Search Results (64)

Forensic DNA phenotyping (FDP) is an important innovation approach in forensics sciences, especially when traditional DNA profiling results are limited, mostly due to the absence of reference samples. FDP is based on the detection of genetic variants in specific genes whose function is related to pigmentation mechanisms and uses the genotypes found in the sample to determine the externally visible traits (EVT) such as the iris, hair, and skin tone or color of the individual; this prediction would help and expedite human identification processes and solve criminal cases. Several technologies have been developed to facilitate EVT prediction; however, most of them have been validated only in European populations. Implementing techniques for FDP in Latin American countries is essential given the problems of disappearance and human identification that have persisted for years. Nonetheless, scientists have a great challenge due to the admixed genetic structure of the population. This review explores the current application of FDP, emphasizing its significance, practical uses, and limitations within Latin American populations. Full article

Background/Objectives: Deep models have achieved remarkable progress in the diagnosis of skin lesions but face two significant drawbacks. First, they cannot effectively explain the basis of their predictions. Although attention visualization tools like Grad-CAM can create heatmaps using deep features, these features often have large receptive fields, resulting in poor spatial alignment with the input image. Second, the design of most deep models neglects interpretable traditional visual features inspired by clinical experience, such as color–texture and edge features. This study aims to propose a novel approach integrating deep learning with traditional visual features to handle these limitations. Methods: We introduce the edge- and color–texture-aware bag-of-local-features model (ECT-BoFM), which limits the receptive field of deep features to a small size and incorporates edge and color–texture information from traditional features. A non-rigid reconstruction strategy ensures that traditional features enhance rather than constrain the model’s performance. Results: Experiments on the ISIC 2018 and 2019 datasets demonstrated that ECT-BoFM yields precise heatmaps and achieves high diagnostic performance, outperforming state-of-the-art methods. Furthermore, training models using only a small number of the most predictive patches identified by ECT-BoFM achieved diagnostic performance comparable to that obtained using full images, demonstrating its efficiency in exploring key clues. Conclusions: ECT-BoFM successfully combines deep learning and traditional visual features, addressing the interpretability and diagnostic accuracy challenges of existing methods. ECT-BoFM provides an interpretable and accurate framework for skin lesion diagnosis, advancing the integration of AI in dermatological research and clinical applications. Full article

The absence of skin color information in skin cancer datasets poses a significant challenge for accurate diagnosis using artificial intelligence models, particularly for non-white populations. In this paper, based on the Monk Skin Tone (MST) scale, which is less biased than the Fitzpatrick scale, we propose MST-AI, a novel method for detecting skin color in images of large datasets, such as the International Skin Imaging Collaboration (ISIC) archive. The approach includes automatic frame, lesion removal, and lesion segmentation using convolutional neural networks, and modeling normal skin tones with a Variational Bayesian Gaussian Mixture Model (VB-GMM). The distribution of skin color predictions was compared with MST scale probability distribution functions (PDFs) using the Kullback-Leibler Divergence (KLD) metric. Validation against manual annotations and comparison with K-means clustering of image and skin mean RGBs demonstrated the superior performance of the MST-AI, with Kendall’s Tau, Spearman’s Rho, and Normalized Discounted Cumulative Gain (NDGC) of 0.68, 0.69, and 1.00, respectively. This research lays the groundwork for developing unbiased AI models for early skin cancer diagnosis by addressing skin color imbalances in large datasets. Full article

Accurate skin color reproduction under varying CCT remains a critical challenge in the graphic arts, impacting applications such as face recognition, portrait photography, and human–computer interaction. Traditional AWB methods like gray-world or max-RGB often rely on statistical assumptions, which limit their accuracy under complex or extreme lighting. We propose SCR-AWB, a novel algorithm that leverages real skin reflectance data to estimate the scene illuminant’s SPD and CCT, enabling accurate skin tone reproduction. The method integrates prior knowledge of human skin reflectance, basis vectors, and camera sensitivity to perform pixel-wise spectral estimation. Experimental results on difficult skin color reproduction task demonstrate that SCR-AWB significantly outperforms traditional AWB algorithms. It achieves lower reproduction angle errors and more accurate CCT predictions, with deviations below 300 K in most cases. These findings validate SCR-AWB as an effective and computationally efficient solution for robust skin color correction. Full article

