Search Results (18)

Background/Objectives: The accurate identification of insect bites from images of skin is daunting due to the fine gradations among diverse bite types, variability in human skin response, and inconsistencies in image quality. Methods: For this work, we introduce DeepBiteNet, a new ensemble-based deep learning model designed to perform robust multiclass classification of insect bites from RGB images. Our model aggregates three semantically diverse convolutional neural networks—DenseNet121, EfficientNet-B0, and MobileNetV3-Small—using a stacked meta-classifier designed to aggregate their predicted outcomes into an integrated, discriminatively strong output. Our technique balances heterogeneous feature representation with suppression of individual model biases. Our model was trained and evaluated on a hand-collected set of 1932 labeled images representing eight classes, consisting of common bites such as mosquito, flea, and tick bites, and unaffected skin. Our domain-specific augmentation pipeline imputed practical variability in lighting, occlusion, and skin tone, thereby boosting generalizability. Results: Our model, DeepBiteNet, achieved a training accuracy of 89.7%, validation accuracy of 85.1%, and test accuracy of 84.6%, and surpassed fifteen benchmark CNN architectures on all key indicators, viz., precision (0.880), recall (0.870), and F1-score (0.875). Our model, optimized for mobile deployment with quantization and TensorFlow Lite, enables rapid on-client computation and eliminates reliance on cloud-based processing. Conclusions: Our work shows how ensemble learning, when carefully designed and combined with realistic data augmentation, can boost the reliability and usability of automatic insect bite diagnosis. Our model, DeepBiteNet, forms a promising foundation for future integration with mobile health (mHealth) solutions and may complement early diagnosis and triage in dermatologically underserved regions. Full article

Photoplethysmography (PPG) is a widely adopted optical technique for cardiovascular monitoring, but its accuracy is often compromised by skin pigmentation, which attenuates the signal in individuals with darker skin tones. This research addresses the challenge of skin pigmentation by developing a PPG sensor system with a novel gain calibration strategy. We present a hardware prototype integrating a programmable gain amplifier (PGA), specifically the OPA3S328 operational amplifier, controlled by a microcontroller. The system performs a one-time gain adjustment at initialization based on the user’s skin tone, which is quantified using RGB image analysis. This “set-and-hold” approach normalizes the signal amplitude across various skin tones while effectively preserving the native morphology of the PPG waveform, which is essential for advanced cardiovascular diagnostics. Experimental validation with over 70 human volunteers demonstrated the PGA’s ability to apply calibrated gain levels, derived from a first-degree polynomial relationship between skin pigmentation and red light absorption. This approach significantly improved signal consistency across different skin tones. The findings highlight the efficacy of pre-measurement gain correction for achieving reliable PPG sensing in diverse populations and lay the groundwork for future optimization of PPG sensor designs to improve reliability in wearable health monitoring devices. Full article

Lasers are widely employed in the treatment of melanocytic lesions. This scoping review evaluates 77 studies on the efficacy and safety of laser treatments for café-au-lait macules (CALMs), nevus of Ota (NOA), Becker’s nevus (BN), lichen planus pigmentosus (LPP), and other pigmented lesions. The Q-switched neodymium-doped yttrium aluminum garnet (Nd:YAG), particularly the 1064 nm, is the most frequently utilized laser, demonstrating strong efficacy for NOA and other dermal pigmentary disorders. Medium-wavelength lasers, including the Q-switched ruby and Alexandrite lasers, also show promise, though results vary based on lesion depth, skin type, and treatment protocols. Recurrence and adverse effects, including post-inflammatory hyperpigmentation (PIH) and hypopigmentation, are common, particularly in patients with darker skin tones. Future studies should standardize and optimize laser parameters across lesion types and skin tones, improve long-term efficacy, and prioritize inclusion of patients with diverse Fitzpatrick skin types to evaluate differential outcomes and promote equitable treatment efficacy. Full article

Skin diseases in melanin-rich skin often present diagnostic challenges due to the unique characteristics of darker skin tones, which can lead to misdiagnosis or delayed treatment. This disparity impacts millions within diverse communities, highlighting the need for accurate, AI-based diagnostic tools. In this paper, we investigated the performance of three machine learning methods -Support Vector Machines (SVMs), Random Forest (RF), and Decision Trees (DTs)-combined with state-of-the-art (SOTA) deep learning models, EfficientNet, MobileNetV2, and DenseNet121, for predicting skin conditions using dermoscopic images from the HAM10000 dataset. The features were extracted using the deep learning models, with the labels encoded numerically. To address the data imbalance, SMOTE and resampling techniques were applied. Additionally, Principal Component Analysis (PCA) was used for feature reduction, and fine-tuning was performed to optimize the models. The results demonstrated that RF with DenseNet121 achieved a superior accuracy of 98.32%, followed by SVM with MobileNetV2 at 98.08%, and Decision Tree with MobileNetV2 at 85.39%. The proposed methods overcome the SVM with the SOTA EfficientNet model, validating the robustness of the proposed approaches. Evaluation metrics such as accuracy, precision, recall, and F1-score were used to benchmark performance, showcasing the potential of these methods in advancing skin disease diagnostics for diverse populations. Full article

