ABSTRACT
BACKGROUND: No international recommendations exist for a minimum imaging requirement per lesion using reflectance confocal microscopy (RCM). This may be beneficial given the increasing use of remote RCM interpretation internationally. OBJECTIVE: To develop international expert recommendations for image acquisition using tissue-coupled RCM for diagnosis of cutaneous tumors. METHODS: Using a modified Delphi approach, a core group developed the scope and drafted initial recommendations before circulation to a larger group, the Cutaneous Imaging Expert Resource Group of the American Academy of Dermatology. Each review round consisted of a period of open comment, followed by revisions. RESULTS: The recommendations were developed after 5 alternating rounds of review among the core group and the Cutaneous Imaging Expert Resource Group. These were divided into subsections of imaging personnel, recommended lesion criteria, clinical and lesion information to be provided, lesion preparation, image acquisition, mosaic cube settings, and additional captures based on lesion characteristics and suspected diagnosis. LIMITATIONS: The current recommendations are limited to tissue-coupled RCM for diagnosis of cutaneous tumors. It is one component of the larger picture of quality assurance and will require ongoing review. CONCLUSIONS: These recommendations serve as a resource to facilitate quality assurance, economical use of time, accurate diagnosis, and international collaboration.
Subject(s)
Dermoscopy , Skin Neoplasms , Humans , Dermoscopy/methods , Skin Neoplasms/pathology , Skin/diagnostic imaging , Skin/pathology , Intravital Microscopy , Microscopy, Confocal/methodsABSTRACT
BACKGROUND: Accurate basal cell carcinoma (BCC) subtyping is requisite for appropriate management, but non-representative sampling occurs in 18% to 25% of biopsies. By enabling non-invasive diagnosis and more comprehensive sampling, integrated reflectance confocal microscopy-optical coherence tomography (RCM-OCT) may improve the accuracy of BCC subtyping and subsequent management. We evaluated RCM-OCT images and histopathology slides for the presence of two key features, angulation and small nests and cords, and calculated (a) sensitivity and specificity of these features, combined and individually, for identifying an infiltrative BCC subtype and (b) agreement across modalities. METHODS: Thirty-three RCM-OCT-imaged, histopathologically-proven BCCs (17 superficial and/or nodular; 16 containing an infiltrative component) were evaluated. RESULTS: The presence of angulation or small nests and cords was sufficient to identify infiltrative BCC on RCM-OCT with 100% sensitivity and 82% specificity, similar to histopathology (100% sensitivity, 88% specificity, kappa = 0.82). When both features were present, the sensitivity for identifying infiltrative BCC was 100% using either modality and specificity was 88% on RCM-OCT vs 94% on histopathology, indicating near-perfect agreement between non-invasive and invasive diagnostic modalities (kappa = 0.94). CONCLUSIONS: RCM-OCT can non-invasively identify key histopathologic features of infiltrative BCC offering a possible alternative to traditional invasive biopsy.
Subject(s)
Carcinoma, Basal Cell/diagnostic imaging , Microscopy, Confocal/methods , Skin Neoplasms/diagnostic imaging , Tomography, Optical Coherence/methods , Adult , Aged , Aged, 80 and over , Carcinoma, Basal Cell/pathology , Female , Humans , Male , Middle Aged , Sensitivity and Specificity , Skin Neoplasms/pathologyABSTRACT
ABSTRACT: Few reported cases discuss distinguishing between melanoma and melanoacanthoma, a seborrheic keratosis (SK) variant, using noninvasive imaging devices. We present a case of a 38-year-old man with Fitzpatrick skin type IV with an asymmetric black papule showing clinical and dermoscopic features of both melanoma and SK. Reflectance confocal microscopy (RCM) and dynamic optical coherence tomography (d-OCT) were used for further evaluation. RCM revealed acanthotic epidermis with a mixed honeycomb and cobblestone pattern, polycyclic bulbous rete ridges, and bright plump cells within entrapped, edged, dermal papillae, compatible with pigmented SK. Also noted were a population of fairly uniform bright dendritic cells scattered quite evenly at all levels of the epidermis and the notable absence of concomitant features of a melanocytic neoplasm (roundish Pagetoid cells, sheets of roundish or dendritic cells at the dermal-epidermal junction, junctional thickenings, and melanocytic nests), suggesting melanoacanthoma. d-OCT showed well-circumscribed, regular, epidermal acanthosis, superficial rounded hypodense structures, normal vascular flow, and notable absence of wiry or contoured vessels, features typically seen in SKs and benign lesions, respectively. Similarly, histologic examination revealed characteristics of pigmented SK containing a population of evenly dispersed dendritic melanocytes (decorated using Melan-A stain) confirming a diagnosis of melanoacanthoma. This case highlights the advantages of incorporating both RCM and d-OCT into clinical practice to noninvasively differentiate melanoma from its clinical mimickers.
