The World Health Organization has recently placed new emphasis on the integration of genetic information for gliomas. While tissue sampling remains the criterion standard, noninvasive imaging ...techniques may provide complimentary insight into clinically relevant genetic mutations. Our aim was to train a convolutional neural network to independently predict underlying molecular genetic mutation status in gliomas with high accuracy and identify the most predictive imaging features for each mutation.
MR imaging data and molecular information were retrospectively obtained from The Cancer Imaging Archives for 259 patients with either low- or high-grade gliomas. A convolutional neural network was trained to classify
(
) mutation status, 1p/19q codeletion, and
(
) promotor methylation status. Principal component analysis of the final convolutional neural network layer was used to extract the key imaging features critical for successful classification.
Classification had high accuracy:
mutation status, 94%; 1p/19q codeletion, 92%; and
promotor methylation status, 83%. Each genetic category was also associated with distinctive imaging features such as definition of tumor margins, T1 and FLAIR suppression, extent of edema, extent of necrosis, and textural features.
Our results indicate that for The Cancer Imaging Archives dataset, machine-learning approaches allow classification of individual genetic mutations of both low- and high-grade gliomas. We show that relevant MR imaging features acquired from an added dimensionality-reduction technique demonstrate that neural networks are capable of learning key imaging components without prior feature selection or human-directed training.
Convolutional neural networks are a powerful technology for image recognition. This study evaluates a convolutional neural network optimized for the detection and quantification of intraparenchymal, ...epidural/subdural, and subarachnoid hemorrhages on noncontrast CT.
This study was performed in 2 phases. First, a training cohort of all NCCTs acquired at a single institution between January 1, 2017, and July 31, 2017, was used to develop and cross-validate a custom hybrid 3D/2D mask ROI-based convolutional neural network architecture for hemorrhage evaluation. Second, the trained network was applied prospectively to all NCCTs ordered from the emergency department between February 1, 2018, and February 28, 2018, in an automated inference pipeline. Hemorrhage-detection accuracy, area under the curve, sensitivity, specificity, positive predictive value, and negative predictive value were assessed for full and balanced datasets and were further stratified by hemorrhage type and size. Quantification was assessed by the Dice score coefficient and the Pearson correlation.
A 10,159-examination training cohort (512,598 images; 901/8.1% hemorrhages) and an 862-examination test cohort (23,668 images; 82/12% hemorrhages) were used in this study. Accuracy, area under the curve, sensitivity, specificity, positive predictive value, and negative-predictive value for hemorrhage detection were 0.975, 0.983, 0.971, 0.975, 0.793, and 0.997 on training cohort cross-validation and 0.970, 0.981, 0.951, 0.973, 0.829, and 0.993 for the prospective test set. Dice scores for intraparenchymal hemorrhage, epidural/subdural hemorrhage, and SAH were 0.931, 0.863, and 0.772, respectively.
A customized deep learning tool is accurate in the detection and quantification of hemorrhage on NCCT. Demonstrated high performance on prospective NCCTs ordered from the emergency department suggests the clinical viability of the proposed deep learning tool.
MicroRNAs have emerged as crucial regulators of cardiac homeostasis and remodeling in various cardiovascular diseases. We previously demonstrated that miR-221 regulated cardiac hypertrophy in vitro. ...In the present study, we demonstrated that the cardiac-specific overexpression of miR-221 in mice evoked cardiac dysfunction and heart failure. The lipidated form of microtubule-associated protein 1 light chain 3 was significantly decreased and sequestosome 1 was accumulated in cardiac tissues of transgenic (TG) mice, indicating that autophagy was impaired. Overexpression of miR-221 in vitro reduced autophagic flux through inhibiting autophagic vesicle formation. Furthermore, mammalian target of rapamycin (mTOR) was activated by miR-221, both in vivo and in vitro. The inactivation of mTOR abolished the miR-221-induced inhibition of autophagy and cardiac remodeling. Our previous study has demonstrated that cyclin-dependent kinase (CDK) inhibitor p27 was a direct target of miR-221 in cardiomyocytes. Consistently, the expression of p27 was markedly suppressed in the myocardia of TG mice. Knockdown of p27 by siRNAs was sufficient to mimic the effects of miR-221 overexpression on mTOR activation and autophagy inhibition, whereas overexpression of p27 rescued miR-221-induced autophagic flux impairment. Inhibition of CDK2 restored the impaired autophagic flux and rescued the cardiac remodeling induced by either p27 knockdown or miR-221 overexpression. These findings reveal that miR-221 is an important regulator of autophagy balance and cardiac remodeling by modulating the p27/CDK2/mTOR axis, and implicate miR-221 as a therapeutic target in heart failure.
