NewEvery arXiv paper, its researchers & institutions — mapped.
the archive

#U-Net

5 results
eess.IV2019

Sparse Annotations with Random Walks for U-Net Segmentation of Biodegradable Bone Implants in Synchrotron Microtomograms

Niclas Bockelmann, Diana Krüger, D. C. Florian Wieland +9

The paper introduces a random-walk based method to generate sparse annotations for training a U‑Net to segment biodegradable bone implants in synchrotron microtomography, achieving…

#bone implant segmentation#synchrotron microtomography#sparse annotations#random walk
eess.IV2019

Deep learning for automatic tumour segmentation in PET/CT images of patients with head and neck cancers

Yngve Mardal Moe, Aurora Rosvoll Groendahl, Martine Mulstad +5

The paper presents a U‑Net based convolutional neural network that automatically segments gross tumour volume and pathological lymph nodes in head‑and‑neck PET/CT scans, achieving…

#tumor segmentation#head and neck cancer#pet/ct imaging#u-net
eess.IV2019

Asymmetric Cascade Networks for Focal Bone Lesion Prediction in Multiple Myeloma

Roxane Licandro, Johannes Hofmanninger, Matthias Perkonigg +7

The paper introduces an asymmetric cascade network composed of two U‑Nets to predict future bone lesions in smoldering multiple myeloma from longitudinal whole‑body T1‑weighted MRI…

#multiple myeloma#bone lesion prediction#asymmetric cascade network#u-net
cs.CV2019

Learning Raw Image Denoising with Bayer Pattern Unification and Bayer Preserving Augmentation

Jiaming Liu, Chi-Hao Wu, Yuzhi Wang +8

The paper proposes a Bayer pattern unification method and a Bayer-preserving augmentation technique to enable effective deep learning-based denoising of raw sensor images, achievin…

#raw image denoising#bayer pattern#data augmentation#deep learning
cs.CV2019

Fully Automated Pancreas Segmentation with Two-stage 3D Convolutional Neural Networks

Ningning Zhao, Nuo Tong, Dan Ruan +1

The paper presents a fully automated two‑stage 3D U‑Net framework for segmenting the pancreas in CT images, achieving a mean Dice score of 85.99% on the NIH dataset.

#pancreas segmentation#3d convolutional neural networks#u-net#medical imaging