Your browser doesn't support javascript.
loading
Mostrar: 20 | 50 | 100
Resultados 1 - 2 de 2
Filtrar
Mais filtros

Base de dados
Ano de publicação
Tipo de documento
Intervalo de ano de publicação
1.
Methods ; 218: 149-157, 2023 10.
Artigo em Inglês | MEDLINE | ID: mdl-37572767

RESUMO

Deep convolutional neural networks (DCNNs) have shown remarkable performance in medical image segmentation tasks. However, medical images frequently exhibit distribution discrepancies due to variations in scanner vendors, operators, and image quality, which pose significant challenges to the robustness of trained models when applied to unseen clinical data. To address this issue, domain generalization methods have been developed to enhance the generalization ability of DCNNs. Feature space-based data augmentation methods have been proven effective in improving domain generalization, but they often rely on prior knowledge or assumptions, which can limit the diversity of source domain data. In this study, we propose a novel random feature augmentation (RFA) method to diversify source domain data at the feature level without prior knowledge. Specifically, our RFA method perturbs domain-specific information while preserving domain-invariant information, thereby adequately diversifying the source domain data. Furthermore, we propose a dual-branches invariant synergistic learning strategy to capture domain-invariant information from the augmented features of RFA, enabling DCNNs to learn a more generalized representation. We evaluate our proposed method on two challenging medical image segmentation tasks, optic cup/disc segmentation on fundus images and prostate segmentation on MRI images. Extensive experimental results demonstrate the superior performance of our method over state-of-the-art domain generalization methods.


Assuntos
Processamento de Imagem Assistida por Computador , Redes Neurais de Computação , Masculino , Humanos
2.
J Cosmet Dermatol ; 18(5): 1560-1563, 2019 Oct.
Artigo em Inglês | MEDLINE | ID: mdl-30697901

RESUMO

INTRODUCTION: The incidence rate of psoriasis vulgaris (PSV) coexisting with Juvenile dermatomyositis (JDM) is low. Through our thorough literature search, we found that PSV arising on JDM with superficial fungal infection of facial skin is rarely reported. So, we hereby, report a case of combination of the above three diseases. Meanwhile, we also reviewed the previous literatures aiming at the related basis, clinical manifestation, diagnosis, and treatment of the diseases. Interestingly, of all cases, this case is the only one in which the symptom of muscle weakness preceded the appearance of rash. CASE PRESENTATION: A 21-year-old man diagnosed with JDM 6 years ago came to our inpatient department due to the appearance of new rash. Skin examination showed some sharply demarcated scaly plaques over the head, neck, torso, and bilateral upper limbs with pruritus and scaling. Histological examination and typical clinical manifestation confirmed the diagnosis of PSV for his new rash. Family history was negative for JDM and PSV. The clear erythema located on his face revealed the existence of superficial fungal infection with the help of fungal fluorescence microscopy. He had marked improvement of his symptoms with the treatment given at our department. In the past 3 months, the patient has been on regular follow-up at our outpatient department, and his condition is stable at present. DISCUSSION: This paper presents a case of PSV arising on JDM coexisting with superficial fungal infection on the face hoping that this will help clinicians in the better diagnosis of the diseases during literature search.

SELEÇÃO DE REFERÊNCIAS
DETALHE DA PESQUISA