Your browser doesn't support javascript.
loading
Mostrar: 20 | 50 | 100
Resultados 1 - 20 de 4.833
Filtrar
1.
Annu Int Conf IEEE Eng Med Biol Soc ; 2020: 1524-1527, 2020 07.
Artigo em Inglês | MEDLINE | ID: mdl-33018281

RESUMO

Developing a fast and accurate classifier is an important part of a computer-aided diagnosis system for skin cancer. Melanoma is the most dangerous form of skin cancer which has a high mortality rate. Early detection and prognosis of melanoma can improve survival rates. In this paper, we propose a deep convolutional neural network for automated melanoma detection that is scalable to accommodate a variety of hardware and software constraints. Dermoscopic skin images collected from open sources were used for training the network. The trained network was then tested on a dataset of 2150 malignant or benign images. Overall, the classifier achieved high average values for accuracy, sensitivity, and specificity of 82.95%, 82.99%, and 83.89% respectively. It outperfomed other exisitng networks using the same dataset.


Assuntos
Diagnóstico por Computador , Melanoma , Neoplasias Cutâneas , Dermoscopia , Humanos , Melanoma/diagnóstico por imagem , Redes Neurais de Computação , Neoplasias Cutâneas/diagnóstico por imagem
2.
Annu Int Conf IEEE Eng Med Biol Soc ; 2020: 1940-1943, 2020 07.
Artigo em Inglês | MEDLINE | ID: mdl-33018382

RESUMO

In this paper, we consider the problem of classifying skin lesions into multiple classes using both dermoscopic and clinical images. Different convolutional neural network architectures are considered for this task and a novel ensemble scheme is proposed, which makes use of a progressive transfer learning strategy. The proposed approach is tested over a dataset of 4000 images containing both dermoscopic and clinical examples and it is shown to achieve an average specificity of 93.3% and an average sensitivity of 79.9% in discriminating skin lesions belonging to four different classes.


Assuntos
Dermatopatias , Neoplasias Cutâneas , Dermoscopia , Humanos , Redes Neurais de Computação , Sensibilidade e Especificidade
4.
Clin Exp Rheumatol ; 38 Suppl 125(3): 132-136, 2020.
Artigo em Inglês | MEDLINE | ID: mdl-32865167

RESUMO

OBJECTIVES: Nailfold videocapillaroscopy (NVC) is the current gold standard for detection and quantification of capillary abnormalities in Raynaud's phenomenon (RP). The objective of this study is to evaluate the role of dermatoscopy as a further screening tool in RP. METHODS: Nailfold capillaries of RP patients were examined by a hand-held non-contact polarised dermatoscope connected to the digital camera (D1) and connected to an iPad (D2). Both dermatoscopic images were marked with an arrowhead. NVC examination was evaluated at the arrowhead. Single blinded reader performed all examinations. NVC was graded as per standard of European League against Rheumatism (EULAR) study group on microcirculation in rheumatic diseases. Consensus evaluation of dermatoscopy characteristics/grade was determined and each dermatoscopic image was given a final impression of 'normal', 'non-specific' or 'scleroderma' pattern. The final interpretation by both techniques was compared after completion of the blinded reading. RESULTS: Classification of 100 consecutive dermatoscopic images resulted in 37 (wide view) 'non-interpretable', 2 'normal', 48 'non-specific' and 13 'scleroderma' pattern with D1; 23 'non-interpretable', 4 'normal', 52 'non-specific' and 21 'scleroderma' pattern by the experts with D2; 0 non-interpretable, 4 normal, 13 non-specific and 83 'scleroderma' pattern with NVC. CONCLUSIONS: Overall, 50% of dermatoscopic images were classified as non-specific and 30% were classified as non-interpretable in RP patients. However, all images classified by dermatoscopy as "normal" or as overt "scleroderma" pattern were confirmed by concomitant NVC analysis. These findings demonstrate tenuous promise for dermatoscopy as a tool for the initial screening of nailfold capillaries in RP. Further regular work up with NVC is needed to further clarify non-interpretable and non-specific findings possibly related to non-scleroderma patterns.


