Artificial Intelligence in Dermatology: A Primer

Conventional and three-dimensional photography as a tool to map distribution patterns of in-transit melanoma metastases on the lower extremity

Background

In melanoma, in-transit metastases characteristically occur at the lower extremity along lymphatic vessels.

Objectives

The objective of this study was to evaluate conventional or three-dimensional photography as a tool to analyze in-transit metastasis pattern of melanoma of the lower extremity. In addition, we assessed risk factors for the development of in-transit metastases in cutaneous melanoma.

Methods

In this retrospective, monocentric study first we compared the clinical data of all evaluable patients with in-transit metastases of melanoma on the lower extremity (n = 94) with melanoma patients without recurrence of disease (n = 288). In addition, based on conventional (n = 24) and three-dimensional photography (n = 22), we defined the specific distribution patterns of the in-transit metastases on the lower extremity.

Results

Using a multivariate analysis we identified nodular melanoma, tumor thickness, and ulceration as independent risk factors to develop in-transit metastases ITM (n = 94). In patients with melanoma on the lower leg (n = 31), in-transit metastases preferentially developed along anatomically predefined lymphatic pathways. In contrast when analyzing in-transit metastases of melanoma on the foot (n = 15) no clear pattern could be visualized. In addition, no difference in distance between in-transit metastases and primary melanoma on the foot compared to the lower leg was observed using three-dimensional photography (n = 22).

Conclusion

A risk-adapted follow-up of melanoma patients to detect in-transit metastases can be applied by knowledge of the specific lymphatic drainage of the lower extremity. Our current analysis suggests a more complex lymphatic drainage of the foot.

Accuracy and clinical relevance of an automated, algorithm-based analysis of facial signs from selfie images of women in the United States of various ages, ancestries and phototypes: A cross-sectional observational study

BACKGROUND

Real-life validation is necessary to ensure our artificial intelligence (AI) skin diagnostic tool is inclusive across a diverse and representative US population of various ages, ancestries and skin phototypes.

OBJECTIVES

To explore the relevance and accuracy of an automated, algorithm-based analysis of facial signs in representative women of different ancestries, ages and phototypes, living in the same country.

METHODS

In a cross-sectional study of selfie images of 1041 US women, algorithm-based analyses of seven facial signs were automatically graded by an AI-based algorithm and by 50 US dermatologists of various profiles (age, gender, ancestry, geographical location). For automated analysis and dermatologist assessment, the same referential skin atlas was used to standardize the grading scales. The average values and their variability were compared with respect to age, ancestry and phototype.

RESULTS

For five signs, the grading obtained by the automated system were strongly correlated with dermatologists' assessments (r ≥ 0.75); cheek skin pores were moderately correlated (r = 0.63) and pigmentation signs, especially for the darkest skin tones, were weakly correlated (r = 0.40) to the dermatologist assessments. Age and ancestry had no effect on the correlations. In many cases, the automated system performed better than the dermatologist-assessed clinical grading due to 0.3-0.5 grading unit differences among the dermatologist panel that were not related to any individual characteristic (e.g. gender, age, ancestry, location). The use of phototypes, as discontinuous categorical variables, is likely a limiting factor in the assessments of grading, whether obtained by automated analysis or clinical assessment of the images.

CONCLUSIONS

The AI-based automatic procedure is accurate and clinically relevant for analysing facial signs in a diverse and inclusive population of US women, as confirmed by a diverse panel of dermatologists, although skin tone requires further improvement.

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

BACKGROUND

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.

THE AIM OF THE STUDY

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.

The Use of a Novel Artificial Intelligence Platform for the Evaluation of Rhytids

BACKGROUND

Artificial intelligence (AI) platforms are increasingly being utilized in various healthcare applications. There are few platforms that provide quantifiable assessments of dermatologic or aesthetic conditions by employing industry established scales.

OBJECTIVES

The authors sought to report the results of a pilot study that evaluated the utilization and functionality of an AI engine to measure and monitor rhytids (fine lines). For this study, glabellar frown lines were employed as the clinical model.

METHODS

Seventy-one patients were enrolled and monitored remotely employing current high-quality mobile phone cameras over a 14-day period. The patients were prompted to take photographs employing this platform at preset intervals, and these photographs were then rated by the AI platform and qualified raters experienced in the field of facial aesthetics.

