Hyperspectral imaging-based erythema classification in atopic dermatitis.

BACKGROUND/PURPOSE: Among the characteristics that appear in the epidermis of the skin, erythema is primarily evaluated through qualitative scales, such as visual assessment (VA). However, VA is not ideal because it relies on the experience and skill of dermatologists. In this study, we propose a new evaluation method based on hyperspectral imaging (HSI) to improve the accuracy of erythema diagnosis in clinical settings and investigate the applicability of HSI to skin evaluation. METHODS: For this study, 23 subjects diagnosed with atopic dermatitis were recruited. The inside of the right arm is selected as the target area and photographed using a hyperspectral camera (HS). Subsequently, based on the erythema severity visually assessed by a dermatologist, the severity classification performance of the RGB and HS images is compared. RESULTS: Erythema severity is classified as high when using (i) all reflectances of the entire HSI band and (ii) a combination of color features (R of RGB, a* of CIEL*a*b*) and five selected bands through band selection. However, as the number of features increases, the amount of calculation increases and becomes inefficient; therefore, (ii), which uses only seven features, is considered to perform classification more efficiently than (i), which uses 150 features. CONCLUSION: In conclusion, we demonstrate that HSI can be applied to erythema severity classification, which can further increase the accuracy and reliability of diagnosis when combined with other features observed in erythema. Additionally, the scope of its application can be expanded to various studies related to skin pigmentation.

Correlation analysis between texture features and elasticity of skin hyperspectral images in the near-infrared band.

BACKGROUND/PURPOSE: Skin elasticity was used to evaluate healthy and diseased skin. Correlation analysis between image texture characteristics and skin elasticity was performed to study the feasibility of assessing skin elasticity using a non-contact method. MATERIALS AND METHODS: Skin images in the near-infrared band were acquired using a hyperspectral camera, and skin elasticity was obtained using a skin elastimeter. Texture features of the mean, standard deviation, entropy, contrast, correlation, homogeneity, and energy were extracted from the acquired skin images, and a correlation analysis with skin elasticity was performed. RESULTS: The texture features, and skin elasticity of skin images in the near-infrared band had the highest correlation on the side of eye and under of arm, and the mean and correlation were features of texture suitable for distinguishing skin elasticity according to the body part. CONCLUSION: In this study, we performed elasticity and correlation analyses for various body parts using the texture characteristics of skin hyperspectral images in the near-infrared band, confirming a significant correlation in some body parts. It is expected that this will be used as a cornerstone of skin elasticity evaluation research using non-contact methods.

Skin color classification of Koreans using clustering.

BACKGROUND/PURPOSE: Skin color is used as an index for diagnosing and predicting skin irritation, dermatitis, and skin conditions because skin color changes based on various factors. Therefore, a new method for consistently and accurately evaluating skin color while overcoming the limitations of the existing skin color evaluation method was proposed, and its usefulness was demonstrated. METHODS: Skin color was quantified using the RGB (Red, Green, Blue), HSV (Hue Saturation Value), CIELab, and YCbCr color spaces in the acquired Korean skin images, which were classified through clustering. In addition, the classification performances of the existing visual scoring method and the proposed skin color classification method were compared and analyzed using multinomial logistic regression, support vector machine, K-nearest neighbor, and random forest. RESULTS: After quantifying the skin color through the color space conversion of the skin image, the skin color classification performance according to the number of quantified features and the classifier was verified. In addition, the usefulness of the proposed classification method was confirmed by comparing its classification performance with that of the existing skin color classification method. CONCLUSION: In this study, a method was proposed to objectively classify skin color values quantified from skin images of Koreans acquired using a digital camera through clustering. To verify the proposed method, its classification performance was compared with that of the existing classification method, and an optimized classification method was presented for the classification of Korean skin color. Thus, the proposed method can objectively classify skin color and can be used as a cornerstone in research to quantify skin color and establish objective classification criteria.

Robust skin microrelief depth estimation using a mobile stereo system.

