Digital Skin Images Research Articles

115 Enhanced psoriasis trial screening using an AI model to remotely assess digital skin images

115 Enhanced psoriasis trial screening using an AI model to remotely assess digital skin images

Framework for psoriasis/molluscum detection in skin images using ResNetV2 variants

BackgroundComputer algorithms are extensively utilized in hospitals for the purpose of achieving expedited and precise disease identification from medical data. The objective of this study is to propose a deep-learning (DL) framework to classify the chosen digital skin image (DSI) database into psoriasis and molluscum with better accuracy. Aims and objectivesAims to develop a DL-tool using the pre-trained ResNetV2 DL-models and verify the performance of the developed tool using a chosen DSI database. Further, confirm the merit of the ResNetV2-based tool against other chosen DL-models. Methods and resultsThis study initially examines the performance of chosen pre-trained DL (PDL) methods using the DSI database using conventional and fused features. Proposed DL-tool consist the following stages; (i) image collection and resizing it 224x224x3 pixels, (ii) deep-features extraction using the selected PDL, (iii) feature reduction and serial features concatenation to get a new features vector, and (iv) the performance evaluation through three-fold cross validation and confirmation. The feature reduction and serial features fusion of this study is performed initially using feature sorting based on its rank and 50% dropout and Particle Swarm Optimization (PSO) based feature reduction. The reduced features of two chosen PDL-models are then considered to obtain the Fused Deep Features (FDF) and the classification task is executed on the DSI data to verify the performance of the developed DL-tool. The experimental outcome of this study confirms that the proposed scheme helps to provide a detection accuracy of >97%, when the K-Nearest Neighbour based classification is executed. ConclusionInvestigational outcome of this study confirms that the proposed DL-tool helps to achieve better detection accuracy when the features of ResNetV2 models are considered to generate the FDF. Further, the accuracy achieved with the PSO based FDF is better compared to the conventional method generated FDF.

USAGE OF PARTICLE SWARM OPTIMIZATION IN DIGITAL IMAGES SELECTION FOR MONKEYPOX VIRUS PREDICTION AND DIAGNOSIS

Identifying skin diseases by using digital images of skin that are also automated, efficient, and accurate is critical for biomedical image analysis. Many researchers have developed numerous machine-learning techniques for the prediction and diagnosis of various diseases that help clinicians identify infections early and provide crucial data for virus management. In this work, we use the inherent attributes of Particle Swarm Optimization (PSO), such as exploration and exploitation, to identify images for monkeypox virus prediction and diagnosis. Alongside, monkeypox, chickenpox, smallpox, cowpox, measles, tomato flu, and normal skin images were all considered in this study for monkeypox virus prediction and diagnosis. We collect photos from the International Skin Imaging Collaboration (ISIC) for analysis and experimentation purposes. Finally, we compare the proposed model Particle Swarm Optimization- Monkeypox Virus (PSOMPX) for monkeypox virus identification with four distinct pre-trained deep learning models (e.g., VGG16, ResNet50, InceptionV3, and Ensemble). Then we use four performance evaluation metrics—accuracy, precision, recall, and F1 score—to evaluate the model and analyze the outcomes of experiments. The experimental results obtained through the PSOMPX model significantly outperform other models due to its numerous traits.

Development of a Novel Multi-Modal Contextual Fusion Model for Early Detection of Varicella Zoster Virus Skin Lesions in Human Subjects

Skin lesion detection is crucial in diagnosing and managing dermatological conditions. In this study, we developed and demonstrated the potential applicability of a novel mixed-scale dense convolution, self-attention mechanism, hierarchical feature fusion, and attention-based contextual information technique (MSHA) model for skin lesion detection using digital skin images of chickenpox and shingles lesions. The model adopts a combination of unique architectural designs, such as a mixed-scale dense convolution layer, self-attention mechanism, hierarchical feature fusion, and attention-based contextual information, enabling the MSHA model to capture and extract relevant features more effectively for chickenpox and shingles lesion classification. We also implemented an effective training strategy to enhance a better capacity to learn and represent the relevant features in the skin lesion images. We evaluated the performance of the novel model in comparison to state-of-the-art models, including ResNet50, VGG16, VGG19, InceptionV3, and ViT. The results indicated that the MSHA model outperformed the other models with accuracy and loss of 95.0% and 0.104, respectively. Furthermore, it exhibited superior performance in terms of true-positive and true-negative rates while maintaining low-false positive and false-negative rates. The MSHA model’s success can be attributed to its unique architectural design, effective training strategy, and better capacity to learn and represent the relevant features in skin lesion images. The study underscores the potential of the MSHA model as a valuable tool for the accurate and reliable detection of chickenpox and shingles lesions, which can aid in timely diagnosis and appropriate treatment planning for dermatological conditions.

