Your browser doesn't support javascript.
loading
Mostrar: 20 | 50 | 100
Resultados 1 - 20 de 71
Filtrar
1.
J Ultrasound Med ; 2021 Nov 09.
Artigo em Inglês | MEDLINE | ID: mdl-34751458

RESUMO

BACKGROUND: This pilot study aims at exploiting machine learning techniques to extract color Doppler ultrasound (CDUS) features and to build an artificial neural network (ANN) model based on these CDUS features for improving the diagnostic performance of thyroid cancer classification. METHODS: A total of 674 patients with 712 thyroid nodules (TNs) (512 from internal dataset and 200 from external dataset) were randomly selected in this retrospective study. We used ANN to build a model (TDUS-Net) for classifying malignant and benign TNs using both the automatically extracted quantitative CDUS features (whole ratio, intranodular ratio, peripheral ratio, and number of vessels) and gray-scale ultrasound (US) features defined by the American College of Radiology (ACR) Thyroid Imaging Reporting and Data System (TI-RADS). Then, we compared the diagnostic performance of the model, the performance of another ANN model based on the gray-scale US features alone (TUS-Net), and that of radiologists. RESULTS: The TDUS-Net (0.898, 95% CI: 0.868-0.922) achieved a higher area under the curve (AUC) than that of TUS-Net (0.881, 95% CI: 0.850-0.908) in the internal tests. Compared with radiologists, TDUS-Net (AUC: 0.925, 95% CI: 0.880-0.958) performed better than radiologists (AUC: 0.810, 95% CI: 0.749-0.862) in the external tests. CONCLUSIONS: Applying a machine learning model by combining both gray-scale US features and CDUS features can achieve comparable or even higher performance than radiologists in classifying TNs.

2.
Ann Transl Med ; 9(20): 1526, 2021 Oct.
Artigo em Inglês | MEDLINE | ID: mdl-34790732

RESUMO

Background: Ultrasound (US) is widely used in the clinical diagnosis of thyroid nodules. Artificial intelligence-powered US is becoming an important issue in the research community. This study aimed to develop an improved deep learning model-based algorithm to classify benign and malignant thyroid nodules (TNs) using thyroid US images. Methods: In total, 592 patients with 600 TNs were included in the internal training, validation, and testing data set; 187 patients with 200 TNs were recruited for the external test data set. We developed a Visual Geometry Group (VGG)-16T model, based on the VGG-16 architecture, but with additional batch normalization (BN) and dropout layers in addition to the fully connected layers. We conducted a 10-fold cross-validation to analyze the performance of the VGG-16T model using a data set of gray-scale US images from 5 different brands of US machines. Results: For the internal data set, the VGG-16T model had 87.43% sensitivity, 85.43% specificity, and 86.43% accuracy. For the external data set, the VGG-16T model achieved an area under the curve (AUC) of 0.829 [95% confidence interval (CI): 0.770-0.879], a radiologist with 15 years' working experience achieved an AUC of 0.705 (95% CI: 0.659-0.801), a radiologist with 10 years' experience achieved an AUC of 0.725 (95% CI: 0.653-0.797), and a radiologist with 5 years' experience achieved an AUC of 0.660 (95% CI: 0.584-0.736). Conclusions: The VGG-16T model had high specificity, sensitivity, and accuracy in differentiating between malignant and benign TNs. Its diagnostic performance was superior to that of experienced radiologists. Thus, the proposed improved deep-learning model can assist radiologists to diagnose thyroid cancer.

3.
J Nanobiotechnology ; 19(1): 386, 2021 Nov 24.
Artigo em Inglês | MEDLINE | ID: mdl-34819078

RESUMO

BACKGROUND: The ratio of fPSA/tPSA in the "grey zone" of tPSA with the concentration range between 4 ng/ml and 10 ng/ml is significant for diagnosis of prostate cancer, and highly efficiency quantification of the ratio of fPSA/tPSA remain elusive mainly because of their extremely low concentration in patients' peripheral blood with high biosample complexity. METHODS: We presented an interdigitated spiral-based MXene-assisted organic electrochemical transistors (isMOECTs) biosensor for highly sensitive determination of fPSA/tPSA. The combination of MXene and the interdigitated multiple spiral architecture synergistically assisted the amplification of amperometric signal of biosensor with dual functionalizations of anti-tPSA and anti-fPSA. RESULTS: The ultrasensitivity of the biosensor was enhanced by tunable multiple spiral architecture and MXene nanomaterials; and the sensor exhibited improved detection limit of tPSA and fPSA down to 0.01 pg/ml and acceptable performance of selectivity, repeatability and stability. Moreover, the isMOECTs displayed area under the curve (AUC) value of 0.8138, confirming the potential applications of isMOECTs in clinics. CONCLUSIONS: The merits of isMOECTs biosensor demonstrated the reliability of MXene-assisted organic electrochemical transistor biosensor with multiple interdigitated spiral for ultrasensitive quantification of fPSA/tPSA, suggesting potential current and future point-of-care testing applications.

