The pathogenesis of Alzheimer's disease (AD) is extremely intricate, which makes AD patients almost incurable. Recent studies have demonstrated that analyzing multi-modal data can offer a comprehensive perspective on the different stages of AD progression, which is beneficial for early diagnosis of AD. In this paper, we propose a deep self-reconstruction fusion similarity hashing (DS-FSH) method to effectively capture the AD-related biomarkers from the multi-modal data and leverage them to diagnose AD. Given that most existing methods ignore the topological structure of the data, a deep self-reconstruction model based on random walk graph regularization is designed to reconstruct the multi-modal data, thereby learning the nonlinear relationship between samples. Additionally, a fused similarity hash based on anchor graph is proposed to generate discriminative binary hash codes for multi-modal reconstructed data. This allows sample fused similarity to be effectively modeled by a fusion similarity matrix based on anchor graph while modal correlation can be approximated by Hamming distance. Especially, extracted features from the multi-modal data are classified using deep sparse autoencoders classifier. Finally, experiments conduct on the AD Neuroimaging Initiative database show that DS-FSH outperforms comparable methods of AD classification. To conclude, DS-FSH identifies multi-modal features closely associated with AD, which are expected to contribute significantly to understanding of the pathogenesis of AD.

The roles of brain region activities and genotypic functions in the pathogenesis of Alzheimer's disease (AD) remain unclear. Meanwhile, current imaging genetics methods are difficult to identify potential pathogenetic markers by correlation analysis between brain network and genetic variation. To discover disease-related brain connectome from the specific brain structure and the fine-grained level, based on the Automated Anatomical Labeling (AAL) and human Brainnetome atlases, the functional brain network is first constructed for each subject. Specifically, the upper triangle elements of the functional connectivity matrix are extracted as connectivity features. The clustering coefficient and the average weighted node degree are developed to assess the significance of every brain area. Since the constructed brain network and genetic data are characterized by non-linearity, high-dimensionality, and few subjects, the deep subspace clustering algorithm is proposed to reconstruct the original data. Our multilayer neural network helps capture the non-linear manifolds, and subspace clustering learns pairwise affinities between samples. Moreover, most approaches in neuroimaging genetics are unsupervised learning, neglecting the diagnostic information related to diseases. We presented a label constraint with diagnostic status to instruct the imaging genetics correlation analysis. To this end, a diagnosis-guided deep subspace clustering association (DDSCA) method is developed to discover brain connectome and risk genetic factors by integrating genotypes with functional network phenotypes. Extensive experiments prove that DDSCA achieves superior performance to most association methods and effectively selects disease-relevant genetic markers and brain connectome at the coarse-grained and fine-grained levels.

Purpose: To assess the characteristics of fibrotic-foci-like lung adenocarcinoma on ¹⁸F-fluorodeoxyglucose PET/computed tomography (¹⁸F-FDG PET/CT) and high-resolution computed tomography (HRCT). Material and methods: This was a retrospective study with 20 cases in the fibrotic-foci-like lung adenocarcinoma group; the control group was old fibrotic-foci of the lung with 20 cases. The following ¹⁸F-FDG PET/CT and HRCT features were evaluated: the maximum standardized uptake value (SUVmax); the tumor-to-background ratios of SUVmax (TBRmax); the long-to-short diameter ratio (L/S); anatomic location; location type; internal characteristics; marginal characteristics and surrounding structures. In the fibrotic-foci-like lung adenocarcinoma group, a comparison of ¹⁸F-FDG uptake between the metastatic group (n = 10) and the non-metastatic group (n = 10) was performed. Finally, the comparison of diagnostic accuracy for fibrotic-foci-like lung adenocarcinoma between ¹⁸F-FDG PET/CT and HRCT was performed. Results: The SUVmax [2.6 (1.7–7.9) vs. 1.0 (0.7–1.4)], TBRmax [2.9 (2.1–9.9) vs. 1.3 (1.2– 1.7)], L/S [2.4 (1.7–3.8) vs. 4.0 (3.2–6.3)], ground-glass opacity (GGO) [13/20 (65.0%) vs. 4/20 (20.0%)], and vessel convergence [7/20 (35.0%) vs. 1/20 (5.0%)] were found to be statistically significant differences between the fibrotic-foci-like lung adenocarcinoma group and the old fibrotic-foci group (P < 0.05). SUVmax [7.9 (4.7–8.8) vs. 1.7 (1.2–2.2)] and TBRmax [9.9 (6.5–11.0) vs. 2.1 (1.6–2.9)] were found to be statistically significant differences between the metastatic group and the non-metastatic group (P < 0.05). ¹⁸F-FDG PET/CT showed the higher diagnostic accuracy for fibrotic-foci-like lung adenocarcinoma than HRCT [95.0% (19/20) vs. 65.0% (13/20), P < 0.05]. Conclusion: The specific characteristics of fibrotic-foci-like lung adenocarcinoma on ¹⁸F-FDG PET/CT and HRCT were high ¹⁸F-FDG uptake, GGO, and vessel convergence, which could be distinguished from old fibrotic-foci of the lung.

Primary intraosseous squamous cell carcinoma is a highly malignant but rare tumor within jaws. We reported the ¹⁸F-FDG PET/CT findings of primary intraosseous squamous cell carcinoma of the mandible in a 42-year-old man. ¹⁸F-FDG PET/CT identified a cystic lesion in the mandible with irregular annular uptake of ¹⁸F-FDG, which has been confirmed as primary intraosseous squamous cell carcinoma pathologically.