|
|
|
| The value of emergency CT-based radiomics in predicting abdominal aortic syndrome |
| LIN Wenxiao1,SU Jiehui1, GUO Yifan2, CHEN Shaoqing1, WU Aiqin1, CHENG Jianmin1 |
| 1.Department of Radiography,the Second Affiliated Hospital of Wenzhou Medical University, Wenzhou 325027, China; 2.Department of Radiography, the First Affiliated Hospital of Zhejiang Chinese Medical University, Hangzhou 310006, China |
|
| Cite this article: |
|
LIN Wenxiao,SU Jiehui,GUO Yifan, et al. The value of emergency CT-based radiomics in predicting abdominal aortic syndrome[J]. JOURNAL OF WEZHOU MEDICAL UNIVERSITY, 2022, 52(4): 283-287,293.
|
|
|
|
Abstract Objective: To evaluate the value of radiomics based on emergency CT plain scan in the diagnosis of abdominal aortic syndrome (AS). Methods: A total of 145 emergency patients who underwent plain and enhanced abdominal CT scan in the Second Affiliated Hospital of Wenzhou Medical University from August 2012 to October 2020 were collected. According to abdominal AS, all subjects were stratified randomly into the training set and the validation set in a ratio of 7:3. The abdominal aorta on CT plain scan images was manually segmented layer by layer, from which the radiomic features were extracted. The radiomic signature was constructed based on the selected features, and the radiomics score (Rad-score) of each patient was calculated.Univariate and multivariate logistic regression analyses were used to identify the risk factors for predicting abdominal AS. Finally, a nomogram based on clinical risk factors and Rad-score was constructed by multivariate logistic regression. Receiver operating characteristic (ROC) curve was used to evaluate the predictive performance of the model. Results: Univariate and multivariate Logistic regression showed that abdominal pain (OR=0.48, 95%CI=0.19-1.22, P=0.12) and displaced calcification (OR=8.76, 95%CI=3.27-23.45, P<0.001) were the clinical risk factors of abdominal AS. The area under the curve (AUC) of ROC curve of the clinical model in the test set was 0.79. Eight radiomic features were selected to construct radiomic signature with an AUC of 0.88 in the test set. The nomogram was obtained by combining the radiomic signature with the clinical model,and its AUC in the test set was 0.89. The clinical decision curve showed that the nomogram had the best clinical practicability. Conclusion: The nomogram based on radiomics of CT plain scan and clinical factors can well predict abdominal AS in emergency patients.
|
|
Received: 07 February 2022
|
| |
|
|
|
| [1] |
ZHOU Yongjin, GAO Ruijie, JIANG Chunyan, DENG Jingjing, XIA Shuiwei, SHEN Shaobo, WANG Zufei, JI Jiansong. CT-based radiomics nomogram to differentiate non-functional pancreatic neuroendocrine tumors from solid pseudopapillary tumors[J]. JOURNAL OF WEZHOU MEDICAL UNIVERSITY, 2022, 52(8): 645-651,656. |
|
|
|
|
