Improved Prediction of Cognitive Outcomes via Globally Aligned Imaging Biomarker Enrichments Over Progressions.

OBJECTIVE: Longitudinal neuroimaging data have been widely used to predict clinical scores for automatic diagnosis of Alzheimer's Disease (AD) in recent years. However, incomplete temporal neuroimaging records of the patients pose a major challenge to use these data for accurately diagnosing AD. In this paper, we propose a novel method to learn an enriched representation for imaging biomarkers, which simultaneously captures the information conveyed by both the baseline neuroimaging records of all the participants in a studied cohort and the progressive variations of the available follow-up records of every individual participant. METHODS: Taking into account that different participants usually take different numbers of medical records at different time points, we develop a robust learning objective that minimizes the summations of a number of not-squared l2-norm distances, which, though, is difficult to efficiently solve in general. Thus we derive a new efficient iterative algorithm with rigorously proved convergence. RESULTS: We have conducted extensive experiments using the Alzheimer's Disease Neuroimaging Initiative (ADNI) dataset. Clear performance gains have been achieved when we predict different cognitive scores using the enriched biomarker representations learned by our new method. We further observe that the top selected biomarkers by our proposed method are in perfect accordance with the known knowledge in existing clinical AD studies. CONCLUSION: All these promising experimental results have demonstrated the effectiveness of our new method. SIGNIFICANCE: We anticipate that our new method is of interest to biomedical engineering communities beyond AD research and have open-sourced the code of our method online.11The code package of this paper have been made publicly available online at https://github.com/lyujian/Improved-Prediction-of-Cognitive-Outcomes.

Predicting Cognitive Declines Using Longitudinally Enriched Representations for Imaging Biomarkers.

A critical challenge in using longitudinal neuroimaging data to study the progressions of Alzheimer's Disease (AD) is the varied number of missing records of the patients during the course when AD develops. To tackle this problem, in this paper we propose a novel formulation to learn an enriched representation with fixed length for imaging biomarkers, which aims to simultaneously capture the information conveyed by both baseline neuroimaging record and progressive variations characterized by varied counts of available follow-up records over time. Because the learned biomarker representations are a set of fixed-length vectors, they can be readily used by traditional machine learning models to study AD developments. Take into account that the missing brain scans are not aligned in terms of time in a studied cohort, we develop a new objective that maximizes the ratio of the summations of a number of l1 -norm distances for improved robustness, which, though, is difficult to efficiently solve in general. Thus, we derive a new efficient and non-greedy iterative solution algorithm and rigorously prove its convergence. We have performed extensive experiments on the Alzheimer's Disease Neuroimaging Initiative (ADNI) cohort. A clear performance gain has been achieved in predicting ten different cognitive scores when we compare the original baseline biomarker representations against the learned representations with longitudinal enrichments. We further observe that the top selected biomarkers by our new method are in accordance with known knowledge in AD studies. These promising results have demonstrated improved performances of our new method that validate its effectiveness.