Skin Imaging Research Articles

Estimation of Scattering Properties Modifications Caused by InVivo Human Skin Optical Clearing Using Line-Field Confocal Optical Coherence Tomography.

The image contrast and probing depth of optical methods applied to invivo skin could be improved by reducing skin scattering using the optical clearing method. The aim of this study was to quantify, from line-field confocal optical coherence tomography (LC-OCT) 3D images, the modifications of skin scattering properties invivo during optical clearing. Nine mixtures of optical clearing agents were used in combination with physical and chemical permeation enhancers on the human skin of three healthy volunteers. Scattering coefficient and anisotropy factor of the epidermis and the upper dermis were estimated from the 3D LC-OCT images of skin using an exponential decay model of the in-depth intensity profile. We were able to demonstrate a decrease in epidermal scattering (down to 33%) related to optical clearing, with the best results obtained by a mixture of polyethylene glycol, oleic acid, and propylene glycol.

An Analysis of the Diversity of Skin Colour Representation in Paediatric Nursing Practitioner Textbooks.

Our study aims to analyse 8 commonly used textbooks to determine how diverse skin tones are represented in paediatric nursing practitioner education. Literature reviewed from 2016 to 2024 demonstrated that the lack of darkly pigmented skin colour representation in health science education leads to diminished patient outcomes for these populations. Our study sought to study representation teaching images and eight commonly referenced nursing textbooks were chosen for this study, given their use in paediatric nurse practitioner education. Of the eight textbooks selected, five were analysed based on inclusion criteria. Two investigators trained in skin prototyping coded each textbook for skin colour representation and coded during 2023-2024. Coders used the widely accepted prototyping scale, the Fitzpatrick Scale (range I-VI, with I being the lightest colour skin and VI the darkest). Teaching photographs were defined as all photos used to provide insight into a disease or diagnostic technique that included human skin. Two individual coders coded and documented data, ensuring each coder was blinded to the overall results. Our analysis of 5 textbooks revealed that 2112 images met the criteria as teaching images. Of the 2112 teaching images, 593.5 included images of type IV-VI skin (darkly pigmented skin), resulting in a 28% representation of dark skin tone images. Additionally, 2 of the 82 total illustrations included patients with dark skin tones, indicating a representation of 2.5%. However, chapters addressing conditions of child abuse/neglect (55.95%) and stigmatised social issues (infectious disease, 54.88%) displayed a disproportionate representation of patients from these demographics. Our results highlight the importance of enhancing equitable representation in educational resources for nursing practitioners. There is room to collaborate with other health science institutions to establish clear guidelines for future improvement in expanding teaching images to include diversity representation in education. No patient or public contribution.

Equitable Skin Disease Prediction Using Transfer Learning and Domain Adaptation

In the realm of dermatology, the complexity of diagnosing skin conditions manually necessitates the expertise of dermatologists. Accurate identification of various skin ailments, ranging from cancer to inflammatory diseases, is paramount. However, existing artificial intelligence (AI) models in dermatology face challenges, particularly in accurately diagnosing diseases across diverse skin tones, with a notable performance gap in darker skin. Additionally, the scarcity of publicly available, unbiased datasets hampers the development of inclusive AI diagnostic tools. To tackle the challenges in accurately predicting skin conditions across diverse skin tones, we employ a transfer-learning approach that capitalizes on the rich, transferable knowledge from various image domains. Our method integrates multiple pre-trained models from a wide range of sources, including general and specific medical images, to improve the robustness and inclusiveness of the skin condition predictions. We rigorously evaluated the effectiveness of these models using the Diverse Dermatology Images (DDI) dataset, which uniquely encompasses both underrepresented and common skin tones, making it an ideal benchmark for assessing our approach. Among all methods, Med-ViT emerged as the top performer due to its comprehensive feature representation learned from diverse image sources. To further enhance performance, we conducted domain adaptation using additional skin image datasets such as HAM10000. This adaptation significantly improved model performance across all models.

