no code implementations • 14 Aug 2019 • Karsten Roth, Jürgen Hesser, Tomasz Konopczyński
We propose a novel procedure to improve liver and lesion segmentation from CT scans for U-Net based models.
1 code implementation • 9 May 2019 • Karsten Roth, Tomasz Konopczyński, Jürgen Hesser
At present, lesion segmentation is still performed manually (or semi-automatically) by medical experts.
Ranked #3 on Liver Segmentation on LiTS2017 (Dice metric)
no code implementations • 6 Jan 2019 • Tomasz Konopczyński, Thorben Kröger, Lei Zheng, Christoph S. Garbe, Jürgen Hesser
Following their idea of feature learning instead of hand-crafted filters, we have extended the method to learn 3D features.
no code implementations • 4 Jan 2019 • Tomasz Konopczyński, Jitendra Rathore, Thorben Kröger, Lei Zheng, Christoph S. Garbe, Simone Carmignato, Jürgen Hesser
We suggest both the metrics and this data set as a reference for studying the performance of different algorithms.
no code implementations • 4 Jan 2019 • Tomasz Konopczyński, Thorben Kröger, Lei Zheng, Jürgen Hesser
We propose a novel approach for automatic extraction (instance segmentation) of fibers from low resolution 3D X-ray computed tomography scans of short glass fiber reinforced polymers.
no code implementations • 4 Jan 2019 • Tomasz Konopczyński, Danish Rathore, Jitendra Rathore, Thorben Kröger, Lei Zheng, Christoph S. Garbe, Simone Carmignato, Jürgen Hesser
We present the first attempt to perform short glass fiber semantic segmentation from X-ray computed tomography volumetric datasets at medium (3. 9 {\mu}m isotropic) and low (8. 3 {\mu}m isotropic) resolution using deep learning architectures.