Development and Validation of a Prediction Model for Differentiation of Benign and Malignant Fat-Poor Renal Tumors Using CT Radiomics

被引:1
作者
Bang, Seokhwan [1 ]
Wang, Hee-Hwan [2 ]
Kim, Hokun [3 ]
Choi, Moon Hyung [4 ]
Cha, Jiook [2 ,5 ]
Choi, Yeongjin [6 ]
Hong, Sung-Hoo [1 ]
机构
[1] Catholic Univ Korea, Seoul St Marys Hosp, Coll Med, Dept Urol, Seoul 06591, South Korea
[2] Seoul Natl Univ, Dept Brain & Cognit Sci, Seoul 08825, South Korea
[3] Catholic Univ Korea, Seoul St Marys Hosp, Coll Med, Dept Radiol, Seoul 06591, South Korea
[4] Catholic Univ Korea, Eunpyung St Marys Hosp, Coll Med, Dept Radiol, Seoul 06591, South Korea
[5] Seoul Natl Univ, Dept Psychol, Seoul 08826, South Korea
[6] Catholic Univ Korea, Seoul St Marys Hosp, Coll Med, Dept Pathol, Seoul 06591, South Korea
来源
APPLIED SCIENCES-BASEL | 2023年 / 13卷 / 20期
关键词
radiomics; renal tumor; renal cell carcinoma; artificial intelligence; ARTIFICIAL-INTELLIGENCE;
D O I
10.3390/app132011345
中图分类号
O6 [化学];
学科分类号
0703 ;
摘要
Objectives: To develop and validate a machine learning-based CT radiomics classification model for distinguishing benign renal tumors from malignant renal tumors. Methods: We reviewed 499 patients who underwent nephrectomy for solid renal tumors at our institution between 2003 and 2021. In this retrospective study, patients who had undergone a computed tomography (CT) scan within 3 months before surgery were included. We randomly divided the dataset in a stratified manner as follows: 75% as the training set and 25% as the test set. By using various feature selection methods and a dimensionality reduction method exclusively for the training set, we selected 160 radiomic features out of 1,288 radiomic features to classify malignant renal tumors. Results: The training set included 396 patients, and the test set included 103 patients. The percentage of extracted radiomic features from patients was 32% (385/1218) after the reproducibility test. In terms of the average Area Under the Receiver Operating Characteristic Curve (AU-ROC) and the average Area Under the Precision-Recall Curve (AU-PRC), the Random Forest model achieved better performance (AU-ROC = 0.725; AU-PRC = 0.899). An average accuracy of 0.778 was obtained on evaluation with the hold-out test set. At the optimal threshold, the Random Forest model showed an F1 score of 0.746, precision of 0.862, sensitivity of 0.657, specificity of 0.651, and Negative Predictive Value (NPV) of 0.364. Conclusions: Our machine learning-based CT radiomics classification model performed well for the independent test set, indicating that it could be a useful tool for discriminating between malignant and benign solid renal tumors.
引用
收藏
页数:9
相关论文
共 23 条
[1]   Optuna: A Next-generation Hyperparameter Optimization Framework [J].
Akiba, Takuya ;
Sano, Shotaro ;
Yanase, Toshihiko ;
Ohta, Takeru ;
Koyama, Masanori .
KDD'19: PROCEEDINGS OF THE 25TH ACM SIGKDD INTERNATIONAL CONFERENCCE ON KNOWLEDGE DISCOVERY AND DATA MINING, 2019, :2623-2631
[2]   Epidemiology of Renal Cell Carcinoma [J].
Capitanio, Umberto ;
Bensalah, Karim ;
Bex, Axel ;
Boorjian, Stephen A. ;
Bray, Freddie ;
Coleman, Jonathan ;
Gore, John L. ;
Sun, Maxine ;
Wood, Christopher ;
Russo, Paul .
EUROPEAN UROLOGY, 2019, 75 (01) :74-84
[3]  
Chambon P, 2022, Arxiv, DOI [arXiv:2210.04133, DOI 10.48550/ARXIV.2210.04133]
[4]   XGBoost: A Scalable Tree Boosting System [J].
Chen, Tianqi ;
Guestrin, Carlos .
KDD'16: PROCEEDINGS OF THE 22ND ACM SIGKDD INTERNATIONAL CONFERENCE ON KNOWLEDGE DISCOVERY AND DATA MINING, 2016, :785-794
[5]   Follow-up for Clinically Localized Renal Neoplasms: AUA Guideline [J].
Donat, Sherri M. ;
Diaz, Mireya ;
Bishoff, Jay Todd ;
Coleman, Jonathan A. ;
Dahm, Philipp ;
Derweesh, Ithaar H. ;
Herrell, S. Duke, III ;
Hilton, Susan ;
Jonasch, Eric ;
Lin, Daniel W. ;
Reuter, Victor E. ;
Chang, Sam S. .
JOURNAL OF UROLOGY, 2013, 190 (02) :407-416
[6]   A CT-based radiomics nomogram for differentiation of benign and malignant small renal masses (≤4 cm) [J].
Feng, Shengxing ;
Gong, Mancheng ;
Zhou, Dongsheng ;
Yuan, Runqiang ;
Kong, Jie ;
Jiang, Feng ;
Zhang, Lijie ;
Chen, Weitian ;
Li, Yueming .
TRANSLATIONAL ONCOLOGY, 2023, 29
[7]   Update on the Diagnosis and Management of Renal Angiomyolipoma [J].
Flum, Andrew S. ;
Hamoui, Nabeel ;
Said, Mohammed A. ;
Yang, Ximing J. ;
Casalino, David D. ;
McGuire, Barry B. ;
Perry, Kent T. ;
Nadler, Robert B. .
JOURNAL OF UROLOGY, 2016, 195 (04) :834-846
[8]   Use of artificial intelligence to characterize renal tumors [J].
Kim, Hokun ;
Hong, Sung-Hoo .
INVESTIGATIVE AND CLINICAL UROLOGY, 2022, 63 (02) :123-125
[9]  
Kirillov A, 2023, Arxiv, DOI arXiv:2304.02643
[10]   A pilot radiometabolomics integration study for the characterization of renal oncocytic neoplasia [J].
Klontzas, Michail E. ;
Koltsakis, Emmanouil ;
Kalarakis, Georgios ;
Trpkov, Kiril ;
Papathomas, Thomas ;
Sun, Na ;
Walch, Axel ;
Karantanas, Apostolos H. ;
Tzortzakakis, Antonios .
SCIENTIFIC REPORTS, 2023, 13 (01)