Traditional methods for skin color classification, such as visual assessments and conventional image classification, face limitations in accuracy and consistency under varying conditions. To address this, we developed AI Dermatochroma Analytica (AIDA), an unsupervised learning system designed to enhance dermatological diagnostics. AIDA applies clustering techniques to classify skin tones without relying on labeled data, evaluating over twelve models, including K-means, density-based, hierarchical, and fuzzy logic algorithms. The model’s key feature is its ability to mimic the process clinicians traditionally perform by visually matching the skin with the Fitzpatrick Skin Type (FST) palette scale but with enhanced precision and accuracy using Euclidean distance-based clustering techniques. AIDA demonstrated superior performance, achieving a 97% accuracy rate compared to 87% for a supervised convolutional neural network (CNN). The system also segments skin images into clusters based on color similarity, providing detailed spatial mapping aligned with dermatological standards. This segmentation reduces the uncertainty related to lighting conditions and other environmental factors, enhancing precision and consistency in skin color classification. This approach offers significant improvements in personalized dermatological care by reducing reliance on labeled data, improving diagnostic accuracy, and paving the way for future applications in diverse dermatological and cosmetic contexts. Full article

This literature review aims to comprehensively evaluate the clinical and dermoscopic presentations of common pediatric diseases among children with skin of color (SoC) while also addressing potential variations based on racial backgrounds. This review encompasses various conditions, such as nevi subtypes, viral infections, infestations, and inflammatory dermatoses, as well as hair diseases and abnormal vascular formations, occurring in pediatric populations. Overall, we identified 7 studies on nevi subtypes, 24 studies on skin infections, 6 on inflammatory dermatoses, 10 on hair diseases and disorders, and 14 on miscellaneous disorders that also satisfied our SoC- and race-specific criteria. In case of no results, we assumed that dermoscopic findings are similar between SoC adults and children, confirming the hypothesis with our cases of dark-skinned Indian child patients. Inflammatory dermatoses such as psoriasis, eczema, and cutaneous mastocytosis, as well as skin infections like cutaneous leishmaniasis, appear with brownish backgrounds or exhibit dark structures more frequently than the respective dermoscopy images of Caucasian populations. Dermoscopy traits such as erythema in tinea capitis are uncommon or even absent on a dark-colored scalp, while a dark skin tone often obscures many characteristic features, such as dark and yellow dots in alopecia areata and even parts of an intradermal parasite in the case of scabies. Race-specific traits were also observed, such as corkscrew hair in tinea capitis, primarily seen in patients of African origin. Many dermoscopic images are consistent between SoC and non-SoC in various skin lesions, including vascular anomalies, juvenile xanthogranuloma, mastocytoma, and viral skin lesions like molluscum contagiosum, as well as in various hair disorders such as trichotillomania, while tinea capitis displays the most diverse reported dermoscopic features across SoC- and race-specific studies. Full article

Knowledge of a person’s level of skin pigmentation, or so-called “skin tone”, has proven to be an important building block in improving the performance and fairness of various applications that rely on computer vision. These include medical diagnosis of skin conditions, cosmetic and skincare support, and face recognition, especially for darker skin tones. However, the perception of skin tone, whether by the human eye or by an optoelectronic sensor, uses the reflection of light from the skin. The source of this light, or illumination, affects the skin tone that is perceived. This study aims to refine and assess a convolutional neural network-based skin tone estimation model that provides consistent accuracy across different skin tones under various lighting conditions. The 10-point Monk Skin Tone Scale was used to represent the skin tone spectrum. A dataset of 21,375 images was captured from volunteers across the pigmentation spectrum. Experimental results show that a regression model outperforms other models, with an estimated-to-target distance of 0.5. Using a threshold estimated-to-target skin tone distance of 2 for all lights results in average accuracy values of 85.45% and 97.16%. With the Monk Skin Tone Scale segmented into three groups, the lighter exhibits strong accuracy, the middle displays lower accuracy, and the dark falls between the two. The overall skin tone estimation achieves average error distances in the LAB space of $16.40\pm 20.62$. Full article

