Dermatological Images Research Articles

Nonfungible tokens (NFTs) in dermatology and health care: A guide for health care professionals

AbstractA nonfungible token (NFT) represents an arbitrary piece of information, which can be created and exchanged on a blockchain, a type of public ledger secured by cryptographic algorithms. NFTs offer the possibility of leveraging blockchain technology‐related benefits, including verifiability, transparent execution, high availability and tamper‐resistance, for any tokenizable piece of information such as for example, clinical images in dermatology. In this narrative review, we explore current and potential future applications, as well as limitations of NFTs in health care. While health care applications for blockchains have been explored and implemented, NFTs have not yet been extensively studied in medical literature. Beyond the currently envisaged use in blood product tracking, consent management and an extension to electronic health records, the medical field and especially dermatology could benefit in other domains from this technology, including for clinical image safety, charge‐sensitive drug tracking and managing processes like referrals, lab orders, patient consent, legal claims such as malpractice, and improved availability and reliability of scientific data. The technology is limited by the sensitive nature of patient data, potentially counteracting the verifiability benefit, as well as accessibility for patients, and the technical skills required to create and maintain the infrastructure.

Dermatology Image Quality Assessment (DIQA): Artificial intelligence to ensure the clinical utility of images for remote consultations and clinical trials

Dermatology Image Quality Assessment (DIQA): Artificial intelligence to ensure the clinical utility of images for remote consultations and clinical trials

GraVIS: Grouping Augmented Views From Independent Sources for Dermatology Analysis.

Self-supervised representation learning has been extremely successful in medical image analysis, as it requires no human annotations to provide transferable representations for downstream tasks. Recent self-supervised learning methods are dominated by noise-contrastive estimation (NCE, also known as contrastive learning), which aims to learn invariant visual representations by contrasting one homogeneous image pair with a large number of heterogeneous image pairs in each training step. Nonetheless, NCE-based approaches still suffer from one major problem that is one homogeneous pair is not enough to extract robust and invariant semantic information. Inspired by the archetypical triplet loss, we propose GraVIS, which is specifically optimized for learning self-supervised features from dermatology images, to group homogeneous dermatology images while separating heterogeneous ones. In addition, a hardness-aware attention is introduced and incorporated to address the importance of homogeneous image views with similar appearance instead of those dissimilar homogeneous ones. GraVIS significantly outperforms its transfer learning and self-supervised learning counterparts in both lesion segmentation and disease classification tasks, sometimes by 5 percents under extremely limited supervision. More importantly, when equipped with the pre-trained weights provided by GraVIS, a single model could achieve better results than winners that heavily rely on ensemble strategies in the well-known ISIC 2017 challenge. Code is available at https://bit.ly/3xiFyjx.

A multi-stage melanoma recognition framework with deep residual neural network and hyperparameter optimization-based decision support in dermoscopy images

This paper developed a novel melanoma diagnosis model from dermoscopy images using a novel hybrid model. Melanoma is the most dangerous and rarest type of skin cancer. It is seen because of the uncontrolled proliferation of melanocyte cells that give color to the skin. Dermoscopy is a critical auxiliary diagnostic method in the differentiation of pigmented moles, which show moles by magnifying 10–20 times from skin cancers. This paper proposes a multi-stage melanoma recognition framework withskin lesion images obtained from dermoscopy. This model developed a practical pre-processing approach that includes dilation andpooling layers to remove hair details and reveal details in dermoscopy images. A deep residual neural network was then utilized as the feature extractor for processed images.Additionally, the Relief algorithm selected practical and distinctive features from these features. Finally, these selected features were fed to the input of the support vector machine (SVM) classifier. In addition, the Bayesian optimization algorithm was used for the optimum parameter selection of the SVM method. The International Skin Imaging Collaboration (ISIC-2019 and ISIC-2020) datasets were used to test the performance of the proposed model. As a result, the proposed model produced approximately 99% accuracy forclassifying melanoma or benign from skin lesion images. These results show that the proposed model can help physicians to automatically identify melanoma based on dermatological imaging.

