Automatic scoliosis detection based on local centroids evaluation on moire topographic images of human backs.

This paper presents a technique for automating human scoliosis detection by computer based on moire topographic images of human backs. Scollosis is a serious disease often suffered by teenagers. For prevention, screening is performed at schools in Japan employing a moire method in which doctors insp...

Volledige beschrijving

Bibliografische gegevens
Gepubliceerd in:	IEEE Transactions on medical imaging 20, 12 (2001).
Hoofdauteur:	Hyoung Seop Kim
Formaat:	Artikel
Taal:	English
Onderwerpen:	Japanese schools. Mahalanobis distance. Automatic scoliosis detection. Doctors exhaustion. Human backs. Leave-out method. Linear discriminant function. Linear discriminant functions. Local centroids evaluation. Moire topographic images. School screening. Serious disease. Spinal deformity. Teenagers. Two-dimensional feature space.