BACKGROUND: The skin surface becomes wrinkled and rough due to various internal and external factors. A three-dimensional (3D) analysis of the skin is required to improve skin conditions. Stereophotogrammetry, a noninvasive 3D analysis method, is easy to install and use, but most stereo systems have a fixed baseline and scale. Previous stereo systems are not suitable for observing micro-range skin features. Therefore, we suggest the optimal conditions and methods for the 3D analysis of skin microrelief using a multi-conditioned stereo system. METHODS: We constructed a nonconvergence model using a mobile device and acquired stereo images under multiscale and multi-baseline conditions. We extracted 3D information of the skin through our process: preprocessing, skin feature extraction, feature matching, and actual depth mapping. We improved the accuracy of the 3D analysis of the skin by using disparity values instead of disparity maps. We compared and analyzed the performances of six local feature detector and descriptor algorithms. In addition, we suggested depth-mapping formulas to estimate the actual depth of the skin microrelief. RESULTS: We confirmed that stereo images with a working distance of 70-75 mm and a baseline of 4-8 mm are effective for the 3D analysis of skin microrelief. In addition, accelerated KAZE exhibited the best performance for features extraction and stereo matching. Finally, the extracted 3D information was converted to the actual depth, and the performance of the 3D analysis was verified. CONCLUSION: The proposed system and method that provide texture information are effective for 3D skin disease analysis and evaluation.

Upper Limb Rehabilitation Tools in Virtual Reality Based on Haptic and 3D Spatial Recognition Analysis: A Pilot Study.

With aging, cerebrovascular diseases can occur more often. Stroke cases involve hemiplegia, which causes difficulties in performing activities of daily living. Existing rehabilitation treatments are based on the subjective evaluation of the therapist as the need for non-contact care arises; it is necessary to develop a system that can self-rehabilitate and offer objective analysis. Therefore, we developed rehabilitation tools that enable self-rehabilitation exercises in a virtual space based on haptics. Thirty adults without neurological damage were trained five times in a virtual environment, and the time, number of collisions, and coordinates were digitized and stored in real time. An analysis of variance (ANOVA) of the time and distance similarity changes revealed that as the number of rounds increased, no changes or increases occurred (p ≥ 0.05), and the collisions and paths were stable as the training progressed (p < 0.05). ANOVA showed a high correlation (0.90) with a decrease in the number of crashes and time required. It was meaningful to users when performing rehabilitation training more than four times and significantly impacted the analysis. This study analyzed the upper limb and cognitive rehabilitation of able-boded people in three-dimensional space in a virtual environment; the performance difficulty could be controlled through variations in rehabilitation models.

Adaptive Fine Distortion Correction Method for Stereo Images of Skin Acquired with a Mobile Phone.

With the development of the mobile phone, we can acquire high-resolution images of the skin to observe its detailed features using a mobile camera. We acquire stereo images using a mobile camera to enable a three-dimensional (3D) analysis of the skin surface. However, geometric changes in the observed skin structure caused by the lens distortion of the mobile phone result in a low accuracy of the 3D information extracted through stereo matching. Therefore, our study proposes a Distortion Correction Matrix (DCM) to correct the fine distortion of close-up mobile images, pixel by pixel. We verified the correction performance by analyzing the results of correspondence point matching in the stereo image corrected using the DCM. We also confirmed the correction results of the image taken at the five different working distances and derived a linear regression model for the relationship between the angle of the image and the distortion ratio. The proposed DCM considers the distortion degree, which appears to be different in the left and right regions of the image. Finally, we performed a fine distortion correction, which is difficult to check with the naked eye. The results of this study can enable the accurate and precise 3D analysis of the skin surface using corrected mobile images.

Development of a Diagnosis and Evaluation System for Hemiplegic Patients Post-Stroke Based on Motion Recognition Tracking and Analysis of Wrist Joint Kinematics.

An inexperienced therapist lacks the analysis of a patient's movement. In addition, the patient does not receive objective feedback from the therapist due to the visual subjective judgment. The aim is to provide a guide for in-depth rehabilitation therapy in virtual space by continuously tracking the user's wrist joint during Leap Motion Controller (LMC) activities and present the basic data to confirm steady therapy results in real-time. The conventional Box and Block Test (BBT) is commonly used in upper extremity rehabilitation therapy. It was modeled in proportion to the actual size and Auto Desk Inventor was used to perform the 3D modeling work. The created 3D object was then implemented in C # through Unity5.6.2p4 based on LMC. After obtaining a wrist joint motion value, the motion was analyzed by 3D graph. Healthy subjects (23 males and 25 females, n = 48) were enrolled in this study. There was no statistically significant counting difference between conventional BBT and system BBT. This indicates the possibility of effective diagnosis and evaluation of hemiplegic patients post-stroke. We can keep track of wrist joints, check real-time continuous feedback in the implemented virtual space, and provide the basic data for an LMC-based quantitative rehabilitation therapy guide.

