s2MRI-ADNet: an interpretable deep learning framework integrating Euclidean-graph representations of Alzheimer's disease solely from structural MRI.

OBJECTIVE: To establish a multi-dimensional representation solely on structural MRI (sMRI) for early diagnosis of AD. METHODS: A total of 3377 participants' sMRI from four independent databases were retrospectively identified to construct an interpretable deep learning model that integrated multi-dimensional representations of AD solely on sMRI (called s2MRI-ADNet) by a dual-channel learning strategy of gray matter volume (GMV) from Euclidean space and the regional radiomics similarity network (R2SN) from graph space. Specifically, the GMV feature map learning channel (called GMV-Channel) was to take into consideration spatial information of both long-range spatial relations and detailed localization information, while the node feature and connectivity strength learning channel (called NFCS-Channel) was to characterize the graph-structured R2SN network by a separable learning strategy. RESULTS: The s2MRI-ADNet achieved a superior classification accuracy of 92.1% and 91.4% under intra-database and inter-database cross-validation. The GMV-Channel and NFCS-Channel captured complementary group-discriminative brain regions, revealing a complementary interpretation of the multi-dimensional representation of brain structure in Euclidean and graph spaces respectively. Besides, the generalizable and reproducible interpretation of the multi-dimensional representation in capturing complementary group-discriminative brain regions revealed a significant correlation between the four independent databases (p < 0.05). Significant associations (p < 0.05) between attention scores and brain abnormality, between classification scores and clinical measure of cognitive ability, CSF biomarker, metabolism, and genetic risk score also provided solid neurobiological interpretation. CONCLUSION: The s2MRI-ADNet solely on sMRI could leverage the complementary multi-dimensional representations of AD in Euclidean and graph spaces, and achieved superior performance in the early diagnosis of AD, facilitating its potential in both clinical translation and popularization.

Jointly constrained group sparse connectivity representation improves early diagnosis of Alzheimer's disease on routinely acquired T1-weighted imaging-based brain network.

Background: Radiomics-based morphological brain networks (radMBN) constructed from routinely acquired structural MRI (sMRI) data have gained attention in Alzheimer's disease (AD). However, the radMBN suffers from limited characterization of AD because sMRI only characterizes anatomical changes and is not a direct measure of neuronal pathology or brain activity. Purpose: To establish a group sparse representation of the radMBN under a joint constraint of group-level white matter fiber connectivity and individual-level sMRI regional similarity (JCGS-radMBN). Methods: Two publicly available datasets were adopted, including 120 subjects from ADNI with both T1-weighted image (T1WI) and diffusion MRI (dMRI) for JCGS-radMBN construction, 818 subjects from ADNI and 200 subjects solely with T1WI from AIBL for validation in early AD diagnosis. Specifically, the JCGS-radMBN was conducted by jointly estimating non-zero connections among subjects, with the regularization term constrained by group-level white matter fiber connectivity and individual-level sMRI regional similarity. Then, a triplet graph convolutional network was adopted for early AD diagnosis. The discriminative brain connections were identified using a two-sample t-test, and the neurobiological interpretation was validated by correlating the discriminative brain connections with cognitive scores. Results: The JCGS-radMBN exhibited superior classification performance over five brain network construction methods. For the typical NC vs. AD classification, the JCGS-radMBN increased by 1-30% in accuracy over the alternatives on ADNI and AIBL. The discriminative brain connections exhibited a strong connectivity to hippocampus, parahippocampal gyrus, and basal ganglia, and had significant correlation with MMSE scores. Conclusion: The proposed JCGS-radMBN facilitated the AD characterization of brain network established on routinely acquired imaging modality of sMRI. Supplementary Information: The online version of this article (10.1007/s13755-023-00269-0) contains supplementary material, which is available to authorized users.

HGM-cNet: Integrating hippocampal gray matter probability map into a cascaded deep learning framework improves hippocampus segmentation.

