Automatic analysis of radiographic images

II. Software implementation and testing on bitewing radiographs

Research output: Contribution to journalArticle

2 Citations (Scopus)

Abstract

A prototype, completely automatic image-analysis system for dental bitewing radiographs was implemented in 'C' on a Unix workstation. A multiple layer hierarchical image model was created in software for each radiograph using production rule-based knowledge. The highest model layer formed an English-like description of anatomical structures including tooth type, interdental alveolar bone crest margins and spaces. A representation of spatial relationships between anatomical structures was formed, providing a method for comparing similar regions of a patient in serial, but not absolutely standardized, images. In 31 clinical radiographs, the system automatically indentified 93% (193) of all available interdental spaces which are the key image regions for model creation. Each image required 2 minutes of processing time. The reproducibility of finding 34 interdental spaces in five films revealed one error. Further work is required to improve the recognition rate of the interdental regions towards 100% and to develop automatic comparisons between areas of change (disease?) in serial films.

Original languageEnglish
Pages (from-to)193-199
Number of pages7
JournalDentomaxillofacial Radiology
Volume20
Issue number4
StatePublished - Nov 1991
Externally publishedYes

Fingerprint

Tooth
Software
Reproducibility of Results
Bone and Bones

All Science Journal Classification (ASJC) codes

  • Otorhinolaryngology
  • Radiology Nuclear Medicine and imaging
  • Dentistry(all)
  • Radiological and Ultrasound Technology

Cite this

@article{5948e9831427409db0cf0ca9649f3d83,
title = "Automatic analysis of radiographic images: II. Software implementation and testing on bitewing radiographs",
abstract = "A prototype, completely automatic image-analysis system for dental bitewing radiographs was implemented in 'C' on a Unix workstation. A multiple layer hierarchical image model was created in software for each radiograph using production rule-based knowledge. The highest model layer formed an English-like description of anatomical structures including tooth type, interdental alveolar bone crest margins and spaces. A representation of spatial relationships between anatomical structures was formed, providing a method for comparing similar regions of a patient in serial, but not absolutely standardized, images. In 31 clinical radiographs, the system automatically indentified 93{\%} (193) of all available interdental spaces which are the key image regions for model creation. Each image required 2 minutes of processing time. The reproducibility of finding 34 interdental spaces in five films revealed one error. Further work is required to improve the recognition rate of the interdental regions towards 100{\%} and to develop automatic comparisons between areas of change (disease?) in serial films.",
author = "Douglas Benn",
year = "1991",
month = "11",
language = "English",
volume = "20",
pages = "193--199",
journal = "Dentomaxillofacial Radiology",
issn = "0250-832X",
publisher = "British Institute of Radiology",
number = "4",

}

TY - JOUR

T1 - Automatic analysis of radiographic images

T2 - II. Software implementation and testing on bitewing radiographs

AU - Benn, Douglas

PY - 1991/11

Y1 - 1991/11

N2 - A prototype, completely automatic image-analysis system for dental bitewing radiographs was implemented in 'C' on a Unix workstation. A multiple layer hierarchical image model was created in software for each radiograph using production rule-based knowledge. The highest model layer formed an English-like description of anatomical structures including tooth type, interdental alveolar bone crest margins and spaces. A representation of spatial relationships between anatomical structures was formed, providing a method for comparing similar regions of a patient in serial, but not absolutely standardized, images. In 31 clinical radiographs, the system automatically indentified 93% (193) of all available interdental spaces which are the key image regions for model creation. Each image required 2 minutes of processing time. The reproducibility of finding 34 interdental spaces in five films revealed one error. Further work is required to improve the recognition rate of the interdental regions towards 100% and to develop automatic comparisons between areas of change (disease?) in serial films.

AB - A prototype, completely automatic image-analysis system for dental bitewing radiographs was implemented in 'C' on a Unix workstation. A multiple layer hierarchical image model was created in software for each radiograph using production rule-based knowledge. The highest model layer formed an English-like description of anatomical structures including tooth type, interdental alveolar bone crest margins and spaces. A representation of spatial relationships between anatomical structures was formed, providing a method for comparing similar regions of a patient in serial, but not absolutely standardized, images. In 31 clinical radiographs, the system automatically indentified 93% (193) of all available interdental spaces which are the key image regions for model creation. Each image required 2 minutes of processing time. The reproducibility of finding 34 interdental spaces in five films revealed one error. Further work is required to improve the recognition rate of the interdental regions towards 100% and to develop automatic comparisons between areas of change (disease?) in serial films.

UR - http://www.scopus.com/inward/record.url?scp=0026247656&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=0026247656&partnerID=8YFLogxK

M3 - Article

VL - 20

SP - 193

EP - 199

JO - Dentomaxillofacial Radiology

JF - Dentomaxillofacial Radiology

SN - 0250-832X

IS - 4

ER -