RESULTS

The AI platform had concordance with 2 qualified raters of 46% to 68%, and the inter-rater concordance between 2 rates ranged from 44% to 66%. The intra-rater concordance for the raters was between 57% and 84%, whereas the AI platform had a 100% concordance with itself. The participant and investigator satisfaction ratings of the platform were high on multiple dimensions of the platform.

CONCLUSIONS

This AI platform evaluated photos on a comparable level of accuracy as the qualified raters, and it evaluated more consistently than the qualified raters. This platform may have high utility in clinical research and development, including the management of clinical trials, and efficient management of patient care at the clinical practices.

Disease severity and status in Stevens–Johnson syndrome and toxic epidermal necrolysis: Key knowledge gaps and research needs

Stevens–Johnson syndrome and toxic epidermal necrolysis (SJS/TEN) are on a spectrum of cutaneous drug reactions characterized by pan-epidermal necrosis with SJS affecting < 10% of body surface area (BSA), TEN > 30%, and SJS/TEN overlap between 10 and 30%. Severity-of-illness score for toxic epidermal necrolysis (SCORTEN) is a validated tool to predict mortality rates based on age, heart rate, BSA, malignancy and serum urea, bicarbonate, and glucose. Despite improved understanding, SJS/TEN mortality remains constant and therapeutic interventions are not universally accepted for a number of reasons, including rarity of SJS/TEN; inconsistent definition of cases, disease severity, and endpoints in studies; low efficacy of interventions; and variations in treatment protocols. Apart from mortality, none of the other endpoints used to evaluate interventions, including duration of hospitalization, is sufficiently standardized to be reproducible across cases and treatment centers. Some of the gaps in SJS/TEN research can be narrowed through international collaboration to harmonize research endpoints. A case is made for an urgent international collaborative effort to develop consensus on definitions of endpoints such as disease status, progression, cessation, and complete re-epithelialization in interventional studies. The deficiencies of using BSA as the sole determinant of SJS/TEN severity, excluding internal organ involvement and extension of skin necrosis beyond the epidermis, are discussed and the role these factors play on time to healing and mortality beyond the acute stage is highlighted. The potential role of artificial intelligence, biomarkers, and PET/CT scan with radiolabeled glucose as markers of disease status, activity, and therapeutic response is also discussed.

Histologic Screening of Malignant Melanoma, Spitz, Dermal and Junctional Melanocytic Nevi Using a Deep Learning Model

OBJECTIVE

The integration of an artificial intelligence tool into pathologists' workflow may lead to a more accurate and timely diagnosis of melanocytic lesions, directly patient care. The objective of this study was to create and evaluate the performance of such a model in achieving clinical-grade diagnoses of Spitz nevi, dermal and junctional melanocytic nevi, and melanomas.

METHODS

We created a beginner-level training environment by teaching our algorithm to perform cytologic inferences on 136,216 manually annotated tiles of hematoxylin and eosin-stained slides consisting of unequivocal melanocytic nevi, Spitz nevi, and invasive melanoma cases. We sequentially trained and tested our network to provide a final diagnosis-classification on 39 cases in total. Positive predictive value (precision) and sensitivity (recall) were used to measure our performance.

RESULTS

The tile-classification algorithm predicted the 136,216 irrelevant, melanoma, melanocytic nevi, and Spitz nevi tiles at sensitivities of 96%, 93%, 94% and 73%, respectively. The final trained model was able to correctly classify and predict the correct diagnosis in 85.7% of unseen cases (n = 28), reporting at or near screening-level performances for precision and recall of melanoma (76.2%, 100.0%), melanocytic nevi (100.0%, 75.0%), and Spitz nevi (100.0%, 75.0%).

CONCLUSIONS

Our pilot study proves that convolutional networks trained on cellular morphology to classify melanocytic proliferations can be used as a powerful tool to assist pathologists in screening for melanoma versus other benign lesions.