This paper presents the preliminary results of an investigation on the unexplored topic of polychromy on provincial stone sculptures from the Roman provinces in Germania through the innovative application of heritage materials science techniques. A group of three life-sized statues dating to the 1st Century CE recovered from Ingelheim, near Mainz, retains remarkably well-preserved traces of pigments. These are ripe for emerging non-invasive technologies supplemented by micro-sampling to validate results and provide information relating to mixing and layering not available to the naked eye. The most strikingly visible areas of extant polychromy were retained on the sculpture of a young woman, reported on here as the first phase of this programme of research. The results suggest that the statue was originally covered in a gypsum layer before the application of complex and diverse recipes of pigment applied as mixtures and in layers to create required hues and shadowing on sculpted features. The palette includes ochres and green earth mixed with small amounts of minium (red lead), realgar and lapis lazuli (ultramarine blue) added to create skin tones, and a vibrant blue-green tunic created from Egyptian blue, bone black, ochres, cinnabar and green earth; the palla and peplos contained ochres, bone black, and orpiment, and mixes of these created the detail of coloured jewellery. Of great interest was the detection of bone black on many features, particularly as a shading agent to enhance sculpted features, such as folds in cloth, providing a more realistic and flowing articulation. This is a revolutionary observation that provides previously unexplored insights into artistic polychromic practice in Antiquity. Full article

Artificial intelligence (AI), notably Generative Adversarial Networks, has the potential to transform medical and patient education. Leveraging GANs in medical fields, especially cosmetic surgery, provides a plethora of benefits, including upholding patient confidentiality, ensuring broad exposure to diverse patient scenarios, and democratizing medical education. This study investigated the capacity of AI models, DALL-E 2, Midjourney, and Blue Willow, to generate realistic images pertinent to cosmetic surgery. We combined the generative powers of ChatGPT-4 and Google’s BARD with these GANs to produce images of various noses, faces, and eyelids. Four board-certified plastic surgeons evaluated the generated images, eliminating the need for real patient photographs. Notably, generated images predominantly showcased female faces with lighter skin tones, lacking representation of males, older women, and those with a body mass index above 20. The integration of AI in cosmetic surgery offers enhanced patient education and training but demands careful and ethical incorporation to ensure comprehensive representation and uphold medical standards. Full article

Neonatal jaundice is a prevalent condition among newborns, with potentially severe complications that can result in permanent brain damage if left untreated during its early stages. The existing approaches for jaundice detection involve invasive procedures such as blood sample collection, which can inflict pain and distress on the patient, and may give rise to additional complications. Alternatively, a non-invasive method using image-processing techniques and implementing kNN, Random Forest, and XGBoost machine learning algorithms as a classifier can be employed to diagnose jaundice, necessitating a comprehensive database of infant images to achieve a diagnosis with high accuracy. This data article presents the NJN collection, a repository of newborn images encompassing diverse birthweights and skin tones, spanning an age range of 2 to 8 days. The dataset is accompanied by an Excel sheet file in CSV format containing the RGB and YCrCb channel values, as well as the status of each sample. The dataset and associated resources are openly accessible at Zenodo website. Moreover, the Python code for data testing utilizing various AI techniques is provided. Consequently, this article offers an unparalleled resource for AI researchers, enabling them to train their AI systems and develop algorithms that can assist neonatal intensive care unit (NICU) healthcare specialists in monitoring neonates while facilitating the fast, real-time, non-invasive, and accurate diagnosis of jaundice. Full article

The impacts of the lack of skin tone diversity in medical education images on healthcare professionals (HCPs) and patients are not well studied. The aim of this study was to assess the diagnostic knowledge of HCPs and correlate this with confidence and training resources used. An online multiple choice quiz was developed. The participants’ demographics, training resources and self-confidence in diagnosing skin conditions were collected. The differences in the results between the subgroups and the correlations between the respondents’ experience, self-reported confidence and quiz results were assessed. The mean score of 432 international participants was 5.37 (SD 1.75) out of a maximum of 10 (highest score). Eleven percent (n = 47) reached the 80% pass mark. Subanalysis showed no difference by the continent (p = 0.270), ethnicity (p = 0.397), profession (p = 0.599), training resources (p = 0.198) or confidence (p = 0.400). A significance was observed in the specialty (p = 0.01). A weak correlation between experience and confidence (Spearman’s ρ = 0.286), but no correlation between scores and confidence or experience (ρ = 0.087 and 0.076), was observed. Of diagnoses, eczema was recognised in 40% and meningococcal rash in 61%. This is the first study assessing the identification of paediatric skin conditions in different skin tones internationally. The correct identification of common/important paediatric conditions was poor, suggesting a possible difference in knowledge across skin tones. There is an urgent need to improve the representation of all skin tones to ensure equity in patient care. Full article