Assuntos
Doença de Raynaud , Doenças Reumáticas , Escleroderma Sistêmico , Capilares , Consenso , Dermoscopia , Europa (Continente) , Humanos , Microcirculação , Angioscopia Microscópica , Unhas
5.
Hautarzt ; 71(9): 669-676, 2020 Sep.
Artigo em Alemão | MEDLINE | ID: mdl-32747996

RESUMO

BACKGROUND: Artificial intelligence (AI) is increasingly being used in medical practice. Especially in the image-based diagnosis of skin cancer, AI shows great potential. However, there is a significant discrepancy between expectations and true relevance of AI in current dermatological practice. OBJECTIVES: This article summarizes promising study results of skin cancer diagnosis by computer-based diagnostic systems and discusses their significance for daily practice. We hereby focus on the analysis of dermoscopic images of pigmented and unpigmented skin lesions. MATERIALS AND METHODS: A selective literature search for recent relevant trials was conducted. The included studies used machine learning, and in particular "convolutional neural networks", which have been shown to be particularly effective for the classification of image data. RESULTS AND CONCLUSIONS: In numerous studies, computer algorithms were able to detect pigmented and nonpigmented neoplasms of the skin with high precision, comparable to that of dermatologists. The combination of the physician's assessment and AI showed the best results. Computer-based diagnostic systems are widely accepted among patients and physicians. However, they are still not applicable in daily practice, since computer-based diagnostic systems have only been tested in an experimental environment. In addition, many digital diagnostic criteria that help AI to classify skin lesions remain unclear. This lack of transparency still needs to be addressed. Moreover, clinical studies on the use of AI-based assistance systems are needed in order to prove its applicability in daily dermatologic practice.


Assuntos
Inteligência Artificial , Diagnóstico por Computador/métodos , Programas de Rastreamento/métodos , Melanoma/diagnóstico , Redes Neurais de Computação , Neoplasias Cutâneas/diagnóstico , Algoritmos , Dermoscopia , Humanos , Processamento de Imagem Assistida por Computador/métodos
6.
J Dtsch Dermatol Ges ; 18(7): 682-690, 2020 07.
Artigo em Inglês | MEDLINE | ID: mdl-32657017

RESUMO

BACKGROUND: The melanin fluorescence of skin lesions is measurable with two-photon excitation, a process termed dermatofluoroscopy, which has shown a shift from the green spectra in benign melanocytic lesions to the red spectra in melanoma. This study addressed the question as to which kind of pigmented lesions can be correctly diagnosed as melanin-bearing malignant tumors. METHODS: 476 pigmented lesions including 101 cutaneous melanomas were analyzed with dermatofluoroscopy, measuring the melanin fluorescence in a grid-like fashion with a separation of measurement points of 0.2 mm. The results of the dermatofluoroscopy are presented as a diagnostic score with a cut-off score of ≥ 28 for the diagnosis of melanin-bearing malignant tumors, and were compared to the gold standard of histopathology. RESULTS: A highly significant difference (p < 0.0001) between the diagnostic scores of different skin tumors was found. Dermatofluoroscopy scores showed the highest sensitivity for melanomas (92.1 %). Interestingly, most pigmented basal cell carcinomas (BCCs, 88.9 %) were diagnosed as melanin-bearing malignant tumors. A higher sensitivity for the correct diagnosis was observed in older patients (≥ 53 years, p = 0.003), in patients with skin tanning (p = 0.025), and in patients with freckles during childhood (p = 0.046). CONCLUSIONS: Two-photon fluorescence is an innovative technique for the diagnosis of pigmented skin lesions, and shows a high sensitivity for detection of melanomas and pigmented BCCs.


