Diagnostic accuracy of different computer-aided diagnostic systems for prostate cancer based on magnetic resonance imaging: A systematic review with diagnostic meta-analysis. Issue 3 (22nd January 2021)

• Record Type: Journal Article
• Authors: Xing, Xiping; Zhao, Xinke; Wei, Huiping; Li, Yingdong
• Other Names: Ding. Jianxun section editor.
• Is Part Of: Medicine. Volume 100:Issue 3(2021)
• Publication Date: 2021-01-22
• Subjects: Computer-aided detection -- diagnostic accuracy -- magnetic resonance imaging -- meta-analysis -- prostate cancer -- systematic review; Medicine -- Periodicals; Medicine -- Periodicals; Médecine -- Périodiques; Geneeskunde; Medicine; Periodicals; Periodicals; 610.5
• DOI: 10.1097/MD.0000000000023817
• Languages: English
• ISSNs: 0025-7974

Abstract

Abstract: Background: Computer-aided detection (CAD) system for accurate and automated prostate cancer (PCa) diagnosis have been developed, however, the diagnostic test accuracy of different CAD systems is still controversial. This systematic review aimed to assess the diagnostic accuracy of CAD systems based on magnetic resonance imaging for PCa. Methods: Cochrane library, PubMed, EMBASE and China Biology Medicine disc were systematically searched until March 2019 for original diagnostic studies. Two independent reviewers selected studies on CAD based on magnetic resonance imaging diagnosis of PCa and extracted the requisite data. Pooled sensitivity, specificity, and the area under the summary receiver operating characteristic curve were calculated to estimate the diagnostic accuracy of CAD system. Results: Fifteen studies involving 1945 patients were included in our analysis. The diagnostic meta-analysis showed that overall sensitivity of CAD system ranged from 0.47 to 1.00 and, specificity from 0.47 to 0.89. The pooled sensitivity of CAD system was 0.87 (95% CI: 0.76–0.94), pooled specificity 0.76 (95% CI: 0.62–0.85), and the area under curve (AUC) 0.89 (95% CI: 0.86–0.91). Subgroup analysis showed that the support vector machines produced the best AUC among the CAD classifiers, with sensitivity ranging from 0.87 to 0.92, and specificity from 0.47 to 0.95. Among different zones of prostate, CAD system produced the best AUC in the transitional zone than the peripheral zone and central gland; sensitivity ranged from 0.89 to 1.00, and specificity from 0.38 to 0.85. Conclusions: CAD system can help improve the diagnostic accuracy of PCa especially using the support vector machines classifier. Whether the performance of the CAD system depends on the specific locations of the prostate needs further investigation.