Classification of Monkeypox Images Using LIME-Enabled Investigation of Deep Convolutional Neural Network.

In this research, we demonstrate a Deep Convolutional Neural Network-based classification model for the detection of monkeypox. Monkeypox can be difficult to diagnose clinically in its early stages since it resembles both chickenpox and measles in symptoms. The early diagnosis of monkeypox helps doctors cure it more quickly. Therefore, pre-trained models are frequently used in the diagnosis of monkeypox, because the manual analysis of a large number of images is labor-intensive and prone to inaccuracy. Therefore, finding the monkeypox virus requires an automated process. The large layer count of convolutional neural network (CNN) architectures enables them to successfully conceptualize the features on their own, thereby contributing to better performance in image classification. The scientific community has recently articulated significant attention in employing artificial intelligence (AI) to diagnose monkeypox from digital skin images due primarily to AI's success in COVID-19 identification. The VGG16, VGG19, ResNet50, ResNet101, DenseNet201, and AlexNet models were used in our proposed method to classify patients with monkeypox symptoms with other diseases of a similar kind (chickenpox, measles, and normal). The majority of images in our research are collected from publicly available datasets. This study suggests an adaptive k-means clustering image segmentation technique that delivers precise segmentation results with straightforward operation. Our preliminary computational findings reveal that the proposed model could accurately detect patients with monkeypox. The best overall accuracy achieved by ResNet101 is 94.25%, with an AUC of 98.59%. Additionally, we describe the categorization of our model utilizing feature extraction using Local Interpretable Model-Agnostic Explanations (LIME), which provides a more in-depth understanding of particular properties that distinguish the monkeypox virus.

A Computer-Aided Feasibility Implementation to Detect Monkeypox from Digital Skin Images with Using Deep Artificial Intelligence Methods

A Computer-Aided Feasibility Implementation to Detect Monkeypox from Digital Skin Images with Using Deep Artificial Intelligence Methods

Computer-Aided Detection and Classification of Monkeypox and Chickenpox Lesion in Human Subjects Using Deep Learning Framework.

Monkeypox is a zoonotic viral disease caused by the monkeypox virus. After its recent outbreak, it has become clear that a rapid, accurate, and reliable diagnosis may help reduce the risk of a future outbreak. The presence of skin lesions is one of the most prominent symptoms of the disease. However, this symptom is also peculiar to chickenpox. The resemblance in skin lesions in the human subject may disrupt effective diagnosis and, as a result, lead to misdiagnosis. Such misdiagnosis can lead to the further spread of the disease as it is a communicable disease and can eventually result in an outbreak. As deep learning (DL) algorithms have recently been regarded as a promising technique in medical fields, we have been attempting to integrate a well-trained DL algorithm to assist in the early detection and classification of skin lesions in human subjects. This study used two open-sourced digital skin images for monkeypox and chickenpox. A two-dimensional convolutional neural network (CNN) consisting of four convolutional layers was applied. Afterward, three MaxPooling layers were used after the second, third, and fourth convolutional layers. Finally, we evaluated the performance of our proposed model with state-of-the-art deep-learning models for skin lesions detection. Our proposed CNN model outperformed all DL models with a test accuracy of 99.60%. In addition, a weighted average precision, recall, F1 score of 99.00% was recorded. Subsequently, Alex Net outperformed other pre-trained models with an accuracy of 98.00%. The VGGNet consisting of VGG16 and VGG19 performed least well with an accuracy of 80.00%. Due to the uniqueness of the proposed model and image augmentation techniques applied, the proposed CNN model is generalized and avoids over-fitting. This model would be helpful for the rapid and accurate detection of monkeypox using digital skin images of patients with suspected monkeypox.