Studying fruit genetic trends, heterosis, and growth traits in pear hybrid progeny provides the foundation for variety breeding. The aim of this research is to reveal the trait performance of the hybrid progeny of Chinese white pear and Western pear and provide a theoretical basis for other breeders to predict the trait performance of their hybrid progeny when selecting Eastern pear and Western pear as parents. Our research team constructed a ‘Yuluxiang’ × ‘Xianghongli’ interspecific hybrid population in 2015, and in 2023, we conducted a two-year investigation of 16 traits in 140 hybrid progeny, including 11 fruit traits and 5 growth traits, and analyzed and compared the genetic variation and heterosis of traits, as well as the correlation between various traits. The results showed that the hybrid progeny was widely segregated for single fruit weight (FW), soluble solid (SS) content, and titratable acid (TA) content and conformed to a normal distribution, with quantitative genetic traits under polygenic control. The highest two-year coefficients of variation for TA were 54.42% in 2023 and 39.17% in 2024. A genetic trend of decreasing FW was observed, which was greatly influenced by the male sex. The ratio of soft soluble flesh to crispy flesh was 1:1, and the gene controlling this trait may be a quality trait controlled by a single gene. The traits that showed transgressive heterosis for two years included fruit longitudinal diameter (FLoD), fruit shape index (FSI), and TA, and those that showed negative heterosis included FW, SS, leaf longitudinal diameter (LLoD), and leaf lateral diameter (LLaD). Correlation analysis indicated that the progeny of crosses in this combination, which had red fruit skin, may also present red early flowering color (EFC) and young leaf color (YLC), reddish brown annual branch color (ABC), and lower FSI, fruit stalk length (FSL), LLaD, and TA. Thus, at the seedling stage, individuals with red-colored fruit may be screened by observing the color of young leaves and young stems and the lateral diameter of the leaves. Principal component analysis showed that among the 16 traits included in six principal components, peel color (PC), FLoD, 2024SS, fruit tape (FT), and FSI were the main factors causing differences in fruit phenotypes. This study systematically elucidated the genetic trends of agronomic traits in pears and will provide a theoretical basis for the selection of parents and early selection of hybrid progeny in pear hybrid breeding. Full article

This research aims to investigate and quantify the possible presence of microplastics (MPs) in usual skin-cleansing products (i.e., liquid soap, micellar water, and micellar cleansing oil), the most popular from the market in terms of brand and customer confidence. Therefore, optical microscopy and micro-Fourier transform infrared spectroscopy (micro-FTIR) were used to determine the MPs’ number, color, shape, size, and chemical composition. For the first time, the results were correlated with the possible exposure paths (i.e., inhalation, ingestion, or adsorption) to assess the human health risk of the analyzed micellar-based cleansers in terms of chronic total exposure dose to microplastics. Finally, a statistical analysis was added to this study for source prediction of MPs in skin-cleansing samples in terms of morphology, chemical composition, and other factors (i.e., brand, packaging, etc.). The various exposures and toxicities of MPs were assessed in terms of potential health risk, knowing that their toxic effect depends on the polymeric structure strongly linked with the size, shape, and concentration in the products. Full article

Forensic DNA phenotyping (FDP) has emerged as an essential tool in criminal investigations, enabling the prediction of physical traits based on genetic information. This review explores the genetic factors influencing skin pigmentation, particularly within Asian populations, with a focus on Thailand. Key genes such as Oculocutaneous Albinism II (OCA2), Dopachrome Tautomerase (DCT), KIT Ligand (KITLG), and Solute Carrier Family 24 Member 2 (SLC24A2) are examined for their roles in melanin production and variations that lead to different skin tones. The OCA2 gene is highlighted for its role in transporting ions that help stabilize melanosomes, while specific variants in the DCT gene, including single nucleotide polymorphisms (SNPs) rs2031526 and rs3782974, are discussed for their potential effects on pigmentation in Asian groups. The KITLG gene, crucial for developing melanocytes, includes the SNP rs642742, which is linked to lighter skin in East Asians. Additionally, recent findings on the SLC24A2 gene are presented, emphasizing its connection to pigmentation through calcium regulation in melanin production. Finally, the review addresses the ethical considerations of using FDP in Thailand, where advances in genetic profiling raise concerns about privacy, consent, and discrimination. Establishing clear guidelines is vital to balancing the benefits of forensic DNA applications with the protection of individual rights. Full article