A robust cascaded deep learning framework with integrated hippocampal gray matter (HGM) probability map was developed to improve the hippocampus segmentation (called HGM-cNet) due to its significance in various neuropsychiatric disorders such as Alzheimer's disease (AD). Particularly, the HGM-cNet cascaded two identical convolutional neural networks (CNN), where each CNN was devised by incorporating Attention Block, Residual Block, and DropBlock into the typical encoder-decoder architecture. The two CNNs were skip-connected between encoder components at each scale. The adoption of the cascaded deep learning framework was to conveniently incorporate the HGM probability map with the feature map generated by the first CNN. Experiments on 135T1-weighted MRI scans and manual hippocampal labels from publicly available ADNI-HarP dataset demonstrated that the proposed HGM-cNet outperformed seven multi-atlas-based hippocampus segmentation methods and six deep learning methods under comparison in most evaluation metrics. The Dice (average > 0.89 for both left and right hippocampus) was increased by around or more than 1% over other methods. The HGM-cNet also achieved a superior hippocampus segmentation performance in each group of cognitive normal, mild cognitive impairment, and AD. The stability, conveniences and generalizability of the cascaded deep learning framework with integrated HGM probability map in improving hippocampus segmentation was validated by replacing the proposed CNN with 3D-UNet, Atten-UNet, HippoDeep, QuickNet, DeepHarp, and TransBTS models. The integration of the HGM probability map in the cascaded deep learning framework was also demonstrated to facilitate capturing hippocampal atrophy more accurately than alternative methods in AD analysis. The codes are publicly available at https://github.com/Liu1436510768/HGM-cNet.git.

How segmentation methods affect hippocampal radiomic feature accuracy in Alzheimer's disease analysis?

OBJECTIVES: Hippocampal radiomic features (HRFs) can serve as biomarkers in Alzheimer's disease (AD). However, how different hippocampal segmentation methods affect HRFs in AD is still unknown. The aim of the study was to investigate how different segmentation methods affect HRF accuracy in AD analysis. METHODS: A total of 1650 subjects were identified from the Alzheimer's Disease Neuroimaging Initiative database (ADNI). The mini-mental state examination (MMSE) and Alzheimer's disease assessment scale (ADAS-cog13) were also adopted. After calculating the HRFs of intensity, shape, and textural features from each side of the hippocampus in structural magnetic resonance imaging (sMRI), the consistency of HRFs calculated from 7 different hippocampal segmentation methods was validated, and the performance of machine learning-based classification of AD vs. normal control (NC) adopting the different HRFs was also examined. Additional 571 subjects from the European DTI Study on Dementia database (EDSD) were to validate the consistency of results. RESULTS: Between different segmentations, HRFs showed a high measurement consistency (R > 0.7), a high significant consistency between NC, mild cognitive impairment (MCI), and AD (T-value plot, R > 0.8), and consistent significant correlations between HRFs and MMSE/ADAS-cog13 (p < 0.05). The best NC vs. AD classification was obtained when the hippocampus was sufficiently segmented by primitive majority voting (threshold = 0.2). High consistent results were reproduced from independent EDSD cohort. CONCLUSIONS: HRFs exhibited high consistency across different hippocampal segmentation methods, and the best performance in AD classification was obtained when HRFs were extracted by the naïve majority voting method with a more sufficient segmentation and relatively low hippocampus segmentation accuracy. KEY POINTS: • The hippocampal radiomic features exhibited high measurement/statistical/clinical consistency across different hippocampal segmentation methods. • The best performance in AD classification was obtained when hippocampal radiomics were extracted by the naïve majority voting method with a more sufficient segmentation and relatively low hippocampus segmentation accuracy.

The regional neuronal activity in left posterior middle temporal gyrus is correlated with the severity of chronic aphasia.

BACKGROUND: Aphasia is one of the most disabling cognitive deficits affecting >2 million people in the USA. The neuroimaging characteristics of chronic aphasic patients (>6 months post onset) remain largely unknown. OBJECTIVE: The objective of this study was to investigate the regional signal changes of spontaneous neuronal activity of brain and the inter-regional connectivity in chronic aphasia. MATERIALS AND METHODS: Resting-state blood oxygenation level-dependent functional magnetic resonance imaging (fMRI) was used to obtain fMRI data from 17 chronic aphasic patients and 20 healthy control subjects in a Siemens Verio 3.0T MR Scanner. The amplitude of low-frequency fluctuation (ALFF) was determined, which directly reflects the regional neuronal activity. The functional connectivity (FC) of fMRI was assessed using a seed voxel linear correlation approach. The severity of aphasia was evaluated by aphasia quotient (AQ) scores obtained from Western Aphasia Battery test. RESULTS: Compared with normal subjects, aphasic patients showed decreased ALFF values in the regions of left posterior middle temporal gyrus (PMTG), left medial prefrontal gyrus, and right cerebellum. The ALFF values in left PMTG showed strong positive correlation with the AQ score (coefficient r=0.79, P<0.05). There was a positive FC in chronic aphasia between left PMTG and left inferior temporal gyrus (BA20), fusiform gyrus (BA37), and inferior frontal gyrus (BA47\45\44). CONCLUSION: Left PMTG might play an important role in language dysfunction of chronic aphasia, and ALFF value might be a promising indicator to evaluate the severity of aphasia.