Multi-Class Skin Lesion Classification Using a Lightweight Dynamic Kernel Deep-Learning-Based Convolutional Neural Network

Skin is the primary protective layer of the internal organs of the body. Nowadays, due to increasing pollution and multiple other factors, various types of skin diseases are growing globally. With variable shapes and multiple types, the classification of skin lesions is a challenging task. Motivated by this spreading deformity in society, a lightweight and efficient model is proposed for the highly accurate classification of skin lesions. Dynamic-sized kernels are used in layers to obtain the best results, resulting in very few trainable parameters. Further, both ReLU and leakyReLU activation functions are purposefully used in the proposed model. The model accurately classified all of the classes of the HAM10000 dataset. The model achieved an overall accuracy of 97.85%, which is much better than multiple state-of-the-art heavy models. Further, our work is compared with some popular state-of-the-art and recent existing models.

Applications of Telemedicine in Dermatology

Telemedicine is a technological tool that enhances well-being all around the globe. Practicing medicine or performing a clinical examination from a distance was a mere thought until this decade's pandemic hit the world. Telemedicine is practicing medicine sitting on one side of a globe and diagnosing and treating a different individual from the opposite part of the world. There is a long way to go for medical practitioners to execute an entire clinical examination analogous to an accurate clinical examination. Telemedicine is a supplement to a patient's total care, not a replacement for in-person doctor visits. Family doctors can easily access specialists using telemedicine, which enables them to monitor their patients closely. Numerous telemedicine systems, including store and forward, real-time and remote, or self-monitoring, are used worldwide for education, healthcare delivery and control, sickness screening, and disaster management. Even if telemedicine cannot solve every issue, it can significantly lessen the strain on the healthcare system. Nevertheless, investigations performed via telemedicine have started incorporating various medical instruments called telemedicine peripherals, including electronic stethoscopes, teleophthalmoscopes, and video-otoscopes. The prevailing disease around the globe of coronavirus has remarkably debilitated the medical infrastructure in providing diagnosis, treatment, monitoring, and follow-ups. As a result, there is a significant change in the way of practicing medicine and managing patients. Telemedicine provides timely patient care and reduces the risk of exposure to various communicable diseases offered to medical practitioners. The development of imaging technologies has significantly impacted dermatology, a specialty that relies on visual signals. Reviewing dermatology's existing situation and potential digital future, in brief, is the goal of this study. This study provides brief information on telemedicine, its application and scope in dermatology, and how it can alter the healthcare system.

Dermoscopic Photographs Impact Confidence and Management of Remotely Triaged Skin Lesions

Introduction

Improving remote triage is crucial given expansions in tele-dermatology and with limited in-person care during COVID-19. In addition to clinical pictures, dermoscopic images may provide utility for triage.

Objectives

To determine if dermoscopic images enhance confidence, triage accuracy, and triage prioritization for tele-dermatology.

Methods

In this preliminary parallel convergent mixed-methods study, a cohort of dermatologists and residents assessed skin lesions using clinical and dermoscopic images. For each case, participants viewed a clinical image and determined diagnostic category, management, urgency, and decision-making confidence. They subsequently viewed the associated dermoscopy and answered the same questions. A moderated focus group discussion followed to explore perceptions on the role of dermoscopy in tele-dermatology.

Results

Dermoscopy improved recognition of malignancies by 23% and significantly reduced triage urgency measures for non-malignant lesions. Participants endorsed specific utilities of tele-dermoscopy, such as for evaluating pigmented lesions, with limitations including poor image quality.

Conclusions

Dermoscopic images may be useful when remotely triaging skin lesions. Standardized imaging protocols are needed.

A Workflow for Computer-Aided Evaluation of Keloid Based on Laser Speckle Contrast Imaging and Deep Learning

A keloid results from abnormal wound healing, which has different blood perfusion and growth states among patients. Active monitoring and treatment of actively growing keloids at the initial stage can effectively inhibit keloid enlargement and has important medical and aesthetic implications. LSCI (laser speckle contrast imaging) has been developed to obtain the blood perfusion of the keloid and shows a high relationship with the severity and prognosis. However, the LSCI-based method requires manual annotation and evaluation of the keloid, which is time consuming. Although many studies have designed deep-learning networks for the detection and classification of skin lesions, there are still challenges to the assessment of keloid growth status, especially based on small samples. This retrospective study included 150 untreated keloid patients, intensity images, and blood perfusion images obtained from LSCI. A newly proposed workflow based on cascaded vision transformer architecture was proposed, reaching a dice coefficient value of 0.895 for keloid segmentation by 2% improvement, an error of 8.6 ± 5.4 perfusion units, and a relative error of 7.8% ± 6.6% for blood calculation, and an accuracy of 0.927 for growth state prediction by 1.4% improvement than baseline.