Neonatal jaundice affects over 80% of newborns globally, posing significant health risks if untreated. Current diagnostic methods either lack accuracy or are prohibitively expensive, limiting accessibility in low-resource settings. This study presents a cost-effective, wearable device for non-invasive bilirubin monitoring based on forehead skin tone analysis. The device, comprising a TCS34725 color sensor and ESP32-C3 microcontroller, offers real-time bilirubin predictions validated against standard clinical methods. Calibration ensures reproducibility across devices, with recovery rates of 91–107%, meeting analytical validation standards. This innovation has the potential to revolutionize neonatal care by providing accessible, sustainable, and accurate monitoring, especially in underserved regions. Full article

Melanogenesis, the biological process responsible for melanin synthesis, plays a crucial role in determining skin and hair color, photoprotection, and serving as a biomarker in various diseases. While various factors regulate melanogenesis, the role of fatty acids in this process remains underexplored. This study investigated the anti-melanogenic properties of 10(E)-pentadecenoic acid (10E-PDA) through both in silico and in vitro analyses. SwissSimilarity was utilized to predict the functional properties of 10E-PDA by comparing it with structurally similar lipids known to exhibit anti-melanogenic effects. Subsequent in vitro experiments demonstrated that 10E-PDA significantly reduced melanin production and intracellular tyrosinase activity in α-MSH (melanocyte-stimulating hormone)-stimulated B16F10 melanoma cells without exhibiting significant cytotoxicity at concentrations up to 15 μM. Further mechanistic studies revealed that 10E-PDA inhibited the nuclear translocation of microphthalmia-associated transcription factor (MITF), consistent with the decrease observed in p-MITF protein levels. It also decreased the mRNA levels of tyrosinase-related proteins (TRP-1, TRP-2) and tyrosinase, while reducing the protein levels of TRP-1 and tyrosinase, but not TRP-2. These findings suggest that 10E-PDA exerts its anti-melanogenic effects by modulating the MITF/tyrosinase axis, presenting potential therapeutic implications for skin pigmentation disorders. Full article

Predicting the post-storage quality of cherry fruits is crucial for determining their suitability for long-distance shipping or domestic distribution. This study aimed to forecast key quality attributes of Staccato sweet cherries after storage, simulating shipping conditions, by analyzing spring soil, leaf, fruitlet, and at-harvest data from thirty orchards in the Okanagan Valley, British Columbia, Canada, over two years. A support vector machine (SVM) was used to predict post-storage variables, with pre-harvest and at-harvest data selected by a genetic algorithm. The SVM accurately predicted soluble solids (R² = 0.88), firmness (R² = 0.83), and acidity (R² = 0.79) after four weeks of storage, as well as visual disorders like slip skin and stem browning. Spring soil properties (Ca, Mg), leaf (N, Ca, Mg, Fe, Zn, B), and fruitlet data (N, Ca, Mg, B) were key predictors. Leaf Ca was vital for firmness and total soluble solids (TSS) prediction, while N in leaves and fruitlets influenced firmness, acidity, and disorders. Leaf Zn helped predict weight and acidity/TSS ratio, and Mg impacted fruit color. Pre-harvest leaf nutrition measured 3–4 weeks before harvest, proved most effective in predicting post-storage quality. Full article