Age and gender differences in skin characteristics: a study of 2543 Japanese individuals using advanced skin imaging techniques

Age and gender differences in skin characteristics: a study of 2543 Japanese individuals using advanced skin imaging techniques

TEC-CNN: Towards Efficient Compressing Convolutional Neural Nets with Low-rank Tensor Decomposition

Most state-of-the-art convolutional neural networks (CNNs) are characterised by excessive parameterisation, leading to a high computational burden. Tensor decomposition has emerged as a model reduction technique for compressing deep neural networks. Previous approaches have predominantly relied on either Tucker decomposition or Canonical Polyadic (CP) decomposition for CNNs. However, CP decomposition exhibits exceptional compression capabilities in comparison to Tucker decomposition, which results in a more pronounced accuracy loss. This paper introduces an efficient model compression method, termed TEC-CNN, designed to achieve significant compression while preserving accuracy levels comparable to those of the original models. In TEC-CNN, convolutional layers are identified to obtain convolutional kernels by analysing given models under the principles of low-rank tensor decomposition, and then, calculating the ranks of convolutional kernels. Furthermore, an efficient decomposition schema for the convolutional kernel is proposed with approximate kernel tensor for reducing parameters. Additionally, a novel format of a convolutional sequence is presented and constructed with a reduced number of parameters to replace the original convolutional layers. Finally, the effectiveness of TEC-CNN is assessed across a range of computer vision tasks. For instance, in CIFAR-100 classification, ResNet18 is compressed to 4.1 MB, while Unext, when applied to image segmentation using the International Skin Imaging Collaboration (ISIC) dataset, is reduced to 3.419 MB. When employed for fire object detection with Yolov7, TEC-CNN achieves a model size reduction of 71.6 MB. Comprehensive experimental results underscore that our approach achieves significant model compression while preserving model performance.

Leveraging convolutional neural networks and hashing techniques for the secure classification of monkeypox disease

The World Health Organization declared a state of emergency in 2022 because of monkeypox. This disease has raised international concern as it has spread beyond Africa, where it is endemic. The global community has shown attention and solidarity in combating this disease as its daily increase becomes evident. Various skin symptoms appear in people infected with this disease, which can spread easily, especially in a polluted environment. It is difficult to diagnose monkeypox in its early stages because of its similarity with the symptoms of other diseases such as chicken pox and measles. Recently, computer-aided classification methods such as deep learning and machine learning within artificial intelligence have been employed to detect various diseases, including COVID-19, tumor cells, and Monkeypox, in a short period and with high accuracy. In this study, we propose the CanDark model, an end-to-end deep-learning model that incorporates cancelable biometrics for diagnosing Monkeypox. CanDark stands for cancelable DarkNet-53, which means that DarkNet-53 CNN is utilized for extracting deep features from Monkeypox skin images. Then a cancelable method is applied to these features to protect patient information. Various cancelable techniques have been evaluated, such as bio-hashing, multilayer perceptron (MLP) hashing, index-of-maximum Gaussian random projection-based hashing (IoM-GRP), and index-of-maximum uniformly random permutation-based hashing (IoM-URP). The proposed approach’s performance is evaluated using various assessment issues such as accuracy, specificity, precision, recall, and fscore. Using the IoM-URP, the CanDark model is superior to other state-of-the-art Monkeypox diagnostic techniques. The proposed framework achieved an accuracy of 98.81%, a specificity of 98.73%, a precision of 98.9%, a recall of 97.02%, and fscore of 97.95%.

HGLeNet DEEP LEARNING FOR SKIN CANCER DETECTION WITH SKIN LESION SEGMENTATION

Skin cancer is deemed to be the most dangerous type of cancer. It occurs due to the damage caused to the DNA and if left untreated can lead to death. Various methods have been devised over the last few years for skin cancer detection. However, their performance was affected by various challenges in image analysis, like color illumination variations, differences in shape, size, etc. Therefore, to tackle these issues the novel framework, deep learning (DL) technique for accurate skin cancer detection and lesion segmentation is developed. Primarily, the skin image is pre-processed by employing a weighted median filtering to eradicate the noises contained. Then, the segmentation of skin lesions is carried out by employing the efficient neural network (ENet). After that, augmentation is accomplished to avoid overfitting, and later, feature extraction is carried out. At last, skin cancer detection is effectuated with the help of hybrid GoogleNet-LeNet (HGLeNet), which is obtained by merging GoogleNet and LeNet, here layers are modified using the regression concept. Furthermore, the introduced framework is examined for its effectiveness through accuracy, sensitivity and specificity. Moreover, HGLeNet attained the highest accuracy of 0.922, sensitivity of 0.928, as well as specificity of 0.924.

