Abstract:
Quantitative susceptibility mapping (QSM) has been applied to the measurement of iron deposition and the auxiliary diagnosis of neurodegenerative disease. There still exists a dipole inversion problem in QSM reconstruction. Recently, deep learning approaches have been proposed to resolve this problem. However, most of these approaches are supervised methods that need pairs of the input phase and ground-truth. It remains a challenge to train a model for all resolutions without using the ground truth and only using one resolution of data. To address this, we proposed a self-supervised QSM deep learning method based on morphology. It consists of a morphological QSM builder to decouple the dependency of the QSM on acquisition resolution, and a morphological loss to reduce artifacts effectively and save training time efficiently. The proposed method can reconstruct arbitrary resolution QSM on both human data and animal data, regardless of whether the resolution is higher or lower than that of the training set. Our method outperforms the previous best-unsupervised method with a 3.6% higher peak signal-to-noise ratio, 16.2% lower normalized root mean square error, and 22.1% lower high-frequency error norm. The morphological loss reduces by 22.1% training time with respect to the cycle gradient loss used in the previous unsupervised methods. Experimental results show that the proposed method accurately measures QSM with arbitrary resolutions, and achieves state-of-the-art results among unsupervised deep learning methods. Research on applications in neurodegenerative diseases found that our method is robust enough to measure a significant increase in striatal magnetic susceptibility in patients during Alzheimer’s disease progression, including subjective cognitive decline, mild cognitive impairment, and AD. A significant increase in susceptibility is detected in substantia nigra susceptibility in Parkinson’s disease patients. Our method can be used as an auxiliary differential diagnosis tool for Alzheimer’s disease and Parkinson’s disease.
Biography:
Junjie He Ph.D. student at Guizhou University, engaged in the application of computer vision in medical imaging, especially the MR reconstruction of QSM images and its application on neurodegenerative disorders. Publishing multiple papers in journals such as NeuroImage, Frontiers in Neuroscience, and Computer Methods and Programs in Biomedicine. Outstanding graduate of Nanjing University. Outstanding Individual Award and the Feature Star Award at Huawei Technologies. Angle Investment Recipient at Ericsson.
Junjie He
