18 F-FDG PET / CT is used clinically for the detection of extramedullary lesions in patients with relapsed acute leukemia (AL). However, the visual analysis of 18 F-FDG diffuse bone marrow uptake in detecting bone marrow involvement (BMI) in routine clinical practice is still challenging. This study aims to improve the diagnostic performance of 18 F-FDG PET/CT in detecting BMI for patients with suspected relapsed AL. Methods : Forty-one patients (35 in training group and 6 in independent validation group) with suspected relapsed AL were retrospectively included in this study. All patients underwent both bone marrow biopsy (BMB) and 18 F-FDG PET/CT within one week. The BMB results were used as the gold standard or real “truth” for BMI. The bone marrow 18 F-FDG uptake was visually diagnosed as positive and negative by three nuclear medicine physicians. The skeletal volumes of interest were manually drawn on PET/CT images. A total of 781 PET and 1045 CT radiomic features were automatically extracted to provide a more comprehensive understanding of the embedded pattern. To select the most important and predictive features, an unsupervised consensus clustering method was first performed to analyze the feature correlations and then used to guide a random forest supervised machine learning model for feature importance analysis. Cross-validation and independent validation were conducted to justify the performance of our model. Results : The training group involved 16 BMB positive and 19 BMB negative patients. Based on the visual analysis of 18 F-FDG PET, 3 patients had focal uptake, 8 patients had normal uptake, and 24 patients had diffuse uptake. The sensitivity, specificity, and accuracy of visual analysis for BMI diagnosis were 62.5%, 73.7%, and 68.6%, respectively. With the cross-validation on the training group, the machine learning model correctly predicted 31 patients in BMI. The sensitivity, specificity, and accuracy of the machine learning model in BMI detection were 87.5%, 89.5%, and 88.6%, respectively, significantly higher than the ones in visual analysis ( P < 0.05). The evaluation on the independent validation group showed that the machine learning model could achieve 83.3% accuracy. Conclusions: 18 F-FDG PET/CT radiomic analysis with machine learning model provided a quantitative, objective and efficient mechanism for identifying BMI in the patients with suspected relapsed AL. It is suggested in particular for the diagnosis of BMI in the patients with 18 F-FDG diffuse uptake patterns.

No abstract

Recent studies in cognitively unimpaired elderly individuals suggest that the APOE ε4 allele exerts a dosage-dependent effect on brain tau deposition. The aim of this study was to investigate sex differences in APOE ε4 gene dosage effects on brain tau deposition in cognitively impaired individuals using quantitative 18F-flortaucipir PET. Preprocessed 18F-flortaucipir tau PET images, T1-weighted structural MRI images, demographic information, global cortical amyloid-β burden measured by 18F-florbetapir PET, CSF total tau and phosphorylated tau measurements were obtained from the Alzheimer’s Disease Neuroimaging Initiative database. Two hundred and sixty-eight cognitively impaired individuals with 146 APOE ε4 non-carriers and 122 carriers (85 heterozygotes and 37 homozygotes) were included in the study. An iterative reblurred Van Cittert iteration partial volume correction method was applied to all downloaded PET images. MRI images were used for PET spatial normalization. Twelve regional standardized uptake value ratios relative to the cerebellum were computed in standard space. APOE ε4 dosage by sex interaction effect on 18F-flortaucipir standardized uptake value ratios was assessed using generalized linear models and sex-stratified analysis. We observed a significant APOE ε4 dosage by sex interaction effect on tau deposition in the lateral temporal, posterior cingulate, medial temporal, inferior temporal, entorhinal cortex, amygdala, parahippocampal gyrus regions after adjusting for age and education level (P &lt; 0.05). The medial temporal, entorhinal cortex, amygdala and parahippocampal gyrus regions retained a significant APOE ε4 dosage by sex interaction effect on tau deposition after adjusting for global cortical amyloid-β (P &lt; 0.05). In sex-stratified analysis, there was no significant difference in tau deposition between female homozygotes and heterozygotes (P &gt; 0.05). In contrast, male homozygotes standardized uptake value ratios were significantly greater than heterozygotes or non-carriers throughout all twelve regions of interest (P &lt; 0.05). Female heterozygotes exhibited significantly increased tau deposition compared to male heterozygotes in the orbitofrontal, posterior cingulate, lateral temporal, inferior temporal, entorhinal cortex, amygdala and parahippocampal gyrus (P &lt; 0.05). Results from voxelwise analysis were similar to the ones obtained from regions of interest analysis. Our findings suggest that an APOE ε4 dosage effect on brain region-specific tau deposition exists in males, but not females. These results have important clinical implications towards developing sex and genotype-guided therapeutics in Alzheimer’s disease and uncovers a potential explanation underlying differential apolipoprotein E ε4-associated Alzheimer’s risk in males and females.