Artificial Intelligence in Dermatology Image Analysis: Current Developments and Future Trends.

Thanks to the rapid development of computer-based systems and deep-learning-based algorithms, artificial intelligence (AI) has long been integrated into the healthcare field. AI is also particularly helpful in image recognition, surgical assistance and basic research. Due to the unique nature of dermatology, AI-aided dermatological diagnosis based on image recognition has become a modern focus and future trend. Key scientific concepts of review: The use of 3D imaging systems allows clinicians to screen and label skin pigmented lesions and distributed disorders, which can provide an objective assessment and image documentation of lesion sites. Dermatoscopes combined with intelligent software help the dermatologist to easily correlate each close-up image with the corresponding marked lesion in the 3D body map. In addition, AI in the field of prosthetics can assist in the rehabilitation of patients and help to restore limb function after amputation in patients with skin tumors. For the benefit of patients, dermatologists have an obligation to explore the opportunities, risks and limitations of AI applications. This study focuses on the application of emerging AI in dermatology to aid clinical diagnosis and treatment, analyzes the current state of the field and summarizes its future trends and prospects so as to help dermatologists realize the impact of new technological innovations on traditional practices so that they can embrace and use AI-based medical approaches more quickly.

Consumer perceptions on privacy and confidentiality in dermatology for 3D total-body imaging.

As 3D total-body photography for the early detection of melanoma is not yet widely used in clinical practice, we do not have a full understanding of patient's concerns about use, privacy and confidentiality, and if their concerns differ depending on the use-case. We conducted a virtual consumer forum to assess patients concerns about privacy and confidentiality in dermatology imaging for research, artificial intelligence development and for their own clinical care.

Towards Transparency in Dermatology Image Datasets with Skin Tone Annotations by Experts, Crowds, and an Algorithm

While artificial intelligence (AI) holds promise for supporting healthcare providers and improving the accuracy of medical diagnoses, a lack of transparency in the composition of datasets exposes AI models to the possibility of unintentional and avoidable mistakes. In particular, public and private image datasets of dermatological conditions rarely include information on skin color. As a start towards increasing transparency, AI researchers have appropriated the use of the Fitzpatrick skin type (FST) from a measure of patient photosensitivity to a measure for estimating skin tone in algorithmic audits of computer vision applications including facial recognition and dermatology diagnosis. In order to understand the variability of estimated FST annotations on images, we compare several FST annotation methods on a diverse set of 460 images of skin conditions from both textbooks and online dermatology atlases. These methods include expert annotation by board-certified dermatologists, algorithmic annotation via the Individual Typology Angle algorithm, which is then converted to estimated FST (ITA-FST), and two crowd-sourced, dynamic consensus protocols for annotating estimated FSTs. We find the inter-rater reliability between three board-certified dermatologists is comparable to the inter-rater reliability between the board-certified dermatologists and either of the crowdsourcing methods. In contrast, we find that the ITA-FST method produces annotations that are significantly less correlated with the experts' annotations than the experts' annotations are correlated with each other. These results demonstrate that algorithms based on ITA-FST are not reliable for annotating large-scale image datasets, but human-centered, crowd-based protocols can reliably add skin type transparency to dermatology datasets. Furthermore, we introduce the concept of dynamic consensus protocols with tunable parameters including expert review that increase the visibility of crowdwork and provide guidance for future crowdsourced annotations of large image datasets.

Constructing a Culturally Conscious Dermatology Image Collection for Undergraduate Medical Education.

Constructing a Culturally Conscious Dermatology Image Collection for Undergraduate Medical Education.