The discovery of somatic mutations in the isocitrate dehydrogenase (IDH) enzymes through a genome-wide mutational analysis in glioblastoma represents a milestone event in cancer biology. The nature ...of the heterozygous, point mutations mapping to arginine residues involved in the substrate binding inspired several research teams to investigate their impact on the biochemical activity of these enzymes. Soon, it became clear that the mutations identified impaired the ability of IDH1 and IDH2 to catalyze the conversion of isocitrate to α-ketoglutarate (αKG), whereas conferring a gain of a novel enzymatic activity leading to the reduction of αKG to the metabolite D2-hydroxyglutarate (D-2HG). Across glioma as well as several hematologic malignancies, mutations in IDH1 and IDH2 have shown prognostic value. Several hypotheses implicating the elevated levels of D-2HG and tumorigenesis, and the therapeutic potential of targeting mutant IDH enzymes will be discussed.
Objective
To examine the associations between personality traits and suicidal ideation (SI) and attempt (SA) in mood disorder patients and community controls.
Method
We recruited 365 bipolar, 296 ...major depressive disorder patients, and 315 community controls to assess their lifetime suicidality. Participants filled out self‐reported personality questionnaires to collect data of personality traits, including novelty seeking (NS), harm avoidance (HA), extraversion (E), and neuroticism (N). We used logistic regression models adjusted for diagnoses to analyze combinational effects of personality traits on the risk of suicide. Additionally, radar charts display personality profiles for suicidal behaviours by groups.
Results
All personality traits were associated with the risk of suicidality with various effect size, except for E that showed protective effect. High N or HA had prominent and independent risk effects on SI and SA. Combinations of high N and low E, or high HA and NS were the risk personality profiles for suicidality. Higher N scores further distinguished SA from SI in mood disorder patients.
Conclusion
Introvert personality traits showed independent risk effects on suicidality regardless of diagnosis status. Among high‐risk individuals with suicidal thoughts, higher neuroticism tendency is further associated with increased risk of suicide attempt.
A new methodology based on tensor algebra that uses a higher order singular value decomposition to perform three-dimensional voxel reconstruction from a series of temporal images obtained using ...dynamic contrast-enhanced magnetic resonance imaging (DCE-MRI) is proposed. Principal component analysis (PCA) is used to robustly extract the spatial and temporal image features and simultaneously de-noise the datasets. Tumour segmentation on enhanced scaled (ES) images performed using a fuzzy C-means (FCM) cluster algorithm is compared with that achieved using the proposed tensorial framework. The proposed algorithm explores the correlations between spatial and temporal features in the tumours. The multi-channel reconstruction enables improved breast tumour identification through enhanced de-noising and improved intensity consistency. The reconstructed tumours have clear and continuous boundaries; furthermore the reconstruction shows better voxel clustering in tumour regions of interest. A more homogenous intensity distribution is also observed, enabling improved image contrast between tumours and background, especially in places where fatty tissue is imaged. The fidelity of reconstruction is further evaluated on the basis of five new qualitative metrics. Results confirm the superiority of the tensorial approach. The proposed reconstruction metrics should also find future applications in the assessment of other reconstruction algorithms.
Mutations in the metabolic enzymes isocitrate dehydrogenase-1 (IDH1) and IDH2 that produce the oncometabolite D-2-hydroxyglutarate (2-HG) occur frequently in human acute myeloid leukemia (AML). 2-HG ...modulates numerous biological pathways implicated in malignant transformation, but the contribution of mutant IDH proteins to maintenance and progression of AML in vivo is currently unknown. To answer this crucial question we have generated transgenic mice that express IDH2R140Q in an on/off- and tissue-specific manner using a tetracycline-inducible system. We found that IDH2R140Q can cooperate with overexpression of HoxA9 and Meis1a and with mutations in FMS-like tyrosine kinase 3 (FLT3) to drive acute leukemia in vivo. Critically, we show that genetic deinduction of mutant IDH2 in leukemic cells in vivo has profound effects on their growth and/or maintenance. Our data demonstrate the proto-oncogenic role of mutant IDH2 and support its relevance as a therapeutic target for the treatment of human AML.
