Autoencoders for Multi-Label Prostate MR Segmentation

06/09/2018

∙

Organ image segmentation can be improved by implementing prior knowledge about the anatomy. One way of doing this is by training an autoencoder to learn a lowdimensional representation of the segmentation. In this paper, this is applied in multi-label prostate MR segmentation, with some positive results.

READ FULL TEXT

Autoencoders for Multi-Label Prostate MR Segmentation

Multi-label Cloud Segmentation Using a Deep Network

Deep Value Networks Learn to Evaluate and Iteratively Refine Structured Outputs

Learning Multi-level Region Consistency with Dense Multi-label Networks for Semantic Segmentation

Multi-label affordance mapping from egocentric vision

Exploiting Clinically Available Delineations for CNN-based Segmentation in Radiotherapy Treatment Planning

PECNet: A Deep Multi-Label Segmentation Network for Eosinophilic Esophagitis Biopsy Diagnostics

Dynamic Multiscale Tree Learning Using Ensemble Strong Classifiers for Multi-label Segmentation of Medical Images with Lesions

Autoencoders for Multi-Label Prostate MR Segmentation

Related Research

Multi-label Cloud Segmentation Using a Deep Network

Deep Value Networks Learn to Evaluate and Iteratively Refine Structured Outputs

Learning Multi-level Region Consistency with Dense Multi-label Networks for Semantic Segmentation

Multi-label affordance mapping from egocentric vision

Exploiting Clinically Available Delineations for CNN-based Segmentation in Radiotherapy Treatment Planning

PECNet: A Deep Multi-Label Segmentation Network for Eosinophilic Esophagitis Biopsy Diagnostics

Dynamic Multiscale Tree Learning Using Ensemble Strong Classifiers for Multi-label Segmentation of Medical Images with Lesions