Lesion identification and malignancy prediction from clinical dermatological images

We consider machine-learning-based lesion identification and malignancy prediction from clinical dermatological images, which can be indistinctly acquired via smartphone or dermoscopy capture. Additionally, we do not assume that images contain single lesions, thus the framework supports both focal or wide-field images. Specifically, we propose a two-stage approach in which we first identify all lesions present in the image regardless of sub-type or likelihood of malignancy, then it estimates their likelihood of malignancy, and through aggregation, it also generates an image-level likelihood of malignancy that can be used for high-level screening processes. Further, we consider augmenting the proposed approach with clinical covariates (from electronic health records) and publicly available data (the ISIC dataset). Comprehensive experiments validated on an independent test dataset demonstrate that (1) the proposed approach outperforms alternative model architectures; (2) the model based on images outperforms a pure clinical model by a large margin, and the combination of images and clinical data does not significantly improves over the image-only model; and (3) the proposed framework offers comparable performance in terms of malignancy classification relative to three board certified dermatologists with different levels of experience.

Skin Color Representation in Ophthalmology Textbooks.

ObjectiveInadequate diversity in dermatologic images has been associated with diagnostic delays and poorer health outcomes. This underrepresentation of darker skin tones has also been demonstrated across various fields of medicine, including rheumatology, urology, and in the COVID-19 pandemic. The distribution of skin tones has not been examined in educational ophthalmology texts. The authors aimed to quantify the representation of skin tones across three leading ophthalmology textbooks.MethodsTwo independent investigators utilized the Fitzpatrick’s skin phototype scale to code images containing skin as either “light” (Fitz. I–IV) or “dark” (Fitz. V–VI) in three fundamental ophthalmology textbooks: Clinical Ophthalmology (Salmon and Kanski), Ophthalmology (Yanoff and Duker), and the 13 Basic and Clinical Science Course texts by the American Academy of Ophthalmology. Images without discernible skin color were excluded.ResultsOf the 9766 images reviewed, 2305 images met inclusion criteria. The three textbooks combined were found to have 2123 (92.1%) images of light skin tones and 182 images (7.9%) of dark skin tones. When compared to national data that found 12.6% of individuals to have dark skin tones, the proportion of images with darker skin tones in ophthalmology textbooks was statistically significantly lower (χ2corr(1, N = 4996) = 211.7, p < 0.001).ConclusionsDarker skin tones are statistically significantly underrepresented in textbooks that are central to education of trainees in ophthalmology. Acknowledgement and inclusion of skin tone diversity in ophthalmology educational materials are necessary to ensure that physicians in the field are equipped with the knowledge and training to provide the highest level of care to all patients.Supplementary InformationThe online version contains supplementary material available at 10.1007/s40670-022-01636-4.

35126 Education to improve general medical doctors’ dermatology referrals

General hospital doctors often find it challenging to correctly diagnose and appropriately refer common benign and malignant skin lesions. A series of dermatology images of melanoma, nonmelanoma malignancies, actinic keratosis and benign lesions was presented in a quiz format to general medical doctors in a model 3 hospital. Dermatology experience, confidence in lesion recognition and decision for dermatology referral was surveyed pre-teaching. A teaching session with follow-up quiz and self-assessed confidence of lesion recognition and diagnosis was surveyed. Comparison pre and post quiz scores were analyzed. Twenty-four medical doctors ranging from intern to consultant participated in this study. 96% (n = 23) had no prior dermatology experience. Following teaching, 61% (n = 14) expressed feeling confident in their diagnosis of presented images, compared with 17% (n = 4) preteaching. The follow-up quiz showed a global 24% increase in lesion recognition. Correct referral of actinic keratosis improved from 79% to 100%, acral melanoma improved from 75% to 90%, melanoma referral improved from 77% to 93% and BCC referral improved from 88% to 100%. 91% (n = 21) found the teaching session helpful for future practice. The teaching session improved the ability to correctly identify features of common benign, premalignant and malignant skin lesions. The follow-up quiz demonstrated improvement in appropriate referrals for premalignant and malignant lesions. Regular dermatology teaching with images and self-assessment quizzes should improve the confidence of general hospital doctors to correctly recognize and refer to dermatology services. This study demonstrates the need for dermatology teaching to general medical doctors to improve the accurate diagnosis and referral of common skin lesions.