The present study discusses the technofunctional properties (color, texture) of grilled chicken with both objective (colorimeter, texture profile) analysis and subjective (sensory) analysis. Besides them, the total content of potentially carcinogenic heterocyclic amines (HCAs) was also monitored by the applied grilling time–temperature combinations. The same samples were analyzed during the heat treatment of chicken breast samples for 5–15 min at 150–230 °C on an electric contact grill. The grilling variables included the effect of skin cover. Among the structural parameters, hardness exhibited a significant difference between the groups of skin-covered and not-covered ones, and in this case, a linear connection was also found with the time and temperature values, respectively. The structural parameters obtained by sensory and instrumental analysis were compared to each other. In addition, the structural parameters were compared to the color ones (sensory, color according to the CIELAB system: brightness, redness, and yellowness) and to the total HCA content. In the case of closed grilling, sensory-evaluated parameters such as juiciness and tenderness showed a strong negative correlation to instrumentally measured hardness (R = −0.879; −0.749) and chewiness (R = −0.872; −0.718) due to the water loss from the increase in grilling temperature and time. The total HCA content positively correlated to chewiness (R = 0.789). The sensory color parameter and the brightness had a strong connection with juiciness (R = 0.738; 0.723), hardness (R = −0.795; −0.706), and chewiness (R = −0.843; −0.818); redness showed positive correlation to cohesiveness (R = 0.764) and chewiness (R = 0.829). Accordingly, juiciness and chewiness showed a connection to the total HCA levels, which makes it possible to carry out further research on instrumental and sensory parameters that may predict the formation of hazardous amounts of carcinogenic heterocyclic amines. Full article

Background/Objectives: Understanding and predicting human pigmentation traits is crucial for individual identification. Genome-wide association studies have revealed numerous pigmentation-associated SNPs, indicating genetic overlap among pigmentation traits and offering the potential to develop predictive models without the need for analyzing large numbers of SNPs. Methods: In this study, we assessed the performance of the HIrisPlex-S system, which predicts eye, hair, and skin color, on 412 individuals from the Spanish population. Model performance was calculated using metrics including accuracy, area under the curve, sensitivity, specificity, and positive and negative predictive value. Results: Our results showed high prediction accuracies (70% to 97%) for blue and brown eyes, brown hair, and intermediate skin. However, challenges arose with the remaining categories. The model had difficulty distinguishing between intermediate eye colors and similar shades of hair and exhibited a significant percentage of individuals with incorrectly predicted dark and pale skin, emphasizing the importance of careful interpretation of final predictions. Future studies considering quantitative pigmentation may achieve more accurate predictions by not relying on categories. Furthermore, our findings suggested that not all previously established SNPs showed a significant association with pigmentation in our population. For instance, the number of markers used for eye color prediction could be reduced to four while still maintaining reasonable predictive accuracy within our population. Conclusions: Overall, our results suggest that it may be possible to reduce the number of SNPs used in some cases without compromising accuracy. However, further validation in larger and more diverse populations is essential to draw firm conclusions and make broader generalizations. Full article

Artificial Intelligence and Deepfake Technologies have brought a new dimension to the generation of fake data, making it easier and faster than ever before—this fake data could include text, images, sounds, videos, etc. This has brought new challenges that require the faster development of tools and techniques to avoid fraudulent activities at pace and scale. Our focus in this research study is to empirically evaluate the use and effectiveness of deep learning models such as Convolutional Neural Networks (CNNs) and Patch-based Neural Networks in the context of successful identification of real and fake images. We chose the healthcare domain as a potential case study where the fake medical data generation approach could be used to make false insurance claims. For this purpose, we obtained publicly available skin cancer data and used recently introduced stable diffusion approaches—a more effective technique than prior approaches such as Generative Adversarial Network (GAN)—to generate fake skin cancer images. To the best of our knowledge, and based on the literature review, this is one of the few research studies that uses images generated using stable diffusion along with real image data. As part of the exploratory analysis, we analyzed histograms of fake and real images using individual color channels and averaged across training and testing datasets. The histogram analysis demonstrated a clear change by shifting the mean and overall distribution of both real and fake images (more prominent in blue and green) in the training data whereas, in the test data, both means were different from the training data, so it appears to be non-trivial to set a threshold which could give better predictive capability. We also conducted a user study to observe where the naked eye could identify any patterns for classifying real and fake images, and the accuracy of the test data was observed to be 68%. The adoption of deep learning predictive approaches (i.e., patch-based and CNN-based) has demonstrated similar accuracy (~100%) in training and validation subsets of the data, and the same was observed for the test subset with and without StratifiedKFold (k = 3). Our analysis has demonstrated that state-of-the-art exploratory and deep-learning approaches are effective enough to detect images generated from stable diffusion vs. real images. Full article

