Computational characterization of reflectance confocal microscopy features reveals potential for automated photoageing assessment

The CSIESA: A Novel Score for the Assessment of Intrinsic and Extrinsic Skin Aging Based on Reflectance Confocal Microscopy Imaging

Skin aging is an intricate physiological process governed by intrinsic and extrinsic factors. Increasing life expectancy has turned skin aging into a growing concern for the general population. Clinical examination of the skin does not fully describe the skin aging process. This study aims to evaluate the healthy skin of five different age groups in order to develop an easy-to-use confocal score for quantifying signs of skin aging and test the correlation between this new score and the already described clinical score, SCINEXA (score of intrinsic and extrinsic skin aging). Thirty-five subjects split into five age groups: <35; 36−45; 46−55; 56−65, and >65 years old were enrolled. Clinical signs were quantified using the SCINEXA score, and known confocal variables of skin aging were evaluated. Three different semi-quantitative scores were calculated: epidermal disarrangement score (EDS), epidermal hyperplasia score (EHS), and dermal score (DS). The EDS showed a stable trend up to the age of 65 and a dramatic increase in older subjects. EHS was characterized by an ascending trend from younger subjects to middle-aged ones. The DS was progressive with age, with a different proportion of distinct collagen types. The confocal CSIESA (confocal score for the assessment of intrinsic and extrinsic skin aging) score correlated well with the SCINEXA score. Reflectance confocal microscopy is a powerful, non-invasive technique for microscopically quantifying aging signs.

Application of a Reflectance Confocal Microscopy Imaging Analysis Score for the Evaluation of Non-Melanogenic Changes in Male Photoaged Skin

The photoaging process is characterized by skin changes due to ultraviolet radiation exposure and is the principal environmental factor affecting skin aging. Reflectance confocal microscopy permits noninvasive skin imaging to understand how the photoaging process may change skin. Since men do not habitually use a sunscreen, the application of skin imaging techniques is important to understand the influence of sunlight on their skin health. The aim of this study was to develop a score based on RCM imaging analyses to evaluate the morphological and structural changes of the photoaged skin according to literature data. The score was applied in order to determine possible correlations between chronological aging and sunscreen use behavior among men. Thus, 40 men aged 18 to 50 years were recruited, images from the frontal region of their skin were obtained and the score was applied. It was observed that habits are more important than age for the skin photoaging process. Men with photoprotection habits showed overall better skin morphological and structural characteristics regardless of age, demonstrating that sun protection behavior is a major key factor in the understanding of photoaging, so that men should be encouraged to start the use of cosmetic products and to perform selfcare.

Towards data-driven quantification of skin ageing using reflectance confocal microscopy

INTRODUCTION

Evaluation of skin ageing is a non-standardized, subjective process, with typical measures relying coarse, qualitatively defined features. Reflectance confocal microscopy depth stacks contain indicators of both chrono-ageing and photo-ageing. We hypothesize that an ageing scale could be constructed using machine learning and image analysis, creating a data-driven quantification of skin ageing without human assessment.

METHODS

En-face sections of reflectance confocal microscopy depth stacks from the dorsal and volar forearm of 74 participants (36/18/20 training/testing/validation) were represented using a histogram of visual features learned using unsupervised clustering of small image patches. A logistic regression classifier was trained on these histograms to differentiate between stacks from 20- to 30-year-old and 50- to 70-year-old volunteers. The probabilistic output of the logistic regression was used as the fine-grained ageing score for that stack in the testing set ranging from 0 to 1. Evaluation was performed in two ways: on the test set, the AUC was collected for the binary classification problem as well as by statistical comparison of the scores for age and body site groups. Final validation was performed by assessing the accuracy of the ageing score measurement on 20 depth stacks not used for training or evaluating the classifier.

RESULTS

The classifier effectively differentiated stacks from age groups with a test set AUC of 0.908. Mean scores were significantly different when comparing age groups (mean 0.70 vs. 0.44; t = -6.62, p = 0.0000) and also when comparing stacks from dorsal and volar body sites (mean 0.64 vs. 0.53; t = 3.12, p = 0.0062). On the final validation set, 17 out of 20 depth stacks were correctly labelled.

DISCUSSION

Despite being limited to only coarse training information in the form of example stacks from two age groups, the trained classifier was still able to effectively discriminate between younger skin and older skin. Curiously, despite being only trained with chronological age, there was still evidence for measurable differences in age scores due to sun exposure-with marked differences in scores on sun-exposed dorsal sites of some volunteers compared with less sun-exposed volar sites. These results suggest that fine-grained data-driven quantification of skin ageing is achievable.

