AUTHOR=Zhai Xiaoli , Sun Penghui , Yu Xianbo , Wang Shuangkun , Li Xue , Sun Weiqian , Liu Xin , Tian Tian , Zhang Bowen 

TITLE=CT−based radiomics signature for differentiating pyelocaliceal upper urinary tract urothelial carcinoma from infiltrative renal cell carcinoma

JOURNAL=Frontiers in Oncology

VOLUME=Volume 13 - 2023

YEAR=2024

URL=https://www.frontiersin.org/journals/oncology/articles/10.3389/fonc.2023.1244585

DOI=10.3389/fonc.2023.1244585

ISSN=2234-943X

ABSTRACT=Objectives To develop a CT-based radiomics model and a combined model for preoperatively discriminating infiltrative renal cell carcinoma (RCC) and pyelocaliceal upper urinary tract urothelial carcinoma (UTUC) which invades renal parenchyma.Eighty patients with pathologically proven 37 infiltrative RCCs and 43 pyelocaliceal UTUCs were retrospectively enrolled and randomly divided into training set (n = 56) and testing set (n = 24) at a ratio of 7:3. Traditional CT imaging characteristics in portal venous phase were collected by two radiologists (SPH and ZXL with 4 and 30 years of experience in abdominal radiology, respectively). Patient demographics and traditional CT imaging characteristics were used to construct the clinical model. Radiomics score was calculated based on the radiomics features extracting from the portal venous CT images and the random forest (RF) algorithm to construct the radiomics model. The combined model was constructed by the radiomics score and significant clinical factors according to the multivariate logistic regression. The diagnostic efficacy of the models was evaluated using receiver operating characteristic (ROC) curve analysis and area under the curves (AUC).The RF score based on the eight validated features extracting from the portal venous CT images was used to build the radiomics model. Painless hematuria as an independent risk factor was used to build the clinical model. The combined model was constructed by the RF score and the selected clinical factor. Both the radiomics model and combined model showed higher efficacy in differentiating infiltrative RCC and pyelocaliceal UTUC in the training and testing cohort, with AUC of 0.95, and 0.90 for radiomics model; 0.99 and 0.90 for combined model. The decision curves of the combined model as well as the radiomics model indicated an overall net benefit over the clinical model. Both the radiomics model and the combined model achieved a notable reduction in false positive and false negative rates, resulting in significantly higher accuracy compared to the visual assessments, both in the train and test cohorts.Radiomics models and combined models had the potential to accurately differentiate infiltrative RCC and pyelocaliceal UTUC which invades renal parenchyma, and provide a new potentially noninvasive method to guide surgery strategies.