Computer-aided diagnosis of rheumatoid arthritis with optical tomography, Part 1: feature extraction

Abstract

Abstract. 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.

In Vivo, Non-Invasive Characterization of Human Bone by Hybrid Broadband (600-1200 nm) Diffuse Optical and Correlation Spectroscopies

“…High penetration depth along with the non-invasive nature of diffuse optical methods has found various applications in in vivo diagnostics: tissue characterization [10], hemodynamics monitoring [11,12,13], brain oximetry [11,14], and optical mammography [15,16,17,18] are few examples where the application of the technique has been explored deeply. Prior attempts to characterize bone tissue by diffuse optical techniques lack either the broadband nature [19,20] or number of subjects [21]. In reference to the problem of osteoporosis, preliminary in vivo results obtained by Pifferi et al, using a time resolved diffuse optical spectrometer [22] on calcaneus bone [21] of five volunteers suggested an interesting correlation of age with various tissue constituents (lipid, collagen, hemoglobin) and the scattering coefficient.…”

Hyperspectral imaging for detection of arthritis: feasibility and prospects

“…[5][6][7][8] However, the reported techniques utilized monochromatic light, and thus did not explore the richness of the spectral information obtained using a broadband light. Spectroscopic data carry useful information about tissue optical properties such as absorption, scattering, and tissue composition.…”

Fast linear solver for radiative transport equation with multiple right hand sides in diffuse optical tomography

“…(8). In our work we employ the zeroth-order Delta-Eddington approximation since it has shown promising results as reported in literature [1, 14, 42]. The frequency domain RTE is simplified with zeroth-order Delta-Eddington approximation as $$true(\frac{i\omega }{\nu }+\mathrm{normal\Omega }·\nabla +{\mu }_{a}false(\mathrm{bold-italicr}false)+{\mu }_s^{\text{'}}false(\mathrm{bold-italicr}false)true)\psi false(\mathrm{bold-italicr},\mathrm{normal\Omega }false)={\mu }_s^{\text{'}}false(\mathrm{bold-italicr}false)\underset{S^{d-1}}{\int }\psi false(\mathrm{bold-italicr},\mathrm{normal\Omega }\text{'}false)d\mathrm{normal\Omega }\text{'}/true(\underset{S^{d-1}}{\int }d\mathrm{normal\Omega }\text{'}true)+qfalse(\mathrm{bold-italicr},\mathrm{normal\Omega }false)$$ where the scattering coefficient μ s and the anisotropic factor g is combined into a reduced scattering coefficient ${\mu }_s^{\text{'}}false(1-gfalse){\mu }_s$.…”