ABSTRACT
Objective:To explore the value of radiomics features extracted from multi-parameter MRI (mp-MRI) in preoperative prediction of triple negative breast cancer (TNBC) and non triple negative breast cancer (NTNBC).Methods:The clinical and preoperative-MRI data of 371 patients with breast cancer confirmed by surgical pathology from January 2017 to July 2019 in Henan Provincial People′s Hospital were retrospectively analyzed. Based on the results of immunohistochemistry (IHC) and fluorescence in situ hybridization (FISH) from postoperative pathological specimens, the cancer was classified as TNBC and NTNBC. Patients were randomly assigned to a training set ( n=250) and a validation set ( n=121). Quantitative radiomics features were extracted from three-dimensional lesions based on dynamic contrast enhanced-T 1WI (DCE-T 1WI) and fat-suppressed T 2WI sequences, and 32 quantitative radiomics features were selected by Mann-Whitney U test, elastic network, and support vector machine recursive feature elimination. Three radiomics signatures were constructed by using the algorithm of support vector machine based on the quantitative radiomics features extracted from fat-suppressed T 2WI, DCE-T 1WI and the mp-MRI of their combination. The prediction performances were evaluated by receiver operating characteristic (ROC) curve and the area under the ROC curve, accuracy, sensitivity, and specificity were calculated. Results:There were 61 patients with TNBC and 310 patients with NTNBC. The clinicopathological characteristics between NTNBC and TNBC were statistically different in the pathological grade (χ2=24.544, P<0.001). Other clinicopathological characteristics (age, maximum diameter of mass, vascular tumor thrombus, axillary lymph nodes) were not statistically differences between NTNBC and TNBC ( P>0.05). The radiomics signature presenting the best performance for predictive TNBC and NTNBC were based on mp-MRI radiomics features. The area under the ROC curve, accuracy, sensitivity, and specificity were 0.91[95% confidence interval (CI) 0.881-0.932], 86.0%, 84.4% and 86.3% in training set, and 0.84 (95%CI 0.807-0.868), 75.2%, 68.7% and 76.1%, in validation set, respectively. Conclusion:Radiomics based on mp-MRI features can be a effectively potential tool for predictive TNBC and NTNBC breast cancer and provide scientific basis for clinicians to make treatment decisions.
ABSTRACT
Brain-computer interface (BCI) system is a system that achieves communication and control among humans and computers and other electronic equipment with the electroencephalogram (EEG) signals. This paper describes the working theory of the wireless smart home system based on the BCI technology. We started to get the steady-state visual evoked potential (SSVEP) using the single chip microcomputer and the visual stimulation which composed by LED lamp to stimulate human eyes. Then, through building the power spectral transformation on the LabVIEW platform, we processed timely those EEG signals under different frequency stimulation so as to transfer them to different instructions. Those instructions could be received by the wireless transceiver equipment to control the household appliances and to achieve the intelligent control towards the specified devices. The experimental results showed that the correct rate for the 10 subjects reached 100%, and the control time of average single device was 4 seconds, thus this design could totally achieve the original purpose of smart home system.
Subject(s)
Humans , Brain-Computer Interfaces , Electroencephalography , Evoked Potentials, Visual , Microcomputers , Wireless TechnologyABSTRACT
Objective To evaluate the relationship between echocardiographic epicardial adipose tissue thickness(EAT) and the presence and severity of coronary artery disease(CAD). Methods One hundredand forty-seven patients (101 patients with CAD and 46 patients with normal coronary arteries by diagnostic coronary angiography) were enrolled. EAT thickness was measured using 2-D echocardiographic parasternal long-and short-axis views. EAT thickness measurements were compared with angiographic findings. Results EAT was significantly higher in CAD group comparison to control group [(7.41 ± 1.63)mm vs (4.41±1.60) mm, P ＜0.01 ]. Furthermore, EAT increased with the severity of CAD [(8.53 ± 1.00)mm vs (6.36 ±1.73)mm, P ＜0.01]. Gensini's score significantly correlated with EAT (r = 0.71, P ＜0.01 ). EAT thickness ≥5.35 mm had 87.13% sensitivity and 80.42% specificity (ROC area 0. 89, P = 0.01,95% CI [0.84 - 0.9;]) for predicting CAD. Conclusions EAT thickness, which is easily and non-invasively evaluated by transthoracic echocardiography, can be an adjunctive marker to classical risk factors for the prediction of CAD, it was significantly correlated with the severity of coronary artery disease.
ABSTRACT
Objective To explore the impact of nursing intervention on negative moods, compliance behavior and life quality of patients with chronic heart failure (CHF). Methods We randomized 100 patients with CHF into the observation group and the control group. The control group only accepted basic nursing, life nursing and treatment; besides these, the observation group were given other interventions, including health education, comfortable environment, physical activity, compliance behavior, diet and mental guidance 3 days after the patients were admitted into hospital. The two groups were tested for anxiety, depression, compliance behavior as well as life quality with Minnesota Living with Heart failure questionnaire both 3 days after the patients were admitted into hospital and when they were discharged. χ2 test and t test were used to analyze the data. Results Before intervention, there were no statistical difference in their anxiety, depression, compliance behavior, and life quality between the observation group and the control group. After intervention, the observation group was superior than the control group in anxiety and depression score, compliance behaviors including on-time medicine administration, regular recheck, rational diet, smoke abatement and alcohal restriction, physical activity, life quality score including physical limitation, emotion, symptom and social constrain. Conclusions Nursing intervention could help improve anxiety and depression of the patients with CHF, promote their compliance behaviors and improve their life quality.