Your browser doesn't support javascript.
loading
Show: 20 | 50 | 100
Results 1 - 5 de 5
Filter
2.
Eur J Nucl Med Mol Imaging ; 47(11): 2516-2524, 2020 10.
Article in English | MEDLINE | ID: mdl-32567006

ABSTRACT

PURPOSE: In the absence of a virus nucleic acid real-time reverse transcriptase-polymerase chain reaction (RT-PCR) test and experienced radiologists, clinical diagnosis is challenging for viral pneumonia with clinical symptoms and CT signs similar to that of coronavirus disease 2019 (COVID-19). We developed an end-to-end automatic differentiation method based on CT images to identify COVID-19 pneumonia patients in real time. METHODS: From January 18 to February 23, 2020, we conducted a retrospective study and enrolled 201 patients from two hospitals in China who underwent chest CT and RT-PCR tests, of which 98 patients tested positive for COVID-19 (118 males and 83 females, with an average age of 42 years). Patient CT images from one hospital were divided among training, validation and test datasets with an 80%:10%:10% ratio. An end-to-end representation learning method using a large-scale bi-directional generative adversarial network (BigBiGAN) architecture was designed to extract semantic features from the CT images. The semantic feature matrix was input for linear classifier construction. Patients from the other hospital were used for external validation. Differentiation accuracy was evaluated using a receiver operating characteristic curve. RESULTS: Based on the 120-dimensional semantic features extracted by BigBiGAN from each image, the linear classifier results indicated that the area under the curve (AUC) in the training, validation and test datasets were 0.979, 0.968 and 0.972, respectively, with an average sensitivity of 92% and specificity of 91%. The AUC for external validation was 0.850, with a sensitivity of 80% and specificity of 75%. Publicly available architecture and computing resources were used throughout the study to ensure reproducibility. CONCLUSION: This study provides an efficient recognition method for coronavirus disease 2019 pneumonia, using an end-to-end design to implement targeted and effective isolation for the containment of this communicable disease.


Subject(s)
Coronavirus Infections/diagnostic imaging , Image Processing, Computer-Assisted/methods , Pneumonia, Viral/diagnostic imaging , Tomography, X-Ray Computed/methods , Adult , Area Under Curve , Betacoronavirus , COVID-19 , Deep Learning , Diagnosis, Differential , Female , Humans , Male , Middle Aged , Pandemics , ROC Curve , Retrospective Studies , Reverse Transcriptase Polymerase Chain Reaction , SARS-CoV-2 , Sensitivity and Specificity
3.
BMC Cancer ; 20(1): 60, 2020 Jan 28.
Article in English | MEDLINE | ID: mdl-31992239

ABSTRACT

BACKGROUND: The value of the CT features and quantitative analysis of lung subsolid nodules (SSNs) in the prediction of the pathological grading of lung adenocarcinoma is discussed. METHODS: Clinical data and CT images of 207 cases (216 lesions) with CT manifestations of an SSNs lung adenocarcinoma confirmed by surgery pathology were retrospectively analysed. The pathological results were divided into three groups, including atypical adenomatous hyperplasia (AAH)/adenocarcinoma in situ (AIS), minimally invasive adenocarcinoma (MIA) and invasive adenocarcinoma (IAC). Then, the quantitative and qualitative data of these nodules were compared and analysed. RESULTS: The mean size, maximum diameter, mean CT value and maximum CT value of the nodules were significantly different among the three groups of AAH/AIS, MIA and IAC and were different between the paired groups (AAH/AIS and MIA or MIA and IAC) (P < 0.05). The critical values of the above indicators between AAH/AIS and MIA were 10.05 mm, 11.16 mm, - 548.00 HU and - 419.74 HU. The critical values of the above indicators between MIA and IAC were 14.42 mm, 16.48 mm, - 364.59 HU and - 16.98 HU. The binary logistic regression analysis of the features with the statistical significance showed that the regression model between AAH/AIS and MIA is logit(p) = - 0.93 + 0.216X1 + 0.004X4. The regression model between MIA and IAC is logit(p) = - 1.242-1.428X5(1) - 1.458X6(1) + 1.146X7(1) + 0.272X2 + 0.005X3. The areas under the curve (AUC) obtained by plotting the receiver operating characteristic curve (ROC) using the regression probabilities of regression models I and II were 0.815 and 0.931. CONCLUSIONS: Preoperative prediction of pathological classification of CT image features has important guiding value for clinical management. Correct diagnosis results can effectively improve the patient survival rate. Through comprehensive analysis of the CT features and qualitative data of SSNs, the diagnostic accuracy of SSNs can be effectively improved. The logistic regression model established in this study can better predict the pathological classification of SSNs lung adenocarcinoma on CT, and the predictive value is significantly higher than the independent use of each quantitative factor.