Deep Learning With Optical Coherence Tomography for Melanoma Identification and Risk Prediction.

Malignant melanoma is the most severe skin cancer with a rising incidence rate. Several noninvasive image techniques and computer-aided diagnosis systems have been developed to help find melanoma in its early stages. However, most previous research utilized dermoscopic images to build a diagnosis model, and only a few used prospective datasets. This study develops and evaluates a convolutional neural network (CNN) for melanoma identification and risk prediction using optical coherence tomography (OCT) imaging of mice skin. Longitudinal tests are performed on four animal models: melanoma mice, dysplastic nevus mice, and their respective controls. The CNN classifies melanoma and healthy tissues with high sensitivity (0.99) and specificity (0.98) and also assigns a risk score to each image based on the probability of melanoma presence, which may facilitate early diagnosis and management of melanoma in clinical settings.

Sodium MRI of the skin using a surface coil to investigate and reduce signal loss and bias.

The purpose was to improve sodium MRI of human skin using a surface coil and twisted projection imaging with smaller, reshaped voxels. Calf skin sodium images were acquired in 14 healthy adults using twisted projection imaging with short TE ˜ 0.1 ms, first with a volume coil and voxels (1.5 × 1.5 × 15 = 34 mm3) reflecting the widely adopted skin imaging protocol (VolPencil). A 5-cm-diameter surface coil then facilitated 5× smaller (0.8 × 0.8 × 10 = 6.4 mm3) voxels with similar signal to noise ratio (SNR) in the same 12-min scan time (SurfPencil). "Pencil-shaped" voxels were then replaced with "pancake-shaped" (0.4 × 4 × 4 = 6.4 mm3) voxels, matching the anatomy of pressed flat skin (SurfPancake). Surface coil B1 was investigated with the novel use of spin-3/2 simulation. Protocol modifications were tested for signal increase (reduced loss) and correlation with (bias by) skin thickness. Higher resolution SurfPencil yielded 44% ± 16% greater skin sodium image intensity than VolPencil, whereas SurfPancake yielded an additional 20% ± 9% (p < 1e-8), reflecting reduced signal loss. Over the 1.0 to 1.8 mm skin thickness across participants, sodium intensity significantly increased 56% ± 19% and 44% ± 12% for VolPencil and SurfPencil, respectively (p < 0.003), but not for SurfPancake, reflecting reduced bias. Imaging yielded skin sodium concentration of 34 ± 5 mM for SurfPancake. This is greater than the ˜20 mM measures from the widely adopted protocol, but simulation (matching experimental trends) identified a remaining 64% signal loss; compensation yields 95 ± 15 mM. Surface coil imaging and "pancake" voxel reshaping increased skin sodium intensity and reduced bias by skin thickness. Simulated loss compensation yields skin sodium concentration similar to that measured by atomic absorption spectroscopy.

MUCM-Net: a Mamba powered UCM-Net for skin lesion segmentation

Aim: Skin lesion segmentation is critical for early skin cancer detection. Challenges in automatic segmentation from dermoscopic images include variations in color, texture, and artifacts of indistinct lesion boundaries. This study aims to develop and evaluate MUCM-Net, a lightweight and efficient model for skin lesion segmentation, leveraging Mamba state-space models integrated with UCM-Net architecture optimized for mobile deployment and early skin cancer detection. Methods: MUCM-Net combines Convolutional Neural Networks (CNNs), multi-layer perceptions (MLPs), and Mamba elements into a hybrid feature learning module. Results: The model was trained and tested on the International Skin Imaging Collaboration (ISIC) 2017 and ISIC2018 datasets, consisting of 2,000 and 2,594 dermoscopic images, respectively. Critical metrics for evaluation included Dice Similarity Coefficient (DSC), sensitivity (SE), specificity (SP), and accuracy (ACC). The model’s computational efficiency was also assessed by measuring Giga Floating-point Operations Per Second (GFLOPS) and the number of parameters. MUCM-Net demonstrated superior performance in skin lesion segmentation with an average DSC of 0.91 on the ISIC2017 dataset and 0.89 on the ISIC2018 dataset, outperforming existing models. It achieved high SE (0.93), SP (0.95), and ACC (0.92) with low computational demands (0.055–0.064 GFLOPS). Conclusions: The model’s innovative Mamba-UCM layer significantly enhanced feature learning while maintaining efficiency that is suitable for mobile devices. MUCM-Net establishes a new standard in lightweight skin lesion segmentation, balancing exceptional ACC with efficient computational performance. Its ability to perform well on mobile devices makes it a scalable tool for early skin cancer detection in resource-limited settings. The open-source availability of MUCM-Net supports further research and collaboration, promoting advances in mobile health diagnostics and the fight against skin cancer. MUCM-Net source code will be posted on https://github.com/chunyuyuan/MUCM-Net.

