Automated Segmentation on the Entire Cardiac Cycle Using a Deep Learning Work - Flow

Research output: Chapter in Book/Report/Conference proceedingConference paperpeer-review

14 Citations (Scopus)

Abstract

The segmentation of the left ventricle (LV) from CINE MRI images is essential to infer important clinical parameters. Typically, machine learning algorithms for automated LV segmentation use annotated contours from only two cardiac phases, diastole, and systole. In this work, we present an analysis work-flow for fully-automated LV segmentation that learns from images acquired through the cardiac cycle. The workflow consists of three components: first, for each image in the sequence, we perform an automated localization and subsequent cropping of the bounding box containing the cardiac silhouette. Second, we identify the LV contours using a Temporal Fully Convolutional Neural Network (T-FCNN), which extends Fully Convolutional Neural Networks (FCNN) through a recurrent mechanism enforcing temporal coherence across consecutive frames. Finally, we further defined the boundaries using either one of two components: fully-connected Conditional Random Fields (CRFs) with Gaussian edge potentials and Semantic Flow. Our initial experiments suggest that significant improvement in performance can potentially be achieved by using a recurrent neural network component that explicitly learns cardiac motion patterns whilst performing LV segmentation.

Original languageEnglish
Title of host publication2018 5th International Conference on Social Networks Analysis, Management and Security, SNAMS 2018
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages153-158
Number of pages6
ISBN (Electronic)9781538695883
DOIs
Publication statusPublished - 30 Nov 2018
Event5th International Conference on Social Networks Analysis, Management and Security, SNAMS 2018 - Valencia, Spain
Duration: 15 Oct 201818 Oct 2018

Conference

Conference5th International Conference on Social Networks Analysis, Management and Security, SNAMS 2018
Country/TerritorySpain
CityValencia
Period15/10/201818/10/2018

Fingerprint

Dive into the research topics of 'Automated Segmentation on the Entire Cardiac Cycle Using a Deep Learning Work - Flow'. Together they form a unique fingerprint.

Cite this