Open Access iconOpen Access

ARTICLE

crossmark

Differentiate Xp11.2 Translocation Renal Cell Carcinoma from Computed Tomography Images and Clinical Data with ResNet-18 CNN and XGBoost

Yanwen Lu1,#, Wenliang Ma1,#, Xiang Dong1,#, Mackenzie Brown2, Tong Lu3,*, Weidong Gan1,*

1 Department of Urology, Nanjing Drum Tower Hospital, The Affiliated Hospital of Nanjing University Medical School, Nanjing, 210008, China
2 School of Data Science, Perdana University, Serdang, 43400, Malaysia
3 State Key Laboratory for Novel Software Technology, Nanjing University, Nanjing, 210008, China

* Corresponding Authors: Tong Lu. Email: email; Weidong Gan. Email: email
# These authors contributed equally to this work

(This article belongs to the Special Issue: Computer Modeling of Artificial Intelligence and Medical Imaging)

Computer Modeling in Engineering & Sciences 2023, 136(1), 347-362. https://doi.org/10.32604/cmes.2023.024909

Abstract

This study aims to apply ResNet-18 convolutional neural network (CNN) and XGBoost to preoperative computed tomography (CT) images and clinical data for distinguishing Xp11.2 translocation renal cell carcinoma (Xp11.2 tRCC) from common subtypes of renal cell carcinoma (RCC) in order to provide patients with individualized treatment plans. Data from 45 patients with Xp11.2 tRCC from January 2007 to December 2021 are collected. Clear cell RCC (ccRCC), papillary RCC (pRCC), or chromophobe RCC (chRCC) can be detected from each patient. CT images are acquired in the following three phases: unenhanced, corticomedullary, and nephrographic. A unified framework is proposed for the classification of renal masses. In this framework, ResNet-18 CNN is employed to classify renal cancers with CT images, while XGBoost is adopted with clinical data. Experiments demonstrate that, if applying ResNet-18 CNN or XGBoost singly, the latter outperforms the former, while the framework integrating both technologies performs similarly or better than urologists. Especially, the possibility of misclassifying Xp11.2 tRCC, pRCC, and chRCC as ccRCC by the proposed framework is much lower than urologists.

Keywords


Cite This Article

APA Style
Lu, Y., Ma, W., Dong, X., Brown, M., Lu, T. et al. (2023). Differentiate xp11.2 translocation renal cell carcinoma from computed tomography images and clinical data with resnet-18 CNN and xgboost. Computer Modeling in Engineering & Sciences, 136(1), 347-362. https://doi.org/10.32604/cmes.2023.024909
Vancouver Style
Lu Y, Ma W, Dong X, Brown M, Lu T, Gan W. Differentiate xp11.2 translocation renal cell carcinoma from computed tomography images and clinical data with resnet-18 CNN and xgboost. Comput Model Eng Sci. 2023;136(1):347-362 https://doi.org/10.32604/cmes.2023.024909
IEEE Style
Y. Lu, W. Ma, X. Dong, M. Brown, T. Lu, and W. Gan "Differentiate Xp11.2 Translocation Renal Cell Carcinoma from Computed Tomography Images and Clinical Data with ResNet-18 CNN and XGBoost," Comput. Model. Eng. Sci., vol. 136, no. 1, pp. 347-362. 2023. https://doi.org/10.32604/cmes.2023.024909



cc This work is licensed under a Creative Commons Attribution 4.0 International License , which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.
  • 778

    View

  • 485

    Download

  • 0

    Like

Share Link