Your browser doesn't support javascript.
loading
Mostrar: 20 | 50 | 100
Resultados 1 - 20 de 24
Filtrar
Mais filtros










Base de dados
Intervalo de ano de publicação
1.
J Cutan Pathol ; 2021 Feb 11.
Artigo em Inglês | MEDLINE | ID: mdl-33576022

RESUMO

BACKGROUND: Novel solutions are needed for expediting margin assessment to guide BCC surgeries. Ex-vivo fluorescence confocal microscopy (FCM) is starting to be used in freshly-excised surgical specimens to examine BCC margins in real-time. Training and educational process are needed for this novel technology to be implemented into clinic. OBJECTIVE: To test a training and reading process, and measure diagnostic accuracy of clinicians with varying expertise level in reading ex-vivo FCM images. METHODS: An international 3-center study was designed for training and reading to assess BCC surgical margins and residual subtypes. Each center included a lead dermatologic/Mohs surgeon (clinical developer of FCM), and 3 additional readers (dermatologist, dermatopathologist, dermatologic/Mohs surgeon), who use confocal in clinical practice. Testing was conducted on 30 samples. RESULTS: Overall, the readers achieved 90% average sensitivity, 78% average specificity in detecting residual BCC margins, showing high and consistent diagnostic reading accuracy. Those with expertise in dermatologic surgery and dermatopathology showed the strongest potential for learning to assess FCM images. LIMITATIONS: Small dataset, variability in mosaic quality between centers. CONCLUSION: Suggested process is feasible and effective. This process is proposed for wider implementation, to facilitate wider adoption of FCM to potentially expedite BCC margin assessment to guide surgery in real-time. This article is protected by copyright. All rights reserved.

2.
Sci Rep ; 11(1): 3679, 2021 Feb 11.
Artigo em Inglês | MEDLINE | ID: mdl-33574486

RESUMO

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.

3.
Sci Data ; 8(1): 34, 2021 01 28.
Artigo em Inglês | MEDLINE | ID: mdl-33510154

RESUMO

Prior skin image datasets have not addressed patient-level information obtained from multiple skin lesions from the same patient. Though artificial intelligence classification algorithms have achieved expert-level performance in controlled studies examining single images, in practice dermatologists base their judgment holistically from multiple lesions on the same patient. The 2020 SIIM-ISIC Melanoma Classification challenge dataset described herein was constructed to address this discrepancy between prior challenges and clinical practice, providing for each image in the dataset an identifier allowing lesions from the same patient to be mapped to one another. This patient-level contextual information is frequently used by clinicians to diagnose melanoma and is especially useful in ruling out false positives in patients with many atypical nevi. The dataset represents 2,056 patients (20.8% with at least one melanoma, 79.2% with zero melanomas) from three continents with an average of 16 lesions per patient, consisting of 33,126 dermoscopic images and 584 (1.8%) histopathologically confirmed melanomas compared with benign melanoma mimickers.


Assuntos
Melanoma , Neoplasias Cutâneas , Inteligência Artificial , Humanos , Melanoma/diagnóstico por imagem , Melanoma/patologia , Melanoma/fisiopatologia , Metadados , Pele/patologia , Neoplasias Cutâneas/diagnóstico por imagem , Neoplasias Cutâneas/patologia , Neoplasias Cutâneas/fisiopatologia
4.
Med Image Anal ; 67: 101841, 2021 01.
Artigo em Inglês | MEDLINE | ID: mdl-33142135

RESUMO

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.