4.
Eur J Histochem ; 65(s1)2021 Oct 01.
Artigo em Inglês | MEDLINE | ID: mdl-34595897

RESUMO

Distinguishing brain venules from arterioles with arteriolosclerosis is less reliable using traditional staining methods. We aimed to immunohistochemically assess the monocarboxylate transporter 1 (MCT1), a specific marker of venous endothelium found in rodent studies, in different caliber vessels in human brains. Both largeand small-caliber cerebral vessels were dissected from four autopsy donors. Immunoreactivity for MCT1 was examined in all autopsied human brain tissues, and then each vessel was identified by neuropathologists using hematoxylin and eosin stain, the Verhoeff's Van Gieson stain, immunohistochemical stain with antibodies for α-smooth muscle actin and MCT1 in sequence. A total of 61 cerebral vessels, including 29 arteries and 32 veins were assessed. Immunoreactivity for MCT1 was observed in the endothelial cells of various caliber veins as well as the capillaries, whereas that was immunenegative in the endothelium of arteries. The different labeling patterns for MCT1 could aid in distinguishing various caliber veins from arteries, whereas assessment using the vessel shape, the internal elastic lamina, and the pattern of smooth muscle fibers failed to make the distinction between small-caliber veins and sclerotic arterioles. In conclusion, MCT1 immunohistochemical staining is a sensitive and reliable method to distinguish cerebral veins from arteries.

5.
Ultrasound Med Biol ; 47(12): 3364-3371, 2021 Dec.
Artigo em Inglês | MEDLINE | ID: mdl-34489133

RESUMO

This prospective study determined the value added by superb microvascular imaging (SMI) and Virtual Touch imaging quantification (VTIQ) to conventional ultrasonography in classifying malignant and benign thyroid nodules. One hundred eighty-three thyroid nodules (TNs) in 120 patients (112 benign and 71 malignant TNs) were evaluated. SMI revealed noticeable variance between benign and malignant TNs (p < 0.001). Malignant nodules tended to have rich vascularity (grade 3: 38/71, 53.5%) compared with benign nodules (grade 3: 33/112, 29.5%). There is a statistically significant difference between malignant and benign TNs with respect to shear-wave speed (SWS) values (all p values <0.001). The SWS mean, maximum and ratio of malignant nodules were 3.97 ± 1.34, 4.79 ± 1.70 and 1.25 ± 0.39, respectively. The SWS mean, maximum and ratio of benign nodules were 2.65 ± 0.42, 2.97 ± 0.46 and 1.15 ± 0.35, respectively. With respect to area under the curve values, the combined use of SMI or VTIQ improved the diagnostic performance of classifying malignant and benign TNs compared with that of ultrasonography alone. The combination of three modalities achieved the greatest area under the curve values (0.9811, 95% confidence interval: 0.95529-1.000), followed by US + VTIQ (0.9747, 0.94543-1.000), US + SMI (0.9032, 0.85345-0.95391) and ultrasonography (0.8291, 0.76417-0.89403).

6.
J Alzheimers Dis ; 84(1): 367-375, 2021.
Artigo em Inglês | MEDLINE | ID: mdl-34542069

RESUMO

BACKGROUND: Few studies have investigated the association between cognition and brain volume associated with cerebral small vessel disease (CSVD). OBJECTIVE: We investigated the association between cognition and brain volume and neuroimaging markers of CSVD in a community-dwelling population. METHODS: Participants (n = 993, age≥35 years) from the community-based Shunyi Study were included to investigate the association between neuroimaging markers and cognition cross-sectionally. Magnetic resonance imaging markers included brain volume measurements of the total cerebrum, white matter, gray matter, and CSVD imaging markers. Cognitive performance was assessed using neuropsychological tests of the Mini-Mental State Examination (MMSE), Montreal Cognitive Assessment (MoCA), Fuld Object Memory, digit span, Trail Making Test (TMT)-A, and TMT-B. RESULTS: For brain volume measurement, subcortical white matter fraction was positively associated with MMSE score (ß= 0.034, p = 0.0062) and MoCA score (ß= 0.034, p = 0.0174), and negatively associated with TMT-A and TMT-B completion time (ß= -2.319, p = 0.0002; ß= -2.827, p = 0.0073, respectively). For evaluation of CSVD imaging markers, the presence of lacunes was positively associated with TMT-B completion time (ß= 17.241, p = 0.0028). CONCLUSION: In community-dwelling populations, reduced white matter volumes, as a consequence of aging and vascular damage, are associated with worse global cognition and executive function. Our findings provide potential insights into the correlation between cognition and CSVD-associated subcortical white matter injury.