Medical Image Classification for Monkeypox Case using Deep Learning Algorithms: A Survey

Due to the importance of maintaining public health and preventing the spread of diseases, nowadays, new diseases have spread at a lot of countries called Monkeypox after the world get rid of covid-19.it is crucial to diagnose Monkeypox and stop the spread of this disease. so that we make this review to give a point of view to Monkeypox spread nowadays. We have recently done nine research to overlay it with different artificial intelligence deep learning methods to diagnose Monkeypox from digital skin images due primarily to AI's success in COVID-19 identification. The VGG16, VGG19, ResNet50, ResNet101, DenseNet201, and AlexNet models were used in our proposed method to classify patients with monkeypox symptoms with other diseases of a similar kind (chickenpox, measles, and normal)., Due to the importance of facing this disease and summarizing these researches according to: methodology and results of detection accuracy, precision.

The mathematics of erythema: Development of machine learning models for artificial intelligence assisted measurement and severity scoring of radiation induced dermatitis

Although significant advancements in computer-aided diagnostics using artificial intelligence (AI) have been made, to date, no viable method for radiation-induced skin reaction (RISR) analysis and classification is available. The objective of this single-center study was to develop machine learning and deep learning approaches using deep convolutional neural networks (CNNs) for automatic classification of RISRs according to the Common Terminology Criteria for Adverse Events (CTCAE) grading system. ScarletredⓇ Vision, a novel and state-of-the-art digital skin imaging method capable of remote monitoring and objective assessment of acute RISRs was used to convert 2D digital skin images using the CIELAB color space and conduct SEV* measurements. A set of different machine learning and deep convolutional neural network-based algorithms has been explored for the automatic classification of RISRs. A total of 2263 distinct images from 209 patients were analyzed for training and testing the machine learning and CNN algorithms. For a 2-class problem of healthy skin (grade 0) versus erythema (grade ≥ 1), all machine learning models produced an accuracy of above 70%, and the sensitivity and specificity of erythema recognition were 67–72% and 72–83%, respectively. The CNN produced a test accuracy of 74%, sensitivity of 66%, and specificity of 83% for predicting healthy and erythema cases. For the severity grade prediction of a 3-class problem (grade 0 versus 1 versus 2), the overall test accuracy was 60–67%, and the sensitivities were 56–82%, 35–59%, and 65–72%, respectively. For estimating the severity grade of each class, the CNN obtained an accuracy of 73%, 66%, and 82%, respectively. Ensemble learning combines several individual predictions to obtain a better generalization performance. Furthermore, we exploited ensemble learning by deploying a CNN model as a meta-learner. The ensemble CNN based on bagging and majority voting shows an accuracy, sensitivity and specificity of 87%, 90%, and 82% for a 2-class problem, respectively. For a 3-class problem, the ensemble CNN shows an overall accuracy of 66%, while for each grade (0, 1, and 2) accuracies were 76%, 69%, and 87%, sensitivities were 70%, 57%, and 71%, and specificities were 78%, 75%, and 95%, respectively. This study is the first to focus on erythema in radiation-dermatitis and produces benchmark results using machine learning models. The outcome of this study validates that the proposed system can act as a pre-screening and decision support tool for oncologists or patients to provide fast, reliable, and efficient assessment of erythema grading.

디지털 피부영상의 관심영역 추출과 조합특징을 이용한 효율적인 병변 분할

본 논문에서는 RGB 색상모델의 디지털 피부영상에서 관심영역 추출과 특징들을 조합한 효율적인 병변분할 기법을 제안한다. 관심영역 추출은 영상의 밝기정보와 색상정보를 이용한 것으로 알고리즘의 효율성과 강건함을 개선하기 위함이다. 또한 특징들의 조합은 색상특징과 질감특징을 조합한 것으로 병변의 분할성능을 좀 더 개선하기 위함이다. 여기서 색상특징은 HSV 모델에서 색조(Hue)을 고려한 채도(Saturation)를 이용하며, 질감특징은 화소간의 통계적 속성을 고려한 전역특징으로 Gray level co-occurrence matrix(GLCM)을 이용한다. 제안된 기법의 성능을 확인하기 위하여 74개 임의크기의 피부병변 디지털 영상(DermQuest 데이터베이스 : 61개, 스마트폰 영상 : 13개)을 대상으로 실험한 결과, 민감도, 특이도, 그리고 정확도에서 우수한 분할성능이 있음을 확인하였다. 또한 색상특징과 질감특징을 조합한 제안방법이 어느 하나의 특징만을 이용한 기법보다도 상대적으로 우수한 분류성능도 있음을 알 수 있다.

