Integrating multiple structured data with AI for medical images and financial markets

Abstract

In recent years, there has been a growing interest in developing methods to integrate multiple sources of information to improve decision-making in various fields. AI techniques such as deep learning and deep reinforcement learning have shown great potential for fusing different types of data and extracting useful features. This thesis focuses on the use of AI techniques to fuse multiple structured data in two different domains: medical imaging and high-frequency trading. In the first part of the thesis, we address the challenge of extracting and segmenting 3D blood vessels from CT images. Automatic blood vessel extraction from 3D medical images is crucial for vascular disease diagnoses. Existing methods based on convolutional neural networks (CNNs) may suffer from discontinuities of extracted vessels when segmenting such thin tubular structures from 3D images. We argue that preserving the continuity of extracted vessels requires taking into account the global geometry. However, 3D convolutions are computationally inefficient, which prohibits the 3D CNNs from sufficiently large receptive fields to capture the global cues in the entire image. In this part, we propose a hybrid representation learning approach to address this challenge. The main idea is to use CNNs to learn local appearances of vessels in image crops while using another point-cloud network to learn the global geometry of vessels in the entire image. In inference, the proposed approach extracts local segments of vessels using CNNs, classifies each segment based on global geometry using the point-cloud network, and finally connects all the segments that belong to the same vessel using the shortest-path algorithm. This combination results in an efficient, fully-automatic, and template-free approach to centerline extraction from 3D images. We validate the proposed approach on CTA datasets and demonstrate its superior performance compared to both traditional and CNN-based baselines. In the second part of the thesis, we focus on the problem of market making in high-frequency trading. Market making is a critical function in financial markets that involves providing liquidity by buying and selling assets. However, the increasing complexity of financial markets and the high volume of data generated by tick-level trading makes it challenging to develop effective market making strategies. To address this challenge, we propose a deep reinforcement learning approach that fuses tick-level data with periodic prediction signals to develop a more accurate and robust market making strategy. Our results of market making strategies based on different deep reinforcement learning algorithms under the simulation scenarios and real data experiments in the cryptocurrency markets show that the proposed framework outperforms existing methods in terms of profitability and risk management. Keywords: Medical image analysis, 3D vessel segmentation, Hybrid representations, High-frequency trading, Market making strategy, Deep reinforcement learning

Date of Award	2023
Original language	English
Awarding Institution	The Hong Kong University of Science and Technology
Supervisor	Can YANG (Supervisor)