Purpose The objective of this study is to investigate the hippocampal neurodegeneration and its associated aberrant functions in mild cognitive impairment (MCI) and Alzheimer's disease (AD) patients using simultaneous PET/MRI. Methods Forty-two cognitively normal controls (NC), 38 MCI, and 22 AD patients were enrolled in this study. All subjects underwent 18 F-FDG PET/functional MRI (fMRI) and high-resolution T1-weighted MRI scans on a hybrid GE Signa PET/ MRI scanner. Neurodegeneration in hippocampus and its subregions was quantified by regional gray matter volume and 18 F-FDG standardized uptake value ratio (SUVR) relative to cerebellum. An iterative reblurred Van Cittert iteration method was used for voxelwise partial volume correction on 18 F-FDG PET images. Regional gray matter volume was estimated from voxel-based morphometric analysis with MRI. fMRI data were analyzed after slice time correction and head motion correction using statistical parametric mapping (SPM12) with DPARSF toolbox. The regions of interest including hippocampus, cornu ammonis (CA1), CA2/3/dentate gyrus (DG), and subiculum were defined in the standard MNI space. Results Patient groups had reduced SUVR, gray matter volume, and functional connectivity compared to NC in CA1, CA2/3/ DG, and subiculum (AD < MCI < NC). There was a linear correlation between the left CA2/3DG gray matter volume and 18 F-FDG SUVR in AD patients (P < 0.001, r = 0.737). Significant correlation was also found between left CA2/3/DG-superior medial frontal gyrus functional connectivity and left CA2/3/DG hypometabolism in patients with AD. The functional connectivity of right CA1-precuneus in patients with MCI and right subiculum-superior frontal gyrus in patients with AD was positively correlated with mini mental status examination scores (P < 0.05). Conclusion Our findings demonstrate that the associations existed at subregional hippocampal level between the functional connectivity measured by fMRI and neurodegeneration measured by structural MRI and 18 F-FDG PET. Our results may provide a basis for precision neuroimaging of hippocampus in AD.

No abstract

Clustering is increasingly important for multiview data analytics and current algorithms are either based on the collaborative learning of local partitions or directly derived global clustering from multi-kernel learning. In this paper, we innovate a clustering model that unifies the local partitions and global clustering in a collaborative learning framework. We firstly construct a common multi-kernel space (CMKS) from a set of basis kernels to better reflect clustering information of each individual view. Then, considering that joint local partitions would conform to the global clustering, we fuse the local partitions and global clustering guidance as a single objective function in accordance with fuzzy clustering form. The collaborative learning strategy enables the mutual and interactive clustering from local partitions and global clustering. The validation was performed over two synthetic and four public databases and the clustering accuracy was measured by NMI and RI. The experimental results demonstrated that the proposed algorithm outperformed the related state-of-the-art algorithms in comparison which included multitask, multi-kernel and multiview clustering approaches.

The study deals with the spatio-temporal distribution of heavy metals in the sediments of Chagan lake, Northeast China. The pollution history of heavy metals is studied simultaneously through the 210Pb dating method by analyzing the characteristic of As, Hg, Cd, Cr, Ni, Cu, Pb, and Zn concentration-depth profiles. The potential ecological risk index (RI) and geo-accumulation index (Igeo) were used to evaluate the contamination degree. Principal component analysis (PCA), based on the logarithmic transformation and isometric log-ratio (ilr) transformed data, was applied with the aim of identifying the sources of heavy metals. The element concentrations show that the heavy metals are enriched in the surface sediment and sediment core with a varying degree, which is higher in the surficial residue. The results of Igeo indicate that the Cd and Hg in the surface sediment have reached a slightly contaminated level while other elements, uncontaminated. The results of RI show that the study area can be classified as an area with moderate ecological risk in which Cd and Hg mostly contribute to the overall risk. For the sediment core, the 210Pb dating results accurately reflect the sedimentary history over 153 years. From two evaluation indices (RI and Igeo) calculated by element concentration, there is no contamination, and the potential ecological risk is low during this period. The comparative study between raw and ilr transformed data shows that the closure effect of the raw data can be eliminated by ilr transformation. After that, the components obtained by robust principal component analysis (RPCA) are more representative than those obtained by PCA, both based on ilr transformed dataset, after eliminating the influence of outliers. Based on ilr transformed data with RPCA, three primary sources could be inferred: Cr, Ni, As, Zn, and Cu are mainly derived from natural sources; the main source of Cd and Hg are associated with agricultural activities and energy development; as for Pb, it originated from traffic and coal-burning activities, which is consistent with the fact that the development of tourism, fishery, and agriculture industries has led to the continuous increasing levels of anthropogenic Pb in Chagan Lake. The summarized results and conclusions will undoubtedly enhance the governmental awareness of heavy metal pollution and facilitate appropriate pollution control measures in Chagan Lake.

No abstract