A Clinical Perspective on the Automated Analysis of Reflectance Confocal Microscopy in Dermatology

BACKGROUND AND OBJECTIVES

Non-invasive optical imaging has the potential to provide a diagnosis without the need for biopsy. One such technology is reflectance confocal microscopy (RCM), which uses low power, near-infrared laser light to enable real-time in vivo visualization of superficial human skin from the epidermis down to the papillary dermis. Although RCM has great potential as a diagnostic tool, there is a need for the development of reliable image analysis programs, as acquired grayscale images can be difficult and time-consuming to visually assess. The purpose of this review is to provide a clinical perspective on the current state of artificial intelligence (AI) for the analysis and diagnostic utility of RCM imaging.

STUDY DESIGN/MATERIALS AND METHODS

A systematic PubMed search was conducted with additional relevant literature obtained from reference lists.

RESULTS

Algorithms used for skin stratification, classification of pigmented lesions, and the quantification of photoaging were reviewed. Image segmentation, statistical methods, and machine learning techniques are among the most common methods used to analyze RCM image stacks. The poor visual contrast within RCM images and difficulty navigating image stacks were mediated by machine learning algorithms, which allowed the identification of specific skin layers.

CONCLUSIONS

AI analysis of RCM images has the potential to increase the clinical utility of this emerging technology. A number of different techniques have been utilized but further refinements are necessary to allow consistent accurate assessments for diagnosis. The automated detection of skin cancers requires more development, but future applications are truly boundless, and it is compelling to envision the role that AI will have in the practice of dermatology. Lasers Surg. Med. © 2020 Wiley Periodicals LLC.

Structural skin changes in elderly people investigated by reflectance confocal microscopy

BACKGROUND

Reflectance confocal microscopy (RCM) is particularly suitable for the study of skin ageing because it provides nearly histological information in vivo and non-invasively. However, there are no studies that evaluated RCM skin features of a large population older than 70 years.

OBJECTIVES

The aim of our investigation was to study age-related skin changes in an elderly population by RCM and to evaluate their topographical and gender differences.

METHODS

We obtained RCM images of photoprotected (volar arm) and chronic (face) and intermittently photoexposed (dorsal forearm) body sites of 209 volunteers (105 women and 104 men, mean age: 77.5, range 74-81 years). 15 previously reported and new RCM parameters related to skin ageing were assessed.

RESULTS

Photoexposed sites had thicker suprapapillary epidermis, more linear, distant and thin furrows, higher presence of mottled pigmentation, polycyclic papillae and coarse and huddled collagen and lower presence of dermal papillae than the photoprotected site. Irregular honeycomb pattern was not higher in photoexposed sites, indicating that it is probably more dependent on intrinsic ageing. Two ageing scores defined for facial skin ageing (epidermal disarray score and epidermal hyperplasia score) were found useful for the identification of photoageing. Gender differences only concerned some RCM parameters (i.e. thickness of different layers of the epidermis, furrows and collagen score) and some body sites, in line with the fact that women and men of our cohort had no major differences in clinically visible skin ageing.

CONCLUSIONS

Our study confirmed that RCM is a powerful non-invasive technique to microscopically quantify ageing signs and our observations contribute to highlight the differences between intrinsic and extrinsic ageing.

Wavelet-based statistical classification of skin images acquired with reflectance confocal microscopy

Detecting skin lentigo in reflectance confocal microscopy images is an important and challenging problem. This imaging modality has not yet been widely investigated for this problem and there are a few automatic processing techniques. They are mostly based on machine learning approaches and rely on numerous classical image features that lead to high computational costs given the very large resolution of these images. This paper presents a detection method with very low computational complexity that is able to identify the skin depth at which the lentigo can be detected. The proposed method performs multiresolution decomposition of the image obtained at each skin depth. The distribution of image pixels at a given depth can be approximated accurately by a generalized Gaussian distribution whose parameters depend on the decomposition scale, resulting in a very-low-dimension parameter space. SVM classifiers are then investigated to classify the scale parameter of this distribution allowing real-time detection of lentigo. The method is applied to 45 healthy and lentigo patients from a clinical study, where sensitivity of 81.4% and specificity of 83.3% are achieved. Our results show that lentigo is identifiable at depths between 50μm and 60μm, corresponding to the average location of the the dermoepidermal junction. This result is in agreement with the clinical practices that characterize the lentigo by assessing the disorganization of the dermoepidermal junction.