Three-dimensional reconstruction of skin disease using multi-view mobile images.

BACKGROUND/PURPOSE: In skin beauty area, interest in diagnosis and management methods for acne is increasing. However, it is difficult to diagnose protruding skin disease by two-dimensional (2D) image. Three-dimensional (3D) approach is needed. The purpose of this study was to propose a system for reconstructing 3D model (visual hull) of 2D images obtained using mobile devices. METHODS: Acne images were acquired using a 3D printing mobile image acquisition system. Using two attached mirrors, five multi-view acne silhouette images were obtained. They were then, reconstructed to 3D. To measure the volume of the formed 3D model (visual hull), post-processing, calculation, and texture mapping were performed. The volume of acne samples designed with 3D printing was compared with the volume calculated in the produced system using statistical analysis program. RESULTS: The 3D modeling program demonstrated its superiority by showing high correlation (r = 0.783) between the actual volume of acne and the volume calculated by the system. The 3D model (visual hull) was successfully reconstructed by capturing 2D images of actual acne. CONCLUSION: In this study, we created a system to reconstruct small sized protruding skin disease images such as acne obtained with mobile devices. The 3D printing system was used to obtain images from mobile camera and reconstructed to 3D. To verify the volume of the reconstructed model, 3D printing samples were produced and compared with the calculated actual volume. It can be used, for initial diagnosis by receiving information about the protruding skin disease without space-time constraints using a mobile device.

Small-animal PET imaging analysis with [18 F]FHBG in a mouse model of HSV1-tk gene expression in melanoma.

The purpose of this study was to establish a small-animal model for molecular imaging and to acquire basic data on assessing the efficacy of candidate melanoma drugs using small-animal PET imaging analysis with [18 F]FHBG for herpes simplex virus 1-thymidine kinase (HSV1-tk) gene expression in a melanoma mouse model. The B16 melanoma cell line was transduced with a recombinant lentiviral vector containing the HSV1-tk gene and inoculated into the back skin of C57BL/6J mice. [18 F]FHBG PET imaging showed better contrast for HSV1-tk(+) melanomas compared to brain, heart, gall bladder, intestine and kidney than did [18 F]FDG PET imaging.

Method for In-Vivo Fluorescence Imaging Contrast Enhancement through Light Modulation.

Early diagnosis is one of the most important factors that increase the therapeutic potential of the disease. Diagnoses conducted by conventional equipment are expensive, time-consuming, burdensome to patients, and do not have high success rates. Diagnostic methods have also been investigated using nanoparticles. However, there have been no significant improvements in the early diagnosis of disease. The diagnosis technique proposed in this paper consumes less time, is more cost-effective, and more accurate. It uses a new concept-a low-intensity fluorescence molecular imaging system with a lock-in technique. This study applied the lock-in technique to basic research in contrast enhancement and optimization. This improved fluorescence distribution analysis, resulting in increased resolution of optical molecular imaging for early diagnosis of disease. An experimental lock-in fluorescence imaging system, which used a variety of fluorescent dyes, achieved signal amplification 100 times greater than that of a conventional fluorescence imaging system. The results of this study demonstrate that the lock-in technique could significantly improve optical molecular imaging technology, making it possible to achieve early diagnosis of disease.

Development of a quantitative assessment method of pigmentary skin disease using ultraviolet optical imaging.

