Apache Spark based kernelized fuzzy clustering framework for single nucleotide polymorphism sequence analysis

Automatic identification of schizophrenia employing EEG records analyzed with deep learning algorithms

Electroencephalography is a method of detecting and analyzing electrical activity in the brain. This electrical activity can be recorded and processed to aid in the clinical diagnosis of mental disorders. In this study, a novel system for classifying schizophrenia patients from EEG recordings is presented. The developed algorithm decomposes the EEG signals into a system of radial basis functions using the method of fuzzy means. This decomposition helps to obtain the information from the various electrodes of the EEG and allows separating between healthy controls and patients with schizophrenia. The proposed method has been compared with classical machine learning algorithms, such as, K-Nearest Neighbor, Adaboost, Support Vector Machine, and Bayesian Linear Discriminant Analysis. The results show that the proposed method obtains the highest values in terms of balanced accuracy, recall, precision and F1 score, close to 93 % in all cases. The model developed in this study can be implemented in brain activity analysis systems that help in the prediction of patients with schizophrenia.

Improved Fuzzy C-Means Clustering Algorithm-Based Dynamic Contrast-Enhanced Magnetic Resonance Imaging Features in the Diagnosis of Invasive Breast Carcinoma before and after Menopause

The application effect of dynamic contrast-enhanced magnetic resonance imaging (DCE-MRI) based on the improved fuzzy C-mean clustering (GA-PFCM) algorithm in analyzing premenopausal and postmenopausal invasive breast carcinoma was discussed. 159 patients with breast carcinoma were selected and divided into the postmenopausal group (71 patients) and the premenopausal group (88 patients) according to their menstrual status. The magnetic resonance images of the two groups were processed and analyzed using GA-PFCM algorithm, and the imaging characteristics and relevant parameters of DCE-MRI examination of the two groups were analyzed. Besides, the sensitivity, specificity, and accuracy of the diagnosis of invasive breast carcinoma by DCE-MRI examination were investigated. The results showed that the percentage of patients with lobulated lumps, patients with burrs on lesion edge, and patients with uniformly enhanced tumors in the premenopausal group was larger than that in the postmenopausal group (P < 0.05). In the postmenopausal group, TCI of 33 patients was shown as platform curves, and that of 34 patients was shown as outflow curves. In the premenopausal group, TCI of 39 patients was shown as platform curves, and that of 41 patients was shown as outflow curves with a high proportion. The number of patients with peak height time ranging between 130 s and 260 s and of patients with early signal enhancement rate ranging between 100% and 200% was large. In contrast, the number of patients with ADC value higher than 1.2 × 10^-3 was the least. In this research, there were 128 patients with positive invasive breast carcinoma and 31 with negative invasive breast carcinoma by pathological examination. Based on DCE-MRI examination, there were 121 patients with positive invasive breast carcinoma and 38 with negative invasive breast carcinoma. The sensitivity, specificity, and accuracy of invasive breast carcinoma by DCE-MRI were 91.41%, 87.1%, and 90.57%, respectively. In addition, the positive and negative predictive values reached 96.69% and 71.05%, respectively. In summary, GA-PFCM algorithm can be applied in the processing and segmentation of DCE-MRI images, and DCE-MRI could better diagnose invasive breast carcinoma with positive guiding value.