Disparities in dermatology AI performance on a diverse, curated clinical image set.

An estimated 3 billion people lack access to dermatological care globally. Artificial intelligence (AI) may aid in triaging skin diseases and identifying malignancies. However, most AI models have not been assessed on images of diverse skin tones or uncommon diseases. Thus, we created the Diverse Dermatology Images (DDI) dataset—the first publicly available, expertly curated, and pathologically confirmed image dataset with diverse skin tones. We show that state-of-the-art dermatology AI models exhibit substantial limitations on the DDI dataset, particularly on dark skin tones and uncommon diseases. We find that dermatologists, who often label AI datasets, also perform worse on images of dark skin tones and uncommon diseases. Fine-tuning AI models on the DDI images closes the performance gap between light and dark skin tones. These findings identify important weaknesses and biases in dermatology AI that should be addressed for reliable application to diverse patients and diseases.

DermoCC-GAN: A new approach for standardizing dermatological images using generative adversarial networks

Background and objectiveDermatological images are typically diagnosed based on visual analysis of the skin lesion acquired using a dermoscope. However, the final quality of the acquired image is highly dependent on the illumination conditions during the acquisition phase. This variability in the light source can affect the dermatologist's diagnosis and decrease the accuracy of computer-aided diagnosis systems. Color constancy algorithms have proven to be a powerful tool to address this issue by allowing the standardization of the image illumination source, but the most commonly used algorithms still present some inherent limitations due to assumptions made on the original image. In this work, we propose a novel Dermatological Color Constancy Generative Adversarial Network (DermoCC-GAN) algorithm to overcome the current limitations by formulating the color constancy task as an image-to-image translation problem. MethodsA generative adversarial network was trained with a custom heuristic algorithm that performs well on the training set. The model hence learns the domain transfer task (from original to color standardized image) and is then able to accurately apply the color constancy on test images characterized by different illumination conditions. ResultsThe proposed algorithm outperforms state-of-the-art color constancy algorithms for dermatological images in terms of normalized median intensity and when using the color-normalized images in a deep learning framework for lesion classification (accuracy of the seven-class classifier: 79.2%) and segmentation (dice score: 90.9%). In addition, we validated the proposed approach on two different external datasets with highly satisfactory results. ConclusionsThe novel strategy presented here shows how it is possible to generalize a heuristic method for color constancy for dermatological image analysis by training a GAN. The overall approach presented here can be easily extended to numerous other applications.

Skin Cancer Classification With Deep Learning: A Systematic Review.

Skin cancer is one of the most dangerous diseases in the world. Correctly classifying skin lesions at an early stage could aid clinical decision-making by providing an accurate disease diagnosis, potentially increasing the chances of cure before cancer spreads. However, achieving automatic skin cancer classification is difficult because the majority of skin disease images used for training are imbalanced and in short supply; meanwhile, the model’s cross-domain adaptability and robustness are also critical challenges. Recently, many deep learning-based methods have been widely used in skin cancer classification to solve the above issues and achieve satisfactory results. Nonetheless, reviews that include the abovementioned frontier problems in skin cancer classification are still scarce. Therefore, in this article, we provide a comprehensive overview of the latest deep learning-based algorithms for skin cancer classification. We begin with an overview of three types of dermatological images, followed by a list of publicly available datasets relating to skin cancers. After that, we review the successful applications of typical convolutional neural networks for skin cancer classification. As a highlight of this paper, we next summarize several frontier problems, including data imbalance, data limitation, domain adaptation, model robustness, and model efficiency, followed by corresponding solutions in the skin cancer classification task. Finally, by summarizing different deep learning-based methods to solve the frontier challenges in skin cancer classification, we can conclude that the general development direction of these approaches is structured, lightweight, and multimodal. Besides, for readers’ convenience, we have summarized our findings in figures and tables. Considering the growing popularity of deep learning, there are still many issues to overcome as well as chances to pursue in the future.