Subject(s)
Keratosis, Seborrheic/pathology , Melanoma/pathology , Skin Neoplasms/pathology , Adult , Diagnosis, Differential , Humans , Keratosis, Seborrheic/diagnostic imaging , Male , Melanocytes/pathology , Melanoma/diagnostic imaging , Microscopy, Confocal , Skin Neoplasms/diagnostic imaging , Tomography, Optical CoherenceABSTRACT
Reflectance confocal microscopy (RCM) is a non-invasive imaging tool for cellular-level examination of skin lesions, typically from the epidermis to the superficial dermis. Clinical studies show RCM imaging is highly sensitive and specific in the diagnosis of skin diseases. RCM is disseminating from academic tertiary care centers with early adopter "experts" into diverse clinical settings, with image acquisition performed by technicians and image interpretation by physicians. In the hands of trained users, RCM serves an aid to accurately diagnose and monitor skin tumors and inflammatory processes. However, exogenous and endogenous artifacts introduced during imaging can obscure RCM images, limiting or prohibiting interpretation. Herein we review the types of artifacts that may occur and techniques for mitigating them during image acquisition, to assist technicians with qualitative image assessment and provide physicians guidance on identifying artifacts that may confound interpretation. Finally, we discuss normal skin "landmarks" and how they can (i) obscure images, (ii) be exploited for additional diagnostic information, and (iii) simulate pathological structures. A deeper understanding of the principles and methods behind RCM imaging and the varying appearance of normal skin structures in the acquired images aids technicians in capturing higher quality image sets and enables physicians to increase interpretation accuracy.
Subject(s)
Anatomic Landmarks , Artifacts , Microscopy, Confocal , Skin Diseases/pathology , Skin/pathology , HumansSubject(s)
Mite Infestations , Mites , Plasma Gases , Rosacea , Animals , Ivermectin/therapeutic use , Microscopy, Confocal , Mite Infestations/drug therapyABSTRACT
OBJECTIVES: Hospital data used to assess regional variability in disease management and outcomes, including mortality, lack information on disease severity. We describe variance between hospitals in 30-day risk-adjusted mortality rates (RAMRs) for stroke, comparing models that include or exclude stroke severity as a covariate. DESIGN: Cohort design linking Australian Stroke Clinical Registry data with national death registrations. Multivariable models using recommended statistical methods for calculating 30-day RAMRs for hospitals, adjusted for demographic factors, ability to walk on admission, stroke type, and stroke recurrence. SETTING: Australian hospitals providing at least 200 episodes of acute stroke care, 2009-2014. MAIN OUTCOME MEASURES: Hospital RAMRs estimated by different models. Changes in hospital rank order and funnel plots were used to explore variation in hospital-specific 30-day RAMRs; that is, RAMRs more than three standard deviations from the mean. RESULTS: In the 28 hospitals reporting at least 200 episodes of care, there were 16 218 episodes (15 951 patients; median age, 77 years; women, 46%; ischaemic strokes, 79%). RAMRs from models not including stroke severity as a variable ranged between 8% and 20%; RAMRs from models with the best fit, which included ability to walk and stroke recurrence as variables, ranged between 9% and 21%. The rank order of hospitals changed according to the covariates included in the models, particularly for those hospitals with the highest RAMRs. Funnel plots identified significant deviation from the mean overall RAMR for two hospitals, including one with borderline excess mortality. CONCLUSIONS: Hospital stroke mortality rates and hospital performance ranking may vary widely according to the covariates included in the statistical analysis.
