Source-free Domain Adaptation via Multicentric Prototype for Alzheimer's Disease Detection

• Published in: 2023 3rd International Conference on Consumer Electronics and Computer Engineering (ICCECE) pp. 181 - 185
• Main Authors: Zhang, Qiongmin, Cai, Hongshun, Long, Ying
• Format: Conference Proceeding
• Language: English
• Published: IEEE 06.01.2023
• Subjects: Adaptation models; Alzheimer's disease; Data privacy; Domain adaptation; Feature extraction; Magnetic resonance imaging; Multicentric Prototype; Prototypes; Source-free; Structural MRI; Supervised learning; Transfer learning

The use of deep learning and transfer learning techniques for the early diagnosis of Alzheimer's Disease (AD) is of great significance for delaying its development. In the real world, due to different scanners, scanning protocols, and subject cohorts, structural Magnetic Resonance Imaging (MRI)...