5.
J Biophotonics ; : e202000207, 2020 Dec 14.
Artigo em Inglês | MEDLINE | ID: mdl-33314673

RESUMO

We investigated the utility of the fluorescent dye Deep Red Anthraquinone 5 (DRAQ5) for digital staining of optically sectioned skin in comparison to acridine orange (AO). Eight fresh-frozen thawed Mohs discard tissue specimens were stained with AO and DRAQ5, and imaged using an ex vivo confocal microscope at three wavelengths (488 nm and 638 nm for fluorescence, 785 nm for reflectance). Images were overlaid (AO + Reflectance, DRAQ5 + Reflectance), digitally stained, and evaluated by three investigators for perceived image quality (PIQ) and histopathological feature identification. In addition to nuclear staining, AO seemed to stain dermal fibers in a subset of cases in digitally stained images, while DRAQ5 staining was more specific to nuclei. Blinded evaluation showed substantial agreement, favoring DRAQ5 for PIQ (82%, Cl 75%-90%, Gwet's AC 0.74) and for visualization of histopathological features in (81%, Cl 73%-89%, Gwet's AC 0.67), supporting its use in digital staining of multimodal confocal micrographs of skin.

7.
JAMA Dermatol ; 156(8): 882-890, 2020 Aug 01.
Artigo em Inglês | MEDLINE | ID: mdl-32459294

RESUMO

Importance: Basal cell carcinoma (BCC) is the most common skin cancer. Dermoscopic imaging has improved diagnostic accuracy; however, diagnosis of nonpigmented BCC remains limited to arborizing vessels, ulceration, and shiny white structures. Objective: To assess multiple aggregated yellow-white (MAY) globules as a diagnostic feature for BCC. Design, Setting, and Participants: In this retrospective, single-center, case-control study, nonpigmented skin tumors, determined clinically, were identified from a database of lesions consecutively biopsied during a 7-year period (January 1, 2009, to December 31, 2015). A subset of tumors was prospectively diagnosed, and reflectance confocal microscopy, optical coherence tomography, and histopathologic correlation were performed. Data analysis was conducted from July 1 to September 31, 2019. Exposures: Investigators evaluated for the presence or absence of known dermoscopic criteria. MAY globules were defined as aggregated, white-yellow structures visualized in polarized and nonpolarized light. Main Outcomes and Measures: The primary outcome was the diagnostic accuracy of MAY globules for the diagnosis of BCC. Secondary objectives included the association with BCC location and subtype. Interrater agreement was estimated. Results: A total of 656 nonpigmented lesions from 643 patients (mean [SD] age, 63.1 [14.9] years; 381 [58.1%] male) were included. In all, 194 lesions (29.6%) were located on the head and neck. A total of 291 (44.4%) were BCCs. MAY globules were seen in 61 of 291 BCC cases (21.0%) and in 3 of 365 other diagnoses (0.8%) (P < .001). The odds ratio for diagnosis of BCC was 32.0 (96% CI, 9.9-103.2). The presence of MAY globules was associated with a diagnosis of histologic high-risk BCC (odds ratio, 6.5; 95% CI, 3.1-14.3). The structure was never seen in cases of superficial BCCs. Conclusions and Relevance: The findings suggest that MAY globules may have utility as a new BCC dermoscopic criterion with a high specificity. MAY globules were negatively associated with superficial BCC and positively associated with deeper-seated, histologic, higher-grade tumor subtypes.

8.
J Biophotonics ; 13(6): e202000048, 2020 Jun.
Artigo em Inglês | MEDLINE | ID: mdl-32246558

RESUMO

Handheld and endoscopic optical-sectioning microscopes are being developed for noninvasive screening and intraoperative consultation. Imaging a large extent of tissue is often desired, but miniature in vivo microscopes tend to suffer from limited fields of view. To extend the imaging field during clinical use, we have developed a real-time video mosaicking method, which allows users to efficiently survey larger areas of tissue. Here, we modified a previous post-processing mosaicking method so that real-time mosaicking is possible at >30 frames/second when using a device that outputs images that are 400 × 400 pixels in size. Unlike other real-time mosaicking methods, our strategy can accommodate image rotations and deformations that often occur during clinical use of a handheld microscope. We perform a feasibility study to demonstrate that the use of real-time mosaicking is necessary to enable efficient sampling of a desired imaging field when using a handheld dual-axis confocal microscope.

10.
J Invest Dermatol ; 140(6): 1214-1222, 2020 06.
Artigo em Inglês | MEDLINE | ID: mdl-31838127

RESUMO

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.

