3D fully convolutional networks for co-segmentation of tumors on PET-CT images

Zisha Zhong; Yusung Kim; Leixin Zhou; Kristin Plichta; Bryan Allen; John Buatti; Xiaodong Wu

doi:10.1109/ISBI.2018.8363561

Back

3D fully convolutional networks for co-segmentation of tumors on PET-CT images

Conference proceeding

Open access

3D fully convolutional networks for co-segmentation of tumors on PET-CT images

Zisha Zhong, Yusung Kim, Leixin Zhou, Kristin Plichta, Bryan Allen, John Buatti and Xiaodong Wu

2018 IEEE 15th International Symposium on Biomedical Imaging (ISBI 2018), Vol.2018-, pp.228-231

04/2018

DOI: 10.1109/ISBI.2018.8363561

PMCID: PMC6878113

PMID: 31772717

Files and links (1)

url

https://www.ncbi.nlm.nih.gov/pmc/articles/6878113View

Open Access

Abstract

Positron emission tomography and computed tomography (PET-CT) dual-modality imaging provides critical diagnostic information in modern cancer diagnosis and therapy. Automated accurate tumor delineation is essentially important in computer-assisted tumor reading and interpretation based on PET-CT. In this paper, we propose a novel approach for the segmentation of lung tumors that combines the powerful fully convolutional networks (FCN) based semantic segmentation framework (3D-UNet) and the graph cut based co-segmentation model. First, two separate deep UNets are trained on PET and CT, separately, to learn high level discriminative features to generate tumor/non-tumor masks and probability maps for PET and CT images. Then, the two probability maps on PET and CT are further simultaneously employed in a graph cut based co-segmentation model to produce the final tumor segmentation results. Comparative experiments on 32 PET-CT scans of lung cancer patients demonstrate the effectiveness of our method.

Computed Tomography

Tumors

Image segmentation

deep learning

Three-dimensional displays

fully convolutional networks

co-segmentation

Lung

lung tumor segmentation

Biomedical imaging

Details

Title: Subtitle: 3D fully convolutional networks for co-segmentation of tumors on PET-CT images
Creators: Zisha Zhong - Department of Electrical and Computer Engineering, University of Iowa, Iowa City, IA
Yusung Kim - Department of Radiation Oncology, University of Iowa, Iowa City, IA
Leixin Zhou - Department of Electrical and Computer Engineering, University of Iowa, Iowa City, IA
Kristin Plichta - Department of Radiation Oncology, University of Iowa, Iowa City, IA
Bryan Allen - Department of Radiation Oncology, University of Iowa, Iowa City, IA
John Buatti - Department of Radiation Oncology, University of Iowa, Iowa City, IA
Xiaodong Wu - Department of Electrical and Computer Engineering, University of Iowa, Iowa City, IA
Resource Type: Conference proceeding
Publication Details: 2018 IEEE 15th International Symposium on Biomedical Imaging (ISBI 2018), Vol.2018-, pp.228-231
DOI: 10.1109/ISBI.2018.8363561
PMID: 31772717
PMCID: PMC6878113
NLM abbreviation: Proc IEEE Int Symp Biomed Imaging
ISSN: 1945-7928
eISSN: 1945-8452
Publisher: IEEE
Language: English
Date published: 04/2018
Academic Unit: Electrical and Computer Engineering; Radiation Oncology; Neurosurgery; Otolaryngology
Record Identifier: 9984046806702771

Metrics

21 Record Views

78 Times Cited - Web of Science