Assuntos
Carcinoma Basocelular/diagnóstico por imagem , Dermoscopia , Fluoroscopia , Melanoma/diagnóstico por imagem , Nevo Pigmentado/diagnóstico por imagem , Neoplasias Cutâneas/diagnóstico por imagem , Diagnóstico Diferencial , Fluorescência , Humanos , Melanócitos , Microscopia de Fluorescência por Excitação Multifotônica , Sensibilidade e Especificidade , Pele/patologia
7.
An Bras Dermatol ; 95(5): 638-640, 2020.
Artigo em Inglês | MEDLINE | ID: mdl-32651044

RESUMO

Scabies is an ectoparasitosis caused by Sarcoptes scabiei var. hominis, characterized clinically by pruritic lesions in typical locations; the crusted form is a rare manifestation. The diagnosis is usually established based on the clinical picture, but dermoscopy can be an important complementary method, as it allows the observation of a brownish triangular structure with a hang-glider appearance. A case of crusted scabies is reported; the magnification of the images obtained by digital dermoscopy allowed the demonstration of a structure usually observed only with videodermoscopy.


Assuntos
Escabiose , Animais , Dermoscopia , Humanos , Sarcoptes scabiei , Escabiose/diagnóstico
8.
An Bras Dermatol ; 95(5): 602-608, 2020.
Artigo em Inglês | MEDLINE | ID: mdl-32718786

RESUMO

BACKGROUND: Dermoscopy increases the diagnostic accuracy in dermatology. The aspects related to training, usage profile, or perceptions of usefulness of dermoscopy among dermatologists in Brazil have not been described. OBJECTIVES: To evaluate the profile of the use of dermoscopy and the perception of the impact of the technique on clinical practice. METHODS: The Brazilian Society of Dermatology invited all members to complete an online form with 20 items regarding demographic data, dermatological assistance, use of dermoscopy, and perceptions of the impact of the technique on clinical practice. The proportions between the categories were compared by analysis of residuals in contingency tables, and p-values < 0.01 were considered significant. RESULTS: The answers from 815 associates (9.1% of those invited to participate) were assessed, 84% of whom were female, and 71% of whom were younger than 50 years of age. The use of dermoscopy was reported in the daily practice of 98% of dermatologists: 88% reported using it more than once a day. Polarized light dermoscopy was the most used method (83%) and pattern analysis was the most used algorithm (63%). The diagnosis and follow-up of melanocytic lesions was identified as the main use of the technique, while the benefit for the diagnosis of inflammatory lesions was acknowledged by less than half of the sample (42%). STUDY LIMITATIONS: This was a non-randomized study. CONCLUSION: Dermoscopy is incorporated into the clinical practice of almost all Brazilian dermatologists, and it is recognized for increasing diagnostic certainty in different contexts, especially for pigmented lesions.


Assuntos
Dermoscopia , Neoplasias Cutâneas , Algoritmos , Brasil , Dermatologistas , Feminino , Humanos , Melanócitos , Pessoa de Meia-Idade
9.
Dermatol Online J ; 26(5)2020 May 15.
Artigo em Inglês | MEDLINE | ID: mdl-32621704

RESUMO

Pseudolymphomatous folliculitis is a benign entity that is included within pseudolymphomas. Because of its rapid clinical growth and suspicious histology it has to be differentiated from malignant entities. Given its low frequency, the dermatoscopic characteristics of this entity are not well-characterized and have been described only once previously. We present a middle-aged woman with a facial erythematous plaque of 6 months' evolution, with dermatoscopy in which follicular plugs on an erythematous base were appreciated. The histology showed a dense lymphocytic infiltrate with folliculotropism and follicular alteration, with numerous peripheral histiocytes positive for S100 and CD1a. The lesion partially disappeared after the biopsy, and completely after topical treatment.