Subject(s)
Adenocarcinoma of Lung/diagnostic imaging , Adenocarcinoma of Lung/pathology , Lung Neoplasms/diagnostic imaging , Lung Neoplasms/pathology , Adult , Aged , Aged, 80 and over , Area Under Curve , Female , Humans , Logistic Models , Male , Middle Aged , Neoplasm Grading , Retrospective Studies
4.
Clin Interv Aging ; 11: 733-8, 2016.
Article in English | MEDLINE | ID: mdl-27307719

ABSTRACT

BACKGROUND AND PURPOSE: Lacunar infarct (LI) is well known as a heterogeneous primary disorder of cerebral small vessel. Compelling results have demonstrated that age is a risk factor to the prevalence of LI. However, the relationship between age and the prevalence of LI remains obscure. It is essential to note the relationship between age and the prevalence of LI through more clinical data. METHODS: A total of 3,500 patients were included in the case-controlled study. All data were collected from the Examination Center of Magnetic Resonance Imaging, Lu'an People's Hospital from January 2014 to December 2015. A primary discharge diagnosis of LI was done, and all subjects were evaluated as retrospective data. The relationship between the risk factors and the prevalence of diabetes and the relationship between age and the prevalence of diabetes was analyzed. A chi-square test was used to analyze the associations between different variables. A one-way analysis of variance was used to test the equality of three or more means at one time by using variances. Statistical significance was defined as a P-value of <0.05. RESULTS: The one-way analysis of variance demonstrated that the prevalence of LI increased with age before 60 years and decreased with age after 69 years. The same results were found in both the male and the female subjects. These results showed that the age-related risk factors (hypertension, diabetes, cerebral infarct, cardiovascular diseases, smoking, and drinking) have no relationship with the prevalence of LI on the basis of age. There is a significant difference among the different age ranges (P=0.0006). Two-tailed P-value (unpaired t-test) showed the mean significant difference between 30-39 years and 40-49 years (P=0.009) and between 70-79 years and 80-100 years (P=0.0196). F-test (to compare variances) demonstrated that the variances of the different age ranges are significantly different between 30-39 years and 40-49 years (P=0.0002), between 40-49 years and 50-59 years (P=0.0424), and between 70-79 years and 80-100 years (P=0.0003). CONCLUSION: The age-related risk factors (hypertension, diabetes, cerebral infarct, cardiovascular diseases, smoking, and drinking) have no relationship with the prevalence of LI on the basis of age. A decreasing prevalence of LI with aging occurs in the elderly, while the prevalence of LI increases with aging in the young and in adults. This investigation implicates that age is not a risk factor for LI in the elderly.


Subject(s)
Aging , Brain/diagnostic imaging , Stroke, Lacunar/diagnostic imaging , Stroke, Lacunar/epidemiology , Adolescent , Adult , Age Distribution , Aged , Aged, 80 and over , Case-Control Studies , Cerebral Infarction/epidemiology , Chi-Square Distribution , Child , China , Diabetes Mellitus/epidemiology , Female , Humans , Hypertension/epidemiology , Magnetic Resonance Imaging , Male , Middle Aged , Retrospective Studies , Risk Factors , Smoking/epidemiology , Young Adult
5.
Zhonghua Nan Ke Xue ; 13(5): 417-20, 2007 May.
Article in Chinese | MEDLINE | ID: mdl-17569257

ABSTRACT

OBJECTIVE: To investigate the clinical significance and diagnosis of testicular microlithiasis (TM). METHODS: We reported 2 cases of TM, reviewed the relevant published literature and analyzed the clinical significance of the condition. RESULTS: Ultrasonographic (US) scanning of the scrotal revealed multiple small calcifications diffusely scattered throughout the testicular parenchyma with rare pinpoint-like 1-2 mm shadows but without acoustic ones, which were diagnosed by scrotal sonography as right limited TM and classic TM accompanied with left varicocele and epididymitis. The testicular tumor markers of AFP, hCG, LDH and testosterone were shown to be normal, so that no intervention was performed for TM. During the 6-8 months follow-up, no abnormality was found in physical examinations and testicular tumor markers, and no characteristic additive change was revealed by testicular ultrasound. CONCLUSION: TM is a rare, usually asymptomatic and non-progressive abnormality, usually detected incidentally during the ultrasound examination of the testis. Though it is still controversial whether TM should be regarded as a premalignant lesion or not, regular follow-up and routine ultrasound examination are quite necessary for TM patients.


Subject(s)
Calculi/diagnostic imaging , Scrotum/diagnostic imaging , Testicular Diseases/diagnostic imaging , Adolescent , Adult , Genital Diseases, Male/diagnostic imaging , Humans , Male , Retrospective Studies , Testicular Neoplasms/diagnostic imaging , Ultrasonography
SELECTION OF CITATIONS
SEARCH DETAIL
...