Multi-DECT Image-based Intratumoral and Peritumoral Radiomics for Preoperative Prediction of Muscle Invasion in Bladder Cancer

被引:0
|
作者
Hu, Mengting [1 ]
Zhang, Jingyi [1 ]
Cheng, Qiye [1 ]
Wei, Wei [1 ]
Liu, Yijun [1 ]
Li, Jianying [2 ]
Liu, Lei [3 ]
机构
[1] Dalian Med Univ, Affiliated Hosp 1, Dept Radiol, Dalian, Peoples R China
[2] GE Healthcare, CT Res, Dalian, Peoples R China
[3] Dalian Med Univ, Affiliated Hosp 1, Dept Urol, Dalian, Peoples R China
关键词
Non-Muscle Invasive Bladder Neoplasms; Radiomics; Tomography; X-Ray Computed; Artificial Intelligence;
D O I
10.1016/j.acra.2024.08.010
中图分类号
R8 [特种医学]; R445 [影像诊断学];
学科分类号
1002 ; 100207 ; 1009 ;
摘要
Objectives: To assess the predictive value of intratumoral and peritumoral radiomics based on Dual-energy CT urography (DECTU) multi-images for preoperatively predicting the muscle invasion status of bladder cancer (BCa). Material and methods: This retrospective analysis involved 202 BCa patients who underwent DECTU. DECTU-derived quantitative parameters were identified as risk factors through stepwise regression analysis to construct a DECT model. The radiomic features from the intratumoral and 3 mm outward peritumoral regions were extracted from the 120 kVp-like, 40 keV, 100 keV, and iodine-based material-decomposition (IMD) images in the venous-phase and were screened using Mann-Whitney U test, Spearman correlation analysis, and LASSO. Radiomics models were developed using the Multilayer Perceptron for the intratumoral, peritumoral and intra- and peritumoral (IntraPeri) regions. Subsequently, a nomogram was created by integrating the multi-image IntraPeri radiomics and DECT model. Model performance was evaluated using area-under-the-curve (AUC), accuracy, sensitivity, and specificity. Results: Normalized iodine concentration (NIC) was identified as an independent predictor for the DECT model. The IntraPeri model demonstrated superior performance compared to the intratumoral and peritumoral models both in 40 keV (0.830 vs. 0.766 vs. 0.763) and IMD images (0.881 vs. 0.840 vs. 0.821) in the test cohort. In the test cohort, the nomogram exhibited the best predictability (AUC=0.886, accuracy=0.836, sensitivity=0.737, and specificity=0.881), outperformed the DECT model (AUC=0.763, accuracy=0.754, sensitivity=0.632, and specificity=0.810) in predicting muscle invasion status of BCa with a statistically significant difference (p < 0.05). Conclusion: The nomogram, incorporating IntraPeri radiomics and NIC, serves as a valuable and non-invasive tool for preoperatively assessing the muscle invasion status of BCa.