8.
Stroke ; 52(12): 3918-3925, 2021 Dec.
Artigo em Inglês | MEDLINE | ID: mdl-34404235

RESUMO

BACKGROUND AND PURPOSE: Researches on rare variants of NOTCH3 in the general Chinese population are lacking. This study aims to describe the spectrum of rare NOTCH3 variants by whole-exome sequencing in a Chinese community-based cohort and to investigate the association between rare NOTCH3 variants and age-related cerebral small vessel disease. METHODS: The cross-sectional study comprised 1065 participants who underwent whole-exome sequencing and brain magnetic resonance imaging. NOTCH3 variants with minor allele frequency<1% in all 4 public population databases (1000 Genomes, ESP6500siv2_ALL, GnomAD_ALL, and GnomAD_EAS) were defined as rare variants. Multivariable linear and logistic regressions were used to investigate the associations between rare NOTCH3 variants and volume of white matter hyperintensities and cerebral small vessel disease burden. Clinical and imaging characteristics of rare NOTCH3 variant carriers were summarized. RESULTS: Sixty-five rare NOTCH3 variants were identified in 147 of 1065 (13.8%) participants, including 57 missense single nucleotide polymorphisms (SNPs), 5 SNPs in splice branching sites, and 3 frameshift deletions. A significantly higher volume of white matter hyperintensities and heavier burden of cerebral small vessel disease was found in carriers of rare NOTCH3 EGFr (epidermal growth factor-like repeats)-involving variants, but not in carriers of EGFr-sparing variants. The carrying rate of rare EGFr-involving NOTCH3 variants in participants with dementia or stroke was significantly higher than those without dementia or stroke (12.4% versus 6.6%, P=0.041). Magnetic resonance imaging signs suggestive of CADASIL were found in 3.4% (5/145) rare EGFr cysteine-sparing NOTCH3 variant carriers but not in 2 cysteine-altering NOTCH3 variant carriers. CONCLUSIONS: Carriers of rare NOTCH3 variants involving the EGFr domain may be genetically predisposed to age-related cerebral small vessel disease in the general Chinese population.

9.
Front Neuroinform ; 15: 641600, 2021.
Artigo em Inglês | MEDLINE | ID: mdl-34262443

RESUMO

We implemented a deep learning (DL) algorithm for the 3-dimensional segmentation of perivascular spaces (PVSs) in deep white matter (DWM) and basal ganglia (BG). This algorithm is based on an autoencoder and a U-shaped network (U-net), and was trained and tested using T1-weighted magnetic resonance imaging (MRI) data from a large database of 1,832 healthy young adults. An important feature of this approach is the ability to learn from relatively sparse data, which gives the present algorithm a major advantage over other DL algorithms. Here, we trained the algorithm with 40 T1-weighted MRI datasets in which all "visible" PVSs were manually annotated by an experienced operator. After learning, performance was assessed using another set of 10 MRI scans from the same database in which PVSs were also traced by the same operator and were checked by consensus with another experienced operator. The Sorensen-Dice coefficients for PVS voxel detection in DWM (resp. BG) were 0.51 (resp. 0.66), and 0.64 (resp. 0.71) for PVS cluster detection (volume threshold of 0.5 within a range of 0 to 1). Dice values above 0.90 could be reached for detecting PVSs larger than 10 mm3 and 0.95 for PVSs larger than 15 mm3. We then applied the trained algorithm to the rest of the database (1,782 individuals). The individual PVS load provided by the algorithm showed a high agreement with a semi-quantitative visual rating done by an independent expert rater, both for DWM and for BG. Finally, we applied the trained algorithm to an age-matched sample from another MRI database acquired using a different scanner. We obtained a very similar distribution of PVS load, demonstrating the interoperability of this algorithm.

