DeepAI
Log In Sign Up

Deep Learning with Anatomical Priors: Imitating Enhanced Autoencoders in Latent Space for Improved Pelvic Bone Segmentation in MRI

03/21/2019
by   Duc Duy Pham, et al.
0

We propose a 2D Encoder-Decoder based deep learning architecture for semantic segmentation, that incorporates anatomical priors by imitating the encoder component of an autoencoder in latent space. The autoencoder is additionally enhanced by means of hierarchical features, extracted by an U-Net module. Our suggested architecture is trained in an end-to-end manner and is evaluated on the example of pelvic bone segmentation in MRI. A comparison to the standard U-Net architecture shows promising improvements.

READ FULL TEXT
11/29/2020

UVid-Net: Enhanced Semantic Segmentation of UAV Aerial Videos by Embedding Temporal Information

Semantic segmentation of aerial videos has been extensively used for dec...
10/27/2018

3D MRI brain tumor segmentation using autoencoder regularization

Automated segmentation of brain tumors from 3D magnetic resonance images...
12/06/2018

Traversing Latent Space using Decision Ferns

The practice of transforming raw data to a feature space so that inferen...
11/15/2022

Clinically Plausible Pathology-Anatomy Disentanglement in Patient Brain MRI with Structured Variational Priors

We propose a hierarchically structured variational inference model for a...
10/28/2021

Probabilistic Autoencoder using Fisher Information

Neural Networks play a growing role in many science disciplines, includi...
09/28/2022

CSSAM: U-net Network for Application and Segmentation of Welding Engineering Drawings

Heavy equipment manufacturing splits specific contours in drawings and c...