Deep learning-based application for multilevel sentiment analysis of Indonesian hotel reviews.

Purpose: In this study, we present a web-based application that retrieves hotel review documents in Indonesian languages from an online travel agent (OTA) and analyses their sentiments from the coarse-grained document to the fine-grained aspect level. Design: /Methodology/Approach: There are four main stages in this study: development of sentiment analysis model at the document level based on a convolutional neural network (CNN), development of sentiment analysis model at the aspect level based on an improved long short-term memory (LSTM), model deployment for multilevel sentiment analysis in a web-based application, and its performance evaluation. The developed application uses several sentiment visualizations types at coarse-grained and fine-grained levels, such as pie charts, line charts, and bar charts. Finding: The application's functionality was demonstrated in practice based on three datasets from three OTA websites, which were analyzed and evaluated based on several matrices, namely, the precision, recall, and F1-score. The results revealed that the performance for the F1-score was 0.95 ± 0.03, 0.87 ± 0.02, and 0.92 ± 0.07 for document-level sentiment analysis, aspect-level sentiment analysis, and aspect-polarity detection, respectively. Originality: The developed application (Sentilytics 1.0) can analyze sentiment at document and aspect levels. The two levels of sentiment analysis are based on two models generated by fine-tuning CNN and LSTM models using specific architectures and domain data (Indonesian hotel reviews).

Cardiac Disease Classification Using Two-Dimensional Thickness and Few-Shot Learning Based on Magnetic Resonance Imaging Image Segmentation.

Cardiac cine magnetic resonance imaging (MRI) is a widely used technique for the noninvasive assessment of cardiac functions. Deep neural networks have achieved considerable progress in overcoming various challenges in cine MRI analysis. However, deep learning models cannot be used for classification because limited cine MRI data are available. To overcome this problem, features from cine image settings are derived by handcrafting and addition of other clinical features to the classical machine learning approach for ensuring the model fits the MRI device settings and image parameters required in the analysis. In this study, a novel method was proposed for classifying heart disease (cardiomyopathy patient groups) using only segmented output maps. In the encoder-decoder network, the fully convolutional EfficientNetB5-UNet was modified to perform the semantic segmentation of the MRI image slice. A two-dimensional thickness algorithm was used to combine the segmentation outputs for the 2D representation of images of the end-diastole (ED) and end-systole (ES) cardiac volumes. The thickness images were subsequently used for classification by using a few-shot model with an adaptive subspace classifier. Model performance was verified by applying the model to the 2017 MICCAI Medical Image Computing and Computer-Assisted Intervention dataset. High segmentation performance was achieved as follows: the average Dice coefficients of segmentation were 96.24% (ED) and 89.92% (ES) for the left ventricle (LV); the values for the right ventricle (RV) were 92.90% (ED) and 86.92% (ES). The values for myocardium were 88.90% (ED) and 90.48% (ES). An accuracy score of 92% was achieved in the classification of various cardiomyopathy groups without clinical features. A novel rapid analysis approach was proposed for heart disease diagnosis, especially for cardiomyopathy conditions using cine MRI based on segmented output maps.

Right ventricular strain and volume analyses through deep learning-based fully automatic segmentation based on radial long-axis reconstruction of short-axis cine magnetic resonance images.

OBJECTIVE: We propose a deep learning-based fully automatic right ventricle (RV) segmentation technique that targets radially reconstructed long-axis (RLA) images of the center of the RV region in routine short axis (SA) cardiovascular magnetic resonance (CMR) images. Accordingly, the purpose of this study is to compare the accuracy of deep learning-based fully automatic segmentation of RLA images with the accuracy of conventional deep learning-based segmentation in SA orientation in terms of the measurements of RV strain parameters. MATERIALS AND METHODS: We compared the accuracies of the above-mentioned methods in RV segmentations and in measuring RV strain parameters by Dice similarity coefficients (DSCs) and correlation coefficients. RESULTS: DSC of RV segmentation of the RLA method exhibited a higher value than those of the conventional SA methods (0.84 vs. 0.61). Correlation coefficient with respect to manual RV strain measurements in the fully automatic RLA were superior to those in SA measurements (0.5-0.7 vs. 0.1-0.2). DISCUSSION: Our proposed RLA realizes accurate fully automatic extraction of the entire RV region from an available CMR cine image without any additional imaging. Our findings overcome the complexity of image analysis in CMR without the limitations of the RV visualization in echocardiography.