A Deep Learning Framework for the Characterization of Thyroid Nodules from Ultrasound Images Using Improved Inception Network and Multi-Level Transfer Learning.

In the past few years, deep learning has gained increasingly widespread attention and has been applied to diagnosing benign and malignant thyroid nodules. It is difficult to acquire sufficient medical images, resulting in insufficient data, which hinders the development of an efficient deep-learning model. In this paper, we developed a deep-learning-based characterization framework to differentiate malignant and benign nodules from the thyroid ultrasound images. This approach improves the recognition accuracy of the inception network by combining squeeze and excitation networks with the inception modules. We have also integrated the concept of multi-level transfer learning using breast ultrasound images as a bridge dataset. This transfer learning approach addresses the issues regarding domain differences between natural images and ultrasound images during transfer learning. This paper aimed to investigate how the entire framework could help radiologists improve diagnostic performance and avoid unnecessary fine-needle aspiration. The proposed approach based on multi-level transfer learning and improved inception blocks achieved higher precision (0.9057 for the benign class and 0.9667 for the malignant class), recall (0.9796 for the benign class and 0.8529 for malignant), and F1-score (0.9412 for benign class and 0.9062 for malignant class). It also obtained an AUC value of 0.9537, which is higher than that of the single-level transfer learning method. The experimental results show that this model can achieve satisfactory classification accuracy comparable to experienced radiologists. Using this model, we can save time and effort as well as deliver potential clinical application value.

A cooperative deep learning model for stock market prediction using deep autoencoder and sentiment analysis.

Stock market prediction is a challenging and complex problem that has received the attention of researchers due to the high returns resulting from an improved prediction. Even though machine learning models are popular in this domain dynamic and the volatile nature of the stock markets limits the accuracy of stock prediction. Studies show that incorporating news sentiment in stock market predictions enhances performance compared to models using stock features alone. There is a need to develop an architecture that facilitates noise removal from stock data, captures market sentiments, and ensures prediction to a reasonable degree of accuracy. The proposed cooperative deep-learning architecture comprises a deep autoencoder, lexicon-based software for sentiment analysis of news headlines, and LSTM/GRU layers for prediction. The autoencoder is used to denoise the historical stock data, and the denoised data is transferred into the deep learning model along with news sentiments. The stock data is concatenated with the sentiment score and is fed to the LSTM/GRU model for output prediction. The model's performance is evaluated using the standard measures used in the literature. The results show that the combined model using deep autoencoder with news sentiments performs better than the standalone LSTM/GRU models. The performance of our model also compares favorably with state-of-the-art models in the literature.