11.
J Am Acad Dermatol ; 2019 Dec 05.
Artigo em Inglês | MEDLINE | ID: mdl-31812621

RESUMO

BACKGROUND: Lentigo maligna/lentigo maligna melanoma (LM/LMM) can present with subclinical extension that may be difficult to define preoperatively and lead to incomplete excision and potential recurrence. Preliminarily studies have used reflectance confocal microscopy (RCM) to assess LM/LMM margins. OBJECTIVE: To evaluate the correlation of LM/LMM subclinical extension defined by RCM compared to the gold standard histopathology. METHODS: Prospective study of LM/LMM patients referred for dermatologic surgery. RCM was performed at the clinically-defined initial surgical margin followed by margin-controlled staged excision with paraffin-embedded tissue and histopathology was correlated with RCM results. RESULTS: Seventy-two patients were included. Mean age was 66.8 years (SD 11.1; 38 - 89 years); 69.4% were males. 70/72 (97.2%) lesions were located on the head neck with mean largest clinical diameter of 1.3cm (0.3 - 5 cm). Diagnostic accuracy for detection of residual melanoma in the tumor debulk (after biopsy) had a sensitivity of 96.7% and a specificity of 66.7% when compared to the histopathology. RCM margin assessment revealed an overall agreement with final histopathology of 85.9% (kappa 0.71; p<0.001). LIMITATIONS: No RCM imaging beyond initial planned margins was performed. CONCLUSION: RCM showed moderate to excellent overall agreement between RCM imaging of LM/LMM and histopathology of staged excision margins.

12.
Dermatol Online J ; 25(8)2019 Aug 15.
Artigo em Inglês | MEDLINE | ID: mdl-31553856

RESUMO

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.


Assuntos
Pontos de Referência Anatômicos , Artefatos , Microscopia Confocal , Dermatopatias/patologia , Pele/patologia , Humanos
13.
Australas J Dermatol ; 60(4): e292-e297, 2019 Nov.
Artigo em Inglês | MEDLINE | ID: mdl-30941757

RESUMO

BACKGROUND/OBJECTIVES: High a naevus counts and atypical naevi are risk factors for cutaneous melanoma. However, many individuals with a high-risk naevus phenotype do not develop melanoma. In this study, we describe the clinical and dermoscopic attributes of naevi associated with melanoma in a high-risk naevus phenotype population. METHODS: This single-centre, hospital-based case-control study included 54 prospectively enrolled adult patients ≥18 years old with a high-risk naevus phenotype (18 cases with a history of melanoma and 36 age- and gender-matched controls without a history of melanoma). We analysed clinical and dermoscopic images of the 20 largest naevi for each participant. RESULTS: Cases had a higher mean age than controls (48.2 vs. 39.1 years, P = 0.007) but there was no difference in the male-to-female ratio between groups. Nearly, all participants (97%) were Fitzpatrick skin type II or III. Naevi in cases were more likely to be truncal, (72.6% vs. 53.6%, P = 0.01), particularly anterior truncal, (29.2% vs. 14.4%, P < 0.001) and larger than 8 mm (17.4% vs. 7.8%%, P = 0.01) compared to controls. CASH score of naevi did not differ between groups. Naevi in cases were more likely to have a multicomponent dermoscopic pattern than in controls (18.4% vs. 12.6%, P = 0.02). CONCLUSION: Larger naevi, truncal naevi, and naevi, with a multicomponent dermoscopic pattern may be risk factors for melanoma among individuals with a high-risk naevus phenotype. Further studies are needed to validate these findings.


