Double-Edge Detection of Radiographic Lumbar Vertebrae Images Using Pressurized Open DGVF Snakes

Abstract

The detection of double edges in X-ray images of lumbar vertebrae is of prime importance in the assessment of vertebral injury or collapse that may be caused by osteoporosis and other spine pathology. In addition, if the above double-edge detection process is conducted within an automatic framework, it would not only facilitate inexpensive and fast means of obtaining objective morphometric measurements on the spine, but also remove the human subjectivity involved in the morphometric analysis. This paper proposes a novel force-formulation scheme, termed as pressurized open directional gradient vector flow snakes, to discriminate and detect the superior and inferior double edges present in the radiographic images of the lumbar vertebrae. As part of the validation process, this algorithm is applied to a set of 100 lumbar images and the detection results are quantified using analyst-generated ground truth. The promising nature of the detection results bears testimony to the efficacy of the proposed approach.

External Force for Deformable Models in Medical Image Segmentation: A Survey

“…Then, four potential functions Ψx, Ψy, Ψxy, and Ψyx are computed using line-by-line interpolations in the horizontal, vertical, and two diagonal directions. The Bounded vector fields are defined based on the gradients of the following potential functions: (46) The external force is given as follows:…”

“…The Parametric deformable models are applied to different image modalities such as Magnetic resonance image [05, 17,18,24,27,29,32,33,37,38,39,40], Ultrasound [20,31,42,43,44], Computed tomography [29,34,45] and X-ray [46]. These are used to segment, visualize, track and quantify, a variety of anatomic structures ranging from the macroscopic to the microscopic such as brain, heart, lung, liver and calculi, etc.…”

“…The proposed approach that combines texture based features, principal component analysis and gradient vector flow to produce a deformable model based segmentation algorithm invariant to the grey level overlap presented by soft tissues. Sridharan K. et al [46] developed an approach of DGVF deformable model to detect the double edges in X-ray images of lumbar vertebral using spine radiographs. In this method, they combined open contoured DGVF deformable models with appropriately defined pressure forces to achieve accurate detection of vertebral double edges in the presence of noise and neighborhood of adjacent vertebrae.…”

Digital Rock Samples Porosity Analysis by OTSU Thresholding Technique Using MATLAB

“…Several practical image segmentation applications are available such as trace tumors and additional pathologies [4], [5], machine vision, object detection [6], face detection, medical imaging [7], [8], anatomic building studies and diagnoses [9], fingerprint recognition and video surveillance.…”

Digital Image Segmentation in Matlab: A Brief Study on Otsu’s Image Thresholding

“…In short, image segmentation changes the illustration of an image to its simplified form which is further momentous and natural to analyze [2,3]. There are several practical application of image segmentation such as trace tumors and additional pathologies [4,5], machine vision, object detection [6], face detection, Medical imaging [7,8], study and diagnosis of anatomical construction [9], fingerprint recognition and video surveillance etc. Several techniques have been undertaken over the past decades for image segmentation including thresholding [10], edge-based segmentation [11] and compression based methods [12], etc.…”