Subject(s)
Hospital Mortality , Hospitals/statistics & numerical data , Quality of Health Care/standards , Stroke/mortality , Aged , Aged, 80 and over , Australia , Female , Humans , Male , Middle Aged , Models, Statistical , Outcome Assessment, Health Care , Prospective Studies , Registries , Risk AdjustmentSubject(s)
Carcinoma, Basal Cell/diagnosis , Dermoscopy/instrumentation , Multimodal Imaging/instrumentation , Skin Neoplasms/diagnosis , Skin/diagnostic imaging , Aged , Amyloid/analysis , Biopsy , Carcinoma, Basal Cell/pathology , Feasibility Studies , Female , Humans , Male , Microscopy, Confocal/instrumentation , Middle Aged , Mucins/analysis , Prospective Studies , Skin/pathology , Skin Neoplasms/pathology , Tomography, Optical Coherence/instrumentation , Young AdultABSTRACT
Current methods for diagnosing dermatophytic infections have various drawbacks. Analysis via skin scrapings and biopsies can be invasive and/or take too long to yield results. Reflectance confocal microscopy (RCM) is an emerging in vivo imaging technology that can potentially be used to diagnose cutaneous dermatophytic infections. This modality provides high-resolution images of the skin extending to the level of the superficial reticular dermis that could reveal the presence of fungal hyphae. In this retrospective chart review, we investigated the application of RCM as a diagnostic tool in the setting of a private practice. Images were used to diagnose dermatophyte infections and the results were compared to those of other established diagnostic methods. We found RCM to be a potentially effective and highly sensitive tool in the diagnosis of cutaneous dermatophytic infections.
Subject(s)
Dermatitis/pathology , Tinea/pathology , Adolescent , Adult , Aged , Antifungal Agents/therapeutic use , Cohort Studies , Dermatitis/diagnosis , Diagnosis, Differential , Humans , Hydroxides , Hyphae , Indicators and Reagents , Microscopy, Confocal , Middle Aged , Potassium Compounds , Retrospective Studies , Tinea/diagnosis , Tinea/drug therapy , Young AdultABSTRACT
BACKGROUND AND AIMS: With the prevalence of e-cigarette use among Australian youth increasing significantly in recent years, greater attention is being paid to encouraging and supporting cessation. However, research to inform such efforts is lacking. The present study sought to (i) measure desire to quit e-cigarette use and actual quitting attempts among young Australians and (ii) explore correlates of quitting-related cognitions and behaviours. DESIGN, SETTING AND PARTICIPANTS: This was a cross-sectional on-line survey conducted in Australia. The participants were 14-25-year-old e-cigarette users (n = 602; 53% women). MEASUREMENTS: Desire to quit vaping and attempts to quit vaping were the primary dependent variables. The independent variables included several individual (e.g. harm perceptions, perceived appeal of vapes), social (descriptive norms) and environmental (e.g. ease of e-cigarette access) factors. FINDINGS: A majority of respondents (61%) expressed a desire to quit vaping, and just over half (55%) had made a quit attempt. Finding vapes easy to access was associated with both a lack of desire [odds ratio (OR) = 0.71] and attempts to quit (OR = 0.77), while self-reported addiction to vaping (OR = 1.42 and OR = 3.11) and perceiving vaping to be associated with mental health risks (OR = 1.30 and OR = 1.40) were positively correlated with these variables. Perceiving that vaping is common among people of one's age (OR = 0.82) and finding vapes appealing (OR = 0.55) were associated with a lack of desire to quit, while perceiving vaping to have physical health risks was positively associated with quitting desire (OR = 1.58). School-based education on vaping was associated with reporting an attempt/s to quit (OR = 0.47). CONCLUSIONS: This survey of young Australian e-cigarette users suggests a high level of desire to quit using e-cigarettes and attempts to quit. Increasing knowledge regarding the physical and mental health risks associated with e-cigarette use may assist with promoting quitting-related intentions. Changing social norms, reducing the accessibility of e-cigarettes and reducing the appeal of the products also constitute potential means of increasing the desire to quit.
Subject(s)
Intention , Smoking Cessation , Vaping , Humans , Female , Male , Australia/epidemiology , Vaping/psychology , Vaping/epidemiology , Adolescent , Adult , Young Adult , Cross-Sectional Studies , Smoking Cessation/psychology , Electronic Nicotine Delivery Systems/statistics & numerical dataABSTRACT
Keratinocyte carcinomas (KCs) are the most prevalent form of cancer worldwide, and their incidence is rising dramatically, with an increasing trend in recent years [...].
ABSTRACT
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.
