Alqahtani Abdulsalam, Bhattacharjee Sourav, Almopti Abdulrahman, Li Chunhui, Nabi Ghulam
School of Medicine, Centre for Medical Engineering and Technology, University of Dundee, Dundee DD1 9SY, UK.
Radiology Department, College of Applied Medical Sciences, Najran University, Najran 55461, Saudi Arabia.
Cancers (Basel). 2024 Sep 10;16(18):3119. doi: 10.3390/cancers16183119.
Upper tract urothelial carcinoma (UTUC) is a rare and aggressive malignancy with a poor prognosis. The accurate prediction of survival and recurrence in UTUC is crucial for effective risk stratification and guiding therapeutic decisions. Models combining radiomics and clinicopathological data features derived from computed tomographic urograms (CTUs) can be a way to predict survival and recurrence in UTUC. Thus, preoperative CTUs and clinical data were analyzed from 106 UTUC patients who underwent radical nephroureterectomy. Radiomics features were extracted from segmented tumors, and the Least Absolute Shrinkage and Selection Operator (LASSO) method was used to select the most relevant features. Multivariable Cox models combining radiomics features and clinical factors were developed to predict the survival and recurrence. Harrell's concordance index (C-index) was applied to evaluate the performance and survival distribution analyses were assessed by a Kaplan-Meier analysis. The significant outcome predictors were identified by multivariable Cox models. The combined model achieved a superior predictive accuracy (C-index: 0.73) and higher recurrence prediction (C-index: 0.84). The Kaplan-Meier analysis showed significant differences in the survival ( < 0.0001) and recurrence ( < 0.002) probabilities for the combined datasets. The CTU-based radiomics models effectively predicted survival and recurrence in the UTUC patients, and enhanced the prognostic performance by combining radiomics features with clinical factors.
上尿路尿路上皮癌（UTUC）是一种罕见且侵袭性强的恶性肿瘤，预后较差。准确预测UTUC的生存和复发对于有效的风险分层及指导治疗决策至关重要。结合从计算机断层扫描尿路造影（CTU）中提取的影像组学和临床病理数据特征的模型，可能是预测UTUC生存和复发的一种方法。因此，对106例行根治性肾输尿管切除术的UTUC患者的术前CTU和临床数据进行了分析。从分割的肿瘤中提取影像组学特征，并使用最小绝对收缩和选择算子（LASSO）方法选择最相关的特征。建立了结合影像组学特征和临床因素的多变量Cox模型，以预测生存和复发情况。应用Harrell一致性指数（C指数）评估模型性能，并通过Kaplan-Meier分析评估生存分布。通过多变量Cox模型确定显著的预后预测因素。联合模型实现了更高的预测准确性（C指数：0.73）和更高的复发预测准确性（C指数：0.84）。Kaplan-Meier分析显示，联合数据集在生存（<0.0001）和复发（<0.002）概率方面存在显著差异。基于CTU的影像组学模型有效地预测了UTUC患者的生存和复发情况，并通过将影像组学特征与临床因素相结合提高了预后性能。