Assuntos
Melanoma/patologia , Nevo Pigmentado/patologia , Medição de Risco , Neoplasias Cutâneas/patologia , Adulto , Estudos de Casos e Controles , Dermoscopia , Feminino , Humanos , Masculino , Pessoa de Meia-Idade , Fenótipo , Projetos Piloto , Estudos Prospectivos
14.
Magn Reson Med ; 79(1): 511-514, 2018 Jan.
Artigo em Inglês | MEDLINE | ID: mdl-28342176

RESUMO

PURPOSE: In this work, we investigated the relative effects of static magnetic field exposure (10.5 Tesla [T]) on two physiological parameters; blood pressure (BP) and heart rate (HR). METHODS: In vivo, we recorded both BP and HR in 4 swine (3 female, 1 male) while they were positioned within a 10.5T magnet. All measurements were performed invasively within these anesthetized animals by the placement of pressure catheters into their carotid arteries. RESULTS: We measured average increases of 2.0 mm Hg (standard deviation [SD], 6.9) in systolic BP and an increase of 4.5 mm Hg (SD, 13.7) in the diastolic BPs: We also noted an average increase of 1.2 beats per minute (SD, 2.5) in the HRs during such. CONCLUSION: Data regarding changes in BP and HR in anesthetized swine attributed to whole-body 10.5T exposure are reported. Magn Reson Med 79:511-514, 2018. © 2017 International Society for Magnetic Resonance in Medicine.


Assuntos
Anestesia , Pressão Sanguínea , Frequência Cardíaca , Campos Magnéticos , Animais , Determinação da Pressão Arterial , Artérias Carótidas/diagnóstico por imagem , Diástole , Feminino , Imagem por Ressonância Magnética , Masculino , Suínos , Sístole
15.
JAMA Dermatol ; 153(12): 1278-1284, 2017 12 01.
Artigo em Inglês | MEDLINE | ID: mdl-29049429

RESUMO

Importance: The management of lentigo maligna (LM) and LM melanoma (LMM) is challenging because of extensive subclinical spread and its occurrence on cosmetically sensitive areas. Reflectance confocal microscopy (RCM) improves diagnostic accuracy for LM and LMM and can be used to delineate their margins. Objectives: To evaluate whether handheld RCM with radial video mosaicing (HRCM-RV) offers accurate presurgical assessment of LM and LMM margins. Design, Setting, and Participants: This prospective study included consecutive patients with biopsy-proven LM and LMM located on the head and neck area who sought consultation for surgical management from March 1, 2016, through March 31, 2017, at the Dermatology Service of the Memorial Sloan Kettering Cancer Center. Thirty-two patients underwent imaging using HRCM-RV, and 22 patients with 23 LM or LMM lesions underwent staged surgery and contributed to the analysis. Main Outcomes and Measures: Clinical lesion size and area, LM and LMM area based on HRCM-RV findings, surgical defect area estimated by HRCM-RV, and observed surgical defect area. In addition, the margins measured in millimeters estimated for tumor clearance in each quadrant based on HRCM-RV findings were calculated and compared with the surgical margins. Results: Among the 22 patients (12 men and 10 women; mean [SD] age, 69.0 [8.6] years [range, 46-83 years]) with 23 lesions included in the final analysis, the mean (SD) surgical defect area estimated with HRCM-RV was 6.34 (4.02) cm2 and the mean (SD) area of surgical excision with clear margins was 7.74 (5.28) cm2. Overall, controlling for patient age and previous surgery, surgical margins were a mean of 0.76 mm (95% CI, 0.67-0.84 mm; P < .001) larger than the HRCM-RV estimate. Conclusions and Relevance: Mapping of LM and LMM with HRCM-RV estimated defects that were similar to but slightly smaller than those found in staged excision. Thus, mapping of LM using HRCM-RV can help spare healthy tissue by reducing the number of biopsies needed in clinically uncertain areas and may be used to plan treatment of LM and LMM and counsel patients appropriately.