引用
收藏
页码:287 / 297
页数:11
相关论文
共 50 条
  • [41] Clinical study on the prediction of ALN metastasis based on intratumoral and peritumoral DCE-MRI radiomics and clinico-radiological characteristics in breast cancer
    Wang, Yunxia
    Shang, Yiyan
    Guo, Yaxin
    Hai, Menglu
    Gao, Yang
    Wu, Qingxia
    Li, Shunian
    Liao, Jun
    Sun, Xiaojuan
    Wu, Yaping
    Wang, Meiyun
    Tan, Hongna
    FRONTIERS IN ONCOLOGY, 2024, 14
  • [42] Multitask prediction models for serous ovarian cancer by preoperative CT image assessments based on radiomics
    Fu, Le
    Wang, Wenjing
    Lin, Lingling
    Gao, Feng
    Yang, Jiani
    Lv, Yunyun
    Ge, Ruiqiu
    Wu, Meixuan
    Chen, Lei
    Liu, Aie
    Xin, Enhui
    Yu, Jianli
    Cheng, Jiejun
    Wang, Yu
    FRONTIERS IN MEDICINE, 2024, 11
  • [43] Preoperative Prediction of Perineural Invasion Status of Rectal Cancer Based on Radiomics Nomogram of Multiparametric Magnetic Resonance Imaging
    Zhang, Yang
    Peng, Jiaxuan
    Liu, Jing
    Ma, Yanqing
    Shu, Zhenyu
    FRONTIERS IN ONCOLOGY, 2022, 12
  • [44] Computed tomography-based radiomics nomogram for the preoperative prediction of perineural invasion in colorectal cancer: a multicentre study
    Qiaoling Chen
    Yanfen Cui
    Ting Xue
    Hui Peng
    Manman Li
    Xinghua Zhu
    Shaofeng Duan
    Hongmei Gu
    Feng Feng
    Abdominal Radiology, 2022, 47 : 3251 - 3263
  • [45] Computed tomography-based radiomics nomogram for the preoperative prediction of perineural invasion in colorectal cancer: a multicentre study
    Chen, Qiaoling
    Cui, Yanfen
    Xue, Ting
    Peng, Hui
    Li, Manman
    Zhu, Xinghua
    Duan, Shaofeng
    Gu, Hongmei
    Feng, Feng
    ABDOMINAL RADIOLOGY, 2022, 47 (09) : 3251 - 3263
  • [46] Preoperative prediction of lymphovascular invasion in invasive breast cancer with dynamic contrast-enhanced-MRI-based radiomics
    Liu, Zhuangsheng
    Feng, Bao
    Li, Changlin
    Chen, Yehang
    Chen, Qinxian
    Li, Xiaoping
    Guan, Jianhua
    Chen, Xiangmeng
    Cui, Enming
    Li, Ronggang
    Li, Zhi
    Long, Wansheng
    JOURNAL OF MAGNETIC RESONANCE IMAGING, 2019, 50 (03) : 847 - 857
  • [47] Development and validation of a CT-based deep learning radiomics nomogram to predict muscle invasion in bladder cancer
    Wei, Zongjie
    Liu, Huayun
    Xv, Yingjie
    Liao, Fangtong
    He, Quanhao
    Xie, Yongpeng
    Lv, Fajin
    Jiang, Qing
    Xiao, Mingzhao
    HELIYON, 2024, 10 (02)
  • [48] Value of the application of computed tomography-based radiomics for preoperative prediction of unfavorable pathology in initial bladder cancer
    Xiong, Situ
    Dong, Wentao
    Deng, Zhikang
    Jiang, Ming
    Li, Sheng
    Hu, Bing
    Liu, Xiaoqiang
    Chen, Luyao
    Xu, Songhui
    Fan, Bin
    Fu, Bin
    CANCER MEDICINE, 2023, 12 (15): : 15868 - 15880
  • [49] Development and Validation of an MRI-Based Radiomics Signature for the Preoperative Prediction of Lymph Node Metastasis in Bladder Cancer
    Wu, Shaoxu
    Zheng, Junjiong
    Li, Yong
    Wu, Zhuo
    Shi, Siya
    Huang, Ming
    Yu, Hao
    Dong, Wen
    Huang, Jian
    Lin, Tianxin
    EBIOMEDICINE, 2018, 34 : 76 - 84
  • [50] Radiomics Prediction of Muscle Invasion in Bladder Cancer Using Semi-Automatic Lesion Segmentation of MRI Compared with Manual Segmentation
    Ye, Yaojiang
    Luo, Zixin
    Qiu, Zhengxuan
    Cao, Kangyang
    Huang, Bingsheng
    Deng, Lei
    Zhang, Weijing
    Liu, Guoqing
    Zou, Yujian
    Zhang, Jian
    Li, Jianpeng
    BIOENGINEERING-BASEL, 2023, 10 (12):