Osteoarthritis severity of the hip by computer-aided grading of radiographic images

Abstract

A computer-aided classification system was developed for the assessment of the severity of hip osteoarthritis (OA). Sixty-four radiographic images of normal and osteoarthritic hips were digitized and enhanced. Employing the Kellgren and Lawrence scale, the hips were grouped by three experienced orthopaedists into three OA-severity categories: Normal, Mild/Moderate and Severe. Utilizing custom-developed software, 64 ROIs corresponding to the radiographic Hip Joint Spaces were manually segmented and novel textural features were generated. These features were used in the design of a two-level classification scheme for characterizing hips as normal or osteoarthritic (1st level) and as of Mild/Moderate or Severe OA (2nd level). At each classification level, an ensemble of three classifiers was implemented. The proposed classification scheme discriminated correctly all normal hips from osteoarthritic hips (100% accuracy), while the discrimination accuracy between Mild/Moderate and Severe osteoarthritic hips was 95.7%. The proposed system could be used as a diagnosis decision-supporting tool.

Double acetabular wall—a misleading point for hip arthroplasty: an anatomical, radiological, clinical study

“…The Altman and Goften classification of hip osteoarthritis considers other aspects such as articular erosion and site of degenerative changes [6,15]. Nowadays, the development of digital modalities for evaluation of radiological views has provided modern computer-aided methods for classification of hip osteoarthritis [16,17]. Although some studies maintain that the medial wall formed by acetabular osteophytes does not get in the way of surgery and thus suggest against removing them [18], the necessity of removing osteophytes during PTHA has been suggested in previous studies [4,5,19,20].…”

Visual organization of hip joint osteoathritis data in low-dimensional biplots

“…In this context, for each feature set, each HJS-ROI was represented be a 15-dimensional feature vector. The ensemble of these 15-D vectors characterize, closely [10][11][12], the properties of the segmented HJS-ROI images and can be effectively utilized to estimate the similarities between the available OA-data in a browsable, lowdimensional terrain. In this way, the problem is now transformed to that of learning the structure in the set of HJS-ROI images through data visualization implemented using a dimensionality reduction scheme.…”

“…Texture-based classification schemes have been previously implemented in a variety of medical imaging applications [8], while radiographic texture has been investigated as an alternative to the quantitative assessment of OA severity in case of knee joint [9]. In previous studies performed by our group, textural features generated from the region of radiographic HJS have been utilized for the assessment of osteoarthritic alterations of the hip joint [10][11][12][13].…”

Quantitative measurement of human ageing using computer-aided radiographic texture analysis

“…Numerous studies provided evidence of link between the radiographic texture of the knee and its physiological or clinical condition, as well as strong correlation with the chronological age (Podsiadlo et al 2008;Shamir et al 2009aShamir et al , 2009bWoloszynski et al 2010;Bolbos et al 2008;Boniatis et al 2006). Experiments with rats showed that alteration of the articular cartilage, which is highly correlated with the alteration of the radiographic texture of the joint (Boniatis et al 2006;Podsiadlo et al 2008); (Shamir et al, 2009a), does not decline in a linear fashion as the animal ages, and identified stages of rapid decline (Schiefke et al 1998). Here, we propose an image analysis method that is based on the radiographic bone texture to quantify and measure the ageing of the human knee and profile its physiological ageing.…”