计算机科学
卷积神经网络
人工智能
分割
深度学习
合成数据
模式识别(心理学)
人工神经网络
数据采集
计算机视觉
机器学习
操作系统
作者
Athanasios Tsamos,Sergei Evsevleev,R. Fioresi,Francesco Faglioni,Giovanni Bruno
出处
期刊:Journal of Imaging
[Multidisciplinary Digital Publishing Institute]
日期:2023-01-19
卷期号:9 (2): 22-22
被引量:17
标识
DOI:10.3390/jimaging9020022
摘要
The greatest challenge when using deep convolutional neural networks (DCNNs) for automatic segmentation of microstructural X-ray computed tomography (XCT) data is the acquisition of sufficient and relevant data to train the working network. Traditionally, these have been attained by manually annotating a few slices for 2D DCNNs. However, complex multiphase microstructures would presumably be better segmented with 3D networks. However, manual segmentation labeling for 3D problems is prohibitive. In this work, we introduce a method for generating synthetic XCT data for a challenging six-phase Al–Si alloy composite reinforced with ceramic fibers and particles. Moreover, we propose certain data augmentations (brightness, contrast, noise, and blur), a special in-house designed deep convolutional neural network (Triple UNet), and a multi-view forwarding strategy to promote generalized learning from synthetic data and therefore achieve successful segmentations. We obtain an overall Dice score of 0.77. Lastly, we prove the detrimental effects of artifacts in the XCT data on achieving accurate segmentations when synthetic data are employed for training the DCNNs. The methods presented in this work are applicable to other materials and imaging techniques as well. Successful segmentation coupled with neural networks trained with synthetic data will accelerate scientific output.
科研通智能强力驱动
Strongly Powered by AbleSci AI