Objective and automatic grading system of facial signs from selfie pictures of South African women: Characterization of changes with age and sun‐exposures

OBJECTIVE

To evaluate the capacity of the automatic detection system to accurately grade, from smartphones' selfie pictures, the severity of fifteen facial signs in South African women and their changes related to age and sun-exposure habits.

METHODS

A two-steps approach was conducted based on self-taken selfie images. At first, to assess on 306 South African women (20-69 years) enrolled in Pretoria area (25.74°S, 28.22°E), age changes on fifteen facial signs measured by an artificial intelligence (AI)-based automatic grading system previously validated by experts/dermatologists. Second, as these South African panelists were recruited according to their usual behavior toward sun-exposure, that is, nonsun-phobic (NSP, N = 151) and sun-phobic (SP, N = 155) and through their regular and early use of a photo-protective product, to characterize the facial photo-damages.

RESULTS

(1) The automatic scores showed significant changes with age, by decade, of sagging and wrinkles/texture (p < 0.05) after 20 and 30 years, respectively. Pigmentation cluster scores presented no significant changes with age whereas cheek skin pores enlarged at a low extent with two plateaus at thirties and fifties. (2) After 60 years, a significantly increased severity of wrinkles/texture and sagging was observed in NSP versus SP women (p < 0.05). A trend of an increased pigmentation of the eye contour (p = 0.06) was observed after 50 years.

CONCLUSION

This work illustrates specific impacts of aging and sun-exposures on facial signs of South African women, when compared to previous experiments conducted in Europe or East Asia. Results significantly confirm the importance of sun-avoidance coupled with photo-protective measures to avoid long-term skin damages. In inclusive epidemiological studies that aim at investigating large human panels in very different contexts, the AI-based system offers a fast, affordable and confidential approach in the detection and quantification of facial signs and their dependency with ages, environments, and lifestyles.

Leveraging Artificial Intelligence to Improve the Diversity of Dermatological Skin Color Pathology: Protocol for an Algorithm Development and Validation Study

Background

The paucity of dark skin images in dermatological textbooks and atlases is a reflection of racial injustice in medicine. The underrepresentation of dark skin images makes diagnosing skin pathology in people of color challenging. For conditions such as skin cancer, in which early diagnosis makes a difference between life and death, people of color have worse prognoses and lower survival rates than people with lighter skin tones as a result of delayed or incorrect diagnoses. Recent advances in artificial intelligence, such as deep learning, offer a potential solution that can be achieved by diversifying the mostly light-skin image repositories through generating images for darker skin tones. Thus, facilitating the development of inclusive cancer early diagnosis systems that are trained and tested on diverse images that truly represent human skin tones.

Objective

We aim to develop and evaluate an artificial intelligence–based skin cancer early detection system for all skin tones using clinical images.

Methods

This study consists of four phases: (1) Publicly available skin image repositories will be analyzed to quantify the underrepresentation of darker skin tones, (2) Images will be generated for the underrepresented skin tones, (3) Generated images will be extensively evaluated for realism and disease presentation with quantitative image quality assessment as well as qualitative human expert and nonexpert ratings, and (4) The images will be utilized with available light-skin images to develop a robust skin cancer early detection model.

Results

This study started in September 2020. The first phase of quantifying the underrepresentation of darker skin tones was completed in March 2021. The second phase of generating the images is in progress and will be completed by March 2022. The third phase is expected to be completed by May 2022, and the final phase is expected to be completed by September 2022.

Conclusions

This work is the first step toward expanding skin tone diversity in existing image databases to address the current gap in the underrepresentation of darker skin tones. Once validated, the image bank will be a valuable resource that can potentially be utilized in physician education and in research applications. Furthermore, generated images are expected to improve the generalizability of skin cancer detection. When completed, the model will assist family physicians and general practitioners in evaluating skin lesion severity and in efficient triaging for referral to expert dermatologists. In addition, the model can assist dermatologists in diagnosing skin lesions.

