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

doi:10.1007/978-3-030-12029-0_21

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 proceeding › Conference 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 language	English
Title of host publication	Statistical Atlases and Computational Models of the Heart. Atrial Segmentation and LV Quantification Challenges. STACOM 2018
Publisher	Springer
Pages	191-199
Number of pages	9
ISBN (Electronic)	9783030120290
ISBN (Print)	9783030120283
DOIs	https://doi.org/10.1007/978-3-030-12029-0_21
Publication status	Published - 14 Feb 2019
Event	9th International Workshop on Statistical Atlases and Computational Models of the Heart: Atrial Segmentation and LV Quantification Challenges - Granada, Spain Duration: 16 Sept 2018 → 16 Sept 2018

Publication series

Name	Lecture Notes in Computer Science
Volume	11395
ISSN (Print)	0302-9743
ISSN (Electronic)	1611-3349

Conference

Conference	9th International Workshop on Statistical Atlases and Computational Models of the Heart: Atrial Segmentation and LV Quantification Challenges
Abbreviated title	STACOM 2018
Country/Territory	Spain
City	Granada
Period	16/09/18 → 16/09/18
Other	Held 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

Access to Document

10.1007/978-3-030-12029-0_21

Cite this

Wang, C., MacGillivray, T., Macnaught, G., Yang, G., & Newby, D. (2019). A Two-Stage U-Net Model for 3D Multi-class Segmentation on Full-Resolution Cardiac Data. In Statistical Atlases and Computational Models of the Heart. Atrial Segmentation and LV Quantification Challenges. STACOM 2018 (pp. 191-199). (Lecture Notes in Computer Science; Vol. 11395). Springer. https://doi.org/10.1007/978-3-030-12029-0_21

@inproceedings{be9945018dd449f5bad5e0d8553dda43,

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

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.",

keywords = "Cardiac CT/MR, Convolutional neural networks, High resolution, Image segmentation",

author = "Chengjia Wang and Tom MacGillivray and Gillian Macnaught and Guang Yang and David Newby",

note = "Funding Information: This work is funded by BHF Centre of Cardiovascular Science and MICCAI 2017 Multi-Modality Whole Heart Segmentation (MM-WHS) challeng. Publisher Copyright: {\textcopyright} 2019, Springer Nature Switzerland AG.; 9th International Workshop on Statistical Atlases and Computational Models of the Heart: Atrial Segmentation and LV Quantification Challenges, STACOM 2018 ; Conference date: 16-09-2018 Through 16-09-2018",

year = "2019",

month = feb,

day = "14",

doi = "10.1007/978-3-030-12029-0_21",

language = "English",

isbn = "9783030120283",

series = "Lecture Notes in Computer Science",

publisher = "Springer",

pages = "191--199",

booktitle = "Statistical Atlases and Computational Models of the Heart. Atrial Segmentation and LV Quantification Challenges. STACOM 2018",

address = "United States",

}

Wang, C, MacGillivray, T, Macnaught, G, Yang, G & Newby, D 2019, A Two-Stage U-Net Model for 3D Multi-class Segmentation on Full-Resolution Cardiac Data. in Statistical Atlases and Computational Models of the Heart. Atrial Segmentation and LV Quantification Challenges. STACOM 2018. Lecture Notes in Computer Science, vol. 11395, Springer, pp. 191-199, 9th International Workshop on Statistical Atlases and Computational Models of the Heart: Atrial Segmentation and LV Quantification Challenges, Granada, Spain, 16/09/18. https://doi.org/10.1007/978-3-030-12029-0_21

A Two-Stage U-Net Model for 3D Multi-class Segmentation on Full-Resolution Cardiac Data. / Wang, Chengjia; MacGillivray, Tom; Macnaught, Gillian et al.
Statistical Atlases and Computational Models of the Heart. Atrial Segmentation and LV Quantification Challenges. STACOM 2018. Springer, 2019. p. 191-199 (Lecture Notes in Computer Science; Vol. 11395).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

TY - GEN

T1 - A Two-Stage U-Net Model for 3D Multi-class Segmentation on Full-Resolution Cardiac Data

AU - Wang, Chengjia

AU - MacGillivray, Tom

AU - Macnaught, Gillian

AU - Yang, Guang

AU - Newby, David

N1 - Funding Information: This work is funded by BHF Centre of Cardiovascular Science and MICCAI 2017 Multi-Modality Whole Heart Segmentation (MM-WHS) challeng. Publisher Copyright: © 2019, Springer Nature Switzerland AG.

PY - 2019/2/14

Y1 - 2019/2/14

N2 - 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.

AB - 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.

KW - Cardiac CT/MR

KW - Convolutional neural networks

KW - High resolution

KW - Image segmentation

UR - http://www.scopus.com/inward/record.url?scp=85064048425&partnerID=8YFLogxK

U2 - 10.1007/978-3-030-12029-0_21

DO - 10.1007/978-3-030-12029-0_21

M3 - Conference contribution

AN - SCOPUS:85064048425

SN - 9783030120283

T3 - Lecture Notes in Computer Science

SP - 191

EP - 199

BT - Statistical Atlases and Computational Models of the Heart. Atrial Segmentation and LV Quantification Challenges. STACOM 2018

PB - Springer

T2 - 9th International Workshop on Statistical Atlases and Computational Models of the Heart: Atrial Segmentation and LV Quantification Challenges

Y2 - 16 September 2018 through 16 September 2018

ER -

Wang C, MacGillivray T, Macnaught G, Yang G, Newby D. A Two-Stage U-Net Model for 3D Multi-class Segmentation on Full-Resolution Cardiac Data. In Statistical Atlases and Computational Models of the Heart. Atrial Segmentation and LV Quantification Challenges. STACOM 2018. Springer. 2019. p. 191-199. (Lecture Notes in Computer Science). doi: 10.1007/978-3-030-12029-0_21

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

Abstract

Publication series

Conference

Keywords

ASJC Scopus subject areas

Access to Document

Other files and links

Fingerprint

Cite this