Limits...
An evaluation of cellular neural networks for the automatic identification of cephalometric landmarks on digital images.

Leonardi R, Giordano D, Maiorana F - J. Biomed. Biotechnol. (2009)

Bottom Line: Differences in the mean errors of automatic and manual landmarking were compared with a 1-way analysis of variance.Furthermore, only few of these differences were statistically significant, but differences were so small to be in most instances clinically meaningless.Therefore the use of X-ray files with respect to scanned X-ray improved landmark accuracy of automatic detection.

View Article: PubMed Central - PubMed

Affiliation: Istituto di II Clinica Odontoiatrica, Policlinico Città Universitaria, Catania, Italy. rleonard@unict.it

ABSTRACT
Several efforts have been made to completely automate cephalometric analysis by automatic landmark search. However, accuracy obtained was worse than manual identification in every study. The analogue-to-digital conversion of X-ray has been claimed to be the main problem. Therefore the aim of this investigation was to evaluate the accuracy of the Cellular Neural Networks approach for automatic location of cephalometric landmarks on softcopy of direct digital cephalometric X-rays. Forty-one, direct-digital lateral cephalometric radiographs were obtained by a Siemens Orthophos DS Ceph and were used in this study and 10 landmarks (N, A Point, Ba, Po, Pt, B Point, Pg, PM, UIE, LIE) were the object of automatic landmark identification. The mean errors and standard deviations from the best estimate of cephalometric points were calculated for each landmark. Differences in the mean errors of automatic and manual landmarking were compared with a 1-way analysis of variance. The analyses indicated that the differences were very small, and they were found at most within 0.59 mm. Furthermore, only few of these differences were statistically significant, but differences were so small to be in most instances clinically meaningless. Therefore the use of X-ray files with respect to scanned X-ray improved landmark accuracy of automatic detection. Investigations on softcopy of digital cephalometric X-rays, to search more landmarks in order to enable a complete automatic cephalometric analysis, are strongly encouraged.

Show MeSH
CNN final output and Pterygoid fissure.
© Copyright Policy - open-access
Related In: Results  -  Collection


getmorefigures.php?uid=PMC2742650&req=5

fig16: CNN final output and Pterygoid fissure.

Mentions: The template parameters and the number of cycles are changed until the right wall of the Pterygoid fissure is detected, with a search constrained by distance from the orbital cavity. The left wall is searched by applying a CNN with similar templates but different parameters, and by using a dynamic threshold to differentiate between white and black pixels and to follow it until the upper part of the Pterygoid fissure is reached and hence the landmark is located. The landmark coordinates are checked against the distance from the right wall of the fissure. If the constraint is not satisfied, a recovery procedure, that depends on the distance between the landmark and the right wall of the fissure (too low or too high), is implemented by changing both the templates (more aggressive or less aggressive) and the threshold used to follow the highlighted wall of the fissure. Figure 16 shows the final computation with the Pterygoid fissure highlighted.


An evaluation of cellular neural networks for the automatic identification of cephalometric landmarks on digital images.

Leonardi R, Giordano D, Maiorana F - J. Biomed. Biotechnol. (2009)

CNN final output and Pterygoid fissure.
© Copyright Policy - open-access
Related In: Results  -  Collection

Show All Figures
getmorefigures.php?uid=PMC2742650&req=5

fig16: CNN final output and Pterygoid fissure.
Mentions: The template parameters and the number of cycles are changed until the right wall of the Pterygoid fissure is detected, with a search constrained by distance from the orbital cavity. The left wall is searched by applying a CNN with similar templates but different parameters, and by using a dynamic threshold to differentiate between white and black pixels and to follow it until the upper part of the Pterygoid fissure is reached and hence the landmark is located. The landmark coordinates are checked against the distance from the right wall of the fissure. If the constraint is not satisfied, a recovery procedure, that depends on the distance between the landmark and the right wall of the fissure (too low or too high), is implemented by changing both the templates (more aggressive or less aggressive) and the threshold used to follow the highlighted wall of the fissure. Figure 16 shows the final computation with the Pterygoid fissure highlighted.

Bottom Line: Differences in the mean errors of automatic and manual landmarking were compared with a 1-way analysis of variance.Furthermore, only few of these differences were statistically significant, but differences were so small to be in most instances clinically meaningless.Therefore the use of X-ray files with respect to scanned X-ray improved landmark accuracy of automatic detection.

View Article: PubMed Central - PubMed

Affiliation: Istituto di II Clinica Odontoiatrica, Policlinico Città Universitaria, Catania, Italy. rleonard@unict.it

ABSTRACT
Several efforts have been made to completely automate cephalometric analysis by automatic landmark search. However, accuracy obtained was worse than manual identification in every study. The analogue-to-digital conversion of X-ray has been claimed to be the main problem. Therefore the aim of this investigation was to evaluate the accuracy of the Cellular Neural Networks approach for automatic location of cephalometric landmarks on softcopy of direct digital cephalometric X-rays. Forty-one, direct-digital lateral cephalometric radiographs were obtained by a Siemens Orthophos DS Ceph and were used in this study and 10 landmarks (N, A Point, Ba, Po, Pt, B Point, Pg, PM, UIE, LIE) were the object of automatic landmark identification. The mean errors and standard deviations from the best estimate of cephalometric points were calculated for each landmark. Differences in the mean errors of automatic and manual landmarking were compared with a 1-way analysis of variance. The analyses indicated that the differences were very small, and they were found at most within 0.59 mm. Furthermore, only few of these differences were statistically significant, but differences were so small to be in most instances clinically meaningless. Therefore the use of X-ray files with respect to scanned X-ray improved landmark accuracy of automatic detection. Investigations on softcopy of digital cephalometric X-rays, to search more landmarks in order to enable a complete automatic cephalometric analysis, are strongly encouraged.

Show MeSH