A Review of Non-Invasive Skin Imaging in Merkel Cell Carcinoma: Diagnostic Utility and Clinical Implications.

Background/Objectives: Merkel cell carcinoma (MCC) is a rare and aggressive cutaneous neuroendocrine malignancy characterized by its propensity for rapid growth and early regional and distant metastasis. Given its potentially lethal nature, accurate and timely diagnosis of MCC is of utmost importance. This review aims to describe non-invasive imaging methods that can serve as additional tools in the examination of MCC. Methods: In this narrative review, we describe the up-to-date spectrum of non-invasive skin-imaging methods that can serve as additional tools in the examination of MCC based on the available literature. Dermoscopy might enhance the clinical diagnosis of MCC, facilitate differentiation from other benign and malignant tumors, and help optimize the treatment plan. New imaging technologies might also provide useful information at a sub-macroscopic level and support clinical diagnosis. These techniques include high-frequency ultrasound (HFUS), reflectance confocal microscopy (RCM) and optical coherence tomography (OCT). Results: Clinically, MCC typically presents as a rapidly growing, red, purple or skin-colored painless and firm nodule. Diagnosis is usually established with histopathological assessment and immunohistochemistry. However, dermoscopy and new imaging technologies might enhance the clinical diagnosis of MCC, facilitate differentiation from other benign and malignant tumors, and help optimize the treatment plan.

LesionNet: an automated approach for skin lesion classification using SIFT features with customized convolutional neural network.

Accurate detection of skin lesions through computer-aided diagnosis has emerged as a critical advancement in dermatology, addressing the inefficiencies and errors inherent in manual visual analysis. Despite the promise of automated diagnostic approaches, challenges such as image size variability, hair artifacts, color inconsistencies, ruler markers, low contrast, lesion dimension differences, and gel bubbles must be overcome. Researchers have made significant strides in binary classification problems, particularly in distinguishing melanocytic lesions from normal skin conditions. Leveraging the "MNIST HAM10000" dataset from the International Skin Image Collaboration, this study integrates Scale-Invariant Feature Transform (SIFT) features with a custom convolutional neural network model called LesionNet. The experimental results reveal the model's robustness, achieving an impressive accuracy of 99.28%. This high accuracy underscores the effectiveness of combining feature extraction techniques with advanced neural network models in enhancing the precision of skin lesion detection.

Combined Pediatric Rheumatology/Dermatology Clinics: Benefits and Challenges.

Integrated care models, like combined rheumatology/dermatology clinics (RDCs), facilitate efficient coordination between specialists and provide comprehensive care. Given the limited literature on pediatric RDC logistics, outcomes, benefits and, challenges, we comprehensively characterized our patient cohort at the UCSF Benioff Children's Hospital RDC and surveyed pediatric dermatologists participating in RDCs. We retrospectively reviewed 71 patients new to the UCSF Pediatric RDC between September 2017 and September 2023. A survey was distributed in 2024 to 17 dermatologists in North America, each representing a unique pediatric RDC. 69% of patients (49/71) were female. Seventeen (24%) presented without a known diagnosis; the first RDC visit established a diagnosis for 7 of them (41%). Of patients with a previously established diagnosis, initial RDC evaluation confirmed it in 52 (96%) and revised it for 2 (4%). The most encountered diagnoses were linear morphea (33%), lupus (23%), and psoriasis (13%). New systemic therapy was prescribed for 23% of patients, and additional work-up was recommended via skin biopsy (8%) and imaging (28%). Survey results revealed all pediatric RDCs include trainees, but only 59% (10/17) receive administrative support. All agreed that RDCs are valuable for patient care and most (15/17, 88%) felt that the RDC was a valuable use of their time. Pediatric RDCs are valuable for consensus diagnosis, streamlined evaluation, and management of complex patients. Though clinical and administrative support for RDCs is generally poor, RDCs are valuable to patients, a good use of time for clinicians, and offer educational opportunities for team members.