Cardiovascular disease is the leading cause of death globally. To provide continuous monitoring of blood pressure (BP), a parameter which has shown to improve health outcomes when monitored closely, many groups are trying to measure blood pressure via noninvasive photoplethysmography (PPG). However, the PPG waveform is subject to variation as a function of patient-specific and device factors and thus a platform to enable the evaluation of these factors on the PPG waveform and subsequent hemodynamic parameter prediction would enable device development. Here, we present a computational workflow that combines Monte Carlo modeling (MC), gaussian combination, and additive noise to create synthetic dataset of volar fingertip PPG waveforms representative of a diverse cohort. First, MC is used to determine PPG amplitude across age, skin tone, and device wavelength. Then, gaussian combination generates accurate PPG waveforms, and signal processing enables data filtration and feature extraction. We improve the limitations of current synthetic PPG frameworks by enabling inclusion of physiological and anatomical effects from body site, skin tone, and age. We then show how the datasets can be used to examine effects of device characteristics such as wavelength, analog to digital converter specifications, filtering method, and feature extraction. Lastly, we demonstrate the use of this framework to show the insensitivity of a support vector machine predictive algorithm compared to a neural network and bagged trees algorithm. Full article

Racial disparities in education have put a spotlight on the role of teachers and the school environment that is created for students. As teachers are seen as a vital element of school climate, the interactions between teachers and students can have a significant effect on students’ success. The purpose of this study was to examine the associations between race, skin tone, and teacher–student relationship (TSR) quality. Data drawn from the Fragile Families and Child Wellbeing Study included 995 ethnically and racially diverse adolescents. Hierarchical regression analyses revealed that being Black, Hispanic, or Multi-racial was significantly associated with TSRs. However, there were no between-group differences in TSRs across racial categories. Skin tone was not a significant predictor of TSRs and did not moderate the relationship between race and TSRs. Findings raise important implications for teacher training and professional development focused on culturally relevant practices that support optimal student interactions and provide promising evidence for school connectedness as an intervening mechanism in improving TSR quality, particularly for students of color. Full article

Skin problems are among the most common ailments on Earth. Despite its popularity, assessing it is not easy because of the complexities in skin tones, hair colors, and hairstyles. Skin disorders provide a significant public health risk across the globe. They become dangerous when they enter the invasive phase. Dermatological illnesses are a significant concern for the medical community. Because of increased pollution and poor diet, the number of individuals with skin disorders is on the rise at an alarming rate. People often overlook the early signs of skin illness. The current approach for diagnosing and treating skin conditions relies on a biopsy process examined and administered by physicians. Human assessment can be avoided with a hybrid technique, thus providing hopeful findings on time. Approaches to a thorough investigation indicate that deep learning methods might be used to construct frameworks capable of identifying diverse skin conditions. Skin and non-skin tissue must be distinguished to detect skin diseases. This research developed a skin disease classification system using MobileNetV2 and LSTM. For this system, accuracy in skin disease forecasting is the primary aim while ensuring excellent efficiency in storing complete state information for exact forecasts. Full article

A real-time Bangla Sign Language interpreter can enable more than 200 k hearing and speech-impaired people to the mainstream workforce in Bangladesh. Bangla Sign Language (BdSL) recognition and detection is a challenging topic in computer vision and deep learning research because sign language recognition accuracy may vary on the skin tone, hand orientation, and background. This research has used deep machine learning models for accurate and reliable BdSL Alphabets and Numerals using two well-suited and robust datasets. The dataset prepared in this study comprises of the largest image database for BdSL Alphabets and Numerals in order to reduce inter-class similarity while dealing with diverse image data, which comprises various backgrounds and skin tones. The papers compared classification with and without background images to determine the best working model for BdSL Alphabets and Numerals interpretation. The CNN model trained with the images that had a background was found to be more effective than without background. The hand detection portion in the segmentation approach must be more accurate in the hand detection process to boost the overall accuracy in the sign recognition. It was found that ResNet18 performed best with 99.99% accuracy, precision, F1 score, sensitivity, and 100% specificity, which outperforms the works in the literature for BdSL Alphabets and Numerals recognition. This dataset is made publicly available for researchers to support and encourage further research on Bangla Sign Language Interpretation so that the hearing and speech-impaired individuals can benefit from this research. Full article