Synthetic Data Generation for Automatic Segmentation of X-ray Computed Tomography Reconstructions of Complex Microstructures.

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.

A Geometric Interpretation of Stochastic Gradient Descent Using Diffusion Metrics.

This paper is a step towards developing a geometric understanding of a popular algorithm for training deep neural networks named stochastic gradient descent (SGD). We built upon a recent result which observed that the noise in SGD while training typical networks is highly non-isotropic. That motivated a deterministic model in which the trajectories of our dynamical systems are described via geodesics of a family of metrics arising from a certain diffusion matrix; namely, the covariance of the stochastic gradients in SGD. Our model is analogous to models in general relativity: the role of the electromagnetic field in the latter is played by the gradient of the loss function of a deep network in the former.

Deep learning techniques for detecting preneoplastic and neoplastic lesions in human colorectal histological images.

Trained pathologists base colorectal cancer identification on the visual interpretation of microscope images. However, image labeling is not always straightforward and this repetitive task is prone to mistakes due to human distraction. Significant efforts are underway to develop informative tools to assist pathologists and decrease the burden and frequency of errors. The present study proposes a deep learning approach to recognize four different stages of cancerous tissue development, including normal mucosa, early preneoplastic lesion, adenoma and cancer. A dataset of human colon tissue images collected and labeled over a 10-year period by a team of pathologists was partitioned into three sets. These were used to train, validate and test the neural network, comprising several convolutional and a few linear layers. The approach used in the present study is 'direct'; it labels raw images and bypasses the segmentation step. An overall accuracy of >95% was achieved, with the majority of mislabeling referring to a near category. Tests on an external dataset with a different resolution yielded accuracies >80%. The present study demonstrated that the neural network, when properly trained, can provide fast, accurate and reproducible labeling for colon cancer images, with the potential to significantly improve the quality and speed of medical diagnoses.