Fully automatic segmentation of femurs with medullary canal definition in high and in low resolution CT scans

• Published in: Medical engineering & physics Vol. 38; no. 12; pp. 1474 - 1480
• Main Authors: Almeida, Diogo F, Ruben, Rui B, Folgado, João, Fernandes, Paulo R, Audenaert, Emmanuel, Verhegghe, Benedict, De Beule, Matthieu
• Format: Journal Article
• Language: English
• Published: England Elsevier Ltd 01-12-2016
• Subjects: 3D femur segmentation; Active shape model (ASM); Automation; CT image; Femur - diagnostic imaging; Humans; Image Processing, Computer-Assisted; Radiology; Signal-To-Noise Ratio; Statistical shape model (SSM); Tomography, X-Ray Computed; Total hip arthroplasty; CT image; Statistical shape model (SSM); Total hip arthroplasty; Active shape model (ASM); 3D femur segmentation
• ISSN: 1350-4533; 1873-4030
• DOI: 10.1016/j.medengphy.2016.09.019

Highlights • A new fully automatic femur segmentation method for CT images is proposed. • This novel segmentation method defines both the femoral external surface and the medullary canal. • The fast and automatic segmentation method is an important contribution for the development of surgical planning software efficient in terms of cost and time reduction. • High convergence was achieved for low and high resolution CT images.