International Registered Report Identifier (IRRID)

DERR1-10.2196/34896

Skin lesion classification system using a K-nearest neighbor algorithm

One of the most critical steps in medical health is the proper diagnosis of the disease. Dermatology is one of the most volatile and challenging fields in terms of diagnosis. Dermatologists often require further testing, review of the patient's history, and other data to ensure a proper diagnosis. Therefore, finding a method that can guarantee a proper trusted diagnosis quickly is essential. Several approaches have been developed over the years to facilitate the diagnosis based on machine learning. However, the developed systems lack certain properties, such as high accuracy. This study proposes a system developed in MATLAB that can identify skin lesions and classify them as normal or benign. The classification process is effectuated by implementing the K-nearest neighbor (KNN) approach to differentiate between normal skin and malignant skin lesions that imply pathology. KNN is used because it is time efficient and promises highly accurate results. The accuracy of the system reached 98% in classifying skin lesions.

Diagnosing onychomycosis: A step forward?

BACKGROUND AND AIMS

There are a number of available methods for diagnosing onychomycosis, but more emerge as technology advances. This review briefly discusses the common diagnostic methods, the use of artificial intelligence (AI) as a diagnostic tool in dermatology as a whole, and then examines research on the use of AI for diagnosing onychomycosis. The studies discussed implemented convolutional neural networks (CNNs) to examine datasets of images of entire nails or histological images and then used the information learned from those datasets to make a diagnostic decision of onychomycosis or not.

RESULTS

Results: It was found that, on average, AI were able to diagnose onychomycosis from the images provided at an equivalent level as human dermatologists. However, there are a number of clear limitations for using AI in this manner. The AI models implemented relied solely on images and therefore were limited by image quality. As only images were examined, other clinical data were not taken into consideration, which could be important to the diagnostic outcome.

CONCLUSION

Conclusion: In conclusion, although AI can be a very helpful tool in the diagnostic process by increasing efficiency and reducing costs, it still requires the precision and expertise of professional dermatologists to be used optimally.

Artificial intelligence for diabetic retinopathy

ABSTRACT

Diabetic retinopathy (DR) is an important cause of blindness globally, and its prevalence is increasing. Early detection and intervention can help change the outcomes of the disease. The rapid development of artificial intelligence (AI) in recent years has led to new possibilities for the screening and diagnosis of DR. An AI-based diagnostic system for the detection of DR has significant advantages, such as high efficiency, high accuracy, and lower demand for human resources. At the same time, there are shortcomings, such as the lack of standards for development and evaluation and the limited scope of application. This article demonstrates the current applications of AI in the field of DR, existing problems, and possible future development directions.

Clinical outcomes and operational impact of a medical photography based teledermatology service with over 8,000 patients in the UK

A new, store-and-forward, fully digitised Teledermatology (TD) pathway was designed and implemented in an urban setting for non-two-week wait routine patients. In total 8,352 new patients had a TD consultation over 37 months. Of these, 4,748 (56.8%) were referred back to their GP, 1,634 (19.6%) were referred directly for a surgical procedure and 1,970 (23.6%) for a face-to-face review with a Dermatologist (F2F). The average waiting time for a TD appointment was 3 vs. 30 weeks for a routine F2F appointment. Between 2019 and 2018, TD referrals rose by 38%, routine dermatology referrals reduced by 16% and cancer referrals increased by 6%. Using medical photographers proved to be effective with only two cases (0.02%) of images being of insufficient quality to form a clinical opinion. Hitherto, savings for the local Commissioning Groups were estimated at £671,218. Last financial year savings (2019-2020) were £284,671. The average cost savings per TD patient appointment was £80.36. Savings in the Trust's overhead costs were £53,587. TD consultants reviewed almost twice the number of patients vs. F2F for the same amount of consultant programmed activities. 95% of surveyed patients would be likely or extremely likely to recommend this service to friends and family.