Assuntos
Sarda Melanótica de Hutchinson/diagnóstico , Margens de Excisão , Melanoma/diagnóstico , Microscopia Confocal/métodos , Neoplasias Cutâneas/diagnóstico , Idoso , Idoso de 80 Anos ou mais , Biópsia , Feminino , Humanos , Sarda Melanótica de Hutchinson/patologia , Sarda Melanótica de Hutchinson/cirurgia , Masculino , Melanoma/patologia , Melanoma/cirurgia , Pessoa de Meia-Idade , Estudos Prospectivos , Neoplasias Cutâneas/patologia , Neoplasias Cutâneas/cirurgia , Gravação em Vídeo
16.
Sci Rep ; 7(1): 10759, 2017 09 07.
Artigo em Inglês | MEDLINE | ID: mdl-28883434

RESUMO

We describe a computer vision-based mosaicking method for in vivo videos of reflectance confocal microscopy (RCM). RCM is a microscopic imaging technique, which enables the users to rapidly examine tissue in vivo. Providing resolution at cellular-level morphology, RCM imaging combined with mosaicking has shown to be highly sensitive and specific for non-invasively guiding skin cancer diagnosis. However, current RCM mosaicking techniques with existing microscopes have been limited to two-dimensional sequences of individual still images, acquired in a highly controlled manner, and along a specific predefined raster path, covering a limited area. The recent advent of smaller handheld microscopes is enabling acquisition of videos, acquired in a relatively uncontrolled manner and along an ad-hoc arbitrarily free-form, non-rastered path. Mosaicking of video-images (video-mosaicking) is necessary to display large areas of tissue. Our video-mosaicking methods addresses this need. The method can handle unique challenges encountered during video capture such as motion blur artifacts due to rapid motion of the microscope over the imaged area, warping in frames due to changes in contact angle and varying resolution with depth. We present test examples of video-mosaics of melanoma and non-melanoma skin cancers, to demonstrate potential clinical utility.


Assuntos
Processamento de Imagem Assistida por Computador/métodos , Microscopia Confocal/métodos , Humanos , Melanoma/diagnóstico por imagem , Melanoma/patologia , Microscopia Confocal/instrumentação , Microscopia de Vídeo/métodos , Neoplasias Cutâneas/diagnóstico por imagem , Neoplasias Cutâneas/patologia
17.
JAMA Dermatol ; 153(7): 689-693, 2017 07 01.
Artigo em Inglês | MEDLINE | ID: mdl-28492924

RESUMO

Importance: Extramammary Paget disease (EMPD) is commonly refractory to surgical and nonsurgical therapies. Identifying recurrent or persistent EMPD is challenging because the disease is multifocal, and multiple blind scouting biopsies are usually performed in this setting. Handheld reflectance confocal microscopy (HRCM) has been used to diagnose and map primary EMPD and therefore may be used to identify EMPD recurrences. Objective: To evaluate HRCM's diagnostic accuracy in the setting of recurrent or persistent EMPD as well as its potential diagnostic pitfalls. Design, Setting, and Participants: This prospective case series study included patients referred to the Dermatology Service at Memorial Sloan Kettering Cancer Center between January 1, 2014, and December 31, 2016, with biopsy-proven EMPD in whom HRCM was used to monitor treatment response. Five patients were included, and 22 sites clinically concerning for recurrent or persistent disease were evaluated using HRCM and histopathologic examination. In 2 patients, video mosaics were created to evaluate large areas. Main Outcomes and Measures: Sensitivity and specificity of HRCM in identifying recurrent or persistent EMPD; causes for false-negative results according to their location, histopathologic findings, and previous treatments. Results: Of the 22 clinically suspicious sites evaluated in 5 patients (4 men, 1 woman; median [range] age, 70 [56-77] years), 9 (40.9%) were positive for recurrent disease on HRCM and histopathologically confirmed, and 13 (59.1%) sites were negative on HRCM, but 3 of the 13 were positive for EMPD on histopathological examination. In general, HRCM had a sensitivity of 75% and a specificity of 100% in identifying recurrent or persistent EMPD. False-negative results were found in 2 patients and occurred at the margins of EMPD, close to previous biopsy sites. Creating video mosaics (or video mosaicking) seemed to improve the detection of EMPD. Conclusions and Relevance: Handheld reflectance confocal microscopy is a useful auxiliary tool for diagnosing EMPD recurrences and can be used to guide scouting biopsies, thus reducing the number of biopsies needed to render a correct diagnosis.