Assuntos
Foliculite/patologia , Pseudolinfoma/patologia , Dermatopatias/patologia , Adulto , Dermoscopia , Diagnóstico Diferencial , Feminino , Humanos , Pessoa de Meia-Idade , Pele/patologia
10.
Dermatol Online J ; 26(5)2020 May 15.
Artigo em Inglês | MEDLINE | ID: mdl-32621706

RESUMO

We present a 30-year-old woman with a solitary circumscribed neuroma (also known as palisaded encapsulated neuroma) diagnosed after surgical excision. We describe the histopathologic correlation and the dermoscopic features we found in this tumor, which have not been previously reported in the literature to our knowledge.


Assuntos
Neuroma/patologia , Neoplasias Cutâneas/patologia , Adulto , Bochecha/patologia , Dermoscopia , Feminino , Humanos
11.
Dermatol Online J ; 26(5)2020 May 15.
Artigo em Inglês | MEDLINE | ID: mdl-32621707

RESUMO

Oculocutaneous albinism is a genetically heterogeneous, autosomal recessive group of disorders characterized by a generalized decreased or absence of melanin pigment in the eyes, hair, and skin. These patients have a greater sensitivity to UV radiation and a predisposition to skin tumors, mainly squamous cell carcinoma and basal cell carcinomas, and to a lesser extent malignant melanomas. Melanoma can be one of the most challenging cancers to diagnose in patients with albinism. We report an uncommon clinical presentation of melanoma, an amelanotic melanoma in the right supraciliar region in a patient with oculocutaneous albinism. The clinical presentation was an erythematous, scaly and ill-defined plaque. The skin biopsy revealed a lentigo maligna melanoma. Amelanotic melanomas are one of the two most difficult to diagnose subtypes of melanoma, together with the nevoid type. Melanoma in oculocutaneous albinism patients are often amelanotic, which makes their clinical diagnosis very difficult. These patients should be examined in the dermatology department at least once a year and it is recommended to have a high index of suspicion.


Assuntos
Albinismo Oculocutâneo/complicações , Melanoma Amelanótico/patologia , Neoplasias Cutâneas/patologia , Adolescente , Adulto , Idoso , Idoso de 80 Anos ou mais , Criança , Dermoscopia , Feminino , Humanos , Lactente , Masculino , Melanoma Amelanótico/complicações , Melanoma Amelanótico/diagnóstico , Pessoa de Meia-Idade , Neoplasias Cutâneas/complicações , Neoplasias Cutâneas/diagnóstico
12.
Dermatol Online J ; 26(5)2020 May 15.
Artigo em Inglês | MEDLINE | ID: mdl-32621709

RESUMO

Terra firma-forme dermatosis is a relatively common but probably underestimated entity characterized by asymptomatic cutaneous pigmentation resembling dirty skin. Dermoscopy is a non-invasive diagnostic tool used in the diagnosis of many cutaneous conditions. In this study we aimed to reveal dermoscopic patterns of the entity. A total of 10 patients diagnosed with terra firma-forme dermatosis were enrolled. The most common dermoscopic pattern was polygonal brown clods arranged in a mosaic pattern (N=7). The other patterns observed were seborrheic keratosis-like pattern (N=2) and perifollicular hyperpigmentation (N=1). Rubbing with 70% ethyl alcohol resulted in complete resolution of the lesions in all patients.


Assuntos
Dermoscopia , Hiperpigmentação/patologia , Adolescente , Adulto , Diagnóstico Diferencial , Etanol/uso terapêutico , Feminino , Humanos , Hiperpigmentação/diagnóstico , Hiperpigmentação/terapia , Ceratose Seborreica/patologia , Masculino , Adulto Jovem
13.
An Acad Bras Cienc ; 92(1): e20190554, 2020.
Artigo em Inglês | MEDLINE | ID: mdl-32491128