Accuracy of commercially available smartphone applications for the detection of melanoma

Artificial intelligence (AI) has shown promise in the analysis of images for detection of melanoma.¹ The number of available dermatology smartphone applications ("apps") is rapidly growing and there is increasing interest in apps that provide diagnosis or triage of skin lesions.^{2, 3} A 2020 systematic review found that nine studies evaluating six apps had poor study design and high risk of bias.³ To date, no studies have evaluated the accuracy of apps using an independent test set of clinical images comparable to those submitted through smartphones .

Characteristics of publicly available skin cancer image datasets: a systematic review

Publicly available skin image datasets are increasingly used to develop machine learning algorithms for skin cancer diagnosis. However, the total number of datasets and their respective content is currently unclear. This systematic review aimed to identify and evaluate all publicly available skin image datasets used for skin cancer diagnosis by exploring their characteristics, data access requirements, and associated image metadata. A combined MEDLINE, Google, and Google Dataset search identified 21 open access datasets containing 106 950 skin lesion images, 17 open access atlases, eight regulated access datasets, and three regulated access atlases. Images and accompanying data from open access datasets were evaluated by two independent reviewers. Among the 14 datasets that reported country of origin, most (11 [79%]) originated from Europe, North America, and Oceania exclusively. Most datasets (19 [91%]) contained dermoscopic images or macroscopic photographs only. Clinical information was available regarding age for 81 662 images (76·4%), sex for 82 848 (77·5%), and body site for 79 561 (74·4%). Subject ethnicity data were available for 1415 images (1·3%), and Fitzpatrick skin type data for 2236 (2·1%). There was limited and variable reporting of characteristics and metadata among datasets, with substantial under-representation of darker skin types. This is the first systematic review to characterise publicly available skin image datasets, highlighting limited applicability to real-life clinical settings and restricted population representation, precluding generalisability. Quality standards for characteristics and metadata reporting for skin image datasets are needed.

Design and Assessment of Convolutional Neural Network Based Methods for Vitiligo Diagnosis

Background: Today's machine-learning based dermatologic research has largely focused on pigmented/non-pigmented lesions concerning skin cancers. However, studies on machine-learning-aided diagnosis of depigmented non-melanocytic lesions, which are more difficult to diagnose by unaided eye, are very few. Objective: We aim to assess the performance of deep learning methods for diagnosing vitiligo by deploying Convolutional Neural Networks (CNNs) and comparing their diagnosis accuracy with that of human raters with different levels of experience. Methods: A Chinese in-house dataset (2,876 images) and a world-wide public dataset (1,341 images) containing vitiligo and other depigmented/hypopigmented lesions were constructed. Three CNN models were trained on close-up images in both datasets. The results by the CNNs were compared with those by 14 human raters from four groups: expert raters (>10 years of experience), intermediate raters (5-10 years), dermatology residents, and general practitioners. F1 score, the area under the receiver operating characteristic curve (AUC), specificity, and sensitivity metrics were used to compare the performance of the CNNs with that of the raters. Results: For the in-house dataset, CNNs achieved a comparable F1 score (mean [standard deviation]) with expert raters (0.8864 [0.005] vs. 0.8933 [0.044]) and outperformed intermediate raters (0.7603 [0.029]), dermatology residents (0.6161 [0.068]) and general practitioners (0.4964 [0.139]). For the public dataset, CNNs achieved a higher F1 score (0.9684 [0.005]) compared to the diagnosis of expert raters (0.9221 [0.031]). Conclusion: Properly designed and trained CNNs are able to diagnose vitiligo without the aid of Wood's lamp images and outperform human raters in an experimental setting.

Patient and general public attitudes towards clinical artificial intelligence: a mixed methods systematic review

