Faster R-CNN-based artificial intelligence image-aided diagnosis platform in identifying EMVI of rectal cancer: A multicenter clinical study
10.19538/j.cjps.issn1005-2208.2019.10.21
- Author:
Shu-hao LIU
1
;
Ke-fan SU
1
;
Xian-xiang ZHANG
1
;
Yun LU
1
Author Information
1. Department of General Surgery,Affiliated Hospital of Qingdao University Qingdao 266003,China
- Publication Type:Journal Article
- Keywords:
artificial intelligence;
rectal cancer;
extramural vascular invasion;
magnetic resonance imaging
- From:
Chinese Journal of Practical Surgery
2019;39(10):1081-1084
- CountryChina
- Language:Chinese
-
Abstract:
OBJECTIVE: To explore the clinical application value of artificial intelligence image aided diagnosis platformbased on Faster R-CNN in identifying EMVI of rectal cancer.METHODS: In the multicenter retrospective study,500 patients with rectal cancer who underwent high-resolution MRI examination between July 2016 and February 2019 wereselected from seven hospitals in China. They were divided into 174 positive and 326 negative patients. Patients wererandomized to a training group(400 patients,including 133 positive and 267 negative) and a validation group(100 patients,including 41 positive and 59 negative) using a random number method. Using the Faster R-CNN to learn and train 20 430 high-resolution MRI images of thetraining group,an artificial intelligence image-aided diagnosis platform was established. The5107 high-resolution MRI images of thevalidation group were clinically validated.Receiver operating characteristic(ROC) curveand area under the curve(AUC) were used tocompare the diagnostic results of the artificialintelligence image-aided diagnosis platform andthe senior image expert.RESULTS: The accuracy,sensitivity,specificity,positive predictive valueand negative predictive value of EMVI forartificial intelligence image-aided diagnosis platform were 93.4%, 97.3%, 89.5%, 0.90 and 0.97,respectively. The area under the receiver operating characteristiccurve(AUC) was 0.98. The time required to automatically recognize a single image was 0.2 seconds,which had clearadvantages compared to radiologists(estimated to be about 10 seconds).CONCLUSION: The artificial intelligence image-assisted diagnosis platform based on Faster R-CNN has high efficiency and feasibility for identifying rectal cancerEMVI,and can assist imaging diagnosis.