Assuntos
Microscopia Confocal/métodos , Recidiva Local de Neoplasia/diagnóstico , Doença de Paget Extramamária/diagnóstico , Neoplasias Cutâneas/diagnóstico , Idoso , Biópsia/métodos , Reações Falso-Negativas , Feminino , Humanos , Masculino , Pessoa de Meia-Idade , Recidiva Local de Neoplasia/patologia , Doença de Paget Extramamária/patologia , Estudos Prospectivos , Sensibilidade e Especificidade , Neoplasias Cutâneas/patologia , Gravação em Vídeo/métodos
18.
IEEE Trans Image Process ; 26(1): 172-184, 2017 Jan.
Artigo em Inglês | MEDLINE | ID: mdl-27723590

RESUMO

Segmenting objects of interest from 3D data sets is a common problem encountered in biological data. Small field of view and intrinsic biological variability combined with optically subtle changes of intensity, resolution, and low contrast in images make the task of segmentation difficult, especially for microscopy of unstained living or freshly excised thick tissues. Incorporating shape information in addition to the appearance of the object of interest can often help improve segmentation performance. However, the shapes of objects in tissue can be highly variable and design of a flexible shape model that encompasses these variations is challenging. To address such complex segmentation problems, we propose a unified probabilistic framework that can incorporate the uncertainty associated with complex shapes, variable appearance, and unknown locations. The driving application that inspired the development of this framework is a biologically important segmentation problem: the task of automatically detecting and segmenting the dermal-epidermal junction (DEJ) in 3D reflectance confocal microscopy (RCM) images of human skin. RCM imaging allows noninvasive observation of cellular, nuclear, and morphological detail. The DEJ is an important morphological feature as it is where disorder, disease, and cancer usually start. Detecting the DEJ is challenging, because it is a 2D surface in a 3D volume which has strong but highly variable number of irregularly spaced and variably shaped "peaks and valleys." In addition, RCM imaging resolution, contrast, and intensity vary with depth. Thus, a prior model needs to incorporate the intrinsic structure while allowing variability in essentially all its parameters. We propose a model which can incorporate objects of interest with complex shapes and variable appearance in an unsupervised setting by utilizing domain knowledge to build appropriate priors of the model. Our novel strategy to model this structure combines a spatial Poisson process with shape priors and performs inference using Gibbs sampling. Experimental results show that the proposed unsupervised model is able to automatically detect the DEJ with physiologically relevant accuracy in the range 10- 20 µm .


Assuntos
Derme/diagnóstico por imagem , Epiderme/diagnóstico por imagem , Imageamento Tridimensional/métodos , Microscopia Confocal/métodos , Algoritmos , Humanos , Distribuição de Poisson
19.
JAMA Dermatol ; 152(6): 676-82, 2016 06 01.
Artigo em Inglês | MEDLINE | ID: mdl-27007917

