Proximal femur segmentation in conventional pelvic x ray

Abstract

A solid and accurate proximal femur segmentation technique using the popular active shape model (ASM) is proposed. For generating an optimal shape prior, the minimum description length, based on 200 supervised manual segmented proximal femur shapes, is used. The segmentation is based on a coarse to fine scaling technique including a profile scale space method. The segmentation results are compared using an optimal defined initial pose and a pose based on a registration technique. Using ideal template initialization, 95% of the shapes have been recovered exactly (average point-to-point error approximately 13 pixels, average point-to-boundary error approximately 7 pixels). Using a template-based initialization based on a registration technique, a successful segmentation rate of approximately 89% is achieved, with an average point-to-point error approximately 12 pixels, and an average point-to-boundary error approximately 8 pixels. With an adequate template initialization and an improved ASM, this method seems to provide an accurate tool for segmentation of the proximal femur shapes on conventional hip overview x-ray images.

Statistical model-based segmentation of the proximal femur in digital antero-posterior (AP) pelvic radiographs

“…Experiments carried out on one hundred clinical AP pelvic radiographs (in a wide range of image qualities) showed an average mean error of 0.96 mm and a standard deviation of 0.35 mm. It was more accurate than those in Behiels et al [7] and Pilgram et al [8], where both works did not reach very high accuracy (with mean segmentation error of approximately 1.9 mm). Due to the combination of both SSM and SAM with the dynamic programming technique, the proposed approach achieved a high accuracy that is comparable to that reported by Lindner et al [9].…”

“…Due to the pervasive applications of AP pelvic radiographs in orthopaedic diagnosis and surgical planning, attempts to develop an automatic solution for proximal femur segmentation have been reported [7][8][9][10][11][12][13]. Behiels et al [7] and Pilgram et al [8] utilized statistical appearance models (SAM) and statistical shape models (SSM) or their extensions, and applied both models in the scenario of femur segmentation. In Lindner et al [9], random forest regression voting was employed to achieve an accuracy of approximately 1 mm that was claimed as the most accurate automatic method for seg-menting femur in AP pelvic radiographs yet reported [9].…”

A complete-pelvis segmentation framework for image-free total hip arthroplasty (THA): methodology and clinical study

“…To our knowledge, the fast, robust and accurate segmentation of the complete pelvis in AP radiographs has not yet been fully explored, despite numerous methods developed and successful results achieved by previous works for the proximal femur delineation, due to the more complicated anatomical structures in the pelvic region than those in the femoral area.…”

“…Attempts to develop an automatic solution for the proximal femur segmentation have been presented previously . Despite numerous methods developed and successful results achieved by previous work for delineating the proximal femur, a fast and robust segmentation of the complete pelvis in AP radiographs with sufficient accuracy has not yet been fully explored due to more complicated anatomical structures in the pelvic region than those in the femoral area.…”

Deep Learning and Computer Vision Techniques for Automated Total Hip Arthroplasty Planning on 2-D Radiographs

“…Automatic hip joint segmentation of 2-D radiographs has been studied less than segmentation of 3-D images. Conventional methods find contours of the pelvis and femur using SSM [40]- [43], ASM [44], shortest path [45], and generic 3-D model projection and registration [46]. Traditionally, segmentation of 2-D radiographic images has been beneficial but rarely studied owing to its difficulties, including poor and non-uniform image contrast, noise, occlusions, and overlap of neighboring structures.…”