Learning Personalized Representation for Inverse Problems in Medical Imaging Using Deep Neural Network
This addresses the data scarcity problem in clinical medical imaging by enabling deep learning applications without large datasets, though it is incremental as it builds on existing deep neural network and optimization methods.
The authors tackled the need for large training datasets in medical imaging by proposing a personalized representation learning framework that uses only a patient's prior images, eliminating the need for prior training pairs. Results from brain PET reconstruction and denoising on simulation and real datasets show that this framework outperforms other widely adopted methods.
Recently deep neural networks have been widely and successfully applied in computer vision tasks and attracted growing interests in medical imaging. One barrier for the application of deep neural networks to medical imaging is the need of large amounts of prior training pairs, which is not always feasible in clinical practice. In this work we propose a personalized representation learning framework where no prior training pairs are needed, but only the patient's own prior images. The representation is expressed using a deep neural network with the patient's prior images as network input. We then applied this novel image representation to inverse problems in medical imaging in which the original inverse problem was formulated as a constraint optimization problem and solved using the alternating direction method of multipliers (ADMM) algorithm. Anatomically guided brain positron emission tomography (PET) image reconstruction and image denoising were employed as examples to demonstrate the effectiveness of the proposed framework. Quantification results based on simulation and real datasets show that the proposed personalized representation framework outperform other widely adopted methods.