期刊
RADIOLOGY-ARTIFICIAL INTELLIGENCE
卷 1, 期 2, 页码 -出版社
RADIOLOGICAL SOC NORTH AMERICA (RSNA)
DOI: 10.1148/ryai.2019180014
关键词
-
资金
- Canada Research Chair in Medical Imaging and Assisted Interventions [950-228359]
- Fondation de l'Association des Radiologistes du Quebec
- Fonds de Recherche du Quebec-Sante [34939]
- Roger Des Groseillers Hepato-Pancreatico-Biliary Surgical Oncology Research Chair
- Natural Sciences and Engineering Research Council of Canada
- PREMIER Internship Award - Institut du Cancer de Montreal
- MEDTEQ
- Polytechnique Montreal
- MITACS-Cluster Accelerate [IT05356]
- Imagia
Purpose: To evaluate the performance, agreement, and efficiency of a fully convolutional network (FCN) for liver lesion detection and segmentation at CT examinations in patients with colorectal liver metastases (CLMs). Materials and Methods: This retrospective study evaluated an automated method using an FCN that was trained, validated, and tested with 115, 15, and 26 contrast material-enhanced CT examinations containing 261, 22, and 105 lesions, respectively. Manual detection and segmentation by a radiologist was the reference standard. Performance of fully automated and user-corrected segmentations was compared with that of manual segmentations. The interuser agreement and interaction time of manual and user-corrected segmentations were assessed. Analyses included sensitivity and positive predictive value of detection, segmentation accuracy, Cohen kappa, Bland-Altman analyses, and analysis of variance. Results: In the test cohort, for lesion size smaller than 10 mm (n = 30), 10-20 mm (n = 35), and larger than 20 mm (n = 40), the detection sensitivity of the automated method was 10%, 71%, and 85%; positive predictive value was 25%, 83%, and 94%; Dice similarity coefficient was 0.14, 0.53, and 0.68; maximum symmetric surface distance was 5.2, 6.0, and 10.4 mm; and average symmetric surface distance was 2.7, 1.7, and 2.8 mm, respectively. For manual and user-corrected segmentation, k values were 0.42 (95% confidence interval: 0.24, 0.63) and 0.52 (95% confidence interval: 0.36, 0.72); normalized interreader agreement for lesion volume was -0.10 +/- 0.07 (95% confidence interval) and -0.10 +/- 0.08; and mean interaction time was 7.7 minutes +/- 2.4 (standard deviation) and 4.8 minutes +/- 2.1 (P <.001), respectively. Conclusion: Automated detection and segmentation of CLM by using deep learning with convolutional neural networks, when manually corrected, improved efficiency but did not substantially change agreement on volumetric measurements. (C) RSNA, 2019
作者
我是这篇论文的作者
点击您的名字以认领此论文并将其添加到您的个人资料中。
推荐
暂无数据