10.
Ann Transl Med ; 9(8): 640, 2021 Apr.
Artigo em Inglês | MEDLINE | ID: mdl-33987338

RESUMO

Background: Considerable evidence has been presented that heart and health-related quality of life are directly linked in patients with various diseases. This exploratory study investigated whether cardiac structure and function were associated with health-related quality of life in the general population. Methods: This cross-sectional study was performed in five villages of Shunyi, a suburban district of Beijing, from June 2013 to April 2016. All inhabitants aged 35 years or older living in five villages of Shunyi were invited to participate. Exclusion criteria were individuals who declined participation, who had incomplete Health-related quality of life (HRQoL) data, and who had suboptimal echocardiograms. HRQoL was evaluated by the Mandarin version of SF-36. The association between the echocardiography-derived cardiac structure and function and each domain of SF-36 was analyzed by the multivariate linear regression analysis after adjusted for conventional risk factors affecting HRQoL. Results: The baseline data of 990 individuals were analyzed. The median age of the participants was 57 (50-63) years, and 367 (37.1%) were male, the average physical and mental component summary scores were 89.3 (79.8-94.3) and 90 (83.5-95) respectively. Tricuspid annular plane systolic excursion, an echocardiography-derived right ventricular parameter, was associated with all the subscales and summarized scores of SF-36 (all P<0.05). The independent association between tricuspid annular plane systolic excursion and physical/mental component summary scores remained after adjusting for age, gender, body mass index, education level, annual personal income, smoking and drinking status, and comorbidities (ß=0.65, 95% confidence interval 0.30-1.01, P<0.01 and ß=0.49, 95% confidence interval 0.23-0.76, P<0.01 for physical and mental component summary scores respectively). Compared with the participants with tricuspid annular plane systolic excursion ≥21 mm, the participants with tricuspid annular plane systolic excursion <21 mm had lower adjusted scores of physical and mental component summary scores (81.8 vs. 84.5, P=0.015, and 85.5 vs. 88.1, P<0.01 for physical and mental component summary scores respectively). Conclusions: In this population-based study, right ventricular systolic function assessed by tricuspid annular plane systolic excursion was independently associated with health-related quality of life assessed by SF-36.

11.
Stroke Vasc Neurol ; 2021 Apr 26.
Artigo em Inglês | MEDLINE | ID: mdl-33903177

RESUMO

BACKGROUND AND PURPOSE: This study aimed to investigate the association of metabolic syndrome (MetS) with both intracranial atherosclerotic stenosis (ICAS) and imaging markers of cerebral small vessel disease (CSVD) in a community-based sample. METHODS: This study included 943 participants (aged 55.6±9.2 years, 36.1% male) from the community-based Shunyi cohort study. MetS was defined according to the joint interim criteria and quantified by the MetS severity Z-score. ICAS was evaluated by brain magnetic resonance angiography. The MRI markers of CSVD, including white matter hyperintensities (WMHs), lacunes, cerebral microbleeds (CMBs) and enlarged perivascular spaces (EPVS), were assessed. Multiple regression models were used to investigate the association of MetS severity Z-score with ICAS and these CSVD markers. RESULTS: We found that risk of ICAS (OR=1.75, 95% CI 1.39 to 2.21, p<0.001) increased consistently with MetS severity. MetS severity was significantly associated with higher risks of WMH volume (ß=0.11, 95% CI 0.01 to 0.20, p=0.02) and lacunes (OR=1.28, 95% CI 1.03 to 1.59, p=0.03) but not the presence of CMBs (OR=0.93, 95% CI 0.74 to 1.16, p=0.51) and PVS severity (EPVS in basal ganglia: OR=0.96, 95% CI 0.84 to 1.09, p=0.51 and EPVS in white matter: OR=1.09, 95% CI 0.96 to 1.23, p=0.21). CONCLUSIONS: Our findings suggest that WMH and lacunes share risk factors with atherosclerosis of the cerebral artery, whereas the impact of glucose and lipid metabolic disorder to CMB or EPVS might be weak.