Inclusive and Accurate Clinical Diagnostics Using Intelligent Computation and Smartphone Imaging.

Smartphone-based colorimetry has been widely applied in clinical analysis, although significant challenges remain in its practical implementation, including the need to consider biases introduced by the ambient imaging environment, which limit its potential within a clinical decision pathway. In addition, most commercial devices demonstrate variability introduced by manufacturer-to-manufacturer differences. Here, we undertake a systematic characterization of the potential imaging interferences that lead to this limited performance in conventional smartphones and, in doing so, provide a comprehensive new understanding of smartphone color imaging. Through derivation of a strongly correlated parameter for sample quantification, we enable real-time imaging, which for the first time, takes the first steps to turning the mobile phone camera into an analytical instrument - irrespective of model, software, and the operating systems used. We demonstrate clinical applicability through the imaging of patients' skin, enabling rapid and convenient diagnosis of cyanosis and measurement of local oxygen concentration to a level that unlocks clinical decision-making for monitoring cardiovascular disease and anemia. Importantly, we show that our solution also accounts for the differences in individuals' skin tones as measured across the Fitzpatrick scale, overcoming potential clinically significant errors in current optical oximetry.

Hybrid Deep Learning Framework for Melanoma Diagnosis Using Dermoscopic Medical Images

Background: Melanoma, or skin cancer, is a dangerous form of cancer that is the major cause of the demise of thousands of people around the world. Methods: In recent years, deep learning has become more popular for analyzing and detecting these medical issues. In this paper, a hybrid deep learning approach has been proposed based on U-Net for image segmentation, Inception-ResNet-v2 for feature extraction, and the Vision Transformer model with a self-attention mechanism for refining the features for early and accurate diagnosis and classification of skin cancer. Furthermore, in the proposed approach, hyperparameter tuning helps to obtain more accurate and optimized results for image classification. Results: Dermoscopic shots gathered by the worldwide skin imaging collaboration (ISIC2020) challenge dataset are used in the proposed research work and achieved 98.65% accuracy, 99.20% sensitivity, and 98.03% specificity, which outperforms the other existing approaches for skin cancer classification. Furthermore, the HAM10000 dataset is used for ablation studies to compare and validate the performance of the proposed approach. Conclusions: The achieved outcome suggests that the proposed approach would be able to serve as a valuable tool for assisting dermatologists in the early detection of melanoma.

A Modified Deep Semantic Segmentation Model for Analysis of Whole Slide Skin Images

Automated segmentation of biomedical image has been recognized as an important step in computer-aided diagnosis systems for detection of abnormalities. Despite its importance, the segmentation process remains an open challenge due to variations in color, texture, shape diversity and boundaries. Semantic segmentation often requires deeper neural networks to achieve higher accuracy, making the segmentation model more complex and slower. Due to the need to process a large number of biomedical images, more efficient and cheaper image processing techniques for accurate segmentation are needed. In this article, we present a modified deep semantic segmentation model that utilizes the backbone of EfficientNet-B3 along with UNet for reliable segmentation. We trained our model on Non-melanoma skin cancer segmentation for histopathology dataset to divide the image in 12 different classes for segmentation. Our method outperforms the existing literature with an increase in average class accuracy from 79 to 83%. Our approach also shows an increase in overall accuracy from 85 to 94%.

Therapeutic Performance of Needle Injection Versus Needle-Free Jet Injector System for Polynucleotide Filler in Skin Rejuvenation.

Polynucleotide (PN) filler often causes pain and can lead to delivery inaccuracies when applied via intradermal injection using a traditional needle. To evaluate the efficacy of treatment and the pain during the procedure using conventional needle injection versus a needle-free jet system for intradermal PN filler application. In this split-face clinical trial, 10 Korean subjects were enrolled. Each subject received an intradermal injection of PN filler on one side of the face and a needle-free jet injection using CureJet on the other side. Assessments included global and 3D skin imaging at each visit. Pain intensity was evaluated using visual analogue scale (VAS) scores during the injection. Additionally, patient satisfaction and adverse events were documented. Findings revealed that Global Aesthetic Improvement Scale scores and patient satisfaction were significantly higher with the CureJet compared to the needle injection method. VAS scores were notably lower on the CureJet side. Improvements in both pore and wrinkle indices were observed from baseline, with a more pronounced improvement rate on the CureJet side compared to the needle injection side. Needle-free injection of PN for aging skin was found to be effective in enhancing pore and wrinkle improvement, while reducing associated discomfort.