Nipple Skin Trauma in Breastfeeding Women During Postpartum Week One.

To objectively describe changes to nipple skin and classify signs of nipple trauma in breastfeeding women during postpartum week 1. This study was conducted in two phases. Phase 1 was an observational prospective study of breastfeeding mothers in which data were obtained from photographs and digital images of nipple skin and analyzed to anatomically classify signs of nipple trauma. In Phase 2, the reliability of signs identified in Phase 1 was verified with the cooperation of eight clinical midwives. A total of 776 images of 50 breastfeeding mothers were obtained daily. The signs of nipple trauma included erythema, swelling, blistering, fissure, and scabbing. Purpura and peeling were identified only with photographic image analysis. Scabbing and blistering were classified as damage to the dermis, and erythema and swelling as damage to the epidermis, based on anatomical evidence and the mothers' subjective experiences of pain intensity. Erythema and swelling were observed from day 0, with erythema most frequently observed. For inter-rater reliability of the five signs of nipple trauma, Kendall's coefficient of concordance ranged from 0.46 (moderate) to 0.85 (almost perfect). Reliability was high for fissure, substantial for blistering and scabbing, and moderate for erythema and swelling. Image analysis revealed five signs of nipple trauma. Erythema and swelling were the most frequently observed signs during postpartum week 1. However, the agreement rate was lower than that for other signs, suggesting the possibility of conflicting interpretations in clinical evaluation.

The Effect of Micro-Spicule Containing Epidermal Growth Factor on Periocular Wrinkles.

BackgroundMicro-needle patches have been recently used to increase skin permeability, which improves drug delivery, and for cosmetic purposes. However, these patches may often have limited efficacy due to insufficient skin penetration and reduced compliance caused by discomfort.ObjectiveWe evaluated the efficacy and the safety of soluble micro-spicule containing epidermal growth factor (MS-EGF) for the treatment of periocular wrinkles.MethodsTwenty healthy volunteers aged 33 to 54 years were enrolled in a randomized, controlled, split-face study. For 4 weeks, a periocular wrinkle was treated daily with either a soluble MS-EGF cream or a cream containing EGF alone. All subjects underwent 8 weeks of follow-up. Efficacy was assessed using an ultrasonic measurement of dermal depth and density, digital skin image analysis, 5-point photonumeric scale for periocular wrinkles and subjective satisfaction.ResultsMS-EGF group showed statistically significant increase of dermal depth and density compared to EGF alone group after 4 and 8 weeks. In addition, there was a marked improvement shown in clinical and 3-dimensional skin image in MS-EGF group. The treatments were well-tolerated; no significant side-effect was noted.ConclusionThe MS-EGF formulation may represent an effective and biocompatible advance in the treatment of periocular wrinkles.

Effects of Jae-Seng Acupuncture Treatment on the Improvement of Nasolabial Folds and Eye Wrinkles.

The microneedle therapy system (MTS), a mechanical method involving making minute multiple holes in the skin, reportedly improves skin condition, such as by reducing flushing and melanin. A newly attempted bloodletting therapy, Jae-Seng Acupuncture, has several advantages over traditional mechanical punching methods because it allows the practitioner to regulate the depth and direction of needle stimulations and to choose whether to stimulate the muscle layers. This study was conducted to determine the efficacy of Jae-Seng Acupuncture in the treatment of nasolabial folds and eye wrinkles. The nasolabial folds and eye wrinkles of 107 patients ranging in age from their 20s to their 70s were subjected to DermaVision, a digital skin image analyzer, before the treatment and one to six months after treatment. Additionally, stimulation of the meridians, such as Taeyang, Tongjaryo, Chongmyong, Sungup, Sabaek, Yonghyang, Chichang, Taeyong, was performed to improve the function of the stomach, large intestine. Analyses of the images indicate that Jae-Seng Acupuncture improved nasolabial folds and eye wrinkles, suggesting that this technique is a safe and effective method for the improvement of facial skin conditions.

