Search

Abstract. Background. The current deep learning diagnosis of breast masses is mainly reflected by the diagnosis of benign and malignant lesions. In China, breast masses are divided into four categories according to the treatment method: inflammatory masses, adenosis, benign tumors, and malignant tumors. These categorizations are important for guiding clinical treatment. In this study, we aimed to develop a convolutional neural network (CNN) for classification of these four breast mass types using ultrasound (US) images. Methods. Taking breast biopsy or pathological examinations as the reference standard, CNNs were used to establish models for the four-way classification of 3623 breast cancer patients from 13 centers. The patients were randomly divided into training and test groups (n = 1810 vs. n = 1813). Separate models were created for two-dimensional (2D) images only, 2D and color Doppler flow imaging (2D-CDFI), and 2D-CDFI and pulsed wave Doppler (2D-CDFI-PW) images. The performance of these three models was compared using sensitivity, specificity, area under receiver operating characteristic curve (AUC), positive (PPV) and negative predictive values (NPV), positive (LR+) and negative likelihood ratios (LR−), and the performance of the 2D model was further compared between masses of different sizes with above statistical indicators, between images from different hospitals with AUC, and with the performance of 37 radiologists. Results. The accuracies of the 2D, 2D-CDFI, and 2D-CDFI-PW models on the test set were 87.9%, 89.2%, and 88.7%, respectively. The AUCs for classification of benign tumors, malignant tumors, inflammatory masses, and adenosis were 0.90, 0.91, 0.90, and 0.89, respectively (95% confidence intervals [CIs], 0.87–0.91, 0.89–0.92, 0.87–0.91, and 0.86–0.90). The 2D-CDFI model showed better accuracy (89.2%) on the test set than the 2D (87.9%) and 2D-CDFI-PW (88.7%) models. The 2D model showed accuracy of 81.7% on breast masses ≤1 cm and 82.3% on breast masses >1 cm; there was a significant difference between the two groups (P

Background: This study aimed to observe the differences in brain gray matter volume in drug-naive female patients after the first episode of major depression with and without stressful life events (SLEs) before the onset of depression. Methods: Forty-three drug-naive female patients voluntarily participated in the present study after the first major depressive episode. The life event scale was used to evaluate the severity of the impact of SLEs during 6 months before the onset of the major depressive episode. High-field magnetic resonance imaging (MRI) scans were obtained, and the VBM and SPM8 software process were used to process and analyze the MRI. Results: Compared to that in patients without SLEs, the volume of brain gray matter was lower in the bilateral temporal lobe, right occipital lobe, and right limbic lobe in the SLE group. However, the gray matter volume did not differ significantly between the two groups after the application of false discovery rate (FDR) correction. Conclusions: Although the results of the present study suggest the absence of significant differences in brain gray matter volume between female drug-naive patients after the first episode of major depression with and without SLEs after FDR correction, the study provides useful information for exploring the definitive role of stress in the onset of depression.

Background: Spinocerebellar ataxia type 3 (SCA3) is the most common subtype of SCA worldwide, and runs a slowly progressive and unremitting disease course. There is currently no curable treatment available. Growing evidence has suggested that nerve growth factor (NGF) may have therapeutic effects in neurodegenerative diseases, and possibly also in SCA3. The objective of this study was to test the efficacy of NGF in SCA3 patients. Methods: We performed an open-label prospective study in genetically confirmed adult (>18 years old) SCA3 patients. NGF was administered by intramuscular injection (18 μg once daily) for 28 days consecutively. All the patients were evaluated at baseline and 2 and 4 weeks after treatment using the Chinese version of the scale for assessment and rating of ataxia (SARA). Results: Twenty-one SCA3 patients (10 men and 11 women, mean age 39.14 ± 7.81 years, mean disease duration 4.14 ± 1.90 years, mean CAG repeats number 77.57 ± 2.27) were enrolled. After 28 days of NGF treatment, the mean total SARA score decreased significantly from a baseline of 8.48 ± 2.40 to 6.30 ± 1.87 (P < 0.001). Subsections SARA scores also showed significant improvements in stance (P = 0.003), speech (P = 0.023), finger chase (P = 0.015), fast alternating hand movements (P = 0.009), and heel-shin slide (P = 0.001). Conclusions: Our preliminary data suggest that NGF may be effective in treating patients with SCA3.