3D segmentation of nasopharyngeal carcinoma from CT images using cascade deep learning

Bilel Daoud, Ken'ichi Morooka, Ryo Kurazume, Farhat Leila, Wafa Mnejja, Jamel Daoud

研究成果: ジャーナルへの寄稿記事

抄録

In the paper, we propose a new deep learning-based method for segmenting nasopharyngeal carcinoma (NPC) in the nasopharynx from three orthogonal CT images. The proposed method introduces a cascade strategy composed of two-phase manners. In CT images, there are organs, called non-target organs, which NPC never invades. Therefore, the first phase is to detect and eliminate non-target organ regions from the CT images. In the second phase, NPC is extracted from the remained regions in the CT images. Convolutional neural networks (CNNs) are applied to detect non-target organs and NPCs. The proposed system determines the final NPC segmentation by integrating three results obtained from coronal, axial and sagittal images. Moreover, we construct two CNN-based NPC detection systems using one kind of overlapping patches with a fixed size and various overlapping patches with different sizes. From the experiments using CT images of 70 NPC patients, our proposed systems, especially the system using various patches, achieves the best performance for detecting NPC compared with conventional NPC detection methods.

元の言語英語
記事番号101644
ジャーナルComputerized Medical Imaging and Graphics
77
DOI
出版物ステータス出版済み - 10 1 2019

Fingerprint

Learning
Neural networks
Experiments
Nasopharynx
Nasopharyngeal carcinoma
Deep learning

All Science Journal Classification (ASJC) codes

  • Radiological and Ultrasound Technology
  • Radiology Nuclear Medicine and imaging
  • Computer Vision and Pattern Recognition
  • Health Informatics
  • Computer Graphics and Computer-Aided Design

これを引用

3D segmentation of nasopharyngeal carcinoma from CT images using cascade deep learning. / Daoud, Bilel; Morooka, Ken'ichi; Kurazume, Ryo; Leila, Farhat; Mnejja, Wafa; Daoud, Jamel.

:: Computerized Medical Imaging and Graphics, 巻 77, 101644, 01.10.2019.

研究成果: ジャーナルへの寄稿記事

Daoud, Bilel ; Morooka, Ken'ichi ; Kurazume, Ryo ; Leila, Farhat ; Mnejja, Wafa ; Daoud, Jamel. / 3D segmentation of nasopharyngeal carcinoma from CT images using cascade deep learning. :: Computerized Medical Imaging and Graphics. 2019 ; 巻 77.
@article{5c8eba2f913e4eba884b5163b1164185,
title = "3D segmentation of nasopharyngeal carcinoma from CT images using cascade deep learning",
abstract = "In the paper, we propose a new deep learning-based method for segmenting nasopharyngeal carcinoma (NPC) in the nasopharynx from three orthogonal CT images. The proposed method introduces a cascade strategy composed of two-phase manners. In CT images, there are organs, called non-target organs, which NPC never invades. Therefore, the first phase is to detect and eliminate non-target organ regions from the CT images. In the second phase, NPC is extracted from the remained regions in the CT images. Convolutional neural networks (CNNs) are applied to detect non-target organs and NPCs. The proposed system determines the final NPC segmentation by integrating three results obtained from coronal, axial and sagittal images. Moreover, we construct two CNN-based NPC detection systems using one kind of overlapping patches with a fixed size and various overlapping patches with different sizes. From the experiments using CT images of 70 NPC patients, our proposed systems, especially the system using various patches, achieves the best performance for detecting NPC compared with conventional NPC detection methods.",
author = "Bilel Daoud and Ken'ichi Morooka and Ryo Kurazume and Farhat Leila and Wafa Mnejja and Jamel Daoud",
year = "2019",
month = "10",
day = "1",
doi = "10.1016/j.compmedimag.2019.101644",
language = "English",
volume = "77",
journal = "Computerized Medical Imaging and Graphics",
issn = "0895-6111",
publisher = "Elsevier Limited",

}

TY - JOUR

T1 - 3D segmentation of nasopharyngeal carcinoma from CT images using cascade deep learning

AU - Daoud, Bilel

AU - Morooka, Ken'ichi

AU - Kurazume, Ryo

AU - Leila, Farhat

AU - Mnejja, Wafa

AU - Daoud, Jamel

PY - 2019/10/1

Y1 - 2019/10/1

N2 - In the paper, we propose a new deep learning-based method for segmenting nasopharyngeal carcinoma (NPC) in the nasopharynx from three orthogonal CT images. The proposed method introduces a cascade strategy composed of two-phase manners. In CT images, there are organs, called non-target organs, which NPC never invades. Therefore, the first phase is to detect and eliminate non-target organ regions from the CT images. In the second phase, NPC is extracted from the remained regions in the CT images. Convolutional neural networks (CNNs) are applied to detect non-target organs and NPCs. The proposed system determines the final NPC segmentation by integrating three results obtained from coronal, axial and sagittal images. Moreover, we construct two CNN-based NPC detection systems using one kind of overlapping patches with a fixed size and various overlapping patches with different sizes. From the experiments using CT images of 70 NPC patients, our proposed systems, especially the system using various patches, achieves the best performance for detecting NPC compared with conventional NPC detection methods.

AB - In the paper, we propose a new deep learning-based method for segmenting nasopharyngeal carcinoma (NPC) in the nasopharynx from three orthogonal CT images. The proposed method introduces a cascade strategy composed of two-phase manners. In CT images, there are organs, called non-target organs, which NPC never invades. Therefore, the first phase is to detect and eliminate non-target organ regions from the CT images. In the second phase, NPC is extracted from the remained regions in the CT images. Convolutional neural networks (CNNs) are applied to detect non-target organs and NPCs. The proposed system determines the final NPC segmentation by integrating three results obtained from coronal, axial and sagittal images. Moreover, we construct two CNN-based NPC detection systems using one kind of overlapping patches with a fixed size and various overlapping patches with different sizes. From the experiments using CT images of 70 NPC patients, our proposed systems, especially the system using various patches, achieves the best performance for detecting NPC compared with conventional NPC detection methods.

UR - http://www.scopus.com/inward/record.url?scp=85070536828&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85070536828&partnerID=8YFLogxK

U2 - 10.1016/j.compmedimag.2019.101644

DO - 10.1016/j.compmedimag.2019.101644

M3 - Article

AN - SCOPUS:85070536828

VL - 77

JO - Computerized Medical Imaging and Graphics

JF - Computerized Medical Imaging and Graphics

SN - 0895-6111

M1 - 101644

ER -