Yidi Chen1, Jiang Huang2, Yuying Zhang2, Jinhuan Xie2, Yiqiong Liang2, Wenzhao Yuan2, Ting Zhou2, Ruizhi Gao3, Rong Wen3, Yuwei Xia4, Liling Long5. 1. Department of Radiology, West China Hospital, Sichuan University, Chengdu, 610041, China. 2. Department of Radiology, The First Affiliated Hospital of Guangxi Medical University, No. 6 Shuangyong Road, Nanning, 530021, Guangxi, China. 3. Department of Medical Ultrasound, The First Affiliated Hospital of Guangxi Medical University, Nanning, 530021, Guangxi, China. 4. Huiying Medical Technology Co. Ltd, Beijing, 100192, China. 5. Department of Radiology, The First Affiliated Hospital of Guangxi Medical University, No. 6 Shuangyong Road, Nanning, 530021, Guangxi, China. cjr.longliling@vip.163.com.
Abstract
PURPOSE: To compare the ability of a clinical-computed tomography (CT) model vs. 2D and 3D radiomics models for predicting occult peritoneal metastasis (PM) in patients with advanced gastric cancer (AGC). METHODS: In this retrospective study, we included 49 patients with occult PM and 49 control patients (without PM) who underwent preoperative CT and subsequent surgery between January 2016 and December 2018. Clinical information and CT semantic features were collected, and CT radiomics features were extracted. A predictive clinical-CT model was created using multivariate logistic regression. The least absolute shrinkage and selection operator algorithm and logistic regression were used for constructing 2D and 3D radiomics models. These models were validated with an external cohort (n = 30). Receiver operating characteristics curve with area under the curve (AUC), sensitivity, and specificity were used to evaluate predictive performance. RESULTS: Tumor size, mild ascites, and serum CA125 were independent factors predictive of occult PM. The clinical-CT model of these independent factors showed better diagnostic performance than 2D and 3D radiomics models. In the external validation cohort, the AUCs of different models were as follows-clinical-CT model: 0.853 (sensitivity, 66.7%; specificity, 93.3%); 2D radiomics model: 0.622 (sensitivity, 80.0%; specificity, 46.7%); and 3D radiomics model: 0.676 (sensitivity, 60.0%; specificity, 86.0%). The clinical-CT model nomogram showed good clinical predictive efficiency to assess occult PM. CONCLUSION: The clinical-CT model was better than the radiomics models in predicting occult PM in AGC.
PURPOSE: To compare the ability of a clinical-computed tomography (CT) model vs. 2D and 3D radiomics models for predicting occult peritoneal metastasis (PM) in patients with advanced gastric cancer (AGC). METHODS: In this retrospective study, we included 49 patients with occult PM and 49 control patients (without PM) who underwent preoperative CT and subsequent surgery between January 2016 and December 2018. Clinical information and CT semantic features were collected, and CT radiomics features were extracted. A predictive clinical-CT model was created using multivariate logistic regression. The least absolute shrinkage and selection operator algorithm and logistic regression were used for constructing 2D and 3D radiomics models. These models were validated with an external cohort (n = 30). Receiver operating characteristics curve with area under the curve (AUC), sensitivity, and specificity were used to evaluate predictive performance. RESULTS: Tumor size, mild ascites, and serum CA125 were independent factors predictive of occult PM. The clinical-CT model of these independent factors showed better diagnostic performance than 2D and 3D radiomics models. In the external validation cohort, the AUCs of different models were as follows-clinical-CT model: 0.853 (sensitivity, 66.7%; specificity, 93.3%); 2D radiomics model: 0.622 (sensitivity, 80.0%; specificity, 46.7%); and 3D radiomics model: 0.676 (sensitivity, 60.0%; specificity, 86.0%). The clinical-CT model nomogram showed good clinical predictive efficiency to assess occult PM. CONCLUSION: The clinical-CT model was better than the radiomics models in predicting occult PM in AGC.
Authors: Jaffer A Ajani; Thomas A D'Amico; Khaldoun Almhanna; David J Bentrem; Joseph Chao; Prajnan Das; Crystal S Denlinger; Paul Fanta; Farhood Farjah; Charles S Fuchs; Hans Gerdes; Michael Gibson; Robert E Glasgow; James A Hayman; Steven Hochwald; Wayne L Hofstetter; David H Ilson; Dawn Jaroszewski; Kimberly L Johung; Rajesh N Keswani; Lawrence R Kleinberg; W Michael Korn; Stephen Leong; Catherine Linn; A Craig Lockhart; Quan P Ly; Mary F Mulcahy; Mark B Orringer; Kyle A Perry; George A Poultsides; Walter J Scott; Vivian E Strong; Mary Kay Washington; Benny Weksler; Christopher G Willett; Cameron D Wright; Debra Zelman; Nicole McMillian; Hema Sundar Journal: J Natl Compr Canc Netw Date: 2016-10 Impact factor: 11.908
Authors: Su Jin Kim; Hyung-Ho Kim; Young Hoon Kim; Sun Hwi Hwang; Hye Seung Lee; Do Joong Park; So Yeon Kim; Kyoung Ho Lee Journal: Radiology Date: 2009-09-29 Impact factor: 11.105
Authors: Eelco de Bree; Wim Koops; Robert Kröger; Serge van Ruth; Arjen J Witkamp; Frans A N Zoetmulder Journal: J Surg Oncol Date: 2004-05-01 Impact factor: 3.454