Fully Convolutional Deep Network Architectures for Automatic Short Glass Fiber Semantic Segmentation from CT scans

by   Tomasz Konopczynski, et al.

We present the first attempt to perform short glass fiber semantic segmentation from X-ray computed tomography volumetric datasets at medium (3.9 μm isotropic) and low (8.3 μm isotropic) resolution using deep learning architectures. We performed experiments on both synthetic and real CT scans and evaluated deep fully convolutional architectures with both 2D and 3D kernels. Our artificial neural networks outperform existing methods at both medium and low resolution scans.


Instance Segmentation of Fibers from Low Resolution CT Scans via 3D Deep Embedding Learning

We propose a novel approach for automatic extraction (instance segmentat...

Scalable 3D Semantic Segmentation for Gun Detection in CT Scans

With the increased availability of 3D data, the need for solutions proce...

Hierarchical 3D Feature Learning for Pancreas Segmentation

We propose a novel 3D fully convolutional deep network for automated pan...

Reference Setup for Quantitative Comparison of Segmentation Techniques for Short Glass Fiber CT Data

Comparing different algorithms for segmenting glass fibers in industrial...

Extracting Lungs from CT Images using Fully Convolutional Networks

Analysis of cancer and other pathological diseases, like the interstitia...

Interactive user interface based on Convolutional Auto-encoders for annotating CT-scans

High resolution computed tomography (HRCT) is the most important imaging...

CT-GAN: Malicious Tampering of 3D Medical Imagery using Deep Learning

In 2018, clinics and hospitals were hit with numerous attacks leading to...