Your browser doesn't support javascript.
loading
Mostrar: 20 | 50 | 100
Resultados 1 - 4 de 4
Filtrar
Mais filtros










Base de dados
Intervalo de ano de publicação
1.
Med Image Anal ; 87: 102810, 2023 07.
Artigo em Inglês | MEDLINE | ID: mdl-37054648

RESUMO

Sensorless freehand 3D ultrasound (US) reconstruction based on deep networks shows promising advantages, such as large field of view, relatively high resolution, low cost, and ease of use. However, existing methods mainly consider vanilla scan strategies with limited inter-frame variations. These methods thus are degraded on complex but routine scan sequences in clinics. In this context, we propose a novel online learning framework for freehand 3D US reconstruction under complex scan strategies with diverse scanning velocities and poses. First, we devise a motion-weighted training loss in training phase to regularize the scan variation frame-by-frame and better mitigate the negative effects of uneven inter-frame velocity. Second, we effectively drive online learning with local-to-global pseudo supervisions. It mines both the frame-level contextual consistency and the path-level similarity constraint to improve the inter-frame transformation estimation. We explore a global adversarial shape before transferring the latent anatomical prior as supervision. Third, we build a feasible differentiable reconstruction approximation to enable the end-to-end optimization of our online learning. Experimental results illustrate that our freehand 3D US reconstruction framework outperformed current methods on two large, simulated datasets and one real dataset. In addition, we applied the proposed framework to clinical scan videos to further validate its effectiveness and generalizability.


Assuntos
Educação a Distância , Imageamento Tridimensional , Humanos , Imageamento Tridimensional/métodos , Algoritmos , Ultrassonografia/métodos
2.
Future Oncol ; 17(6): 701-710, 2021 Feb.
Artigo em Inglês | MEDLINE | ID: mdl-33401925

RESUMO

Aim: This study aimed to explore the mechanism of lncRNA PCAT7 underlying the progression of breast cancer, which will provide a basis for accurate diagnosis and targeted treatment. Methods: Data from The Cancer Genome Atlas data associated with breast cancer were used to identify the target lncRNA. In vitro experiments were conducted to detect gene expression and the effect of the lncRNA on cancer cell activities. Results: PCAT7 was found to be highly expressed in breast cancer tissue and cells, which activated the ErbB/PI3K/Akt pathway to potentiate cancer cell proliferation, migration and invasion and suppress apoptosis. Conclusion: PCAT7 is likely to promote tumor cell activities by activating ErbB/PI3K/Akt pathway, in turn potentiating tumor malignant progression.


Assuntos
Neoplasias da Mama/genética , Regulação Neoplásica da Expressão Gênica , RNA Longo não Codificante/metabolismo , Mama/patologia , Mama/cirurgia , Neoplasias da Mama/diagnóstico , Neoplasias da Mama/patologia , Neoplasias da Mama/cirurgia , Carcinogênese/genética , Linhagem Celular Tumoral , Conjuntos de Dados como Assunto , Progressão da Doença , Receptores ErbB/metabolismo , Feminino , Perfilação da Expressão Gênica , Humanos , Mastectomia , Fosfatidilinositol 3-Quinase/metabolismo , Pós-Menopausa , Pré-Menopausa , Prognóstico , Proteínas Proto-Oncogênicas c-akt/metabolismo , Transdução de Sinais/genética , Regulação para Cima
3.
IEEE Trans Med Imaging ; 38(10): 2338-2351, 2019 10.
Artigo em Inglês | MEDLINE | ID: mdl-30908201

RESUMO

Adequate medical images are often indispensable in contemporary deep learning-based medical imaging studies, although the acquisition of certain image modalities may be limited due to several issues including high costs and patients issues. However, thanks to recent advances in deep learning techniques, the above tough problem can be substantially alleviated by medical images synthesis, by which various modalities including T1/T2/DTI MRI images, PET images, cardiac ultrasound images, retinal images, and so on, have already been synthesized. Unfortunately, the arterial spin labeling (ASL) image, which is an important fMRI indicator in dementia diseases diagnosis nowadays, has never been comprehensively investigated for the synthesis purpose yet. In this paper, ASL images have been successfully synthesized from structural magnetic resonance images for the first time. Technically, a novel unbalanced deep discriminant learning-based model equipped with new ResNet sub-structures is proposed to realize the synthesis of ASL images from structural magnetic resonance images. The extensive experiments have been conducted. Comprehensive statistical analyses reveal that: 1) this newly introduced model is capable to synthesize ASL images that are similar towards real ones acquired by actual scanning; 2) synthesized ASL images obtained by the new model have demonstrated outstanding performance when undergoing rigorous tests of region-based and voxel-based corrections of partial volume effects, which are essential in ASL images processing; and 3) it is also promising that the diagnosis performance of dementia diseases can be significantly improved with the help of synthesized ASL images obtained by the new model, based on a multi-modal MRI dataset containing 355 demented patients in this paper.


Assuntos
Encéfalo/diagnóstico por imagem , Aprendizado Profundo , Interpretação de Imagem Assistida por Computador/métodos , Imageamento por Ressonância Magnética/métodos , Idoso , Demência/diagnóstico por imagem , Humanos , Pessoa de Meia-Idade , Marcadores de Spin
4.
Acta Cardiol Sin ; 31(2): 152-7, 2015 Mar.
Artigo em Inglês | MEDLINE | ID: mdl-27122863

RESUMO

BACKGROUND: This study aimed to evaluate the efficacy of vascular intervention in percutaneous transluminal angioplasty (PTA) for the treatment of hepatic artery and hepatic vein stenosis after liver transplantation (LT), including thrombotic total occluded lesions. METHODS: Percutaneous transluminal angioplasty after orthotopic liver transplantation was performed to re-open hepatic vessel lesions. We daily used routine Doppler ultrasound during admission for early detection of graft hepatic vessel lesions, including hepatic artery and vein lesions. In outpatients, Doppler ultrasound was performed every month. Urokinase was delivered with a dose of 150,000-300,000 IU by catheter before PTA for thrombotic total occlusion of the graft for hepatic artery patients. Laboratory data were collected to evaluate the effects of the PTA procedure. RESULTS: The study involved a total of seven patients, six of whom were successfully treated by a first PTA procedure. Thrombolysis use of urokinase in totally occluded donor hepatic arteries post-LT following stenting was successful in three patients. One complication occurred, an arterial dissection and perforation, finalizing the success rate at ~86% and the complication rate at ~14%. Therefore, our study has a primary patency rate of 100% at 1 and 3 months. Also, the graft survival rate was 100 % and 86 % in the first and third months, respectively. CONCLUSIONS: PTA with stenting is an effective treatment for hepatic vessel stenosis, including hepatic arteries and hepatic veins, after a liver transplantation without an increase in the complication rate. In addition, thrombolysis using urokinase intra-artery infusion in graft thrombotic total occluded patients is a good treatment strategy as well. KEY WORDS: Angioplasty; Complication; Liver transplantation.

SELEÇÃO DE REFERÊNCIAS
DETALHE DA PESQUISA
...