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.

Download Full-text

In vivo reflectance confocal microscopy in a typical case of melasma

Anais Brasileiros de Dermatologia ◽

10.1590/s0365-05962012000500021 ◽

2012 ◽

Vol 87 (5) ◽

pp. 782-784 ◽

Cited By ~ 5

Author(s):

Mariana Carvalho Costa ◽

Hernando Vega Eljaiek ◽

Leonardo Spagnol Abraham ◽

Luna Azulay-Abulafia ◽

Marco Ardigo

Keyword(s):

Confocal Microscopy ◽

Real Time ◽

Typical Case ◽

Reflectance Confocal Microscopy ◽

Noninvasive Evaluation ◽

Common Disorder ◽

Face Images ◽

Cellular Resolution ◽

En Face

Melasma is a common disorder of hypermelanosis that affects mainly young and middle-aged women of Fitzpatrick's phototypes III-V. The disease significantly impacts their lives. In vivo reflectance confocal microscopy, a spreading technology for the noninvasive evaluation of the skin up to the papillary dermis, provides real-time en face images with cellular resolution. We present a case of melasma with in vivo reflectance confocal microscopy findings closely correlated to the histopathological features described in the literature.

Download Full-text

In Vivo Reflectance Confocal Microscopy of Halo Nevus

Journal of Cutaneous Medicine and Surgery ◽

10.2310/7750.2012.12019 ◽

2013 ◽

Vol 17 (1) ◽

pp. 33-38 ◽

Cited By ~ 2

Author(s):

Rodrigo J. Schwartz ◽

Karla Vera ◽

Nelson Navarrete ◽

Pedro Lobos

Keyword(s):

High Resolution ◽

Malignant Melanoma ◽

Confocal Microscopy ◽

Skin Diseases ◽

Dermal Papilla ◽

Reflectance Confocal Microscopy ◽

Melanocytic Lesions ◽

Global Patterns ◽

Dermal Papillae

Background: RCM (reflectance confocal microscopy) is a noninvasive, high-resolution technology that has been proven to improve the diagnostic accuracy over clinical examination in several skin diseases. Objective: The aim of this article is to describe the morphologic features of halo nevi (HN) observed with RCM and correlate them with their dermoscopic characteristics. Method: Nine patients with the clinical diagnosis of HN were assessed with RCM. A second assessment was performed up to 12 months later. Dermoscopic global patterns were obtained and correlated with the RCM findings. Results: In five (55.6%) cases, pagetoid cells were observed. Nonedged dermal papilla and junctional thickening were found in three (33%) cases. Nucleated cells in the dermal papillae and plump bright cells were observed in seven (77.8%) and six (66.7%) cases, respectively. Conclusion: Our study shows that HN observed by RCM can show atypical features that overlap with those observed on atypical melanocytic lesions and malignant melanoma.

Download Full-text

In vivo Diagnosis of Primary Cutaneous Amyloidosis —the Role of Reflectance Confocal Microscopy

Diagnostics ◽

10.3390/diagnostics9030066 ◽

2019 ◽

Vol 9 (3) ◽

pp. 66 ◽

Cited By ~ 1

Author(s):

Ana-Maria Ionescu ◽

Mihaela-Adriana Ilie ◽

Virginia Chitu ◽

Andrei Razvan ◽

Daniela Lixandru ◽

...

Keyword(s):

Confocal Microscopy ◽

Skin Diseases ◽

Reflectance Confocal Microscopy ◽

Skin Area ◽

Impaired Wound Healing ◽

Non Invasive ◽

Imaging Tool ◽

In Vivo Diagnosis ◽

In Vivo Characterization

Primary cutaneous amyloidosis (PCA) is a form of localized amyloidosis. It is characterized by the deposition of a fibrillar material in the superficial dermis, without affecting other systems or organs. The diagnosis can be made clinically, but usually a skin biopsy is performed in order to exclude other skin diseases with similar appearance. Reflectance confocal microscopy (RCM) is a novel imaging tool that enables in vivo characterization of various skin changes with a high, quasi-microscopic resolution. This technique might have an important role in the differential diagnosis of cutaneous amyloidosis, by the in vivo assessment of epidermal changes and dermal amyloid deposition. Moreover, it is completely non-invasive and can be safely repeated on the same skin area. However, to date, there is only one published paper presenting the confocal features of primary cutaneous amyloidosis. Hereby, we describe the in vivo RCM features of PCA lesions from a patient with diabetes and correlate them with histologic findings. This strengthens the clinical usefulness of in vivo RCM examination for the non-invasive diagnosis of cutaneous amyloidosis, especially in patients that might associate diseases with impaired wound healing.

Download Full-text

In Vivo Reflectance Confocal Microscopy in General Dermatology: How to Choose the Right Indication

Dermatology Practical & Conceptual ◽

10.5826/dpc.1002a32 ◽

2020 ◽

pp. e2020032

Author(s):

Chiara Franceschini ◽

Flavia Persechino ◽

Marco Ardigò

Keyword(s):

Confocal Microscopy ◽

Skin Diseases ◽

Reflectance Confocal Microscopy ◽

Anatomical Site ◽

Inflammatory Skin Diseases ◽

Clinical Presentations ◽

Probe Selection ◽

Noninvasive Imaging Technique ◽

The Right

Reflectance confocal microscopy (RCM) is a high-resolution, noninvasive imaging technique being increasingly used as an aid to diagnosis in the dermatology setting. RCM is applied in the diagnosis of both melanoma and nonmelanoma skin tumors, but also in the interpretation and management of inflammatory skin diseases. Two different devices with different designs for specific indications are available in the market: a static and a handheld probe. Several clinical presentations of the lesion could affect the examination, such as the presence of ulceration or hyperkeratosis; moreover, the anatomical site can drive the probe selection as well as the effective indication to RCM examination. In this review article, indications for the use of RCM are described in detail with a schematic approach for practical purposes.

Download Full-text

Artificial Intelligence-Based Approaches to Reflectance Confocal Microscopy Image Analysis in Dermatology

Journal of Clinical Medicine ◽

10.3390/jcm11020429 ◽

2022 ◽

Vol 11 (2) ◽

pp. 429

Author(s):

Ana Maria Malciu ◽

Mihai Lupu ◽

Vlad Mihai Voiculescu

Keyword(s):

Artificial Intelligence ◽

Machine Learning ◽

Image Analysis ◽

Confocal Microscopy ◽

Image Quality Assessment ◽

Skin Diseases ◽

Learning Technologies ◽

Reflectance Confocal Microscopy ◽

Imaging Method

Reflectance confocal microscopy (RCM) is a non-invasive imaging method designed to identify various skin diseases. Confocal based diagnosis may be subjective due to the learning curve of the method, the scarcity of training programs available for RCM, and the lack of clearly defined diagnostic criteria for all skin conditions. Given that in vivo RCM is becoming more widely used in dermatology, numerous deep learning technologies have been developed in recent years to provide a more objective approach to RCM image analysis. Machine learning-based algorithms are used in RCM image quality assessment to reduce the number of artifacts the operator has to view, shorten evaluation times, and decrease the number of patient visits to the clinic. However, the current visual method for identifying the dermal-epidermal junction (DEJ) in RCM images is subjective, and there is a lot of variation. The delineation of DEJ on RCM images could be automated through artificial intelligence, saving time and assisting novice RCM users in studying the key DEJ morphological structure. The purpose of this paper is to supply a current summary of machine learning and artificial intelligence’s impact on the quality control of RCM images, key morphological structures identification, and detection of different skin lesion types on static RCM images.

Download Full-text