BACKGROUND/PURPOSE: The visual scoring method has been used as a subjective evaluation of pigmentary skin disorders. Severity of pigmentary skin disease, especially melasma, is evaluated using a visual scoring method, the MASI (melasma area severity index). This study differentiates between epidermal and dermal pigmented disease. The study was undertaken to determine methods to quantitatively measure the severity of pigmentary skin disorders under ultraviolet illumination. METHODS: The optical imaging system consists of illumination (white LED, UV-A lamp) and image acquisition (DSLR camera, air cooling CMOS CCD camera). Each camera is equipped with a polarizing filter to remove glare. To analyze images of visible and UV light, images are divided into frontal, cheek, and chin regions of melasma patients. Each image must undergo image processing. To reduce the curvature error in facial contours, a gradient mask is used. RESULTS: The new method of segmentation of front and lateral facial images is more objective for face-area-measurement than the MASI score. Image analysis of darkness and homogeneity is adequate to quantify the conventional MASI score. Under visible light, active lesion margins appear in both epidermal and dermal melanin, whereas melanin is found in the epidermis under UV light. CONCLUSION: This study objectively analyzes severity of melasma and attempts to develop new methods of image analysis with ultraviolet optical imaging equipment. Based on the results of this study, our optical imaging system could be used as a valuable tool to assess the severity of pigmentary skin disease.

Single fiber curvature for muscle impairment assessment: Phase contrast imaging of stroke-induced animals.

There are technical challenges in imaging studies that can three-dimensionally (3D) analyze a single fiber (SF) to observe the functionality of the entire muscle after stroke. This study proposes a 3D assessment technique that only segments the SF of the right stroke-induced soleus muscle of a gerbil using synchrotron radiation x-ray microcomputed tomography (SR-µCT), which is capable of muscle structure analysis. Curvature damage in the SF of the left soleus muscle (impaired) progressed at 7-day intervals after the stroke in the control; particularly on the 7 days (1 week) and 14 days (2 weeks), as observed through visualization analysis. At 2 weeks, the SF volume was significantly reduced in the control impaired group (p = .033), and was significantly less than that in the non-impaired group (p = .009). We expect that animal post-stroke studies will improve the basic field of rehabilitation therapy by diagnosing the degree of SF curvature. RESEARCH HIGHLIGHTS: Muscle evaluation after ischemic stroke using synchrotron radiation x-ray microcomputed tomography (SR-µCT). Curvature is measured by segmenting a single fiber (SF) in the muscle. Structural changes in the SF of impaired gerbils at 7-day intervals were assessed.

Simultaneous visualization of micro-damage in cortical bone, trabecular bone, and intracortical vasculature for diagnosing osteoporosis: An animal model synchrotron imaging.

Osteoporosis (OP) is difficult to diagnose through the three-dimensional visualization of micro-damage. In this study, aimed to make an objective diagnosis by visualizing micro-damage caused by OP using synchrotron radiation-based µCT (SR-µCT). Female mice (n = 12) were randomly divided into an ovariectomized group (OVX, n = 6) in which both ovaries were excised and OP occurred, and a sham-operated group (SHAM, n = 6). After six weeks, all femurs (left and right) were excised from both groups (n = 12 per group). Thereafter, femurs were randomly divided into SR-µCT (OVX group, n = 6; SHAM group, n = 6) and µCT (OVX group, n = 6; SHAM group, n = 6) groups. In the SR-µCT group, micro-damage was visualized by manually segmenting the cortical bone, trabecular bone, and intracortical vasculature using a water-shedding algorithm. In addition, trabecular bone was obtained by automatic segmentation using µCT. Cortical bone volume/total volume was greater (p = .015), and cortical thickness was greater in the SHAM group than in the OVX group (p = .007). Among the trabecular bone parameters, the bone volume/total volume (TV) in OVX was significantly lower than that in the SHAM group (p = .012). The canal volume was greater (p = .021) and lacuna volume was greater (p < .001) in the SHAM group than in the OVX group. We expect that it will be possible to analyze damage and recovery mechanisms in the field of rehabilitation. SR-µCT has been proposed as an objective method for OP diagnosis as it allows the visualization of microstructures. RESEARCH HIGHLIGHTS: Damage mechanism for diagnosis and evaluation in an osteoporosis model. Synchrotron radiation can objectively diagnose osteoporosis. Visualization is possible by segmenting microdamage caused by osteoporosis.

Efficacy of oregonin investigated by non-invasive evaluation in a B16 mouse melanoma model.