12.
J Alzheimers Dis ; 80(2): 567-576, 2021.
Artigo em Inglês | MEDLINE | ID: mdl-33579854

RESUMO

BACKGROUND: Mechanisms through which arterial stiffness impacts cognitive function are crucial for devising better strategies to prevent cognitive decline. OBJECTIVE: To examine the associations of arterial stiffness with white matter integrity and cognition in community dwellings, and to investigate whether white matter injury was the intermediate of the associations between arterial stiffness and cognition. METHODS: This study was a cross-sectional analysis on 952 subjects (aged 55.5±9.1 years) who underwent diffusion tensor imaging and measurement of brachial-ankle pulse wave velocity (baPWV). Both linear regression and tract-based spatial statistics were used to investigate the association between baPWV and white matter integrity. The association between baPWV and global cognitive function, measured as the mini-mental state examination (MMSE) was evaluated. Mediation analysis was performed to assess the influence of white matter integrity on the association of baPWV with MMSE. RESULTS: Increased baPWV was significantly associated with lower mean global fractional anisotropy (ß= -0.118, p < 0.001), higher mean diffusivity (ß= 0.161, p < 0.001), axial diffusivity (ß= 0.160, p < 0.001), and radial diffusivity (ß= 0.147, p < 0.001) after adjustment of age, sex, and hypertension, which were measures having a direct effect on arterial stiffness and white matter integrity. After adjustment of age, sex, education, apolipoprotein E ɛ4, cardiovascular risk factors, and brain atrophy, we found an association of increased baPWV with worse performance on MMSE (ß= -0.093, p = 0.011). White matter disruption partially mediated the effect of baPWV on MMSE. CONCLUSION: Arterial stiffness is associated with white matter disruption and cognitive decline. Reduced white matter integrity partially explained the effect of arterial stiffness on cognition.


Assuntos
Disfunção Cognitiva/diagnóstico por imagem , Rigidez Vascular , Substância Branca/diagnóstico por imagem , Adulto , Idoso , Idoso de 80 Anos ou mais , Anisotropia , Índice Tornozelo-Braço , China , Cognição , Disfunção Cognitiva/psicologia , Estudos de Coortes , Estudos Transversais , Manual Diagnóstico e Estatístico de Transtornos Mentais , Imagem de Tensor de Difusão , Feminino , Humanos , Vida Independente , Imageamento por Ressonância Magnética , Masculino , Testes de Estado Mental e Demência , Pessoa de Meia-Idade
13.
Sci China Life Sci ; 64(9): 1473-1480, 2021 Sep.
Artigo em Inglês | MEDLINE | ID: mdl-33439457

RESUMO

We aimed to assess the associations of large artery stenosis (LAS) and cerebral small vessel disease (CSVD) with the risk of ischemic stroke and to investigate their respective and combined contributions. In the prospective population-based Shunyi Study, 1,082 stroke-free participants aged 55.9±9.1 years were included. Participants were followed for incident stroke throughout the study period (2013-2019). Total small vessel disease score was used to measure CSVD burden. Cervico-cerebral large artery stenosis was evaluated via brain magnetic resonance angiography and carotid ultrasound. We estimated the risk of ischemic stroke in relation to LAS and CSVD with Cox regression models. During a mean follow-up of 4.2 years, 34 participants (3.1%) experienced at least one ischemic stroke. Severe LAS (≥50% stenosis versus no stenosis: HR=3.27 (95% CI: 1.31-8.18)) and high CSVD burden (total small vessel disease score 2-4 versus 0 point: HR=12.73 (4.83-33.53)) were associated with increased stroke risk independently. In multivariate models, CSVD burden (7.72%) explained a larger portion of the variation in stroke risk than severity of LAS (3.49%). Our findings identified that both LAS and CSVD were associated with future ischemic stroke in asymptomatic subjects, while those with high CSVD burden deserve more attention in primary prevention of stroke.

14.
J Cereb Blood Flow Metab ; 41(3): 561-568, 2021 03.
Artigo em Inglês | MEDLINE | ID: mdl-32312169

RESUMO

Our aim is to investigate whether vascular risk factors are associated with cerebral deep medullary veins (DMVs) and whether DMVs are associated with MRI markers of cerebral small vessel disease (CSVD) or risk of stroke. In a community-based cohort of 1056 participants (mean age 55.7 years), DMVs were identified on susceptibility-weighted imaging (SWI) and counted in periventricular regions. Neuroimaging markers including lacunes, whiter matter hyperintensity (WMH), microbleeds, enlarged perivascular space, and brain atrophy were evaluated. The number of DMVs decreased with age (p = 0.007). After adjusting for age and sex, the number of DMVs was not associated with traditional vascular risk factors. Fewer DMVs was associated with increase of WMH and lacunes, but the association vanished after adjustment for vascular risk factors. However, fewer DMVs were independently associated with brain atrophy (p < 0.001). DMVs were not associated with three-year risk of stroke. Our results suggest that DMV is significantly different from other MRI markers of CSVD regarding risk factors, association with other CSVD markers, and risk of stroke. Nonetheless, the significant association between DMV and brain atrophy suggested the potential role of venules in age-related neurodegenerative process, which deserves further investigation.