Innovatív in vivo képalkotó módszerek a bőrgyógyászatban

As a result of advances in the development of medical imaging, the toolbox of dermatological imaging in the XXI. century expanded considerably. In addition to the histological examination that is currently the gold standard in diagnostics, a number of noninvasive imaging methods have emerged in recent decades that have become part of the clinical and preclinical practice. The characteristics of many dermatological diseases have been described in vivo studies with commercially available devices. The authors summarize the principles of terahertz imaging, photoacoustic imaging, reflectance and autofluorescence imaging, near-infrared spectroscopy, and nonlinear microscopy, as well as the in vivo dermatological results and clinical applications of these modalities.

Applications of multispectral and hyperspectral imaging in dermatology.

Vision is essential in the diagnostic capabilities in the speciality of dermatology. However, humans are limited in colour vision by the trichromatic visual system that we possess. Multispectral and hyperspectral imaging can overcome this limitation and non-invasively provide novel information about a skin lesion at the cellular level. A literature review from January 2019 to March 2021 for hyperspectral and multispectral imaging in the field of dermatology was conducted. Multispectral/Hyperspectral imaging continues to generate significant research and interest in dermatology. Much of this research is on distinguishing melanoma from benign nevi as this could allow for a diagnosis without biopsy. In addition, adding multispectral/hyperspectral imaging to smartphones is being researched in order to create a portable and low-cost device that can be used in remote areas. One of the limitations in developing devices utilizing hyperspectral imaging has been a sacrifice in specificity in order to maximize sensitivity. Potential solutions to combat this that are being researched include combining multispectral/hyperspectral imaging with other imaging modalities such as photoacoustic imaging in order to overcome the limitations of using each individually. Multispectral/Hyperspectral imaging could be an instrumental aid for clinicians in examining, diagnosing and developing the management plan for patient's skin lesions.

Digital skin imaging applications, part I: Assessment of image acquisition technique features.

The rapid adoption of digital skin imaging applications has increased the utilization of smartphone-acquired images in dermatology. While this has enormous potential for scaling the assessment of concerning skin lesions, the insufficient quality of many consumer/patient-taken images can undermine clinical accuracy and potentially harm patients due to lack of diagnostic interpretability. We aim to characterize the current state of digital skin imaging applications and comprehensively assess how image acquisition features address image quality. Publicly discoverable mobile, web, and desktop-based skin imaging applications, identified through keyword searches in mobile app stores, Google Search queries, previous teledermatology studies, and expert recommendations were independently assessed by three reviewers. Applications were categorized by primary audience (consumer-facing, nonhospital-based practice, or enterprise/health system), function (education, store-and-forward teledermatology, live-interactive teledermatology, electronic medical record adjunct/clinical imaging storage, or clinical triage), in-app connection to a healthcare provider (yes or no), and user type (patient, provider, or both). Just over half (57%) of 191 included skin imaging applications had at least one of 14 image acquisition technique features. Those that were consumer-facing, intended for educational use, and designed for both patient and physician users had significantly greater feature richness (p<0.05). The most common feature was the inclusion of text-based imaging tips, followed by the requirement to submit multiple images and body area matching. Very few skin imaging applications included more than one image acquisition technique feature. Feature richness varied significantly by audience, function, and user categories. Users of digital dermatology tools should consider which applications have standardized features that improve image quality.

Multiscale confocal photoacoustic dermoscopy to evaluate skin health.