Artificial intelligence (AI) promises to change health care, with some studies showing proof of concept of a provider-level performance in various medical specialties. However, there are many barriers to implementing AI, including patient acceptance and understanding of AI. Patients' attitudes toward AI are not well understood. We systematically reviewed the literature on patient and general public attitudes toward clinical AI (either hypothetical or realised), including quantitative, qualitative, and mixed methods original research articles. We searched biomedical and computational databases from Jan 1, 2000, to Sept 28, 2020, and screened 2590 articles, 23 of which met our inclusion criteria. Studies were heterogeneous regarding the study population, study design, and the field and type of AI under study. Six (26%) studies assessed currently available or soon-to-be available AI tools, whereas 17 (74%) assessed hypothetical or broadly defined AI. The quality of the methods of these studies was mixed, with a frequent issue of selection bias. Overall, patients and the general public conveyed positive attitudes toward AI but had many reservations and preferred human supervision. We summarise our findings in six themes: AI concept, AI acceptability, AI relationship with humans, AI development and implementation, AI strengths and benefits, and AI weaknesses and risks. We suggest guidance for future studies, with the goal of supporting the safe, equitable, and patient-centred implementation of clinical AI.

Clinical and immunologic differences in cellulitis vs. pseudocellulitis

Introduction: The immunologic mechanisms between cellulitis and pseudocellulitis differ greatly, even though their clinical presentations may overlap.Areas covered: This article discusses cellulitis and common entities within the pseudocellulitis spectrum including acute lymphedema, superficial venous thrombosis, allergic contact dermatitis, lipodermatosclerosis, stasis dermatitis, erythema nodosum, cutaneous gout, and bursitis. The literature search was conducted from PubMed search engine between March and May 2021.Expert commentary: While immunologic differences in cellulitis and the various entities of pseudocellulitis are clear, there is a practice gap in applying these differences to the clinic and hospital setting. Further, existing studies are weakened by the lack of a gold-standard diagnosis in this disease category. Additional work is necessary in developing a gold-standard for the diagnosis and secondly, to project these immunologic differences as biomarkers to differentiate sterile inflammation from a potential life threatening bacterial or fungal infection.

Deep-learning approach in the study of skin lesions

BACKGROUND

Medical technology is far from reaching its full potential. An area that is currently expanding is that of precision medicine. The aim of this article is to present an application of precision medicine-a deep-learning approach to computer-aided diagnosis in the field of dermatology.

MATERIALS AND METHODS

The main dataset was proposed in the edition of the ISIC Challenge that took place in 2019 and included 25 331 dermoscopic images from eight different categories of lesions-three of them were malignant and five benign. The behavior of the model was also tested on a dataset collected from the second Department of Dermatology, of the Colentina Clinical Hospital.

RESULTS

The overall accuracy of the model was 78.11%. Of the total 5031 samples included in the test subset, 3958 were correctly classified. The accuracy of the model on the clinical dataset is lower than that obtained in the first instance.

CONCLUSION

The architecture of the model can be considered of general use, being able to be adapted in an optimal way for a wide range of classifications. The model has achieved performance within the expected limits but can be further improved by new methods.

Comparing the self-perceived effects of a facial anti-aging product to those automatically detected from selfie images of Chinese women of different ages and cities

OBJECTIVE

To assess the agreement, after 1-month application of a popular and efficient anti-aging product, between self-perceived facial signs of aging and those detected and graded by an automatic A.I-based system, using smartphones' selfie images.

MATERIAL AND METHODS

Of 1065 Chinese women, aged 18-60 years, from eight different Chinese cities were recruited. They were asked to apply daily, for 1 month, a referential anti-aging product onto their whole face. Selfie images were taken by all subjects at D₀ and D₂₈ and sent to our facilities for being analyzed through 10 different facial signs. At D₂₈ , all subjects were asked to fill a questionnaire on the status of their faces, through six general statements.

RESULTS

A global agreement between both approaches is reached, particularly among women older than 40 years where the severity of facial signs is already more pronounced or among younger women who present at least facial signs scored above one grading units. This limit becomes, therefore, a prerequisite in the recruitment of Chinese subjects in the case of anti-aging applied studies and possible automatically based on automatic grading system. When respecting such conditions, the positive effects of the product on most facial signs can be demonstrated after 28 days of successive applications.

CONCLUSION

Such methodological approach paves the road in fulfilling the need of consumers of a better transparency in the claims of an anti-aging product.

