Development and evaluation of a software for automatic locating cephalometric landmarks

Message:
Abstract:
Background and Aim
The cephalometric analysis should be done for patients seeking orthognathic surgical treatments to diagnose dentoalveolar relationships properly. Finding a landmark for the analysis must be time consuming and depends on individual experience or errors and further needs more training. The aim of this study was to develop and evaluate a software for automatically locating of the cephalometric landmarks. Methods & Materials: A software was designed and developed by programmers group using 140 cephalometric radiographs as databases. Further to cephalograms were grabbed by a digital camera (Sony cybershot 1000X1200) in JPEG format and displayed on LCD monitor (Toshiba, 1600X1200 UXGA) for three expert orthodontists and asked them to locate 10 landmarks. The statistic analysis was based on Paired t test.
Results
The results showed 51% of the assigned points by software locating were within 1mm accuracy, 63% within 2 mm and 92% within 4mm accuracy. The mean distance from reference (the mean distance of three observers’ points) of seven out of ten points was less than maximum difference between observers. For B point the mean distance difference in computer locating (0.4mm) was less than mean distance observers’ points (3.1mm). For S point the mean distance difference from reference point was 3.4mm in computer locating which was greater than the mean distance difference between observers (0.6mm).
Conclusion
The study showed that landmark locating errors by computer were not greater than errors of individuals so, perhaps, computer could be a proper substitute for individuals for locating and analysis of cephalometric landmarks.
Language:
Persian
Published:
Journal of Dental School, Volume:25 Issue: 1, 2007
Pages:
93 to 101
magiran.com/p481595  
دانلود و مطالعه متن این مقاله با یکی از روشهای زیر امکان پذیر است:
اشتراک شخصی
با عضویت و پرداخت آنلاین حق اشتراک یک‌ساله به مبلغ 1,390,000ريال می‌توانید 70 عنوان مطلب دانلود کنید!
اشتراک سازمانی
به کتابخانه دانشگاه یا محل کار خود پیشنهاد کنید تا اشتراک سازمانی این پایگاه را برای دسترسی نامحدود همه کاربران به متن مطالب تهیه نمایند!
توجه!
  • حق عضویت دریافتی صرف حمایت از نشریات عضو و نگهداری، تکمیل و توسعه مگیران می‌شود.
  • پرداخت حق اشتراک و دانلود مقالات اجازه بازنشر آن در سایر رسانه‌های چاپی و دیجیتال را به کاربر نمی‌دهد.
In order to view content subscription is required

Personal subscription
Subscribe magiran.com for 70 € euros via PayPal and download 70 articles during a year.
Organization subscription
Please contact us to subscribe your university or library for unlimited access!