Oregonin has been reported to act as a mediator of antibiosis, a liver-protective agent, an antioxidant, an anti-inflammatory agent, and to prevent cancer outbreaks. B16 melanoma cells were separated with trypsin-ethylenediaminetetraacetic acid, resuspended in 50 µl of phosphate-buffered saline and transplanted into the backs of 6- to 8-week-old male Balb/c nude mice through subcutaneous injection. Treatment doses of oregonin were administered three times weekly, for 30 days from the 11th day after transplantation of the melanoma cells, in each group. The study consisted of a control group, a dacarbazine group, an oregonin group and a dacarbazine + oregonin group. Measurements were taken before treatment and on the 5th, 7th, 10th and 15th days after treatment for each group. Based on survival rates after transplantation, the control group showed less than 50% survival after 20 days, while the treatment groups showed at least 50% survival up to the 41st day.

Influence of surface charge of gold nanorods on skin penetration.

BACKGROUND/PURPOSE: The skin plays an important role as a protective barrier against toxic environments and also is a route of drug administration. In spite of evidence for and interest in the skin penetration of nanoparticles, no study has examined the effect of nanoparticle surface charge on percutaneous absorption. In this study, we investigated the effect of surface charges of gold nanorods (GNs) on skin penetration. METHODS: Using transmission electron microscopy (TEM) and image analysis, we quantitatively measured the ability of GNs to penetrate the skin. RESULTS: Our results showed that the area density of the electron-dense dots of GNs, which penetrated into the stratum corneum, significantly increased for negatively charged GNs compared to those with a positive charge (P < 0.01). To investigate the percutanoues absorption of charged GNs, in vitro skin permeation studies were carried out using a Franz-type diffusion cell (FDC). The penetration of GNs through the skin was quantified by inductively coupled plasma mass spectrometry. Consistent with TEM observations, our penetration study using an FDC also revealed that negative particles were frequently detected in samples of receptor fluid at 48 h after exposure (P < 0.01). CONCLUSION: Together our results showed that anionic GNs penetrate skin better than cationic GNs.

4D dynamic system for visual-motor integration analysis.

It is very important to evaluate visual-motor integration (VMI), as it is used as an index to evaluate cognitive abilities. However, it is difficult to use the existing paper-based tests to evaluate the dynamic process, including spatial and depth perception abilities. Therefore, this study aims to extract kinematic and dynamic features for dynamic assessment for VMI. We propose a 4D dynamic analysis system that implements a VMI test in a virtual space using Leap motion controller and Unity3D and acquires the time-series data of hand joints and traces. We selected three categories of features: postural control ability, spatial and depth perception ability, and 4D analysis. The degree and patterns of postural maintenance differed between subjects in the VMI and MC tests. In addition, the personal patterns were identified with dynamic features, including their fluency and hesitation in relation to the task figures of the VMI test tool. As such, this system enables dynamic feature extraction and analysis which were previously impossible and presents performance results for healthy adults.

Quantitative color assessment of dermoscopy images using perceptible color regions.

BACKGROUND: Dermoscopy is a non-invasive in vivo skin imaging technique that assists dermatologists in diagnosing melanoma. However, the use of dermoscopy for diagnosis requires extensive training since this approach often provides extremely complex and subjective information. The presence of an imperceptible color difference in dermoscopy images is one of the serious problems associated with the use of this technique. This imperceptible color difference leads to inaccurate lesion extraction at the borders and hinders the assessment of lesion features. Therefore, objective and quantitative assessment based on perceptible color differences is important for the diagnosis of melanoma using dermoscopy. METHODS: In this study, we developed a method for assessing colors in a lesion. Twenty-seven perceptible color regions based on the multi-thresholding method in each color channel were constructed, and dominant color region (DCR), bluish dominant region (BDR), and the number of colors were assessed as three diagnostic parameters from these perceptible color regions on 150 dermoscopy images. RESULTS/CONCLUSION: Diagnostic accuracy was calculated by combination of three diagnostic parameters derived from DCR, BDR, and the number of colors. Diagnostic accuracy with 73.33% sensitivity and 90.67% specificity was obtained in case of positive features in more than two parameters.

