A Two-Stage U-Net Model for 3D Multi-class Segmentation on Full-Resolution Cardiac Data

Chengjia Wang*, Tom MacGillivray, Gillian Macnaught, Guang Yang, David Newby

*Corresponding author for this work

Research output: Chapter in Book/Report/Conference proceedingConference contribution

19 Citations (Scopus)

Abstract

Deep convolutional neural networks (CNNs) have achieved state-of-the-art performances for multi-class segmentation of medical images. However, a common problem when dealing with large, high resolution 3D data is that the volumes input into the deep CNNs has to be either cropped or downsampled due to limited memory capacity of computing devices. These operations can lead to loss of resolution and class imbalance in the input data batches, thus downgrade the performances of segmentation algorithms. Inspired by the architecture of image super-resolution CNN (SRCNN), we propose a two-stage modified U-Net framework that simultaneously learns to detect a ROI within the full volume and to classify voxels without losing the original resolution. Experiments on a variety of multi-modal 3D cardiac images have demonstrated that this framework shows better segmentation performances than state-of-the-art Deep CNNs with trained with the same similarity metrics.

Original languageEnglish
Title of host publicationStatistical Atlases and Computational Models of the Heart. Atrial Segmentation and LV Quantification Challenges. STACOM 2018
PublisherSpringer
Pages191-199
Number of pages9
ISBN (Electronic)9783030120290
ISBN (Print)9783030120283
DOIs
Publication statusPublished - 14 Feb 2019
Event9th International Workshop on Statistical Atlases and Computational Models of the Heart: Atrial Segmentation and LV Quantification Challenges - Granada, Spain
Duration: 16 Sept 201816 Sept 2018

Publication series

NameLecture Notes in Computer Science
Volume11395
ISSN (Print)0302-9743
ISSN (Electronic)1611-3349

Conference

Conference9th International Workshop on Statistical Atlases and Computational Models of the Heart: Atrial Segmentation and LV Quantification Challenges
Abbreviated titleSTACOM 2018
Country/TerritorySpain
CityGranada
Period16/09/1816/09/18
OtherHeld in conjunction with Medical Image Computing and Computer-Assisted Intervention, MICCAI 2018.

Keywords

  • Cardiac CT/MR
  • Convolutional neural networks
  • High resolution
  • Image segmentation

ASJC Scopus subject areas

  • Theoretical Computer Science
  • General Computer Science

Fingerprint

Dive into the research topics of 'A Two-Stage U-Net Model for 3D Multi-class Segmentation on Full-Resolution Cardiac Data'. Together they form a unique fingerprint.

Cite this