O-GlcNAcylation enhances anaplastic thyroid carcinoma malignancy.

O-linked N-acetylglucosamine (O-GlcNAc) glycosylation (O-GlcNAcylation), a dynamic post-translational modification of nuclear and cytoplasmic proteins, may have a critical role in the regulation of biological cell processes and human cancer. O-GlcNAcylation is dynamically regulated by O-GlcNAc transferase (OGT) and O-GlcNAc hydrolase (OGA). Accumulating evidence suggests that O-GlcNAcylation is involved in a variety of types of human cancer. However, the exact role of O-GlcNAcylation in tumor pathogenesis or progression remains to be established. Computed tomography scans of patients with anaplastic thyroid carcinoma (ATC) reveal a rapid growth rate and invasion. The present study demonstrated that O-GlcNAcylation accelerates the progression of ATC. The global O-GlcNAc level of intracellular proteins was increased by overexpression of OGT or downregulation of OGA activity with the specific inhibitor Thiamet-G. By contrast, the global O-GlcNAc level was decreased by silencing of OGT. MTT assay indicated that O-GlcNAcylation significantly promotes cell proliferation. Furthermore, O-GlcNAcylation enhanced cellular biological functions, such as colony formation ability, migration and invasion, of ATC cells in vitro. The findings of the present study suggest that O-GlcNAcylation is associated with malignant properties of thyroid cancer, and may be a potential target for the diagnosis and treatment of thyroid cancer.

Clinicopathologic Implications of Eukaryotic Initiation Factor 3f and Her-2/neu Expression in Gastric Cancer.

BACKGROUND: To detect the expression of eIF3f and human epidermal growth factor receptor 2 (Her-2)/neu in gastric cancer (GC), correlation with their clinicopathological parameters and the relationship of eIF3f and Her-2/neu in the occurrence and development of GC. METHODS: A total of 195 gastrectomy specimens with stage I to III were examined for eIF3f expression by immunohistochemistry and for Her-2/neu expression by fluorescence in situ hybridization (FISH) with the median follow-up period of 38 months. RESULTS: The positive expression rate of eIF3f in GC and adjacent noncancerous tissue were 33.8% and 59.5%, respectively. eIF3f levels were linked to more advanced tumor stages and likelihood of recurrence (all p < 0.05). The Kaplan-Meier survival curves indicated that decreased expression of eIF3f could serve as a prognosis marker for poor outcome of GC patients (p = 0.04). 15.9% of GC specimens were positive for Her-2/neu, but whose expression was of no correlation with patients' survival. Patients who were positive for Her-2/neu also had high eIF3f expression levels (p = 0.0295). CONCLUSION: Results suggest that eIF3f may play an important role in recurrence, thus representing a promising predictive marker for the prognosis of GC. But Her-2/neu has no relationship with the prognosis of GC. The clinical significance of eIF3f and Her-2/neu remains to be further investigated.

Expression of eukaryotic initiation factor 3f is associated with prognosis in gastric carcinomas.

BACKGROUND: Eukaryotic initiation factor 3f (eIF3f) expression, which plays an important role in human cancer, is significantly decreased in various types of cancers. The aim of this study was to detect the expression of eIF3f in gastric carcinoma (GC), which until now has not been reported. METHODS: Expression of eIF3f was detected by immunohistochemistry in GC tissues and adjacent non-cancerous tissues (ANCT) from 195 patients with stage I-III GC who underwent curative gastrectomy. Clinicopathological results, including survival, were analyzed. RESULTS: Expression rate of eIF3f in GC and ANCT were 44.8 and 81.7% respectively. Low expression of eIF3f was significantly associated with an increased serum level of carcinoma embryonic antigen (p = 0.02), but not with levels of carbohydrate antigen 19-9 (p = 0.29). eIF3f levels were linked to more advanced tumor stages and likelihood of recurrence (all p < 0.05).The Kaplan-Meier survival curves indicated that decreased expression of eIF3f was a significant factor for a poor prognosis for GC patients (p = 0.04). CONCLUSION: eIF3f may play an important role in recurrence. Its function and potential as a prognostic marker should be further verified in GC.