In recent years, due to breeding improvements, strawberries with low anthocyanin content and a white rind are now available, and they are highly valued in the market. Strawberries with white skin color do not turn red when ripe, making it difficult to judge ripeness. The soluble solids content (SSC) is an indicator of fruit quality and is closely related to ripeness. In this study, visible–near-infrared (Vis-NIR) spectroscopy and near-infrared (NIR) spectroscopy are used for non-destructive evaluation of the SSC. Vis-NIR (500–978 nm) and NIR (908–1676 nm) data collected from 180 samples of “Tochigi iW1 go” white strawberries and 150 samples of “Tochigi i27 go” red strawberries are investigated. The white strawberry SSC model developed by partial least squares regression (PLSR) in Vis-NIR had a determination coefficient R²_p of 0.89 and a root mean square error prediction (RMSEP) of 0.40%; the model developed in NIR showed satisfactory estimation accuracy with an R²_p of 0.85 and an RMSEP of 0.43%. These estimation accuracies were comparable to the results of the red strawberry model. Absorption derived from anthocyanin and chlorophyll pigments in white strawberries was observed in the Vis-NIR region. In addition, a dataset consisting of red and white strawberries can be used to predict the pigment-independent SSC. These results contribute to the development of methods for a rapid fruit sorting system and the development of an on-site ripeness determination system. Full article

The color potato has the function of both a food and vegetable. The color potato not only contains various amino acids and trace elements needed by the human body but also contains anthocyanins. Anthocyanins have many functions, such as antioxidation, inflammation inhibition, vision improvement, and cancer prevention, so colored potatoes are deeply loved by consumers and have good market prospects. However, at present, the detection of anthocyanin content in color potatoes mainly depends on chemical methods, which are time-consuming and laborious, so it is necessary to study a fast and accurate detection method. In this study, microscopic hyperspectral equipment was used to collect the spectral information of the outer skin and inner skin of potatoes. The original spectrum, pretreatment spectrum, and characteristic spectrum variables of the outer skin and inner skin were predicted by the convolution neural network (CNN) algorithm and partial least squares regression (PLS) algorithm, respectively, and the performance of the model was evaluated by the prediction set correlation coefficient (Rp), prediction set root mean square error (RMSEP), correction set correlation coefficient (Rc), correction set root mean square error (RMSEC), and residual prediction deviation (RPD). The results revealed that the inner skin Raw + CNN model constructed under raw spectral data is optimal with Rc = 0.9508, RMSEC = 0.0374%, Rp = 0.9461, RMSEP = 0.2361% and RPD = 4.4933. The inner skin Savitzky-Golay (SG) + Detrend (DET) + CNN model constructed from pre-processed spectral data is optimal with Rc = 0.9499, RMSEC = 0.0359%, Rp = 0.9439, RMSEP = 0.2384%, RPD = 4.6516. The inner skin DET + competitive adaptive reweighted sampling (CARS) +CNN model constructed from the feature-based spectral data was optimal with Rc = 0.9527, RMSEC = 0.0708%, Rp = 0.9457, RMSEP = 0.2711%, and RPD = 4.1623. It can be seen that the Rp, RMSEP, Rc, RMSEC, and RPD values for modeling the spectral information of the inner skin were higher than those of the outer skin under the three different spectral data. The prediction accuracy of the model built by the CNN algorithm was better than the conventional algorithm PLS, the application of the CNN algorithm in inner skin can achieve accurate prediction of anthocyanin content in potato. Full article