Recognition of chest radiograph orientation for picture archiving and communications systems display using neural networks

John M Boone, Sadananda Seshagiri, Robert M. Steiner

Research output: Contribution to journalArticle

31 Citations (Scopus)

Abstract

A neural network classification scheme was developed that enables a picture archiving and communications system workstation to determine the correct orientation of posteroanterior or anteroposterior chest images. This technique permits thoracic images to be displayed conventionally when called up on the workstation, and therefore reduces the need for reorientation of the image by the observer. Feature data were extracted from 1,000 digitized chest radiographs and used to train a two-layer neural network designed to classify the image into one of the eight possible orientations for a posteroanterior chest image. Once trained, the neural network identified the correct image orientation in 888 of 1,000 images that had not previously been seen by the neural network. Of the 112 images that were incorrectly classified, 106 were mirror images of the correct orientation, whereas only 6 actually had the caudal-cranial axis aligned incorrectly. The causes for misalignment are discussed.

Original languageEnglish (US)
Pages (from-to)190-193
Number of pages4
JournalJournal of Digital Imaging
Volume5
Issue number3
DOIs
StatePublished - Aug 1992
Externally publishedYes

Fingerprint

Radiology Information Systems
Picture archiving and communication systems
Thorax
Neural networks
Mirrors

ASJC Scopus subject areas

  • Radiological and Ultrasound Technology
  • Radiology Nuclear Medicine and imaging
  • Computer Science Applications
  • Computer Vision and Pattern Recognition

Cite this

Recognition of chest radiograph orientation for picture archiving and communications systems display using neural networks. / Boone, John M; Seshagiri, Sadananda; Steiner, Robert M.

In: Journal of Digital Imaging, Vol. 5, No. 3, 08.1992, p. 190-193.

Research output: Contribution to journalArticle

@article{2ed6ea00da4e4e959f4ffb5fefef6b18,
title = "Recognition of chest radiograph orientation for picture archiving and communications systems display using neural networks",
abstract = "A neural network classification scheme was developed that enables a picture archiving and communications system workstation to determine the correct orientation of posteroanterior or anteroposterior chest images. This technique permits thoracic images to be displayed conventionally when called up on the workstation, and therefore reduces the need for reorientation of the image by the observer. Feature data were extracted from 1,000 digitized chest radiographs and used to train a two-layer neural network designed to classify the image into one of the eight possible orientations for a posteroanterior chest image. Once trained, the neural network identified the correct image orientation in 888 of 1,000 images that had not previously been seen by the neural network. Of the 112 images that were incorrectly classified, 106 were mirror images of the correct orientation, whereas only 6 actually had the caudal-cranial axis aligned incorrectly. The causes for misalignment are discussed.",
author = "Boone, {John M} and Sadananda Seshagiri and Steiner, {Robert M.}",
year = "1992",
month = "8",
doi = "10.1007/BF03167769",
language = "English (US)",
volume = "5",
pages = "190--193",
journal = "Journal of Digital Imaging",
issn = "0897-1889",
publisher = "Springer New York",
number = "3",

}

TY - JOUR

T1 - Recognition of chest radiograph orientation for picture archiving and communications systems display using neural networks

AU - Boone, John M

AU - Seshagiri, Sadananda

AU - Steiner, Robert M.

PY - 1992/8

Y1 - 1992/8

N2 - A neural network classification scheme was developed that enables a picture archiving and communications system workstation to determine the correct orientation of posteroanterior or anteroposterior chest images. This technique permits thoracic images to be displayed conventionally when called up on the workstation, and therefore reduces the need for reorientation of the image by the observer. Feature data were extracted from 1,000 digitized chest radiographs and used to train a two-layer neural network designed to classify the image into one of the eight possible orientations for a posteroanterior chest image. Once trained, the neural network identified the correct image orientation in 888 of 1,000 images that had not previously been seen by the neural network. Of the 112 images that were incorrectly classified, 106 were mirror images of the correct orientation, whereas only 6 actually had the caudal-cranial axis aligned incorrectly. The causes for misalignment are discussed.

AB - A neural network classification scheme was developed that enables a picture archiving and communications system workstation to determine the correct orientation of posteroanterior or anteroposterior chest images. This technique permits thoracic images to be displayed conventionally when called up on the workstation, and therefore reduces the need for reorientation of the image by the observer. Feature data were extracted from 1,000 digitized chest radiographs and used to train a two-layer neural network designed to classify the image into one of the eight possible orientations for a posteroanterior chest image. Once trained, the neural network identified the correct image orientation in 888 of 1,000 images that had not previously been seen by the neural network. Of the 112 images that were incorrectly classified, 106 were mirror images of the correct orientation, whereas only 6 actually had the caudal-cranial axis aligned incorrectly. The causes for misalignment are discussed.

UR - http://www.scopus.com/inward/record.url?scp=0026901845&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=0026901845&partnerID=8YFLogxK

U2 - 10.1007/BF03167769

DO - 10.1007/BF03167769

M3 - Article

C2 - 1520746

AN - SCOPUS:0026901845

VL - 5

SP - 190

EP - 193

JO - Journal of Digital Imaging

JF - Journal of Digital Imaging

SN - 0897-1889

IS - 3

ER -