Lili Wang1, Jing Gong2, Xinming Huang1, Guifang Lin1, Bin Zheng3, Jingming Chen1, Jiangao Xie1, Ruolan Lin1, Qing Duan1, Weiwen Lin4. 1. Department of Radiology, Fujian Medical University Union Hospital, Fuzhou, 350001, China. 2. Department of Radiology, Fudan University Shanghai Cancer Center, 270 Dongan Road, Shanghai, 200023, China; Department of Oncology, Shanghai Medical College, Fudan University, Shanghai, 200032, China. 3. School of Electrical and Computer Engineering, University of Oklahoma, Norman, OK, 73019, USA. 4. Department of Radiology, Fujian Medical University Union Hospital, Fuzhou, 350001, China. Electronic address: wwl152559063@163.com.
Abstract
INTRODUCTION: Preoperative diagnosis of No.10 lymph nodes (LNs) metastases in advanced proximal gastric cancer (APGC) patients remains a challenge. The aim of this study was to develop a CT-based radiomics nomogram for identification of No.10 LNs status in APGCs. MATERIALS AND METHODS: A total of 515 patients with primary APGCs were retrospectively selected and divided into a training cohort (n = 340) and a validation cohort (n = 175). Total incidence of No.10 LNM was 12.4% (64/515). CT based radiomics nomogram combining with radiomic signature calculated from venous CT imaging features and CT-defined No.10 LNs status evaluated by radiologists was built and tested to predict the No.10 LNs status in APGCs. RESULTS: CT based radiomics nomogram yielded classification accuracy with areas under ROC curves, AUC = 0.896 and 0.814 in training and validation cohort, respectively, while radiomic signature and radiologist' diagnosis based on contrast-enhanced CT images yielded lower AUCs ranging in 0.742-0.866 and 0.619-0.685, respectively. In the specificity higher than 80%, the sensitivity of using radiomics nomogram, radiomic signature and radiologists' evaluation to detect No.10 LNs positive cases was 82.8% (53/64), 67.2% (43/64) and 39.1% (25/64), respectively. CONCLUSIONS: The CT-based radiomics nomogram provides a promising and more effective method to yield high accuracy in identification of No.10 LNs metastases in APGC patients.
INTRODUCTION: Preoperative diagnosis of No.10 lymph nodes (LNs) metastases in advanced proximal gastric cancer (APGC) patients remains a challenge. The aim of this study was to develop a CT-based radiomics nomogram for identification of No.10 LNs status in APGCs. MATERIALS AND METHODS: A total of 515 patients with primary APGCs were retrospectively selected and divided into a training cohort (n = 340) and a validation cohort (n = 175). Total incidence of No.10 LNM was 12.4% (64/515). CT based radiomics nomogram combining with radiomic signature calculated from venous CT imaging features and CT-defined No.10 LNs status evaluated by radiologists was built and tested to predict the No.10 LNs status in APGCs. RESULTS: CT based radiomics nomogram yielded classification accuracy with areas under ROC curves, AUC = 0.896 and 0.814 in training and validation cohort, respectively, while radiomic signature and radiologist' diagnosis based on contrast-enhanced CT images yielded lower AUCs ranging in 0.742-0.866 and 0.619-0.685, respectively. In the specificity higher than 80%, the sensitivity of using radiomics nomogram, radiomic signature and radiologists' evaluation to detect No.10 LNs positive cases was 82.8% (53/64), 67.2% (43/64) and 39.1% (25/64), respectively. CONCLUSIONS: The CT-based radiomics nomogram provides a promising and more effective method to yield high accuracy in identification of No.10 LNs metastases in APGC patients.