Key points are not available for this paper at this time.
You have accessJournal of UrologyImaging/Uroradiology II (MP30)1 May 2024MP30-08 DELTA-RADIOMICS ANALYSIS IN COMPARISON TO RADIOMICS ANALYSIS USING DYNAMIC COMPUTED TOMOGRAPHY FOR PREOPERATIVE RISK STRATIFICATION IN UPPER URINARY TRACT UROTHELIAL CARCINOMA Motohiro Fujiwara, Daisuke Hirahara, Tatsunori Saho, Eichi Takaya, Shunya Matsumoto, Kasumi Yoshitomi, Masaki Kobayashi, Yuki Nakamura, Bo Fan, Yudai Ishikawa, Shohei Fukuda, Yuma Waseda, Hajime Tanaka, Soichiro Yoshida, and Yasuhisa Fujii Motohiro FujiwaraMotohiro Fujiwara , Daisuke HiraharaDaisuke Hirahara , Tatsunori SahoTatsunori Saho , Eichi TakayaEichi Takaya , Shunya MatsumotoShunya Matsumoto , Kasumi YoshitomiKasumi Yoshitomi , Masaki KobayashiMasaki Kobayashi , Yuki NakamuraYuki Nakamura , Bo FanBo Fan , Yudai IshikawaYudai Ishikawa , Shohei FukudaShohei Fukuda , Yuma WasedaYuma Waseda , Hajime TanakaHajime Tanaka , Soichiro YoshidaSoichiro Yoshida , and Yasuhisa FujiiYasuhisa Fujii View All Author Informationhttps://doi.org/10.1097/01.JU.0001009416.90901.7b.08AboutPDF ToolsAdd to favoritesDownload CitationsTrack CitationsPermissionsReprints ShareFacebookLinked InTwitterEmail Abstract INTRODUCTION AND OBJECTIVE: The prognosis of patients with upper urinary tract urothelial carcinoma (UTUC) is generally poor, particularly in advanced cases. Although neoadjuvant treatment may improve the survival outcomes after surgery, further explorations are required to identify the patients at high risk for recurrence preoperatively. We previously reported the usefulness of radiomics analysis for predicting the metastatic recurrence of UTUC (Kaneko et al. Int J Urol. 2023). In this study, we further investigated the utility of delta-radiomics in comparison to radiomics analysis using CT images for preoperative risk stratification in UTUC. METHODS: We analyzed 99 patients with UTUC who underwent radical surgery without neoadjuvant therapy (the approval ID: M2019-192). All the patients were required to have dynamic CT, on which the tumor was identified. The tumor contour was outlined, and the tumor volume of interest was set in each CT phase. Radiomics analysis was conducted using the non-contrast and corticomedullary phase images. Delta-radiomics features were calculated by subtracting the values obtained from each phase image. Ten machine learning algorithms were conducted in each analysis to predict metastatic recurrence. We selected the algorithm with the highest area under the receiver operator characteristic curve (AUC) of 10-fold internal cross-validation for each analysis. The AUC calculated from each algorithm was compared. RESULTS: The tumor was located in the renal pelvis and the ureter in 56 and 43 patients, respectively. Clinical T stages were Ta-1, 2, and≥3 in 51, 28, and 20 patients, respectively. During the median follow-up of 37 months, 18 patients experienced metastatic recurrence. Light GBM, Quadratic Discriminant Analysis, and Naive Bayes yielded the highest AUCs for radiomics using non-contrast and corticomedullary phase, and delta-radiomics, respectively. The AUC of delta-radiomics was higher (0.725) than those of radiomics using non-contrast (0.580) and corticomedullary phase (0.608) images. CONCLUSIONS: Delta-radiomics analysis may improve the predictive accuracy for metastatic recurrence in UTUC. It may help the preoperative risk stratification and decision-making in the management of patients with UTUC. Download PPT Source of Funding: This study is not founded by any foundation © 2024 by American Urological Association Education and Research, Inc.FiguresReferencesRelatedDetails Volume 211Issue 5SMay 2024Page: e493 Advertisement Copyright & Permissions© 2024 by American Urological Association Education and Research, Inc.Metrics Author Information Motohiro Fujiwara More articles by this author Daisuke Hirahara More articles by this author Tatsunori Saho More articles by this author Eichi Takaya More articles by this author Shunya Matsumoto More articles by this author Kasumi Yoshitomi More articles by this author Masaki Kobayashi More articles by this author Yuki Nakamura More articles by this author Bo Fan More articles by this author Yudai Ishikawa More articles by this author Shohei Fukuda More articles by this author Yuma Waseda More articles by this author Hajime Tanaka More articles by this author Soichiro Yoshida More articles by this author Yasuhisa Fujii More articles by this author Expand All Advertisement PDF downloadLoading ...
Fujiwara et al. (Mon,) studied this question.