Subject(s)
Dysplastic Nevus Syndrome/pathology , Melanoma/pathology , Microscopy, Confocal/methods , Microscopy, Confocal/standards , Neoplasm Grading/methods , Skin Neoplasms/pathology , Algorithms , Dermatology/instrumentation , Dysplastic Nevus Syndrome/classification , Humans , Neoplasm Grading/instrumentation , Neoplasm Grading/standards , Pathology, Clinical/instrumentation , Pilot Projects , Reproducibility of ResultsABSTRACT
Tertiary lymphoid structures (TLS) are specialized lymphoid formations that serve as local repertoire of T- and B-cells at sites of chronic inflammation, autoimmunity, and cancer. While presence of TLS has been associated with improved response to immune checkpoint blockade therapies and overall outcomes in several cancers, its prognostic value in basal cell carcinoma (BCC) has not been investigated. Herein, we determined the prognostic impact of TLS by relating its prevalence and maturation with outcome measures of anti-tumor immunity, namely tumor infiltrating lymphocytes (TILs) and tumor killing. In 30 distinct BCCs, we show the presence of TLS was significantly enriched in tumors harboring a nodular component and more mature primary TLS was associated with TIL counts. Moreover, assessment of the fibrillary matrix surrounding tumors showed discrete morphologies significantly associated with higher TIL counts, critically accounting for heterogeneity in TIL count distribution within TLS maturation stages. Specifically, increased length of fibers and lacunarity of the matrix with concomitant reduction in density and alignment of fibers were present surrounding tumors displaying high TIL counts. Given the interest in inducing TLS formation as a therapeutic intervention as well as its documented prognostic value, elucidating potential impediments to the ability of TLS in driving anti-tumor immunity within the tumor microenvironment warrants further investigation. These results begin to address and highlight the need to integrate stromal features which may present a hindrance to TLS formation and/or effective function as a mediator of immunotherapy response.
ABSTRACT
Response to immunotherapies can be variable and unpredictable. Pathology-based phenotyping of tumors into 'hot' and 'cold' is static, relying solely on T-cell infiltration in single-time single-site biopsies, resulting in suboptimal treatment response prediction. Dynamic vascular events (tumor angiogenesis, leukocyte trafficking) within tumor immune microenvironment (TiME) also influence anti-tumor immunity and treatment response. Here, we report dynamic cellular-level TiME phenotyping in vivo that combines inflammation profiles with vascular features through non-invasive reflectance confocal microscopic imaging. In skin cancer patients, we demonstrate three main TiME phenotypes that correlate with gene and protein expression, and response to toll-like receptor agonist immune-therapy. Notably, phenotypes with high inflammation associate with immunostimulatory signatures and those with high vasculature with angiogenic and endothelial anergy signatures. Moreover, phenotypes with high inflammation and low vasculature demonstrate the best treatment response. This non-invasive in vivo phenotyping approach integrating dynamic vasculature with inflammation serves as a reliable predictor of response to topical immune-therapy in patients.
Subject(s)
Immunotherapy , Tumor Microenvironment , Humans , Immunologic Factors , Inflammation , PhenotypeABSTRACT
Reflectance confocal microscopy (RCM) is a non-invasive imaging tool that reduces the need for invasive histopathology for skin cancer diagnoses by providing high-resolution mosaics showing the architectural patterns of skin, which are used to identify malignancies in-vivo. RCM mosaics are similar to dermatopathology sections, both requiring extensive training to interpret. However, these modalities differ in orientation, as RCM mosaics are horizontal (parallel to the skin surface) while histopathology sections are vertical, and contrast mechanism, RCM with a single (reflectance) mechanism resulting in grayscale images and histopathology with multi-factor color-stained contrast. Image analysis and machine learning methods can potentially provide a diagnostic aid to clinicians to interpret RCM mosaics, eventually helping to ease the adoption and more efficiently utilizing RCM in routine clinical practice. However standard supervised machine learning may require a prohibitive volume of hand-labeled training data. In this paper, we present a weakly supervised machine learning model to perform semantic segmentation of architectural patterns encountered in RCM mosaics. Unlike more widely used fully supervised segmentation models that require pixel-level annotations, which are very labor-demanding and error-prone to obtain, here we focus on training models using only patch-level labels (e.g. a single field of view within an entire mosaic). We segment RCM mosaics into "benign" and "aspecific (nonspecific)" regions, where aspecific regions represent the loss of regular architecture due to injury and/or inflammation, pre-malignancy, or malignancy. We adopt Efficientnet, a deep neural network (DNN) proven to accurately accomplish classification tasks, to generate class activation maps, and use a Gaussian weighting kernel to stitch smaller images back into larger fields of view. The trained DNN achieved an average area under the curve of 0.969, and Dice coefficient of 0.778 showing the feasibility of spatial localization of aspecific regions in RCM images, and making the diagnostics decision model more interpretable to the clinicians.