Raising the Bar for Randomized Trials Involving Artificial Intelligence: The SPIRIT-Artificial Intelligence and CONSORT-Artificial Intelligence Guidelines

Artificial intelligence (AI)-based applications have the potential to improve the quality and efficiency of patient care in dermatology. Unique challenges in the development and validation of these technologies may limit their generalizability and real-world applicability. Before the widespread adoption of AI interventions, randomized trials should be conducted to evaluate their efficacy, safety, and cost effectiveness in clinical settings. The recent Standard Protocol Items: Recommendations for Interventional Trials-AI extension and Consolidated Standards of Reporting Trials-AI extension guidelines provide recommendations for reporting the methods and results of trials involving AI interventions. High-quality trials will provide gold standard evidence to support the adoption of AI for the benefit of patient care.

Stress testing reveals gaps in clinic readiness of image-based diagnostic artificial intelligence models

Artificial intelligence models match or exceed dermatologists in melanoma image classification. Less is known about their robustness against real-world variations, and clinicians may incorrectly assume that a model with an acceptable area under the receiver operating characteristic curve or related performance metric is ready for clinical use. Here, we systematically assessed the performance of dermatologist-level convolutional neural networks (CNNs) on real-world non-curated images by applying computational "stress tests". Our goal was to create a proxy environment in which to comprehensively test the generalizability of off-the-shelf CNNs developed without training or evaluation protocols specific to individual clinics. We found inconsistent predictions on images captured repeatedly in the same setting or subjected to simple transformations (e.g., rotation). Such transformations resulted in false positive or negative predictions for 6.5-22% of skin lesions across test datasets. Our findings indicate that models meeting conventionally reported metrics need further validation with computational stress tests to assess clinic readiness.

Deep learning-enabled medical computer vision

A decade of unprecedented progress in artificial intelligence (AI) has demonstrated the potential for many fields-including medicine-to benefit from the insights that AI techniques can extract from data. Here we survey recent progress in the development of modern computer vision techniques-powered by deep learning-for medical applications, focusing on medical imaging, medical video, and clinical deployment. We start by briefly summarizing a decade of progress in convolutional neural networks, including the vision tasks they enable, in the context of healthcare. Next, we discuss several example medical imaging applications that stand to benefit-including cardiology, pathology, dermatology, ophthalmology-and propose new avenues for continued work. We then expand into general medical video, highlighting ways in which clinical workflows can integrate computer vision to enhance care. Finally, we discuss the challenges and hurdles required for real-world clinical deployment of these technologies.

The impact of demographics, socioeconomics, and health care access on melanoma outcomes

Disparities in melanoma care exist in the United States. Disparities in provider type, patient demographics, place of residence, insurance status, socioeconomic status, race/ethnicity, and age impact melanoma outcomes. Melanomas detected by dermatologists are thinner, at an earlier stage, and have better survival outcomes compared with detection by primary care providers or patients. Lower socioeconomic status, race/ethnicity, and place of residence are associated with decreased access to or use of dermatologists, or both, and more advanced melanomas at diagnosis. Additionally, uninsured and publicly insured individuals are more likely to present with late-stage melanomas, resulting in worse outcomes. This review provides a comprehensive overview of how structural and patient-level characteristics influence melanoma outcomes in order to inform clinical care and health care policy as it relates to addressing gaps in melanoma care.

The role of technology in melanoma screening and diagnosis

Melanoma presents challenges for timely and accurate diagnosis. Expert panels have issued risk-based screening guidelines, with recommended screening by visual inspection. To assess how recent technology can impact the risk/benefit considerations for melanoma screening, we comprehensively reviewed non-invasive visual-based technologies. Dermoscopy increases lesional diagnostic accuracy for both dermatologists and primary care providers; total body photography and sequential digital dermoscopic imaging also increase diagnostic accuracy, are supported by automated lesion detection and tracking, and may be best suited to use by dermatologists for longitudinal follow-up. Specialized imaging modalities using non-visible light technology have unproven benefit over dermoscopy and can be limited by cost, access, and training requirements. Mobile apps facilitate image capture and lesion tracking. Teledermatology has good concordance with face-to-face consultation and increases access, with increased accuracy using dermoscopy. Deep learning models can surpass dermatologist accuracy, but their clinical utility has yet to be demonstrated. Technology-aided diagnosis may change the calculus of screening; however, well-designed prospective trials are needed to assess the efficacy of these different technologies, alone and in combination to support refinement of guidelines for melanoma screening.