A generative flow-based model for volumetric data augmentation in 3D deep learning for computed tomographic colonography.
Researchers
Journal
Modalities
Models
Abstract
Deep learning can be used for improving the performance of computer-aided detection (CADe) in various medical imaging tasks. However, in computed tomographic (CT) colonography, the performance is limited by the relatively small size and the variety of the available training datasets. Our purpose in this study was to develop and evaluate a flow-based generative model for performing 3DÂ data augmentation of colorectal polyps for effective training of deep learning in CADe for CT colonography.
We developed a 3D-convolutional neural network (3DÂ CNN) based on a flow-based generative model (3DÂ Glow) for generating synthetic volumes of interest (VOIs) that has characteristics similar to those of the VOIs of its training dataset. The 3DÂ Glow was trained to generate synthetic VOIs of polyps by use of our clinical CT colonography case collection. The evaluation was performed by use of a human observer study with three observers and by use of a CADe-based polyp classification study with a 3DÂ DenseNet.
The area-under-the-curve values of the receiver operating characteristic analysis of the three observers were not statistically significantly different in distinguishing between real polyps and synthetic polyps. When trained with data augmentation by 3DÂ Glow, the 3DÂ DenseNet yielded a statistically significantly higher polyp classification performance than when it was trained with alternative augmentation methods.
The 3DÂ Glow-generated synthetic polyps are visually indistinguishable from real colorectal polyps. Their application to data augmentation can substantially improve the performance of 3D CNNs in CADe for CT colonography. Thus, 3D Glow is a promising method for improving the performance of deep learning in CADe for CT colonography.