Bone suppression for chest X-ray image using a convolutional neural filter

Naoki Matsubara, Atsushi Teramoto, Kuniaki Saito, Hiroshi Fujita

Research output: Contribution to journalArticle

Abstract

Chest X-rays are used for mass screening for the early detection of lung cancer. However, lung nodules are often overlooked because of bones overlapping the lung fields. Bone suppression techniques based on artificial intelligence have been developed to solve this problem. However, bone suppression accuracy needs improvement. In this study, we propose a convolutional neural filter (CNF) for bone suppression based on a convolutional neural network which is frequently used in the medical field and has excellent performance in image processing. CNF outputs a value for the bone component of the target pixel by inputting pixel values in the neighborhood of the target pixel. By processing all positions in the input image, a bone-extracted image is generated. Finally, bone-suppressed image is obtained by subtracting the bone-extracted image from the original chest X-ray image. Bone suppression was most accurate when using CNF with six convolutional layers, yielding bone suppression of 89.2%. In addition, abnormalities, if present, were effectively imaged by suppressing only bone components and maintaining soft-tissue. These results suggest that the chances of missing abnormalities may be reduced by using the proposed method. The proposed method is useful for bone suppression in chest X-ray images.

Original languageEnglish
JournalAustralasian Physical and Engineering Sciences in Medicine
DOIs
Publication statusAccepted/In press - 01-01-2019

Fingerprint

Wave filters
chest
bones
Bone
Thorax
X-Rays
retarding
filters
Bone and Bones
X rays
x rays
lungs
Pixels
pixels
abnormalities
artificial intelligence
Lung
Mass Screening
Artificial Intelligence
nodules

All Science Journal Classification (ASJC) codes

  • Biophysics
  • Biomedical Engineering
  • Radiology Nuclear Medicine and imaging
  • Physics and Astronomy(all)

Cite this

@article{7c6ee8bf6ecb41199235b2f86970f6c3,
title = "Bone suppression for chest X-ray image using a convolutional neural filter",
abstract = "Chest X-rays are used for mass screening for the early detection of lung cancer. However, lung nodules are often overlooked because of bones overlapping the lung fields. Bone suppression techniques based on artificial intelligence have been developed to solve this problem. However, bone suppression accuracy needs improvement. In this study, we propose a convolutional neural filter (CNF) for bone suppression based on a convolutional neural network which is frequently used in the medical field and has excellent performance in image processing. CNF outputs a value for the bone component of the target pixel by inputting pixel values in the neighborhood of the target pixel. By processing all positions in the input image, a bone-extracted image is generated. Finally, bone-suppressed image is obtained by subtracting the bone-extracted image from the original chest X-ray image. Bone suppression was most accurate when using CNF with six convolutional layers, yielding bone suppression of 89.2{\%}. In addition, abnormalities, if present, were effectively imaged by suppressing only bone components and maintaining soft-tissue. These results suggest that the chances of missing abnormalities may be reduced by using the proposed method. The proposed method is useful for bone suppression in chest X-ray images.",
author = "Naoki Matsubara and Atsushi Teramoto and Kuniaki Saito and Hiroshi Fujita",
year = "2019",
month = "1",
day = "1",
doi = "10.1007/s13246-019-00822-w",
language = "English",
journal = "Australasian Physical and Engineering Sciences in Medicine",
issn = "0158-9938",
publisher = "Springer Netherlands",

}

TY - JOUR

T1 - Bone suppression for chest X-ray image using a convolutional neural filter

AU - Matsubara, Naoki

AU - Teramoto, Atsushi

AU - Saito, Kuniaki

AU - Fujita, Hiroshi

PY - 2019/1/1

Y1 - 2019/1/1

N2 - Chest X-rays are used for mass screening for the early detection of lung cancer. However, lung nodules are often overlooked because of bones overlapping the lung fields. Bone suppression techniques based on artificial intelligence have been developed to solve this problem. However, bone suppression accuracy needs improvement. In this study, we propose a convolutional neural filter (CNF) for bone suppression based on a convolutional neural network which is frequently used in the medical field and has excellent performance in image processing. CNF outputs a value for the bone component of the target pixel by inputting pixel values in the neighborhood of the target pixel. By processing all positions in the input image, a bone-extracted image is generated. Finally, bone-suppressed image is obtained by subtracting the bone-extracted image from the original chest X-ray image. Bone suppression was most accurate when using CNF with six convolutional layers, yielding bone suppression of 89.2%. In addition, abnormalities, if present, were effectively imaged by suppressing only bone components and maintaining soft-tissue. These results suggest that the chances of missing abnormalities may be reduced by using the proposed method. The proposed method is useful for bone suppression in chest X-ray images.

AB - Chest X-rays are used for mass screening for the early detection of lung cancer. However, lung nodules are often overlooked because of bones overlapping the lung fields. Bone suppression techniques based on artificial intelligence have been developed to solve this problem. However, bone suppression accuracy needs improvement. In this study, we propose a convolutional neural filter (CNF) for bone suppression based on a convolutional neural network which is frequently used in the medical field and has excellent performance in image processing. CNF outputs a value for the bone component of the target pixel by inputting pixel values in the neighborhood of the target pixel. By processing all positions in the input image, a bone-extracted image is generated. Finally, bone-suppressed image is obtained by subtracting the bone-extracted image from the original chest X-ray image. Bone suppression was most accurate when using CNF with six convolutional layers, yielding bone suppression of 89.2%. In addition, abnormalities, if present, were effectively imaged by suppressing only bone components and maintaining soft-tissue. These results suggest that the chances of missing abnormalities may be reduced by using the proposed method. The proposed method is useful for bone suppression in chest X-ray images.

UR - http://www.scopus.com/inward/record.url?scp=85076103645&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85076103645&partnerID=8YFLogxK

U2 - 10.1007/s13246-019-00822-w

DO - 10.1007/s13246-019-00822-w

M3 - Article

C2 - 31773501

AN - SCOPUS:85076103645

JO - Australasian Physical and Engineering Sciences in Medicine

JF - Australasian Physical and Engineering Sciences in Medicine

SN - 0158-9938

ER -