Subject(s)
Image Processing, Computer-Assisted , Microscopy, Confocal , Skin Neoplasms/diagnosis , Skin/ultrastructure , Humans , Machine Learning , Neural Networks, Computer , Semantics , Skin/diagnostic imaging , Skin/pathology , Skin Neoplasms/diagnostic imaging , Skin Neoplasms/pathologyABSTRACT
In-vivo optical microscopy is advancing into routine clinical practice for non-invasively guiding diagnosis and treatment of cancer and other diseases, and thus beginning to reduce the need for traditional biopsy. However, reading and analysis of the optical microscopic images are generally still qualitative, relying mainly on visual examination. Here we present an automated semantic segmentation method called "Multiscale Encoder-Decoder Network (MED-Net)" that provides pixel-wise labeling into classes of patterns in a quantitative manner. The novelty in our approach is the modeling of textural patterns at multiple scales (magnifications, resolutions). This mimics the traditional procedure for examining pathology images, which routinely starts with low magnification (low resolution, large field of view) followed by closer inspection of suspicious areas with higher magnification (higher resolution, smaller fields of view). We trained and tested our model on non-overlapping partitions of 117 reflectance confocal microscopy (RCM) mosaics of melanocytic lesions, an extensive dataset for this application, collected at four clinics in the US, and two in Italy. With patient-wise cross-validation, we achieved pixel-wise mean sensitivity and specificity of 74% and 92%, respectively, with 0.74 Dice coefficient over six classes. In the scenario, we partitioned the data clinic-wise and tested the generalizability of the model over multiple clinics. In this setting, we achieved pixel-wise mean sensitivity and specificity of 77% and 94%, respectively, with 0.77 Dice coefficient. We compared MED-Net against the state-of-the-art semantic segmentation models and achieved better quantitative segmentation performance. Our results also suggest that, due to its nested multiscale architecture, the MED-Net model annotated RCM mosaics more coherently, avoiding unrealistic-fragmented annotations.
Subject(s)
Image Processing, Computer-Assisted , Neural Networks, Computer , Humans , Microscopy, ConfocalABSTRACT
Reflectance confocal microscopy (RCM) presents a non-invasive method to image actinic keratosis (AK) at a cellular level. However, RCM criteria for AK response monitoring vary across studies and a universal, standardized approach is lacking. We aimed to identify reliable AK response criteria and to compare the clinical and RCM evaluation of responses across AK severity grades. Twenty patients were included and randomized to receive either cryotherapy (n = 10) or PDT (n = 10). Clinical assessment and RCM evaluation of 12 criteria were performed in AK lesions and photodamaged skin at baseline, 3 and 6 months. We identified the RCM criteria that reliably characterize AK at baseline and display significant reduction following treatment. Those with the highest baseline odds ratio (OR), good interobserver agreement, and most significant change over time were atypical honeycomb pattern (OR: 12.7, CI: 5.7-28.1), hyperkeratosis (OR: 13.6, CI: 5.3-34.9), stratum corneum disruption (OR: 7.8, CI: 3.5-17.3), and disarranged epidermal pattern (OR: 6.5, CI: 2.9-14.8). Clinical evaluation demonstrated a significant treatment response without relapse. However, in grade 2 AK, 10/12 RCM parameters increased from 3 to 6 months, which suggested early subclinical recurrence detection by RCM. Incorporating standardized RCM protocols for the assessment of AK may enable a more meaningful comparison across clinical trials, while allowing for the early detection of relapses and evaluation of biological responses to therapy over time.
ABSTRACT
Conventional tissue sampling can lead to misdiagnoses and repeated biopsies. Additionally, tissue processed for histopathology suffers from poor nucleic acid quality and/or quantity for downstream molecular profiling. Targeted micro-sampling of tissue can ensure accurate diagnosis and molecular profiling in the presence of spatial heterogeneity, especially in tumors, and facilitate acquisition of fresh tissue for molecular analysis. In this study, we explored the feasibility of performing 1-2 mm precision biopsies guided by high-resolution reflectance confocal microscopy (RCM) and optical coherence tomography (OCT), and reflective metallic grids for accurate spatial targeting. Accurate sampling was confirmed with either histopathology or molecular profiling through next generation sequencing (NGS) in 9 skin cancers in 7 patients. Imaging-guided 1-2 mm biopsies enabled spatial targeting for in vivo diagnosis, feature correlation and depth assessment, which were confirmed with histopathology. In vivo 1-mm targeted biopsies achieved adequate quantity and high quality of DNA for next-generation sequencing. Subsequent mutational profiling was confirmed on 1 melanoma in situ and 2 invasive melanomas, using a 505-gene mutational panel called Memorial Sloan Kettering-Integrated mutational profiling of actionable cancer targets (MSK-IMPACT). Differential mutational landscapes, in terms of number and types of mutations, were found between invasive and in situ melanomas in a single patient. Our findings demonstrate feasibility of accurate sampling of regions of interest for downstream histopathological diagnoses and molecular pathology in both in vivo and ex vivo settings with broad diagnostic, therapeutic and research potential in cutaneous diseases accessible by RCM-OCT imaging.
