Melissa Gill

Reflectance Confocal Microscopy of Cutaneous Tumors: An Atlas with Clinical, Dermoscopic and Histological Correlations

Reflectance Confocal Microscopy of Cutaneous Tumors: An Atlas with Clinical, Dermoscopic and Histological Correlations - Libros de Medicina - Dermatologia clinica - 165,18

In vivo confocal microscopy for detection and grading of dysplastic nevi: A pilot study

BACKGROUND Dysplastic nevi are thought to be precursors of melanoma during a stepwise process. However, this concept is still controversial and precise correlation between clinical and histopathologic features is lacking. In vivo confocal microscopy represents a noninvasive imaging technique producing horizontal sections at nearly histopathologic resolution. OBJECTIVE We sought to determine whether specific histologic features in dysplastic nevi have reliable correlates on confocal microscopy and to develop an in vivo microscopic grading system. METHODS Sixty melanocytic lesions with equivocal dermatoscopic aspects, corresponding to 19 nondysplastic nevi, 27 dysplastic nevi, and 14 melanomas, were analyzed by confocal microscopy and histopathology, using the Duke grading criteria. RESULTS All architectural and cytologic features of the Duke grading score had significant reflectance confocal microscopy correlates. Confocally, dysplastic nevi were characterized by a ringed pattern, in association with a meshwork pattern in a large proportion of cases, along with atypical junctional cells in the center of the lesion, and irregular junctional nests with short interconnections. A simplified algorithm was developed to distinguish dysplastic nevi from melanoma and nondysplastic nevi. The contemporary presence of cytologic atypia and of atypical junctional nests (irregular, with short interconnections, and/or with nonhomogeneous cellularity) was suggestive of histologic dysplasia, whereas a widespread pagetoid infiltration, widespread cytologic atypia at the junction, and nonedged papillae suggested melanoma diagnosis. LIMITATIONS A small number of cases were evaluated because of the necessity to analyze numerous histopathologic and confocal features. CONCLUSION The possibility to detect dysplastic nevi in vivo may lead to an appropriate management decision.

Reflectance confocal microscopy for diagnosis of mammary and extramammary Paget’s disease

Background  Paget’s disease is an intraepidermal adenocarcinoma that is difficult to diagnose clinically as it mimics inflammatory or infectious diseases. As a consequence, it may be clinically misdiagnosed resulting in a delay in appropriate management. Reflectance confocal microscopy allows the visualization of the upper layers of the skin and mucosa at cellular resolution. Paget’s disease is characterized histologically by the presence of neoplastic cells scattered throughout all layers of the epidermis in a pattern similar to that also observed in melanoma (and termed Pagetoid spread).

Non-invasive in vivo dermatopathology: identification of reflectance confocal microscopic correlates to specific histological features seen in melanocytic neoplasms.

Reflectance confocal microscopy (RCM) allows for non‐invasive, in vivo evaluation of skin lesions and it has been extensively applied in skin oncology although systematic studies on nevi characterization are still lacking.

Reflectance Confocal Microscopy of Molluscum Contagiosum

R EFLECTANCE CONFOCAL MICROSCOPY (RCM) allows noninvasive imaging of the skin at cellular-level resolution. However, unlike pathologic analysis, RCM obtains horizontal optical sections (en face). We present RCM images (Figure 1A and Figure 2A) with histopathologic correlation (Figure 1B and Figure 2B) of molluscum contagiosum, a viral infection that manifests clinically as solitary or multiple umbilicated, dome-shaped papules (Figure 1C). The 4 4-mm RCM mosaic image (Figure 1A) shows a round, wellcircumscribed lesion with central round cystic areas filled with brightly refractile material. The corresponding histopathologic image (Figure 1B [hematoxylin-eosin, original magnification 20]) shows several regular, rounded, squamoid lobules opening into central dilated infundibula filled with keratotic plugs. (The line in Figure 1B indicates the level of the corresponding Figure 1A RCM image.) The characteristic molluscum bodies seen on histopathologic analysis (Figure 2B, arrow [hematoxylin-eosin, original magnification 100]) correlated with refractile structures seen on 0.5 0.5-mm RCM optical sections (Figure 2A, arrow). This is a repeatable pattern seen on RCM of patients with molluscum. Additional Contributions: Daphne Demas, MA, provided technical assistance in the preparation of the figures.