Photoacoustic dermoscopy (PAD) is a promising branch of photoacoustic microscopy (PAM) that can provide a range of functional and morphologic information for clinical assessment and diagnosis of dermatological conditions. However, most PAM setups are unsuitable for clinical dermatology because their single-scale mode and narrow frequency band result in insufficient imaging depth or poor spatiotemporal resolution when visualizing the internal texture of the skin. We developed a multiscale confocal photoacoustic dermoscopy (MC-PAD) with a multifunction opto-sono objective that could achieve high quality dermatological imaging. Using the objective to coordinate the spatial resolution and penetration depth, the MC-PAD was used to visualize pathophysiological biomarkers and vascular morphology from the epidermis (EP) to the dermis, which enabled us to quantify skin abnormalities without using exogenous contrast agents for human skin. The MC-PAD was shown to have the ability to differentiate between different types of cells (such as red blood cells and melanoma cells), image and quantify pigment of the skin, and visualize skin morphology and blood capillary landmarks. The MC-PAD detected a significant difference in the structures of some pigmented and vascular lesions of skin diseases compared with that of healthy skin (P<0.01). The café au lait macule (CALM) skin type was found to have a relatively higher melanin concentration and thicker stratum basale (SB) in the EP than healthy skin. The dermal vascular network of skin that had a port wine stain (PWS) had greater diameters and a denser distribution than healthy skin, as reported in clinical trials. The MC-PAD has a broad range of applications for the diagnosis of human skin diseases and evaluation of the curative effect of treatments, and it can offer new perspectives in biomedical sciences.

Superpixel-Oriented Label Distribution Learning for Skin Lesion Segmentation.

Lesion segmentation is a critical task in skin cancer analysis and detection. When developing deep learning-based segmentation methods, we need a large number of human-annotated labels to serve as ground truth for model-supervised learning. Due to the complexity of dermatological images and the subjective differences of different dermatologists in decision-making, the labels in the segmentation target boundary region are prone to produce uncertain labels or error labels. These labels may lead to unsatisfactory performance of dermoscopy segmentation. In addition, the model trained by the errored one-hot label may be overconfident, which can lead to arbitrary prediction and model overfitting. In this paper, a superpixel-oriented label distribution learning method is proposed. The superpixels formed by the simple linear iterative cluster (SLIC) algorithm combine one-hot labels constraint and define a distance function to convert it into a soft probability distribution. Referring to the model structure of knowledge distillation, after Superpixel-oriented label distribution learning, we get soft labels with structural prior information. Then the soft labels are transferred as new knowledge to the lesion segmentation network for training. Ours method on ISIC 2018 datasets achieves an Dice coefficient reaching 84%, sensitivity 79.6%, precision 80.4%, improved by 19.3%, 8.6% and 2.5% respectively in comparison with the results of U-Net. We also evaluate our method on the tasks of skin lesion segmentation via several general neural network architectures. The experiments show that ours method improves the performance of network image segmentation and can be easily integrated into most existing deep learning architectures.

The Role of Standards in Accelerating the Uptake of Artificial Intelligence in Dermatology

Background The use of artificial intelligence (AI) for dermatology is showing great promise in research contexts. However, the clinical use of AI in dermatology is still limited. The uptake of medical imaging standards for dermatology imaging is also limited. Standards adoption is more widespread in other imaging specialties (eg, radiology) as is the clinical use of AI. Digital Image Communication in Medicine (DICOM) is the standard for medical imaging. DICOM standardizes image formats and associated metadata. Further, DICOM facilitates interoperability between actors in the digital health ecosystem. Objective This study aimed to identify how medical imaging standards, in particular DICOM, can support the clinical use of AI. Methods Design Science Research Methodology was used to determine the role of DICOM in AI-based medical imaging workflows. Scenarios were identified and synthesized using expert consensus. Results The key benefits of using DICOM to improve the clinical use of AI were the potential to encode artefacts derived from the AI process as DICOM objects and store them alongside the original images. Such objects include downsized or down-sampled images, segmentation objects, or visual explainability maps (eg, class activation maps). DICOM can facilitate interoperability between actors in the medical imaging workflow pipeline and permits the inclusion of AI evidence creators in this pipeline. Owing to standardized image formats and metadata, DICOM can be beneficial for the curation of multi-institutional data sets. The key challenge of using DICOM is limited uptake in some specialties including dermatology. Conclusions DICOM offers potential to accelerate the clinical adoption of AI in dermatology by addressing several technological issues. More widespread uptake of DICOM in dermatology imaging is required to achieve this potential. Conflicts of Interest None declared.