RESUMO

Skin is the outermost and largest organ of the human body that protects us from the external agents. Among the various types of diseases affecting the skin, melanoma (skin cancer) is the most dangerous and deadliest disease. Though it is one of the dangerous forms of cancer, it has a high survival rate if and only if it is diagnosed at the earliest. In this study, skin cancer classification (SCC) system is developed using dermoscopic images. It is considered as a classification problem with the help of Bendlet Transform (BT) as features and Support Vector Machine (SVM) as a classifier. First, the unwanted information's such as hair and noises are removed using median filtering approach. Then, directional representation based feature extraction system that precisely classifies curvature, location and orientation is employed. Finally, two SVM classifiers are designed for the classification. The performance of the SCC system based on Bendlet is superior to other image representation systems such as Wavelets, Curvelets, Contourlets and Shearlets.


Assuntos
Dermoscopia/métodos , Melanoma/diagnóstico por imagem , Neoplasias Cutâneas/diagnóstico por imagem , Máquina de Vetores de Suporte , Diagnóstico por Computador , Humanos , Reprodutibilidade dos Testes , Sensibilidade e Especificidade
14.
An Bras Dermatol ; 95(4): 518-520, 2020.
Artigo em Inglês | MEDLINE | ID: mdl-32482551

RESUMO

Syphilis is an infectious disease that has afflicted mankind for centuries, but a recent increase in worldwide incidence has been evidenced. The authors describe a patient with typical lesions of secondary syphilis and moth-eaten alopecia, whose dermoscopic examination demonstrated empty hair follicles, vellus hair, follicular hyperkeratosis, peripheral black dots, dilated and tortuous vessels, reddish brown background, and hypopigmentation of the hair shafts. Furthermore, this case presented an erythematous background more evident than previously described cases.


Assuntos
Alopecia , Sífilis Cutânea , Dermoscopia , Cabelo , Doenças do Cabelo , Folículo Piloso , Humanos
15.
An Bras Dermatol ; 95(4): 514-517, 2020.
Artigo em Inglês | MEDLINE | ID: mdl-32522451

RESUMO

Dissecting cellulitis is a chronic, progressive, and relapsing inflammatory disease that predominantly affects the vertex and occiput of young Afro-descendent men. It starts with papules and pustules that evolve to nodules, abscesses, and cicatricial alopecia. This article illustrates the evolutive trichoscopy of dissecting cellulitis, from its early phase, through the abscess phase, to the fibrotic cicatricial phase. Trichoscopy complements clinical-pathological classification, representing a complementary tool useful in early diagnosis and monitoring of the patient during treatment.


Assuntos
Celulite (Flegmão) , Dermoscopia , Alopecia , Vesícula , Humanos , Masculino , Recidiva
17.
Stud Health Technol Inform ; 270: 1303-1304, 2020 Jun 16.
Artigo em Inglês | MEDLINE | ID: mdl-32570630

RESUMO

In the context of increasing interest in computer-assisted diagnosis for skin lesion images and mobile applications to be used in real life settings, we propose a combined desktop-smartphone solution for dermatological image classification. Hierarchical agglomerative and divisive clustering are both implemented as methods of cluster analysis, with the RGB color histogram as descriptor for a global image analysis. The cosine similarity is employed for classifying the query image in one of the available clusters, characterized by their centroids. The solution has been tested with a public database of dermoscopic images, with an overall accuracy of 0.73, 95%CI (0.58;0.85).


Assuntos
Dermatologia , Algoritmos , Análise por Conglomerados , Dermoscopia , Diagnóstico por Computador , Humanos , Processamento de Imagem Assistida por Computador , Melanoma , Neoplasias Cutâneas
18.
PLoS One ; 15(6): e0234352, 2020.
Artigo em Inglês | MEDLINE | ID: mdl-32544197

RESUMO

Asymmetry, color variegation and diameter are considered strong indicators of malignant melanoma. The subjectivity inherent in the first two features and the fact that 10% of melanomas tend to be missed in the early diagnosis due to having a diameter less than 6mm, deem it necessary to develop an objective computer vision system to evaluate these criteria and aid in the early detection of melanoma which could eventually lead to a higher 5-year survival rate. This paper proposes an approach for evaluating the three criteria objectively, whereby we develop a measure to find asymmetry with the aid of a decision tree which we train on the extracted asymmetry measures and then use to predict the asymmetry of new skin lesion images. A range of colors that demonstrate the suspicious colors for the color variegation feature have been derived, and Feret's diameter has been utilized to find the diameter of the skin lesion. The decision tree is 80% accurate in determining the asymmetry of skin lesions, and the number of suspicious colors and diameter values are objectively identified.