Comparing In Vivo Reflectance Confocal Microscopy, Dermoscopy, and Histology of Clear-Cell Acanthoma

BACKGROUND Clear cell acanthoma (CCA) is a rare, benign neoplasm of unknown etiology, whose dermoscopic and histological features have been previously described. Usually, CCA can be diagnosed by clinical and dermoscopic examination. In some cases, diagnosis remains uncertain, and histological examination is needed. The aim of this paper was to describe the features of reflectance confocal microscopy (RCM) in diagnosing CCA, compare them with findings on dermoscopy and histology, and evaluate their possible usefulness in CCA evaluation. PATIENTS AND METHODS Five lesions diagnosed clinically as CCA were imaged using dermoscopy and RCM. All lesions were surgically excised to confirm the diagnosis and compare the morphological attributes under light microscopy with in vivo imaging. RESULTS RCM showed well‐circumscribed lesions, often edged by a hyperkeratotic collarette with parakeratosis; inflammatory cells in the spinous layer; large keratinocytes; acanthosis with papillomatosis; epidermal disarray; and dilated capillaries forming glomeruloid shapes in the upper dermis. CONCLUSIONS In this small study, RCM was able to identify most of the established diagnostic histological features of CCA. RCM appears to be a useful tool for in vivo diagnosis of CCA and may help avoid unnecessary biopsies.

A machine learning method for identifying morphological patterns in reflectance confocal microscopy mosaics of melanocytic skin lesions in-vivo

We present a machine learning algorithm that can imitate the clinicians qualitative and visual process of analyzing reflectance confocal microscopy (RCM) mosaics at the dermal epidermal junction (DEJ) of skin. We divide the mosaics into localized areas of processing, and capture the textural appearance of each area using dense Speeded Up Robust Feature (SURF). Using these features, we train a support vector machine (SVM) classifier that can distinguish between meshwork, ring, clod, aspecific and background patterns in benign conditions and melanomas. Preliminary results on 20 RCM mosaics labeled by expert readers show classification with 55 − 81% sensitivity and 81 − 89% specificity in distinguishing these patterns.

Deep learning based classification of morphological patterns in RCM to guide noninvasive diagnosis of melanocytic lesions (Conference Presentation)

In this study we present a deep learning based classification algorithm for discriminating morphological patterns that appear in RCM mosaics of melanocytic lesions collected at the dermal epidermal junction (DEJ). These patterns are classified into 6 distinct types in the literature: background, meshwork, ring, clod, mixed, and aspecific. Clinicians typically identify these morphological patterns by examination of their textural appearance at 10X magnification. To mimic this process we divided mosaics into smaller regions, which we call tiles, and classify each tile in a deep learning framework. We used previously acquired DEJ mosaics of lesions deemed clinically suspicious, from 20 different patients, which were then labelled according to those 6 types by 2 expert users. We tried three different approaches for classification, all starting with a publicly available convolutional neural network (CNN) trained on natural image, consisting of a series of convolutional layers followed by a series of fully connected layers: (1) We fine-tuned this network using training data from the dataset. (2) Instead, we added an additional fully connected layer before the output layer network and then re-trained only last two layers, (3) We used only the CNN convolutional layers as a feature extractor, encoded the features using a bag of words model, and trained a support vector machine (SVM) classifier. Sensitivity and specificity were generally comparable across the three methods, and in the same ranges as our previous work using SURF features with SVM . Approach (3) was less computationally intensive to train but more sensitive to unbalanced representation of the 6 classes in the training data. However we expect CNN performance to improve as we add more training data because both the features and the classifier are learned jointly from the data. *First two authors share first authorship.

Reflectance Confocal Microscopy for Imaging Pigmented Basal Cell Cancers in vivo

Reflectance confocal microscopy (RCM) may permit in-vivo diagnosis of pigmented basal cell carcinomas. RCM demonstrated distinctive aggregations of tumor cells forming cords and nodules of variable brightness, associated with bright granular and dendritic structures.