Search

Hyperspectral imaging (HSI) is an optical remote sensing technology that has the advantages of high spatial and spectral resolution. Aside from its use in geographical research, HSI has been widely used in medical diagnosis. Systemic sclerosis (SSc) is a multiorgan autoimmune disease that leads to skin tightness, thickness, and fibrosis. Internal organ involvement and mortality in this progressive disease are strongly correlated with the extent and severity of abnormal skin thickness. Our prior study demonstrated that HSI can outperform conventional assessment tools as a diagnostic modality to evaluate the severity of skin sclerosis in SSc patients. However, the analysis algorithm has its limitations. This study aimed to investigate a novel soft abundance score for HSI. We also explored the influence of band selection on the HSI analysis of SSc patients. In total, we enrolled 30 SSc patients (male: 10; female: 20, median age±range, 49.9±17.0 years) and 24 healthy controls (male: 12; female: 12, median age±range, 37.0±11.0 years). We found that most of the spectral bands generated by different band selection methods were similar. Moreover, in the task of distinguishing SSc patients from healthy controls, the soft abundance scores calculated from these bands exhibited greater discriminative power than a spectral angle mapper (SAM), skin scores determined by clinical assessments, or skin thickness determined through ultrasonography. Our results suggest that the spectral bands selected in this study should be taken into consideration to guide future hardware improvement. The analytic algorithm can also be applied as a new clinical method.

Accurate quantification of brain tissue is a fundamental and challenging task in neuroimaging. Over the past two decades, statistical parametric mapping (SPM) and FMRIB’s Automated Segmentation Tool (FAST) have been widely used to estimate gray matter (GM) and white matter (WM) volumes. However, they cannot reliably estimate cerebrospinal fluid (CSF) volumes. To address this problem, we developed the TRIO algorithm (TRIOA), a new magnetic resonance (MR) multispectral classification method. SPM8, SPM12, FAST, and the TRIOA were evaluated using the BrainWeb database and real magnetic resonance imaging (MRI) data. In this paper, the MR brain images of 140 healthy volunteers ( 51.5 ± 15.8 y / o ) were obtained using a whole-body 1.5 T MRI system (Aera, Siemens, Erlangen, Germany). Before classification, several preprocessing steps were performed, including skull stripping and motion and inhomogeneity correction. After extensive experimentation, the TRIOA was shown to be more effective than SPM and FAST. For real data, all test methods revealed that the participants aged 20–83 years exhibited an age-associated decline in GM and WM volume fractions. However, for CSF volume estimation, SPM8-s and SPM12-m both produced different results, which were also different compared with those obtained by FAST and the TRIOA. Furthermore, the TRIOA performed consistently better than both SPM and FAST for GM, WM, and CSF volume estimation. Compared with SPM and FAST, the proposed TRIOA showed more advantages by providing more accurate MR brain tissue classification and volume measurements, specifically in CSF volume estimation.