Assuntos
Veias Cerebrais/fisiologia , Imageamento por Ressonância Magnética , Adulto , Idoso , Encéfalo/irrigação sanguínea , Doenças de Pequenos Vasos Cerebrais/diagnóstico , Doenças de Pequenos Vasos Cerebrais/epidemiologia , Veias Cerebrais/diagnóstico por imagem , China/epidemiologia , Estudos de Coortes , Feminino , Humanos , Incidência , Masculino , Pessoa de Meia-Idade , Fatores de Risco
15.
J Atheroscler Thromb ; 28(3): 283-292, 2021 Mar 01.
Artigo em Inglês | MEDLINE | ID: mdl-32536634

RESUMO

AIMS: The relationship between central arterial stiffness and aging-related intracranial arteriopathy is not well investigated in the general population. In a population-based study, we investigated arterial stiffness in relation to intracranial atherosclerotic stenosis and intracranial arterial dolichoectasia. METHODS: This study was a cross-sectional analysis on 1,123 subjects (aged 56.0±9.3 years, 37.9% men) of the population-based Shunyi study in China. Arterial stiffness was assessed by measuring brachial-ankle pulse wave velocity (baPWV). Intracranial atherosclerotic stenosis and intracranial arterial dolichoectasia were evaluated via brain magnetic resonance angiography. Multivariate regression models were constructed to investigate the association between baPWV and intracranial large artery diseases. RESULTS: Increased baPWV was significantly associated with higher prevalence of intracranial atherosclerotic stenosis (odds ratio for the highest quartile of baPWV compared with the lowest quartile, 3.66 [95% confidence interval, 1.57- 8.54]), after adjustment for cardiovascular risk factors in multivariate analysis. BaPWV was not associated with the presence of basilar artery dolichoectasia and dilation of basilar artery and internal carotid artery. When the diameters of intracranial arteries were regarded as continuous variables, increased baPWV was inversely related to the internal carotid artery diameter in fully adjusted models (ß±SE, -0.083±0.042, p = 0.047). CONCLUSIONS: This population-based study demonstrates that arterial stiffness was more likely associated with intracranial stenotic arteriopathy other than intracranial dilative arteriopathy.

16.
Ultrasonics ; 110: 106300, 2021 Feb.
Artigo em Inglês | MEDLINE | ID: mdl-33232887

RESUMO

Breast and thyroid cancers are the two common cancers to affect women worldwide. Ultrasonography (US) is a commonly used non-invasive imaging modality to detect breast and thyroid cancers, but its clinical diagnostic accuracy for these cancers is controversial. Both thyroid and breast cancers share some similar high frequency ultrasound characteristics such as taller-than-wide shape ratio, hypo-echogenicity, and ill-defined margins. This study aims to develop an automatic scheme for classifying thyroid and breast lesions in ultrasound images using deep convolutional neural networks (DCNN). In particular, we propose a generic DCNN architecture with transfer learning and the same architectural parameter settings to train models for thyroid and breast cancers (TNet and BNet) respectively, and test the viability of such a generic approach with ultrasound images collected from clinical practices. In addition, the potentials of the thyroid model in learning the common features and its performance of classifying both breast and thyroid lesions are investigated. A retrospective dataset of 719 thyroid and 672 breast images captured from US machines of different makes between October 2016 and December 2018 is used in this study. Test results show that both TNet and BNet built on the same DCNN architecture have achieved good classification results (86.5% average accuracy for TNet and 89% for BNet). Furthermore, we used TNet to classify breast lesions and the model achieves sensitivity of 86.6% and specificity of 87.1%, indicating its capability in learning features commonly shared by thyroid and breast lesions. We further tested the diagnostic performance of the TNet model against that of three radiologists. The area under curve (AUC) for thyroid nodule classification is 0.861 (95% CI: 0.792-0.929) for the TNet model and 0.757-0.854 (95% CI: 0.658-0.934) for the three radiologists. The AUC for breast cancer classification is 0.875 (95% CI: 0.804-0.947) for the TNet model and 0.698-0.777 (95% CI: 0.593-0.872) for the radiologists, indicating the model's potential in classifying both breast and thyroid cancers with a higher level of accuracy than that of radiologists.


