Deep Learning with Convolutional Neural Network for Differentiation of Liver Masses at Dynamic Contrast-enhanced CT: A Preliminary Study
Top Cited Papers
- 1 March 2018
- journal article
- research article
- Published by Radiological Society of North America (RSNA) in Radiology
- Vol. 286 (3), 887-896
- https://doi.org/10.1148/radiol.2017170706
Abstract
To investigate diagnostic performance by using a deep learning method with a convolutional neural network (CNN) for the differentiation of liver masses at dynamic contrast agent–enhanced computed tomography (CT). This clinical retrospective study used CT image sets of liver masses over three phases (noncontrast-agent enhanced, arterial, and delayed). Masses were diagnosed according to five categories (category A, classic hepatocellular carcinomas [HCCs]; category B, malignant liver tumors other than classic and early HCCs; category C, indeterminate masses or mass-like lesions [including early HCCs and dysplastic nodules] and rare benign liver masses other than hemangiomas and cysts; category D, hemangiomas; and category E, cysts). Supervised training was performed by using 55 536 image sets obtained in 2013 (from 460 patients, 1068 sets were obtained and they were augmented by a factor of 52 [rotated, parallel-shifted, strongly enlarged, and noise-added images were generated from the original images]). The CNN was composed of six convolutional, three maximum pooling, and three fully connected layers. The CNN was tested with 100 liver mass image sets obtained in 2016 (74 men and 26 women; mean age, 66.4 years ± 10.6 [standard deviation]; mean mass size, 26.9 mm ± 25.9; 21, nine, 35, 20, and 15 liver masses for categories A, B, C, D, and E, respectively). Training and testing were performed five times. Accuracy for categorizing liver masses with CNN model and the area under receiver operating characteristic curve for differentiating categories A–B versus categories C–E were calculated. Median accuracy of differential diagnosis of liver masses for test data were 0.84. Median area under the receiver operating characteristic curve for differentiating categories A–B from C–E was 0.92. Deep learning with CNN showed high diagnostic performance in differentiation of liver masses at dynamic CT. © RSNA, 2017 Online supplemental material is available for this article.Keywords
This publication has 21 references indexed in Scilit:
- Investigation of the freely available easy-to-use software ‘EZR’ for medical statisticsBone Marrow Transplantation, 2012
- Imaging Study of Early Hepatocellular Carcinoma: Usefulness of Gadoxetic Acid–enhanced MR ImagingRadiology, 2011
- Differential diagnosis of CT focal liver lesions using texture features, feature selection and ensemble driven classifiersArtificial Intelligence in Medicine, 2007
- Diagnosis of Hepatic Tumors With Texture Analysis in Nonenhanced Computed Tomography ImagesAcademic Radiology, 2006
- Focal Liver Lesions: Pattern-based Classification Scheme for Enhancement at Arterial Phase CTRadiology, 2000
- Gradient-based learning applied to document recognitionProceedings of the IEEE, 1998
- Dual-phase helical CT of the liver: value of an early-phase acquisition in the differential diagnosis of noncystic focal lesions.American Journal of Roentgenology, 1997
- CT diagnosis of early hepatocellular carcinoma: sensitivity, findings, and CT-pathologic correlation.American Journal of Roentgenology, 1995
- CT of hepatic masses: significance of prolonged and delayed enhancementAmerican Journal of Roentgenology, 1986
- Neocognitron: A new algorithm for pattern recognition tolerant of deformations and shifts in positionPattern Recognition, 1982