Refine
Year of publication
- 2020 (2) (remove)
Document Type
- Article (2)
Language
- English (2)
Has Fulltext
- yes (2)
Is part of the Bibliography
- no (2)
Keywords
- Alzheimer’s disease (2) (remove)
Institute
Alzheimer’s disease (AD) is the most prevalent neurodegenerative disease causing dementia and poses significant health risks to middle-aged and elderly people. Brain magnetic resonance imaging (MRI) is the most widely used diagnostic method for AD. However, it is challenging to collect sufficient brain imaging data with high-quality annotations. Weakly supervised learning (WSL) is a machine learning technique aimed at learning effective feature representation from limited or low-quality annotations. In this paper, we propose a WSL-based deep learning (DL) framework (ADGNET) consisting of a backbone network with an attention mechanism and a task network for simultaneous image classification and image reconstruction to identify and classify AD using limited annotations. The ADGNET achieves excellent performance based on six evaluation metrics (Kappa, sensitivity, specificity, precision, accuracy, F1-score) on two brain MRI datasets (2D MRI and 3D MRI data) using fine-tuning with only 20% of the labels from both datasets. The ADGNET has an F1-score of 99.61% and sensitivity is 99.69%, outperforming two state-of-the-art models (ResNext WSL and SimCLR). The proposed method represents a potential WSL-based computer-aided diagnosis method for AD in clinical practice.
Background: Hyperhomocysteinemia is considered a possible contributor to the complex pathology of Alzheimer’s disease (AD). For years, researchers in this field have discussed the apparent detrimental effects of the endogenous amino acid homocysteine in the brain. In this study, the roles of hyperhomocysteinemia driven by vitamin B deficiency, as well as potentially beneficial dietary interventions, were investigated in the novel AppNL-G-F knock-in mouse model for AD, simulating an early stage of the disease. Methods: Urine and serum samples were analyzed using a validated LC-MS/MS method and the impact of different experimental diets on cognitive performance was studied in a comprehensive behavioral test battery. Finally, we analyzed brain samples immunohistochemically in order to assess amyloid-β (Aβ) plaque deposition. Results: Behavioral testing data indicated subtle cognitive deficits in AppNL-G-F compared to C57BL/6J wild type mice. Elevation of homocysteine and homocysteic acid, as well as counteracting dietary interventions, mostly did not result in significant effects on learning and memory performance, nor in a modified Aβ plaque deposition in 35-week-old AppNL-G-F mice. Conclusion: Despite prominent Aβ plaque deposition, the AppNL-G-F model merely displays a very mild AD-like phenotype at the investigated age. Older AppNL-G-F mice should be tested in order to further investigate potential effects of hyperhomocysteinemia and dietary interventions.