Assuntos
Neoplasias da Mama/diagnóstico por imagem , Aprendizado Profundo , Neoplasias da Glândula Tireoide/diagnóstico por imagem , Ultrassonografia/métodos , Conjuntos de Dados como Assunto , Diagnóstico Diferencial , Feminino , Humanos , Interpretação de Imagem Assistida por Computador , Pessoa de Meia-Idade , Estudos Retrospectivos , Sensibilidade e Especificidade , Ultrassonografia Mamária
17.
Front Neurol ; 11: 598650, 2020.
Artigo em Inglês | MEDLINE | ID: mdl-33281735

RESUMO

Cases of autoimmune glial fibrillary acidic protein (GFAP) astrocytopathy who were initially diagnosed with chronic lymphocytic inflammation with pontine perivascular enhancement responsive to steroids (CLIPPERS) were rarely reported. Herein, we reported a 31-year-old woman who presented with 7 years of recurrent headache. Her clinical history, symptoms, brain MRI enhancement features, and response to treatment during each attack were reviewed. Her brain MRI 7 years ago demonstrated characteristic pepper-like enhancement of pontine and cerebellum and her symptoms resolved completely after taking a high-dose of steroids. She was suspected with the diagnosis of CLIPPERS, and she experienced five relapses once the oral steroid was tapered below 20 mg/day. During her last relapse, she experienced fever and psychosis, and GFAPα-antibodies were detected in her serum and cerebrospinal fluid by antigen-transfected HEK293 cell-based assay (indirect immunofluorescence assay). She obtained relief again after steroid therapy, and her diagnosis converted to autoimmune GFAP astrocytopathy. Autoimmune GFAP astrocytopathy may mimic CLIPPERS, both clinically and radiologically. Long-term follow-up is essential for necessary diagnosis revision at each new attack in patients with a diagnosis of CLIPPERS.

18.
Cerebrovasc Dis ; 49(5): 522-530, 2020.
Artigo em Inglês | MEDLINE | ID: mdl-33091907

RESUMO

BACKGROUND AND PURPOSE: To compare the risk factors and risk of stroke between lacune and large perivascular spaces (PVSs) in a community-based sample. METHODS: Large PVSs were assessed using 3.0T MRI in a population-based cohort consisting of 1,204 participants. The relationship between cardiovascular risk factors, neuroimaging changes, and incidental stroke risk and the presence of lacune or large PVSs was assessed with univariate and multivariable ordinal logistic regression analysis. RESULTS: Of the 1,204 study participants (55.7 ± 9.3 years, 37.0% men), a total of 347 large PVSs were detected in 235 (19.5%) subjects, while a total of 219 lacunes were detected in 183 subjects (15.2%). The presence of lacunes was found to be significantly associated with age, male gender, hypertension, and diabetes, whereas only age (p < 0.01) and ApoEε4 carrier status (p < 0.01) were related to the presence of large PVSs. Those who had lacunes detected on MRI at baseline had a significant increased risk of stroke (hazard ratio [HR] 4.68; 95% confidence interval [CI], 1.15-19.07) during the 3-year follow-up independent of age, gender, and other vascular risk factors. However, there was no significant relationship between the presence of large PVSs and incident stroke (HR 3.84; 95% CI, 0.82-18.04). CONCLUSIONS: The lack of association between large PVSs and cardiovascular risk factors or risk of stroke indicated a nonvascular pathogenic mechanism underlying large PVSs, suggesting the importance of distinguishing large PVSs from lacunes in clinical practice.


Assuntos
Artérias Cerebrais/diagnóstico por imagem , Sistema Glinfático/diagnóstico por imagem , Imageamento por Ressonância Magnética , Acidente Vascular Cerebral Lacunar/diagnóstico por imagem , Acidente Vascular Cerebral/diagnóstico por imagem , Idoso , Feminino , Humanos , Masculino , Pessoa de Meia-Idade , Valor Preditivo dos Testes , Medição de Risco , Fatores de Risco , Acidente Vascular Cerebral/etiologia , Acidente Vascular Cerebral Lacunar/etiologia
19.
J Stroke Cerebrovasc Dis ; 29(11): 105274, 2020 Nov.
Artigo em Inglês | MEDLINE | ID: mdl-33066887