Display omitted
•Development of a doxycycline-inducible mouse model of IDH2R140Q•IDH2R140Q drives aberrant self-renewal and a block of differentiation in HSPCs•IDH2R140Q cooperates with Flt3ITD to drive acute leukemia in vivo•IDH2R140Q is essential for leukemia maintenance
Kats et al. show that mutant IDH2 drives self-renewal of HSPCs and cooperates with oncogenes FLT3, HoxA9, and Meis1a to drive initiation of leukemia in vivo.
MicroRNAs (miRNAs) are small RNAs that suppress gene expression by their interaction with 3'untranslated region of specific target mRNAs. Although the dysregulation of miRNAs has been identified in ...human cancer, only a few of these miRNAs have been functionally documented in breast cancer. Thus, defining the important miRNA and functional target involved in chemoresistance is an urgent need for human breast cancer treatment. In this study, we, for the first time, identified a key role of miRNA 520h (miR-520h) in drug resistance. Through protecting cells from paclitaxel-induced apoptosis, expression of miR-520h promoted the drug resistance of human breast cancer cells. Bioinformatics prediction, compensatory mutation and functional validation further confirmed the essential role of miR-520h-suppressed Death-associated protein kinase 2 (DAPK2) expression, as restoring DAPK2 abolished miR-520h-promoted drug resistance, and knockdown of DAPK2 mitigated cell death caused by the depletion of miR-520h. Furthermore, we observed that higher level of miR-520h is associated with poor prognosis and lymph node metastasis in human breast cancer patients. These results show that miR-520h is not only an independent prognostic factor, but is also a potential functional target for future applications in cancer therapeutics.
Abstract
We report the detailed transcriptomic profiles of human innate myeloid cells using RNA sequencing. Monocytes migrate from blood into infected or wounded tissue to differentiate into ...macrophages, and control inflammation via phagocytosis or cytokine secretion. We differentiated culture primary monocytes with either GM- or M-CSF to obtain pro- or anti-inflammatory macrophages, and respectively activated them with either LPS/IFNγ or anti-inflammatory cytokines. We also treated the THP-1 monocytic cell line with PMA and similar cytokines to mimic differentiation and activation. We detected thousands of expression and alternative-splicing changes during monocyte-to-macrophage differentiation and activation, and a net increase in exon inclusion. MBNL1 knockdown phenocopies several alternative-splicing changes and strongly impairs PMA differentiation, suggesting functional defects in monocytes from Myotonic Dystrophy patients. This study provides general insights into alternative splicing in the monocyte-macrophage lineage, whose future characterization will elucidate their contribution to immune functions, which are altered in immunodeficiencies, autoimmunity, atherosclerosis and cancer.
Summary
Background
Previous studies have defined transcriptomic subtypes of adult asthma using samples of induced sputum and bronchial epithelium; however, those procedures are not readily applicable ...in the clinic, especially for childhood asthma.
Objective
We aim to dissect the transcriptomic clusters of childhood asthma using highly variably expressed genes of peripheral blood mononuclear cells (PBMC) among patients.
Methods
Gene expression of PBMC from 133 asthmatic children and 11 healthy controls was measured with Illumina microarrays. We applied the k‐means clustering algorithm of 2048 genes to assign asthmatic children into clusters. Genes with differential expression between asthma clusters and healthy controls were used to investigate whether they could identify severe asthma of children and adults.
Results
We identified 3 asthma clusters with distinct inflammatory profiles in peripheral blood. Cluster 1 had the highest eosinophil count. Cluster 2 showed lower counts of both eosinophils and neutrophils. Cluster 3 had the highest neutrophil count and the poorest treatment control. Compared with other patients, Cluster 3 exhibited a unique gene expression pattern which was associated with changes in the glucocorticoid signalling and activation of the T helper 1/T helper 17 (TH1/TH17) immune pathways. In the validation studies, an 84‐gene signature could identify severe asthma in children on leucocytes, as well as severe asthma in adults on CD8+ T cells.
Conclusions and Clinical Relevance
Gene expression profiling of PBMC is useful for the identification of TH1/TH17‐mediated asthma with poor treatment control. PBMC and CD8+ T cells could be important targets for the investigation and identification of severe asthma.