کد مقاله کد نشریه سال انتشار مقاله انگلیسی نسخه تمام متن
525789 869025 2013 12 صفحه PDF دانلود رایگان
عنوان انگلیسی مقاله ISI
Hierarchical segmentation and identification of thoracic vertebra using learning-based edge detection and coarse-to-fine deformable model
موضوعات مرتبط
مهندسی و علوم پایه مهندسی کامپیوتر چشم انداز کامپیوتر و تشخیص الگو
پیش نمایش صفحه اول مقاله
Hierarchical segmentation and identification of thoracic vertebra using learning-based edge detection and coarse-to-fine deformable model
چکیده انگلیسی


• A New supervised learning based bone edge detectors using efficient features and classification.
• A New hierarchical, coarse-to-fine deformation strategy for vertebra segmentation.
• Vertebrae mean shapes based effective identification of different thoracic vertebra.
• State-of-the-art performance on vertebra segmentation accuracy and identification success rate.
• Extended to other orthopedic structures, e.g., manubrium.

Precise segmentation and identification of thoracic vertebrae is important for many medical imaging applications though it remains challenging due to the vertebra’s complex shape and varied neighboring structures. In this paper, a new method based on learned bone-structure edge detectors and a coarse-to-fine deformable surface model is proposed to segment and identify vertebrae in 3D CT thoracic images. In the training stage, a discriminative classifier for object-specific edge detection is trained using steerable features and statistical shape models for 12 thoracic vertebrae are also learned. For the run-time testing, we design a new coarse-to-fine, two-stage segmentation strategy: subregions of a vertebra first deform together as a group; then vertebra mesh vertices in a smaller neighborhood move group-wise to progressively drive the deformable model towards edge response maps by optimizing a probability cost function. In this manner, the smoothness and topology of vertebrae shapes are guaranteed. This algorithm performs successfully with reliable mean point-to-surface errors 0.95 ± 0.91 mm on 40 volumes. Consequently a vertebra identification scheme is also proposed via mean surface mesh matching. We achieve a success rate of 73.1% using a single vertebra, and over 95% for 8 or more vertebra which is comparable or slightly better than state-of-the-art [5].

ناشر
Database: Elsevier - ScienceDirect (ساینس دایرکت)
Journal: Computer Vision and Image Understanding - Volume 117, Issue 9, September 2013, Pages 1072–1083
نویسندگان
, ,