Subject(s)
Biopsy/methods , Microscopy, Confocal/methods , Skin Neoplasms/genetics , Tomography, Optical Coherence/methods , Alleles , Carcinoma, Basal Cell/pathology , High-Throughput Nucleotide Sequencing , Humans , Hutchinson's Melanotic Freckle/pathology , Keratinocytes/pathology , Keratosis, Actinic/pathology , Melanoma/pathology , Mutation , Pathology, Molecular , Precision Medicine , Reproducibility of Results , Skin Neoplasms/pathologyABSTRACT
BACKGROUND: Diagnostic accuracy and preferred therapeutic strategies for actinic keratoses (AKs) and squamous cell carcinoma (SCC) have significant public health implications. OBJECTIVE: To evaluate clinical-pathologic agreement on the diagnosis of AKs and early SCCs and to characterize the effect of diagnosis on therapeutic decisions. METHODS & MATERIALS: Nine dermatologists and two dermatopathologists reviewed an image-based dataset of AKs and early SCCs. Clinical-pathologic agreement, inter- and intraobserver reliability for clinical diagnosis, and frequencies of therapies according to pathologic diagnosis were assessed. RESULTS: Clinical-pathologic (κ=0.10) agreement was poor, whereas interobserver (κ=0.24) and intraobserver (κ=0.28) agreements were fair. Participants were more likely to treat AKs with cryotherapy (64.2%) and to manage SCCs with surgery (72.8%). Therapeutic choice rarely changed after participants were shown histological photomicrographs. Participating clinicians treated most lesions histologically diagnosed as SCC in situ arising within AK using surgery, whereas pathologists selected cryotherapy or curettage and electrodesiccation for these lesions. CONCLUSION: We found poor clinical-pathologic agreement and reproducibility for clinically distinguishing between AK and early SCC even between skin cancer specialists from a single academic group practice. Nomenclature used in the pathologic diagnosis of AK and SCC affects clinicians' therapeutic decisions. The authors have indicated no significant interest with commercial supporters.
Subject(s)
Carcinoma, Squamous Cell/pathology , Carcinoma, Squamous Cell/therapy , Dermatology/standards , Skin Neoplasms/pathology , Skin Neoplasms/therapy , Algorithms , Aminoquinolines/therapeutic use , Biopsy/statistics & numerical data , Carcinoma in Situ/pathology , Cryosurgery/statistics & numerical data , Curettage/statistics & numerical data , Diagnosis, Differential , Fluorouracil/therapeutic use , Humans , Imiquimod , Keratosis, Actinic/pathology , Keratosis, Actinic/therapy , Mohs Surgery/statistics & numerical data , Photochemotherapy , Precancerous Conditions/pathology , Reproducibility of Results , Terminology as Topic , United StatesABSTRACT
In vivo reflectance confocal microscopy (RCM) enables clinicians to examine lesions' morphological and cytological information in epidermal and dermal layers while reducing the need for biopsies. As RCM is being adopted more widely, the workflow is expanding from real-time diagnosis at the bedside to include a capture, store, and forward model with image interpretation and diagnosis occurring offsite, similar to radiology. As the patient may no longer be present at the time of image interpretation, quality assurance is key during image acquisition. Herein, we introduce a quality assurance process by means of automatically quantifying diagnostically uninformative areas within the lesional area by using RCM and coregistered dermoscopy images together. We trained and validated a pixel-level segmentation model on 117 RCM mosaics collected by international collaborators. The model delineates diagnostically uninformative areas with 82% sensitivity and 93% specificity. We further tested the model on a separate set of 372 coregistered RCM-dermoscopic image pairs and illustrate how the results of the RCM-only model can be improved via a multimodal (RCM + dermoscopy) approach, which can help quantify the uninformative regions within the lesional area. Our data suggest that machine learning-based automatic quantification offers a feasible objective quality control measure for RCM imaging.