RESUMO

IMPORTANCE: Both colors and structures are considered important in the dermoscopic evaluation of skin lesions but their relative significance is unknown. OBJECTIVE: To determine if diagnostic accuracy for common skin lesions differs between gray-scale and color dermoscopic images. DESIGN, SETTING, AND PARTICIPANTS: A convenience sample of 40 skin lesions (8 nevi, 8 seborrheic keratoses, 7 basal cell carcinomas, 7 melanomas, 4 hemangiomas, 4 dermatofibromas, 2 squamous cell carcinomas [SCCs]) was selected and shown to attendees of a dermoscopy course (2014 Memorial Sloan Kettering Cancer Center dermoscopy course). Twenty lesions were shown only once, either in gray-scale (n = 10) or color (n = 10) (nonpaired). Twenty lesions were shown twice, once in gray-scale (n = 20) and once in color (n = 20) (paired). Participants provided their diagnosis and confidence level for each of the 60 images. Of the 261 attendees, 158 participated (60.5%) in the study. Most were attending physicians (n = 76 [48.1%]). Most participants were practicing or training in dermatology (n = 144 [91.1%]). The median (interquartile range) experience evaluating skin lesions and using dermoscopy of participants was 6 (13.5) and 2 (4.0) years, respectively. MAIN OUTCOMES AND MEASURES: Diagnostic accuracy and confidence level of participants evaluating gray-scale and color images. Two separate analyses were performed: (1) an unpaired evaluation comparing gray-scale and color images shown either once or for the first time, and (2) a paired evaluation comparing pairs of gray-scale and color images of the same lesion. RESULTS: In univariate analysis of unpaired images, color images were less likely to be diagnosed correctly compared with gray-scale images (odds ratio [OR], 0.8; P < .001). Using gray-scale images as the reference, multivariate analyses of both unpaired and paired images found no association between correct lesion diagnosis and use of color images (OR, 1.0; P = .99, and OR, 1.2; P = .82, respectively). Stratified analysis of paired images using a color by diagnosis interaction term showed that participants were more likely to make a correct diagnosis of SCC and hemangioma in color (P < .001 for both comparisons) and dermatofibroma in gray-scale (P < .001). CONCLUSIONS AND RELEVANCE: Morphologic characteristics (ie, structures and patterns), not color, provide the primary diagnostic clue in dermoscopy. Use of gray-scale images may improve teaching of dermoscopy to novices by emphasizing the evaluation of morphology.


Assuntos
Dermatologia/métodos , Dermoscopia/métodos , Dermatopatias/diagnóstico , Neoplasias Cutâneas/diagnóstico , Adulto , Idoso , Cor , Feminino , Humanos , Ceratose Seborreica/diagnóstico , Ceratose Seborreica/patologia , Masculino , Pessoa de Meia-Idade , Análise Multivariada , Nevo/diagnóstico , Nevo/patologia , Estudos Retrospectivos , Dermatopatias/patologia , Neoplasias Cutâneas/patologia , Adulto Jovem
20.
JAMA Dermatol ; 151(12): 1338-1345, 2015 Dec 01.
Artigo em Inglês | MEDLINE | ID: mdl-26287475

RESUMO

Importance: Although nevi with a peripheral rim of globules (peripheral globular nevi [PGN]) observed with dermoscopy are associated with enlarging melanocytic nevi, their actual growth dynamics remain unknown. Because change is a sensitive but nonspecific marker for melanoma, beginning to understand the growth patterns of nevi may improve the ability of physicians to differentiate normal from abnormal growth and reduce unnecessary biopsies. Objective: To study the growth dynamics and morphologic evolution of PGN on dermoscopy. Design, Setting, and Participants: A total of 84 participants with 121 PGN from September 1, 1999, through May 1, 2013, were identified retrospectively. Cohorts were recruited from the Memorial Sloan Kettering Cancer Center; Melanoma Unit of the Hospital Clinic, University of Barcelona; and Study of Nevi in Children. All 3 cohorts underwent longitudinal monitoring with serial dermoscopic imaging of their PGN. Data analysis was performed from May 1, 2014, through April 1, 2015. Main Outcomes and Measures: Establishment of the natural growth curve of PGN. The secondary aim was to establish the median time to growth cessation in those PGN for which the size eventually stabilized and/or had begun to decrease during the study period. Results: The median duration of follow-up was 25.1 (range, 2.0-114.4) months. Most of the nevi (116 [95.9%]) enlarged at some point during sequential monitoring. The rate of increase in the surface area of PGN varied among cohorts and ranged from -0.47 to 2.26 mm2/mo (mean rate, 0.25 [95% CI, 0.14-0.36] mm2/mo). The median time to growth cessation in the 26 PGN that stabilized or decreased in size (21.5%) was 58.6 months. All lesions changed in a symmetric manner and 91 (75.2%) displayed a decrease in the density of peripheral globules over time. Conclusions and Relevance: Nevi displaying a peripheral globular pattern enlarged symmetrically with apparent growth cessation occurring during a span of 4 to 5 years. Our results reiterate the important concept that not all growth is associated with malignancy.

SELEÇÃO DE REFERÊNCIAS
DETALHE DA PESQUISA