Assuntos
Processamento de Imagem Assistida por Computador/métodos , Melanoma/diagnóstico por imagem , Melanoma/diagnóstico , Neoplasias Cutâneas/diagnóstico por imagem , Neoplasias Cutâneas/diagnóstico , Algoritmos , Cor , Tomada de Decisões Assistida por Computador , Dermoscopia/métodos , Humanos , Melanoma/patologia , Dermatopatias , Neoplasias Cutâneas/patologia
19.
PLoS One ; 15(6): e0234334, 2020.
Artigo em Inglês | MEDLINE | ID: mdl-32525908

RESUMO

BACKGROUND: Onychomycosis is the most common nail disorder and is associated with diagnostic challenges. Emerging non-invasive, real-time techniques such as dermoscopy and deep convolutional neural networks have been proposed for the diagnosis of this condition. However, comparative studies of the two tools in the diagnosis of onychomycosis have not previously been conducted. OBJECTIVES: This study evaluated the diagnostic abilities of a deep neural network (http://nail.modelderm.com) and dermoscopic examination in patients with onychomycosis. METHODS: A prospective observational study was performed in patients presenting with dystrophic features in the toenails. Clinical photographs were taken by research assistants, and the ground truth was determined either by direct microscopy using the potassium hydroxide test or by fungal culture. Five board-certified dermatologists determined a diagnosis of onychomycosis using the clinical photographs. The diagnosis was also made using the algorithm and dermoscopic examination. RESULTS: A total of 90 patients (mean age, 55.3; male, 43.3%) assessed between September 2018 and July 2019 were included in the analysis. The detection of onychomycosis using the algorithm (AUC, 0.751; 95% CI, 0.646-0.856) and that by dermoscopy (AUC, 0.755; 95% CI, 0.654-0.855) were seen to be comparable (Delong's test; P = 0.952). The sensitivity and specificity of the algorithm at the operating point were 70.2% and 72.7%, respectively. The sensitivity and specificity of diagnosis by the five dermatologists were 73.0% and 49.7%, respectively. The Youden index of the algorithm (0.429) was also comparable to that of the dermatologists' diagnosis (0.230±0.176; Wilcoxon rank-sum test; P = 0.667). CONCLUSIONS: As a standalone method, the algorithm analyzed photographs taken by non-physician and showed comparable accuracy for the diagnosis of onychomycosis to that made by experienced dermatologists and by dermoscopic examination. Large sample size and world-wide, multicentered studies should be investigated to prove the performance of the algorithm.


Assuntos
Aprendizado Profundo , Dermoscopia , Dermatoses do Pé/diagnóstico , Onicomicose/diagnóstico , Adulto , Algoritmos , Sistemas Computacionais , Dermatologistas , Diagnóstico por Computador , Erros de Diagnóstico , Feminino , Dermatoses do Pé/diagnóstico por imagem , Dermatoses do Pé/microbiologia , Humanos , Hidróxidos , Masculino , Pessoa de Meia-Idade , Técnicas de Tipagem Micológica , Redes Neurais de Computação , Onicomicose/diagnóstico por imagem , Onicomicose/microbiologia , Fotografação , Compostos de Potássio , Valor Preditivo dos Testes , Estudos Prospectivos , Adulto Jovem
SELEÇÃO DE REFERÊNCIAS
DETALHE DA PESQUISA