Reliability and agreement in the use of four- and six-point ordinal scales for the assessment of erythema in digital images of canine skin.

Grading of erythema in clinical practice is a subjective assessment that cannot be confirmed using a definitive test; nevertheless, erythema scores are typically measured in clinical trials assessing the response to treatment interventions. Most commonly, ordinal scales are used for this purpose, but the optimal number of categories in such scales has not been determined. This study aimed to compare the reliability and agreement of a four-point and a six-point ordinal scale for the assessment of erythema in digital images of canine skin. Fifteen digital images showing varying degrees of erythema were assessed by specialist dermatologists and laypeople, using either the four-point or the six-point scale. Reliability between the raters was assessed using intraclass correlation coefficients and Cronbach's α. Agreement was assessed using the variation ratio (the percentage of respondents who chose the mode, the most common answer). Intraobserver variability was assessed by comparing the results of two grading sessions, at least 6weeks apart. Both scales demonstrated high reliability, with intraclass correlation coefficient values and Cronbach's α above 0.99. However, the four-point scale demonstrated significantly superior agreement, with variation ratios for the four-point scale averaging 74.8%, compared with 56.2% for the six-point scale. Intraobserver consistency for the four-point scale was very high. Although both scales demonstrated high reliability, the four-point scale was superior in terms of agreement. For the assessment of erythema in clinical trials, a four-point ordinal scale is recommended.

Impact of various color LED flashlights and different lighting source to skin distances on the manual and the computer‐aided detection of basal cell carcinoma borders

Quantitative analysis based on digital skin image has been proven to be helpful in dermatology. Moreover, the borders of the basal cell carcinoma (BCC) lesions have been challenging borders for the automatic detection methods. In this work, a computer-aided dermatoscopy system was proposed to enhance the clinical detection of BCC lesion borders. Fifty cases of BCC were selected and 2000 pictures were taken. The lesion images data were obtained with eight colors of flashlights and in five different lighting source to skin distances (SSDs). Then, the image-processing techniques were used for automatic detection of lesion borders. Further, the dermatologists marked the lesions on the obtained photos. Considerable differences between the obtained values referring to the photographs that were taken at super blue and aqua green color lighting were observed for most of the BCC borders. It was observed that by changing the SSD, an optimum distance could be found where that the accuracy of the detection reaches to a maximum value. This study clearly indicates that by changing SSD and lighting color, manual and automatic detection of BCC lesions borders can be enhanced.

Automatic measurement of skin textures of the dorsal hand in evaluating skin aging

Changes in skin textures have been used to evaluate skin aging in many studies. In our previous study, we built some skin texture parameters, which can be used to evaluate skin aging of human dorsal hand. However, it will take too much time and need to work arduously to get the information from digital skin image by manual work. So, we want to build a simple and effective method to automatically count some of those skin texture parameters by using digital image-processing technology. A total of 100 subjects aged 30years and above were involved. Sun exposure history and demographic information were collected by using a questionnaire. The skin image of subjects' dorsal hand was obtained by using a portable skin detector. The number of grids, which is one of skin texture parameters built in our previous study, was measured manually and automatically. Automated image analysis program was developed by using Matlab 7.1 software. The number of grids counted automatically (NGA) was significantly correlated with the number of grids counted manually (NGM) (r=0.9287, P<0.0001). And in each age group, there were no significant differences between NGA and NGM. The NGA was negatively correlated with age and lifetime sun exposure, and decreased with increasing Beagley-Gibson score from 3 to 6. In addition, even after adjusting for NGA, the standard deviation of grid areas for each image was positively correlated with age, sun exposure, and Bealey-Gibson score. The method introduced in present study can be used to measure some skin aging parameters automatically and objectively. And it will save much time, reduce labor, and avoid measurement errors of deferent investigators when evaluating a great deal of skin images in a short time.

