488-495. doi: 10.2967/jnumed.118.222893. Epub 2020 Feb 14.
4
Radiomics and Artificial Intelligence for Biomarker and Prediction Model Development in Oncology.肿瘤学中用于生物标志物和预测模型开发的放射组学与人工智能
Comput Struct Biotechnol J. 2019 Jul 12;17:995-1008. doi: 10.1016/j.csbj.2019.07.001. eCollection 2019.
5
MRI-based radiomics nomogram may predict the response to induction chemotherapy and survival in locally advanced nasopharyngeal carcinoma.MRI 基放射组学列线图可预测局部晚期鼻咽癌对诱导化疗的反应和生存。
Eur Radiol. 2020 Jan;30(1):537-546. doi: 10.1007/s00330-019-06211-x. Epub 2019 Aug 1.
6
The UMBRELLA SIOP-RTSG 2016 Wilms tumour pathology and molecular biology protocol.UMBRELLA SIOP-RTSG 2016 威尔姆斯肿瘤病理学和分子生物学协议。
Nat Rev Urol. 2018 Nov;15(11):693-701. doi: 10.1038/s41585-018-0100-3.
7
An MRI-based Radiomics Classifier for Preoperative Prediction of Ki-67 Status in Breast Cancer.基于 MRI 的放射组学分类器用于术前预测乳腺癌 Ki-67 状态。
Acad Radiol. 2018 Sep;25(9):1111-1117. doi: 10.1016/j.acra.2018.01.006. Epub 2018 Feb 7.
8
Wilms Tumor Treatment Outcomes: Perspectives From a Low-Income Setting.肾母细胞瘤的治疗结果:低收入环境下的视角
J Glob Oncol. 2016 Dec 21;3(5):555-562. doi: 10.1200/JGO.2016.005389. eCollection 2017 Oct.
9
Computational Radiomics System to Decode the Radiographic Phenotype.用于解码影像学表型的计算放射组学系统
Cancer Res. 2017 Nov 1;77(21):e104-e107. doi: 10.1158/0008-5472.CAN-17-0339.
10
Position paper: Rationale for the treatment of Wilms tumour in the UMBRELLA SIOP-RTSG 2016 protocol.立场文件:采用 SIOP-RTSG 2016 方案治疗肾母细胞瘤的理由。
Nat Rev Urol. 2017 Dec;14(12):743-752. doi: 10.1038/nrurol.2017.163. Epub 2017 Oct 31.