Temporally Local Weighting-Based Phase-Locked Time-Shift Data Augmentation Method for Fast-Calibration SSVEP-BCI.

Various training-based spatial filtering methods have been proposed to decode steady-state visual evoked potentials (SSVEPs) efficiently. However, these methods require extensive calibration data to obtain valid spatial filters and temporal templates. The time-consuming data collection and calibration process would reduce the practicality of SSVEP-based brain-computer interfaces (BCIs). Therefore, we propose a temporally local weighting-based phase-locked time-shift (TLW-PLTS) data augmentation method to augment training data for calculating valid spatial filters and temporal templates. In this method, the sliding window strategy using the SSVEP response period as a time-shift step is to generate the augmented data, and the time filter which maximises the temporally local covariance between the original template signal and the sine-cosine reference signal is used to suppress the temporal noise in the augmented data. For the performance evaluation, the TLW-PLTS method was incorporated with state-of-the-art training-based spatial filtering methods to calculate classification accuracies and information transfer rates (ITRs) using three SSVEP datasets. Compared with state-of-the-art training-based spatial filtering methods and other data augmentation methods, the proposed TLW-PLTS method demonstrates superior decoding performance with fewer calibration data, which is promising for the development of fast-calibration BCIs.

Usefulness of prenatal magnetic resonance imaging in differential diagnosis of fetal congenital cystic adenomatoid malformation and bronchopulmonary sequestration.

BACKGROUND: Congenital cystic adenomatoid malformation (CCAM) and bronchopulmonary sequestration (BPS) are the most common lung diseases in fetuses. There are differences in the prognosis and treatment of CCAM and BPS, and the clinical diagnosis and treatment plan is usually prepared prior to birth. Therefore, it is quite necessary to make a clear diagnosis before delivery. CCAM and BPS have similar imaging features, and the differentiation mainly relies on the difference in supply vessels. However, it is hard to distinguish them due to invisible supplying vessels on some images. AIM: To explore the application value of magnetic resonance imaging (MRI) in the differential diagnosis of fetal CCAM and BPS. METHODS: Data analysis for 32 fetuses with CCAM and 14 with BPS diagnosed by prenatal MRI at Huzhou Maternal and Child Health Care Hospital and Anhui Provincial Children's Hospital from January 2017 to January 2020 was performed to observe the source blood vessels of lesions and their direction. Pathological confirmation was completed through CT examination and/or operations after birth. RESULTS: After birth, 31 cases after birth were confirmed to be CCAM, and 15 were confirmed to be BPS. The CCAM group consisted of 21 macrocystic cases and 10 microcystic cases. In 18 cases, blood vessels were visible in lesions. Blood supply of the pulmonary artery could be traced in eight cases, and in 10 cases, only vessels running from the midline to the lateral down direction were observed. No lesions were found in four macrocystic cases and one microcystic case with CCAM through CT after birth; two were misdiagnosed by MRI, and three were misdiagnosed by prenatal ultrasonography. The BPS group consisted of 12 intralobar cases and three extralobar cases. Blood vessels were visible in lesions of nine cases, in four of which, the systemic circulation blood supply could be traced, and in five of which, only vessels running from the midline to the lateral up direction were observed. Three were misdiagnosed by MRI, and four were misdiagnosed by prenatal ultrasonography. CONCLUSION: CCAM and BPS can be clearly diagnosed based on the origin of blood vessels, and correct diagnosis can be made according to the difference in the direction of the blood vessels, but it is hard distinguish microcystic CCAM and BPS without supplying vessels. In some CCAM cases, mainly the macrocystic ones, the lesions may disappear after birth.

Microstructure Evolution and Performance Improvement of Hypereutectic Al-Mg2Si Metallic Composite with Ca or Sb.

In this article, the modification effects on Al-Mg2Si before and after heat treatment were investigated with Ca, Sb, and (Ca + Sb). In comparison with single Ca or Sb, the samples with composition modifiers (Ca + Sb) had the optimal microstructure. The sample with a molar ratio for Ca-to-Sb of 1:1 obtained relatively higher properties, for which the Brinell hardness values before and after heat treatment were remarkably increased by 31.74% and 28.93% in comparison with bare alloy. According to differential scanning calorimetry analysis (DSC), it was found that the nucleation behavior of the primary Mg2Si phase could be significantly improved by using chemical modifiers. Some white particles were found to be embedded in the center of Mg2Si phases, which were deduced to be Ca5Sb3 through X-ray diffraction (XRD) and field-emission scanning electron microscope (FESEM) analyses. Furthermore, Ca5Sb3 articles possess a rather low mismatch degree with Mg2Si particles based on Phase Transformation Crystallography Lab software (PTCLab) calculation, meaning that the efficient nucleation capability of Ca5Sb3 for Mg2Si particles could be estimated.

Pancreatic cancer biomarker detection by two support vector strategies for recursive feature elimination.

AIM: Pancreatic cancer is one of the worst malignant tumors in prognosis. Therefore, to reduce the mortality rate of pancreatic cancer, early diagnosis and prompt treatment are particularly important. RESULTS: We put forward a new feature-selection method that was used to find clinical markers for pancreatic cancer by combination of Support Vector Machine Recursive Feature Elimination (SVM-RFE) and Large Margin Distribution Machine Recursive Feature Elimination (LDM-RFE) algorithms. As a result, seven differentially expressed genes were predicted as specific biomarkers for pancreatic cancer because of their highest accuracy of classification on cancer and normal samples. CONCLUSION: Three (MMP7, FOS and A2M) out of the seven predicted gene markers were found to encode proteins secreted into urine, providing potential diagnostic evidences for pancreatic cancer.

Clinical value of prenatal MRI for diagnosis of isolated ventriculomegaly and prediction of early postnatal developmental outcomes.

OBJECTIVE: To investigate the relationship of ventriculomegaly (VM) with postnatal neurological development. METHODS: Fetuses with isolated VM on MRI (n = 160; VM group) were separated into three subgroups according to lateral ventricle width: subgroup A (10.0-12.0 mm; n = 113), subgroup B (12.1-15.0 mm; n = 37), and subgroup C (>15.0 mm; n = 10). Fifty normal fetuses formed a control group. Post-delivery changes in ventricular width and neurological development were assessed with MRI/ultrasonography and the Gesell Development Schedules (GDS), respectively, at 3, 6, 12, and 18 months. RESULTS: GDS scores of subgroup A and subgroup B did not differ from that of the controls at 3 and 6 months. Subgroup B scores differed significantly from the control scores at 12 and 18 months. Subgroup C scores differed from the control scores at all-time points (all P < 0.05). In the VM group, GDS scores at 12 and 18 months were significantly different from the scores at 3 months, and the score at 18 months was significantly different from the score at 6 months (P < 0.05 for all). CONCLUSION: The milder the VM, the more likely it was to disappear or improve in the postnatal period. However, specific postnatal rehabilitation should be considered when fetal ventricular width is greater than 12.1 mm.