A medical ontology for intelligent web-based skin lesions image retrieval

Researchers have applied increasing efforts towards providing formal computational frameworks to consolidate the plethora of concepts and relations used in the medical domain. In the domain of skin related diseases, the variability of semantic features contained within digital skin images is a major barrier to the medical understanding of the symptoms and development of early skin cancers. The desideratum of making these standards machine-readable has led to their formalization in ontologies. In this work, in an attempt to enhance an existing Core Ontology for skin lesion images, hand-coded from image features, high quality images were analyzed by an autonomous ontology creation engine. We show that by exploiting agglomerative clustering methods with distance criteria upon the existing ontological structure, the original domain model could be enhanced with new instances, attributes and even relations, thus allowing for better classification and retrieval of skin lesion categories from the web.

Independent component analysis for assessing therapeutic response in vitiligo skin disorder

This paper describes an image analysis technique that objectively measures skin repigmentation for the assessment of therapeutic response in vitiligo treatments. Skin pigment disorders due to the abnormality of melanin production, such as vitiligo, cause irregular pale patches of skin. The therapeutic response to treatment is repigmentation of the skin. However the repigmentation process is very slow and is only observable after a few months of treatment. Currently, there is no objective method to assess the therapeutic response of skin pigment disorder treatment, particularly for vitiligo treatment. In this work, we apply principal component analysis followed by independent component analysis to represent digital skin images in terms of melanin and haemoglobin composition respectively. Vitiligo skin areas are identified as skin areas that lack melanin (non-melanin areas). Results obtained using the technique have been verified by dermatologists. Based on 20 patients, the proposed technique effectively monitored the progression of repigmentation over a shorter time period of six weeks and can thus be used to evaluate treatment efficacy objectively and more effectively.

Quantitative evaluation of elderly skin based on digital image analysis

The evaluation of the skin state when it is healthy at the time of examination, but predisposed to disease, is based solely on the subjective assessment of clinicians. This assessment may vary from moment to moment and from rater to rater. We focused on skin texture and aimed to develop a new method to evaluate skin integrity of the elderly using a digital skin image, by verifying the reliability of the clinical evaluation of elderly skin image by specialists to create a 'gold standard,' and by analyzing a digital skin image to identify the indices that explain the skin condition as evaluated by specialists. A total of 208 skin images were collected from 34 subjects. And then we processed and analyzed images. Modified Kobayashi's method and texture analysis method were used in image analysis. Kobayashi's method included the process of density transformation, cross binarization, short straight line matching and extraction of main sulcus, and calculation of each index. Texture analysis was performed on cross-binarized images for quantification of uniformity. On the other hand, skin textures in images were scored by six plastic surgeons, using a 10-point Likert scale, where 1 represented 'very bad regularity' and 10 represented 'very good regularity.' The inter-rater reliability was verified by means of the intraclass correlation coefficients (ICC). Finally, stepwise multiple regression analysis was used to extract useful indices; where the clinical evaluation of the physicians (gold standard) was considered to be a dependent variable, and indices obtained from digital skin image analysis to be independent variables. The ICC of raters was 0.92 (95% confidence interval; 0.91-0.94) when including all raters, therefore the score of all raters was used. As a result of stepwise multiple regression, the index of interval (L), thickness (T(ave)), energy 0 degrees , and entropy 45 degrees independently explained the clinician evaluation. R(2) in multiple regression equation was 0.59. It is shown that quantitative evaluation using skin images and their analysis is one method of determining skin integrity in the elderly. The indices to explain the clinical evaluation of specialists were defined and these indices were obtained simply by using a skin image.

Automatic colour correction of digital skin images in teledermatology

We have developed an algorithm for automatic colour correction of skin images obtained in imperfect conditions. The algorithm has been incorporated into a computer program, TransImage. In a set of 31 digital skin images (including cases of dermatitis, eczema, mycotic lesions and skin cancer), 19 images underwent colour correction with the computer program, while 12 remained uncorrected. The images were presented to three experienced dermatologists who reviewed them without knowing if they had been corrected or not. The mean colour accuracy score (on a scale from 1 = very poor to 5 = excellent) for the corrected skin images was 4.1, while the mean score for uncorrected images was 3.7; the difference was significant (P&lt;0.05). Using the 19 corrected images, the dermatologists made 11 inaccurate diagnoses out of 57 (a mean diagnostic accuracy of 81 %). Using the 12 uncorrected images, three dermatologists made 16 inaccurate diagnoses out of 36 (i.e. a mean diagnostic accuracy of 56%); the difference was significant (P&lt;0.05). Colour correction increased the diagnostic accuracy of teledermatology.