Search

This is the first part of a two-part paper on the application of computer-aided diagnosis to diffuse optical tomography (DOT). An approach for extracting heuristic features from DOT images and a method for using these features to diagnose rheumatoid arthritis (RA) are presented. Feature extraction is the focus of Part 1, while the utility of five classification algorithms is evaluated in Part 2. The framework is validated on a set of 219 DOT images of proximal interphalangeal (PIP) joints. Overall, 594 features are extracted from the absorption and scattering images of each joint. Three major findings are deduced. First, DOT images of subjects with RA are statistically different (p<0.05) from images of subjects without RA for over 90% of the features investigated. Second, DOT images of subjects with RA that do not have detectable effusion, erosion, or synovitis (as determined by MRI and ultrasound) are statistically indistinguishable from DOT images of subjects with RA that do exhibit effusion, erosion, or synovitis. Thus, this subset of subjects may be diagnosed with RA from DOT images while they would go undetected by reviews of MRI or ultrasound images. Third, scattering coefficient images yield better one-dimensional classifiers. A total of three features yield a Youden index greater than 0.8. These findings suggest that DOT may be capable of distinguishing between PIP joints that are healthy and those affected by RA with or without effusion, erosion, or synovitis.

This is the second part of a two-part paper on the application of computer-aided diagnosis to diffuse optical tomography (DOT) for diagnosing rheumatoid arthritis (RA). A comprehensive analysis of techniques for the classification of DOT images of proximal interphalangeal joints of subjects with and without RA is presented. A method for extracting heuristic features from DOT images was presented in Part 1. The ability of five classification algorithms to accurately label each DOT image as belonging to a subject with or without RA is analyzed here. The algorithms of interest are the k-nearest-neighbors, linear and quadratic discriminant analysis, self-organizing maps, and support vector machines (SVM). With a polynomial SVM classifier, we achieve 100.0% sensitivity and 97.8% specificity. Lower bounds for these results (at 95.0% confidence level) are 96.4% and 93.8%, respectively. Image features most predictive of RA are from the spatial variation of optical properties and the absolute range in feature values. The optimal classifiers are low-dimensional combinations (<7 features). These results underscore the high potential for DOT to become a clinically useful diagnostic tool and warrant larger prospective clinical trials to conclusively demonstrate the ultimate clinical utility of this approach.