Within a decade, single trial analysis of functional Near Infrared Spectroscopy (fNIRS) signals has gained significant momentum, and fNIRS joined the set of modalities frequently used for active and passive Brain Computer Interfaces (BCI). A great variety of methods for feature extraction and classification have been explored using state-of-the-art Machine Learning methods. In contrast, signal preprocessing and cleaning pipelines for fNIRS often follow simple recipes and so far rarely incorporate the available state-of-the-art in adjacent fields. In neuroscience, where fMRI and fNIRS are established neuroimaging tools, evoked hemodynamic brain activity is typically estimated across multiple trials using a General Linear Model (GLM). With the help of the GLM, subject, channel, and task specific evoked hemodynamic responses are estimated, and the evoked brain activity is more robustly separated from systemic physiological interference using independent measures of nuisance regressors, such as short-separation fNIRS measurements. When correctly applied in single trial analysis, e.g., in BCI, this approach can significantly enhance contrast to noise ratio of the brain signal, improve feature separability and ultimately lead to better classification accuracy. In this manuscript, we provide a brief introduction into the GLM and show how to incorporate it into a typical BCI preprocessing pipeline and cross-validation. Using a resting state fNIRS data set augmented with synthetic hemodynamic responses that provide ground truth brain activity, we compare the quality of commonly used fNIRS features for BCI that are extracted from (1) conventionally preprocessed signals, and (2) signals preprocessed with the GLM and physiological nuisance regressors. We show that the GLM-based approach can provide better single trial estimates of brain activity as well as a new feature type, i.e., the weight of the individual and channel-specific hemodynamic response function (HRF) regressor. The improved estimates yield features with higher separability, that significantly enhance accuracy in a binary classification task when compared to conventional preprocessing-on average +7.4% across subjects and feature types. We propose to adapt this well-established approach from neuroscience to the domain of single-trial analysis and preprocessing wherever the classification of evoked brain activity is of concern, for instance in BCI.

Warmth is a characteristic but nondiagnostic feature of cellulitis. We assessed the diagnostic utility of skin surface temperature in differentiating cellulitis from pseudocellulitis. Adult patients presenting to the emergency department of a large urban hospital with presumed cellulitis were enrolled. Patients were randomized to dermatology consultation (n = 40) versus standard of care (n = 32). Thermal images of affected and unaffected skin were obtained for each patient. Analysis was performed on dermatology consultation patients to establish a predictive model for cellulitis, which was then validated in the other cohort. Of those evaluated by dermatology consultation, pseudocellulitis was diagnosed in 28%. Cellulitis patients had an average maximum affected skin temperature of 34.1°C, which was 3.7°C warmer than the corresponding unaffected area (95% confidence interval = 2.7-4.8°C, P < 0.00001). Pseudocellulitis patients had an average maximum affected temperature of 31.5°C, which was 0.2°C warmer than the corresponding unaffected area (95% confidence interval = -1.1 to 1.5°C, P = 0.44). Temperature differences between sites were greater in cellulitis patients than in pseudocellulitis patients (3.7 vs. 0.2°C, P = 0.002). A logistic regression model showed that a temperature difference of 0.47°C or greater conferred a 96.6% sensitivity, 45.5% specificity, 82.4% positive predictive value, and 83.3% negative predictive value for cellulitis diagnosis. When validated in the other cohort, this model gave the correct diagnosis for 100% of patients with cellulitis and 50% of those with pseudocellulitis. A difference threshold of 0.47°C or greater between affected and unaffected skin showed an 87.5% accuracy in cellulitis diagnosis.

Background and ObjectiveMolecules native to tissue that fluoresce upon light excitation can serve as reporters of cellular activity and protein structure. In skin, the fluorescence ascribed to tryptophan is a marker of cellular proliferation, whereas the fluorescence ascribed to cross‐links of collagen is a structural marker. In this work, we introduce and demonstrate a simple but robust optical method to image the functional process of epithelialization and the exposed dermal collagen in wound healing of human skin in an organ culture model.Materials and MethodsNon‐closing non‐grafted, partial closing non‐grafted, and grafted wounds were created in ex vivo human skin and kept in culture. A wide‐field UV fluorescence excitation imaging system was used to visualize epithelialization of the exposed dermis and quantitate wound area, closure, and gap. Histology (H&E staining) was also used to evaluate epithelialization.ResultsThe endogenous fluorescence excitation of cross‐links of collagen at 335 nm clearly shows the dermis missing epithelium, while the endogenous fluorescence excitation of tryptophan at 295 nm shows keratinocytes in higher proliferating state. The size of the non‐closing wound was 11.4 ± 1.8 mm and remained constant during the observation period, while the partial‐close wound reached 65.5 ± 4.9% closure by day 16. Evaluations of wound gaps using fluorescence excitation images and histology images are in agreement.ConclusionsWe have established a fluorescence imaging method for studying epithelialization processes, evaluating keratinocyte proliferation, and quantitating closure during wound healing of skin in an organ culture model: the dermal fluorescence of pepsin‐digestible collagen cross‐links can be used to quantitate wound size, closure extents, and gaps; and, the epidermal fluorescence ascribed to tryptophan can be used to monitor and quantitate functional states of epithelialization. UV fluorescence excitation imaging has the potential to become a valuable tool for research, diagnostic and educational purposes on evaluating the healing of wounds. Lasers Surg. Med. 48:678–685, 2016. © 2016 The Authors. Lasers in Surgery and Medicine Published by Wiley Periodicals, Inc.