AUTHOR=Peng Canjie , He Quanhao , Lv Fajin , Jiang Qing , Chen Yong , Wei Zongjie , Xv Yingjie , Liao Fangtong , Xiao Mingzhao 

TITLE=A stacking ensemble system for identifying the presence of histological variants in bladder carcinoma: a multicenter study

JOURNAL=Frontiers in Oncology

VOLUME=Volume 14 - 2024

YEAR=2025

URL=https://www.frontiersin.org/journals/oncology/articles/10.3389/fonc.2024.1469427

DOI=10.3389/fonc.2024.1469427

ISSN=2234-943X

ABSTRACT=PurposeTo create a system to enable the identification of histological variants of bladder cancer in a simple, efficient, and noninvasive manner.Material and methodsIn this multicenter diagnostic study, we retrospectively collected basic information and CT images about the patients concerned from three hospitals. An interactive deep learning-based bladder cancer image segmentation framework was constructed using the Swin UNETR algorithm for further features extraction. Radiomic features and deep learning features were extracted for further stacking ensemble system construction. The segmentation model’ performance was assessed by using Dice Similarity (Dice) metrics, Intersection Over Union (IOU), Sensitivity (SEN) and Specificity (SPE). To evaluate the system’s performance, we used the Receiver Operating Characteristics (ROC) curve, the Accuracy Score (ACC) and Decision Curve Analysis (DCA).Results410 patients from one hospital were included in the training set, while 60 patients from two other hospitals were included in the test set. A total of 50 features comprising 46 radiomic features and 4 deep learning features were finally retained for further stacking ensemble model building. The interactive segmentation model and system exhibited excellent performance in both training (Dice = 0.78, IOU = 0.65, SEN = 0.83, SPE = 1.00, AUC = 0.940, ACC = 0.868) and testing datasets (Dice = 0.80, IOU = 0.67, SEN = 0.89, SPE = 1.00, AUC = 0.905, ACC = 0.900).ConclusionWe successfully constructed a stacking ensemble machine learning model for early, non-invasive identification of histological variants in bladder cancer which will help urologists make clinical decisions.