Computer Modelling of Textures on Images with Human Skin Wound Areas

In this paper, we concentrate on the images of the wounds on the human skin and propose to consider each image as a set of smaller pieces – crops or patches containing different textures. We overview, develop and compare deep learning feature extraction methods to model image crops as 200-dimensional feature vectors using various artificial neural network architectures: convolutional autoencoders, variational convolutional autoencoders, and Siamese convolutional networks trained in the contrastive learning manner. Also, we develop a custom convolutional encoder and decoder, use them in the aforementioned architectures and compare them with the ResNet encoder and decoder alternatives. Finally, we train and evaluate k-nearest neighbors and Multi-Layer Perceptron classifiers on the features extracted with the model above options to discriminate skin, wound, and background image patches. Classification evaluation results on the features, extracted with the Siamese network, show the best test accuracy for all implementations without a significant shift between model versions (accuracy &gt; 93%); variational autoencoders show random results for all options (accuracy around 33%), and convolutional autoencoders reached good results (accuracy &gt; 77%) but with a noticeable difference between the custom and ResNet versions; the latter is better. Custom encoder and decoder implementations are faster and smaller than the ResNet alternatives but may be less stable on larger datasets, which still needs investigation. Possible applications of the feature vectors include an area of interest extraction during wound segmentation or classification and usage as patch embeddings while training vision transformer architectures.

Dataset of human skin and fingernails images for non-invasive haemoglobin level assessment

Anaemia, a decrease in total concentration of haemoglobin (Hb) in blood, affects substantial percentage of the population worldwide. Currently, the gold standard for determining the Hb level is the invasive analysis of venous blood. Yet, more and more research groups demonstrate the possibility of non-invasive Hb assessment using white light imaging of tissue sites where Hb is the main chromophore, in particular, fingernails. Despite the promising declarations, non-invasive Hb assessment via RGB-imaging is still poorly used in practice. The main reason is the difficulty in establishing the true accuracy of the methods presented in different works since they are tested on private datasets collected under different experimental conditions. Here we present an open dataset containing RGB images of skin and fingernails for patients with a known level of Hb, thus providing a single benchmark for researchers and engineers in the field, aimed at fostering translation of non-invasive imaging methods to the bedside.

Artificial Intelligence Smartphone Application for Detection of Simulated Skin Changes: An In Vivo Pilot Study.

The development of artificial intelligence (AI) is rapidly expanding, showing promise in the dermatological field. Skin checks are a resource-heavy challenge that could potentially benefit from AI-tool assistance, particularly if provided in widely available AI solutions. A novel smartphone application(app)-based AI system, "SCAI," was developed and trained to recognize spots in paired images of skin, pursuing identification of new skin lesions. This pilot study aimed to investigate the feasibility of the SCAI-app to identify simulated skin changes in vivo. The study was conducted in a controlled setting with healthy volunteers and standardized, simulated skin changes (test spots), consisting of customized 3-mm adhesive spots in three colors (black, brown, and red). Each volunteer had a total of eight test spots adhered to four areas on back and legs. The SCAI-app collected smartphone- and template-guided standardized images before and after test spot application, using its backend AI algorithms to identify changes between the paired images. Twenty-four volunteers were included, amounting to a total of 192 test spots. Overall, the detection algorithms identified test spots with a sensitivity of 92.0% (CI: 88.1-95.9) and a specificity of 95.5% (CI: 95.0-96.0). The SCAI-app's positive predictive value was 38.0% (CI: 31.0-44.9), while the negative predictive value was 99.7% (CI: 99.0-100). This pilot study showed that SCAI-app could detect simulated skin changes in a controlled in vivo setting. The app's feasibility in a clinical setting with real-life skin lesions remains to be investigated, where the challenge with false positives in particular needs to be addressed.