Optimization of neural network for cancer microRNA biomarkers classification

Automated classification of ulcerative lesions in small intestine using densenet with channel attention and residual dilated blocks

Objective. Ulceration of the small intestine, which has a high incidence, includes Crohn's disease (CD), intestinal tuberculosis (ITB), primary small intestinal lymphoma (PSIL), cryptogenic multifocal ulcerous stenosing enteritis (CMUSE), and non-specific ulcer (NSU). However, the ulceration morphology can easily be misdiagnosed through enteroscopy.Approach. In this study, DRCA-DenseNet169, which is based on DenseNet169, with residual dilated blocks and a channel attention block, is proposed to identify CD, ITB, PSIL, CMUSE, and NSU intelligently. In addition, a novel loss function that incorporates dynamic weights is designed to enhance the precision of imbalanced datasets with limited samples. DRCA-Densenet169 was evaluated using 10883 enteroscopy images, including 5375 ulcer images and 5508 normal images, which were obtained from the Shanghai Changhai Hospital.Main results. DRCA-Densenet169 achieved an overall accuracy of 85.27% ± 0.32%, a weighted-precision of 83.99% ± 2.47%, a weighted-recall of 84.36% ± 0.88% and a weighted-F1-score of 84.07% ± 2.14%.Significance. The results demonstrate that DRCA-Densenet169 has high recognition accuracy and strong robustness in identifying different types of ulcers when obtaining immediate and preliminary diagnoses.

A neural network-based method for exhaustive cell label assignment using single cell RNA-seq data

The fast-advancing single cell RNA sequencing (scRNA-seq) technology enables researchers to study the transcriptome of heterogeneous tissues at a single cell level. The initial important step of analyzing scRNA-seq data is usually to accurately annotate cells. The traditional approach of annotating cell types based on unsupervised clustering and marker genes is time-consuming and laborious. Taking advantage of the numerous existing scRNA-seq databases, many supervised label assignment methods have been developed. One feature that many label assignment methods shares is to label cells with low confidence as "unassigned." These unassigned cells can be the result of assignment difficulties due to highly similar cell types or caused by the presence of unknown cell types. However, when unknown cell types are not expected, existing methods still label a considerable number of cells as unassigned, which is not desirable. In this work, we develop a neural network-based cell annotation method called NeuCA (Neural network-based Cell Annotation) for scRNA-seq data obtained from well-studied tissues. NeuCA can utilize the hierarchical structure information of the cell types to improve the annotation accuracy, which is especially helpful when data contain closely correlated cell types. We show that NeuCA can achieve more accurate cell annotation results compared with existing methods. Additionally, the applications on eight real datasets show that NeuCA has stable performance for intra- and inter-study annotation, as well as cross-condition annotation. NeuCA is freely available as an R/Bioconductor package at https://bioconductor.org/packages/NeuCA .

Application of breast cancer diagnosis based on a combination of convolutional neural networks, ridge regression and linear discriminant analysis using invasive breast cancer images processed with autoencoders

Invasive ductal carcinoma cancer, which invades the breast tissues by destroying the milk channels, is the most common type of breast cancer in women. Approximately, 80% of breast cancer patients have invasive ductal carcinoma and roughly 66.6% of these patients are older than 55 years. This situation points out a powerful relationship between the type of breast cancer and progressed woman age. In this study, the classification of invasive ductal carcinoma breast cancer is performed by using deep learning models, which is the sub-branch of artificial intelligence. In this scope, convolutional neural network models and the autoencoder network model are combined. In the experiment, the dataset was reconstructed by processing with the autoencoder model. The discriminative features obtained from convolutional neural network models were utilized. As a result, the most efficient features were determined by using the ridge regression method, and classification was performed using linear discriminant analysis. The best success rate of classification was achieved as 98.59%. Consequently, the proposed approach can be admitted as a successful model in the classification.