Quantitative method for measuring therapeutic efficacy of the 308 nm excimer laser for vitiligo.

BACKGROUND: There are several available treatments for vitiligo, but measurement of their therapeutic efficacy is not standardized and is somewhat arbitrary based largely on the global impression of the overall response. The purpose of this study was to develop a quantitative method for evaluating the treatment response of vitiligo measuring changes in area using digital image analysis. We applied this parametric model to the evaluation of efficacy of the 308 nm excimer laser. METHODS: This study was a retrospective study, designed as a before and after trial with a single arm. A total of 18 patients were enrolled who had been treated with a 308 nm excimer laser as monotherapy twice a week for 20 sessions. The repigmentation percentage was calculated by measuring changes in area before and after treatment using digital image analysis and graded on a five-point ordinal scale [global assessment scale (GAS)]. GAS was also measured by physician and patient for comparison with our estimates. Additional GASs were also measured by four different evaluators for inter-rater variability. RESULTS: The mean repigmentation percentage after treatment was 45.3% (range, 0.7-100%). The changes in area after treatment were statistically significant (P < 0.05). A substantial agreement of outcomes was observed between physicians and digital image analysis (κ(w) = 0.78), but lower agreement was observed between patients and digital image analysis (κ(w) = 0.49). The inter-rater variability for GAS was substantially low (Krippendorff's α = 79.3%). CONCLUSION: Measurement of changes in area using digital image analysis could be used as a quantitative method in evaluating efficacy of treatment for vitiligo. Because vitiligo lesions can occur in any location with various shapes and sizes, digital image analysis would be a more objective method for measuring treatment response than a GAS.

Automatic analysis system for abnormal red blood cells in peripheral blood smears.

The type and ratio of abnormal red blood cells (RBCs) in blood can be identified through peripheral blood smear test. Accurate classification is important because the accompanying diseases indicated by abnormal RBCs vary. In clinical practice, this task is time-consuming because the RBCs are manually classified. In addition, because the classification depends on the subjective criteria of pathologists, objective classification is difficult to achieve. In this paper, an automatic classification method that is solely based on images of RBCs captured under a microscope and processed using machine learning (ML) is proposed. The size and hemoglobin abnormalities of RBCs were classified by optimizing the criteria used in clinical practice. For morphologically abnormal RBCs classification, used seven geometric features information (major axis, minor axis, ratio of major and minor axis, perimeter, circularity, number of convex hulls, difference between area and convex area) and five types of multiple classifiers (Support Vector Machine, Decision Tree, K-Nearest Neighbor, Random Forest, and Adaboost models). Among was categorized using SVM, highly accurate results (99.9%) were obtained. The classification is performed simultaneously, and results are provided to the user through a graphical user interface (GUI).

Analysis of type I osteoporosis animal models using synchrotron radiation.

Preclinical experiments to analyze the trabecular space of spongy bones using small animals are required for the evaluation and treatment of patients with osteoporosis (OP). We performed ovariectomy to create OP models. A total of four mice were used. Ovariectomized group (OVX, n = 2) in which both ovaries were resected at random, and the sham operated group (SHAM, n = 2) performed surgery without resecting the ovaries. We propose a study that enables OP analysis by analyzing tibia microstructures of OVX and SHAM using synchrotron radiation (SR). SR imaging is a technology capable of irradiating an extremely small object in the order of several tens of nanometers using a nondestructive method at the microscopic level. Unlike previous imaging diagnoses (staining, micro-CT [Computed Tomography]) it was possible to preserve the real shape and analyze bone microstructures in real-time and analyze and evaluate spongy bones to secure data and increase the reliability of OP analysis. We were able to confirm the possibility of OP diagnosis through experimental animals for spongy bone damage related to bone mineral density. Therefore, we aimed to provide a rehabilitation and medicine therapy intervention method through basic research on the evaluation of OP diagnosis through human-based segmentation of challenging spongy bones while supplementing the limitations of existing imaging methods. RESEARCH HIGHLIGHTS: We present an analysis of osteoporosis through spongy bone using phase-contrast X-ray source. Unlike existing methods, it is possible to analyze the internal microstructure of the tibia with this method. This is an objective mechanism for OP and a basis for rehabilitation.