Automated Segmentation of Skin Strata in Reflectance Confocal Microscopy Depth Stacks

Reflectance confocal microscopy (RCM) is a powerful tool for in-vivo examination of a variety of skin diseases. However, current use of RCM depends on qualitative examination by a human expert to look for specific features in the different strata of the skin. Developing approaches to quantify features in RCM imagery requires an automated understanding of what anatomical strata is present in a given en-face section. This work presents an automated approach using a bag of features approach to represent en-face sections and a logistic regression classifier to classify sections into one of four classes (stratum corneum, viable epidermis, dermal-epidermal junction and papillary dermis). This approach was developed and tested using a dataset of 308 depth stacks from 54 volunteers in two age groups (20–30 and 50–70 years of age). The classification accuracy on the test set was 85.6%. The mean absolute error in determining the interface depth for each of the stratum corneum/viable epidermis, viable epidermis/dermal-epidermal junction and dermal-epidermal junction/papillary dermis interfaces were 3.1 μm, 6.0 μm and 5.5 μm respectively. The probabilities predicted by the classifier in the test set showed that the classifier learned an effective model of the anatomy of human skin.

The dynamic anatomy and patterning of skin

The skin is often viewed as a static barrier that protects the body from the outside world. Emphasis on studying the skin's architecture and biomechanics in the context of restoring skin movement and function is often ignored. It is fundamentally important that if skin is to be modelled or developed, we do not only focus on the biology of skin but also aim to understand its mechanical properties and structure in living dynamic tissue. In this review, we describe the architecture of skin and patterning seen in skin as viewed from a surgical perspective and highlight aspects of the microanatomy that have never fully been realized and provide evidence or concepts that support the importance of studying living skin's dynamic behaviour. We highlight how the structure of the skin has evolved to allow the body dynamic form and function, and how injury, disease or ageing results in a dramatic changes to the microarchitecture and changes physical characteristics of skin. Therefore, appreciating the dynamic microanatomy of skin from the deep fascia through to the skin surface is vitally important from a dermatological and surgical perspective. This focus provides an alternative perspective and approach to addressing skin pathologies and skin ageing.

High-definition optical coherence tomography intrinsic skin ageing assessment in women: a pilot study

Several non-invasive two-dimensional techniques with different lateral resolution and measurable depth range have proved to be useful in assessing and quantifying morphological changes in skin ageing. Among these, only in vivo microscopy techniques permit histometric measurements in vivo. Qualitative and quantitative assessment of chronological (intrinsic) age-related (IAR) morphological changes of epidermis, dermo-epidermal junction (DEJ), papillary dermis (PD), papillary-reticular dermis junction and reticular dermis (RD) have been performed by high-definition optical coherence tomography in real time 3-D. HD-OCT images were taken at the internal site of the right upper arm. Qualitative HD-OCT IAR descriptors were reported at skin surface, at epidermal layer, DEJ, PD and upper RD. Quantitative evaluation of age-related compaction and backscattered intensity or brightness of different skin layers was performed by using the plugin plot z-axis profile of ImageJ^® software permitting intensity assessment of HD-OCT (DICOM) images (3-D images). Analysis was in blind from all clinical information. Sixty, fair-skinned (Fitzpatrick types I–III) healthy females were analysed retrospectively in this study. The subjects belonged to three age groups: twenty in group I aged 20–39, twenty in group II aged 40–59 and twenty in group III aged 60–79. Only intrinsic ageing in women has been studied. Significant age-related qualitative and quantitative differences could be noticed. IAR changes in dermal matrix fibers morphology/organisation and in microvasculature were observed. The brightness and compaction of the different skin layers increased significantly with intrinsic skin ageing. The depth of visibility of fibers in RD increased significantly in the older age group. In conclusion, HD-OCT allows 3-D in vivo and real time qualitative and quantitative assessment of chronological (intrinsic) age-related morphological skin changes at high resolution from skin surface to a depth of the superficial reticular dermis.

Formulation design for topical drug and nanoparticle treatment of skin disease

The skin has evolved to resist the penetration of foreign substances and particles. Topical therapeutic and cosmeceutical delivery is a growing field founded on selectively overcoming this barrier. Both the biology of the skin and the nature of the formulation/active ingredient must be aligned for efficient transcutaneous delivery. This review discusses the biological changes in the skin barrier that occur with common dermatological conditions. This context is the foundation for the discussion of formulation strategies to improve penetration profiles of common active ingredients in dermatology. Finally, we compare and contrast those approaches to recent advances described in the research literature with an eye toward the future of topical formulation design.

Confocal microscopy: a new era in understanding the pathophysiologic background of inflammatory skin diseases

One of the emerging and intriguing applications of reflectance confocal microscopy is the evaluation of 'dynamic' processes of the skin that cannot be otherwise analysed using histopathology that offers a picture of the tissue at one time point. This is nicely illustrated by recent article by Wolberink et al. in the current issue of Exp Dermatol, in which the Authors evaluated patterns and time interval of polymorphonuclear neutrophil (PMN) migration in psoriatic plaques by means of reflectance confocal microscopy (RCM). This example underscores that a new era of confocal microscopy is starting, which promises to reveal a dynamic in vivo understanding of the pathophysiology of human skin diseases.