RESUMO

BACKGROUND AND OBJECTIVE: Cerebral venous thrombosis (CVT) is not rare in women of childbearing age. Chinese couples have been encouraged to have two children by the new family-planning policy. Concerns have been raised about the effect of CVT on subsequent pregnancies, but few studies have focused on the Chinese population. We aimed to analyze the clinical features of Chinese female CVT patients of childbearing age and study the outcome of their subsequent pregnancies after CVT. METHODS: We retrospectively analyzed the clinical data of female patients at fertile age (15-45 years) diagnosed with CVT in our hospital between January 2009 and January 2019. Information on recurrence of venous thrombotic events as well as obstetrical outcomes of subsequent pregnancies was obtained and evaluated during follow-up. RESULTS: A total of 72 patients were enrolled, mean age at CVT onset was 29.4 ± 7.9 years. The main risk factors included autoimmune system disease (27.8%), pregnancy or puerperium (12.5%), and inherited thrombophilia (11.1%). Furthermore, 58 patients were followed up for a mean time of 63.1 ± 31.4 months and 17 new pregnancies occurred in 13 women. Among the 17 pregnancies, one CVT (5.9%) recurred in a patient with antiphospholipid syndrome. Overall, 10 (58.8%) pregnancies resulted in the birth of healthy children, including 8 full-term and 2 preterm births; 7 were terminated, including 3 (17.6%) spontaneous abortions. All patients with spontaneous abortions had antiphospholipid syndrome or Behcet's disease. CONCLUSIONS: Autoimmune system disease was the most common risk factor in Chinese female CVT patients. Recurrent pregnancy-associated CVT was infrequent in women with prior CVT, but attention should be paid during subsequent pregnancies.


Assuntos
Doenças Autoimunes/complicações , Trombose Intracraniana/etiologia , Complicações Cardiovasculares na Gravidez/etiologia , Resultado da Gravidez , Trombose Venosa/etiologia , Aborto Induzido , Aborto Espontâneo , Adolescente , Adulto , Doenças Autoimunes/diagnóstico , Doenças Autoimunes/terapia , China , Feminino , Humanos , Trombose Intracraniana/diagnóstico , Trombose Intracraniana/terapia , Nascido Vivo , Pessoa de Meia-Idade , Gravidez , Complicações Cardiovasculares na Gravidez/diagnóstico , Complicações Cardiovasculares na Gravidez/terapia , Recidiva , Estudos Retrospectivos , Fatores de Risco , Trombose Venosa/diagnóstico , Trombose Venosa/terapia , Adulto Jovem
20.
Chin Med J (Engl) ; 134(2): 178-184, 2020 Oct 26.
Artigo em Inglês | MEDLINE | ID: mdl-33109952

RESUMO

BACKGROUND: Homozygous or compound heterozygous mutations in high temperature requirement serine peptidase A1 (HTRA1) gene are responsible for cerebral autosomal recessive arteriopathy with subcortical infarcts and leukoencephalopathy (CARASIL). Recently, increasing evidence has shown that heterozygous HTRA1 mutations are also associated with cerebral small vessel disease (CSVD) with an autosomal dominant pattern of inheritance. This study was aimed to analyze the genetic and clinical characteristics of HTRA1-related autosomal dominant CSVD. METHODS: We presented three new Chinese cases of familial CSVD with heterozygous HTRA1 mutations and reviewed all clinical case reports and articles on HTRA1-related autosomal dominant CSVD included in PUBMED by the end of March 1, 2020. CARASIL probands with genetic diagnosis reported to date were also reviewed. The genetic and clinical characteristics of HTRA1-related autosomal dominant CSVD were summarized and analyzed by comparing with CARASIL. RESULTS: Forty-four HTRA1-related autosomal dominant CSVD probands and 22 CARASIL probands were included. Compared with typical CARASIL, HTRA1-related autosomal dominant probands has a higher proportion of vascular risk factors (P < 0.001), a later onset age (P < 0.001), and a relatively slower clinical progression. Alopecia and spondylosis can be observed, but less than those in the typical CARASIL. Thirty-five heterozygous mutations in HTRA1 were reported, most of which were missense mutations. Amino acids located close to amino acids 250-300 were most frequently affected, followed by these located near 150∼200. While amino acids 250∼300 were also the most frequently affected region in CARASIL patients, fewer mutations precede the 200th amino acids were detected, especially in the Kazal-type serine protease domain. CONCLUSIONS: HTRA1-related autosomal dominant CSVD is present as a mild phenotype of CARASIL. The trend of regional concentration of mutation sites may be related to the concentration of key sites in these regions which are responsible for pathogenesis of HTRA1-related autosomal dominant CSVD.


Assuntos
Doenças de Pequenos Vasos Cerebrais , Serina Peptidase 1 de Requerimento de Alta Temperatura A , Leucoencefalopatias , Infarto Cerebral , Doenças de Pequenos Vasos Cerebrais/genética , Heterozigoto , Serina Peptidase 1 de Requerimento de Alta Temperatura A/genética , Humanos , Leucoencefalopatias/genética , Mutação/genética
SELEÇÃO DE REFERÊNCIAS
DETALHE DA PESQUISA
...