Abstract
Longitudinal analysis of a disease is an important issue to understand its progression and design prognosis and early diagnostic tools. From the longitudinal images where data is collected from multiple time points, both the spatial structural information and the longitudinal variations are captured. The temporal dynamics are more informative than static observations of the symptoms, particularly for neurodegenerative diseases such as Alzheimer’s disease, whose progression spans over the years with early subtle changes. In this paper, we propose a new generative framework to predict the lesion progression over time. Our method first encodes images into the structural and longitudinal state vectors, where interpolation or extrapolation of feature vectors in the time axis can be performed for the manipulation of these feature vectors. These processed feature vectors can be decoded into image space to predict the image at the time point which we are interested in. During the training, we force the model to encode longitudinal changes into longitudinal state features and capture the structural information in a separate vector. Moreover, we introduce a personalized memory for the online update scheme, which adapts the model to the target subject, which helps the model preserve fine details of brain image structures in each subject. Experimental results on the public longitudinal brain magnetic resonance imaging dataset show the effectiveness of the proposed method.
Highlights
L ONGITUDINAL analysis of a disease takes scans of patients at different time points where structural abnormalities and temporal changes are captured
The strength of our method is that it can generate sharp and detailed images, and the disease progression is well-captured in the generated longitudinal sequence, which is boosted by the online adaptive training in the personalized memory
We evaluate the quality of the predicted images by using Structural Similarity Index (SSIM) [30] and mean squared error (MSE) on the independent test data
Summary
L ONGITUDINAL analysis of a disease takes scans of patients at different time points where structural abnormalities and temporal changes are captured. Bowles et al propose a Wasserstein generative adversarial network to model brain MR images with Alzheimer’s disease features. We propose a new model that generates patient-specific longitudinal brain images by using personalized memory. To improve the quality of the generated images, we devise a personalized memory with the online adaptive training where the model is fine-tuned to the target patient in a short time. The proposed method can effectively model the temporal changes of longitudinal brain MR images by separating the structural features and the temporal state features. Experimental results show that the proposed adaptive training scheme for personalized modeling of longitudinal progression in the memory can be a promising solution for the future prediction of brain MR images
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
