Diagnostic accuracy of CT-based radiomics and deep learning for predicting lymph node metastasis in esophageal cancer

被引:1
|
作者
Jannatdoust, Payam [1 ]
Valizadeh, Parya [1 ]
Pahlevan-Fallahy, Mohammad-Taha [1 ]
Hassankhani, Amir [2 ,3 ]
Amoukhteh, Melika [2 ,3 ]
Behrouzieh, Sadra [1 ]
Ghadimi, Delaram J. [4 ]
Bilgin, Cem [3 ]
Gholamrezanezhad, Ali [2 ]
机构
[1] Univ Tehran Med Sci, Sch Med, Tehran, Iran
[2] Univ Southern Calif USC, Keck Sch Med, Dept Radiol, 1441 Eastlake Ave Ste 2315, Los Angeles, CA 90089 USA
[3] Mayo Clin, Dept Radiol, Rochester, MN USA
[4] Shahid Beheshti Univ Med Sci, Sch Med, Tehran, Iran
关键词
Esophageal neoplasms; Lymphatic metastasis; Radiomics; Deep learning; Tomography; X-ray computed; SQUAMOUS-CELL CARCINOMA; COMPUTED-TOMOGRAPHY;
D O I
10.1016/j.clinimag.2024.110225
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
Background: Esophageal cancer remains a global challenge due to late diagnoses and limited treatments. Lymph node metastasis (LNM) is crucial for prognosis, yet traditional diagnostics fall short. Integrating radiomics and deep learning (DL) with CT imaging for LNM diagnosis could revolutionize prognostic assessment and treatment planning. Methods: A systematic review and meta-analysis were conducted by searching PubMed, Scopus, Web of Science, and Embase up to October 1, 2023. The focus was on studies developing CT-based radiomics and/or DL models for preoperative LNM detection in esophageal cancer. Methodological quality was assessed using the METhodological RadiomICs Score (METRICS). Results: Twelve studies were reviewed, and seven were included in the meta-analysis, most showing excellent methodological quality. Training sets revealed a pooled AUC of 87 % (95 % CI: 78 %-90 %), and internal validation sets showed an AUC of 85 % (95 % CI: 76 %-89 %), with no significant difference (p = 0.39). Sensitivity and specificity for training sets were 78.7 % and 81.8 %, respectively, with validation sets at 81.2 % and 76.2 %. DL models in training sets showed better diagnostic accuracy than radiomics (p = 0.054), significant after removing outliers (p < 0.01). Incorporating clinical data improved sensitivity in validation sets (p = 0.029). No significant difference was found between models based on CE or non-CE imaging (p = 0.281) or arterial or venous phase imaging (p = 0.927). Conclusion: Integrating CT-based radiomics and DL improves LNM detection in esophageal cancer. Including clinical data could enhance model performance. Future research should focus on multicenter studies with independent validations to confirm these findings and promote broader clinical adoption.
引用
收藏
页数:19
相关论文
共 50 条
  • [31] Novel deep learning algorithm based MRI radiomics for predicting lymph node metastases in rectal cancer
    Weiqun Ao
    Sikai Wu
    Neng Wang
    Guoqun Mao
    Jian Wang
    Jinwen Hu
    Xiaoyu Han
    Shuitang Deng
    Scientific Reports, 15 (1)
  • [32] Dual-energy CT–based deep learning radiomics can improve lymph node metastasis risk prediction for gastric cancer
    Jing Li
    Di Dong
    Mengjie Fang
    Rui Wang
    Jie Tian
    Hailiang Li
    Jianbo Gao
    European Radiology, 2020, 30 : 2324 - 2333
  • [33] Radiomics analysis based on CT for predicting lymph node metastasis and prognosis in duodenal papillary carcinoma
    Tang, Chao-Tao
    Wu, Yonghui
    Jiang, Longzhou
    Zeng, Chun-Yan
    Chen, You-Xiang
    INSIGHTS INTO IMAGING, 2024, 15 (01):
  • [34] Radiomics and Clinicopathological Characteristics for Predicting Lymph Node Metastasis in Testicular Cancer
    Lisson, Catharina Silvia
    Manoj, Sabitha
    Wolf, Daniel
    Lisson, Christoph Gerhard
    Schmidt, Stefan A.
    Beer, Meinrad
    Thaiss, Wolfgang
    Bolenz, Christian
    Zengerling, Friedemann
    Goetz, Michael
    CANCERS, 2023, 15 (23)
  • [35] 18F-FDG PET/CT-based radiomics nomogram for the preoperative prediction of lymph node metastasis in gastric cancer
    Xue, Xiu-qing
    Yu, Wen-Ji
    Shi, Xun
    Shao, Xiao-Liang
    Wang, Yue-Tao
    FRONTIERS IN ONCOLOGY, 2022, 12
  • [36] Predicting Breast Cancer Metastasis in Sentinel Lymph Node with Deep Learning Technology
    Zheng, Lan
    Nguyen, Nghia
    Wang, Xiaohong Iris
    Zhang, Songlin
    Ding, Jianmin
    Sun, Hongxia
    LABORATORY INVESTIGATION, 2022, 102 (SUPPL 1) : 1105 - 1105
  • [37] Predicting Breast Cancer Metastasis in Sentinel Lymph Node with Deep Learning Technology
    Zheng, Lan
    Nguyen, Nghia
    Wang, Xiaohong Iris
    Zhang, Songlin
    Ding, Jianmin
    Sun, Hongxia
    MODERN PATHOLOGY, 2022, 35 (SUPPL 2) : 1105 - 1105
  • [38] Ultrasound radiomics based on axillary lymph nodes images for predicting lymph node metastasis in breast cancer
    Tang, Yu-Long
    Wang, Bin
    Ou-Yang, Tao
    Lv, Wen-Zhi
    Tang, Shi-Chu
    Wei, An
    Cui, Xin-Wu
    Huang, Jiang-Sheng
    FRONTIERS IN ONCOLOGY, 2023, 13
  • [39] Development and validation of CT-based radiomics deep learning signatures to predict lymph node metastasis in non-functional pancreatic neuroendocrine tumors: a multicohort study
    Gu, Wenchao
    Chen, Yingli
    Zhu, Haibin
    Chen, Haidi
    Yang, Zongcheng
    Mo, Shaocong
    Zhao, Hongyue
    Chen, Lei
    Nakajima, Takahito
    Yu, Xianjun
    Ji, Shunrong
    Gu, Yajia
    Chen, Jie
    Tang, Wei
    ECLINICALMEDICINE, 2023, 65
  • [40] CT-based radiomics-deep learning model predicts occult lymph node metastasis in early-stage lung adenocarcinoma patients: A multicenter study
    Yin, Xiaoyan
    Lu, Yao
    Cui, Yongbin
    Zhou, Zichun
    Wen, Junxu
    Huang, Zhaoqin
    Yan, Yuanyuan
    Yu, Jinming
    Meng, Xiangjiao
    CHINESE JOURNAL OF CANCER RESEARCH, 2025, 37 (01)