Entropy-Based Automatic Segmentation of Bones in Digital X-ray Images

Abstract

Abstract. Bone image segmentation is an integral component of orthopedic Xray image analysis that aims at extracting the bone structure from the muscles and tissues. Automatic segmentation of the bone part in a digital X-ray image is a challenging problem because of its low contrast with the surrounding flesh, which itself needs to be discriminated against the background. The presence of noise and spurious edges further complicates the segmentation. In this paper, we propose an efficient entropy-based segmentation technique that integrates several simple steps, which are fully automated. Experiments on several X-ray images reveal encouraging results as evident from a segmentation entropy quantitative assessment (SEQA) metric [Hao, et al. 2009].

Long-bone fracture detection in digital X-ray images based on digital-geometric techniques

“…1(b), is (1,3)(210756543) when traversed from the start-point S = (1, 3); Fig. 1(c) shows a close-ended digital curve, whose chain code is (3,3)(6543121075) with the start point S = (3,3).…”

“…Segmentation of bone using an entropy-based approach. Entropy-based segmentation techniques [2,3] can also be used for bone-image segmentation. In this method, local-entropy represents the grayscale intensity variation in the neighborhood of a pixel.…”

“…It has been observed that k-means clustering may produce over-segmented bone regions in many X-ray images. Thus, we have evaluated another method based on entropy-standard deviation [2,3] for bone-region segmentation.…”

“…In previous work [3], an entropy-based thresholding approach was used for segmenting a bone X-ray image from its surrounding flesh region. Elementary analysis of fractured-bone contours and correction of discontinuities therein, also appeared in prior work [1], [2].…”

“…The segmentation of a bone region of a digital X-ray image from its flesh part and generation of exact bone-contour play a crucial role in fracture detection. The proposed tool integrates an entropy-based segmentation method [3] with an adaptive thresholding-based contour tracing [2] to generate the bone-contour of an X-ray image. The algorithm traverses the bone-contour and rectifies the false discontinuities using certain new geometric techniques.…”