Institutes
Refine
Document Type
- Article (7) (remove)
Language
- English (7)
Has Fulltext
- yes (7)
Is part of the Bibliography
- no (7)
Keywords
- Machine learning (2)
- Prostate cancer (2)
- Artificial intelligence (1)
- Cancer (1)
- Immunology (1)
- K-homology RNA-binding domain (1)
- Multiparametric MRI (1)
- Prediction (1)
- Quantitative features (1)
- Radiomics (1)
- Statistical analysis (1)
- adjuvant chemotherapy (1)
- amyotrophic lateral sclerosis (ALS) (1)
- bladder cancer (1)
- computational pathology (1)
- consensus classification (1)
- deep learning (1)
- double negative (1)
- ensemble cNN (1)
- fragile-X-associated tremor-ataxia syndrome (1)
- fronto-temporal-lobar-dementia (1)
- histology (1)
- immunohistochemistry (1)
- inositol signaling (1)
- long-term potentiation (1)
- molecular diagnostic techniques (1)
- molecular subtyping (1)
- molecular typing (1)
- neurexin (1)
- spatial learning (1)
- stomach neoplasms (1)
- synaptic plasticity (1)
- tauopathies (1)
Institute
Background: Prostate cancer is a major health concern in aging men. Paralleling an aging society, prostate cancer prevalence increases emphasizing the need for efcient diagnostic algorithms.
Methods: Retrospectively, 106 prostate tissue samples from 48 patients (mean age,
66 ± 6.6 years) were included in the study. Patients sufered from prostate cancer (n = 38) or benign prostatic hyperplasia (n = 10) and were treated with radical prostatectomy or Holmium laser enucleation of the prostate, respectively. We constructed tissue microarrays (TMAs) comprising representative malignant (n = 38) and benign (n = 68) tissue cores. TMAs were processed to histological slides, stained, digitized and assessed for the applicability of machine learning strategies and open–source tools in diagnosis of prostate cancer. We applied the software QuPath to extract features for shape, stain intensity, and texture of TMA cores for three stainings, H&E, ERG, and PIN-4. Three machine learning algorithms, neural network (NN), support vector machines (SVM), and random forest (RF), were trained and cross-validated with 100 Monte Carlo random splits into 70% training set and 30% test set. We determined AUC values for single color channels, with and without optimization of hyperparameters by exhaustive grid search. We applied recursive feature elimination to feature sets of multiple color transforms.
Results: Mean AUC was above 0.80. PIN-4 stainings yielded higher AUC than H&E and
ERG. For PIN-4 with the color transform saturation, NN, RF, and SVM revealed AUC of 0.93 ± 0.04, 0.91 ± 0.06, and 0.92 ± 0.05, respectively. Optimization of hyperparameters improved the AUC only slightly by 0.01. For H&E, feature selection resulted in no increase of AUC but to an increase of 0.02–0.06 for ERG and PIN-4.
Conclusions: Automated pipelines may be able to discriminate with high accuracy between malignant and benign tissue. We found PIN-4 staining best suited for classifcation. Further bioinformatic analysis of larger data sets would be crucial to evaluate the reliability of automated classifcation methods for clinical practice and to evaluate potential discrimination of aggressiveness of cancer to pave the way to automatic precision medicine.
The nuclear factor kappa beta (NFκB) signaling pathway plays an important role in liver homeostasis and cancer development. Tax1-binding protein 1 (Tax1BP1) is a regulator of the NFκB signaling pathway, but its role in the liver and hepatocellular carcinoma (HCC) is presently unknown. Here we investigated the role of Tax1BP1 in liver cells and murine models of HCC and liver fibrosis. We applied the diethylnitrosamine (DEN) model of experimental hepatocarcinogenesis in Tax1BP1+/+ and Tax1BP1−/− mice. The amount and subsets of non-parenchymal liver cells in in Tax1BP1+/+ and Tax1BP1−/− mice were determined and activation of NFκB and stress induced signaling pathways were assessed. Differential expression of mRNA and miRNA was determined. Tax1BP1−/− mice showed increased numbers of inflammatory cells in the liver. Furthermore, a sustained activation of the NFκB signaling pathway was found in hepatocytes as well as increased transcription of proinflammatory cytokines in isolated Kupffer cells from Tax1BP1−/− mice. Several differentially expressed mRNAs and miRNAs in livers of Tax1BP1−/− mice were found, which are regulators of inflammation or are involved in cancer development or progression. Furthermore, Tax1BP1−/− mice developed more HCCs than their Tax1BP1+/+ littermates. We conclude that Tax1BP1 protects from liver cancer development by limiting proinflammatory signaling.
Several microRNAs (miRNAs) are associated with the molecular pathogenesis of hepatocellular carcinoma (HCC). However, previous studies analyzing the dysregulation of miRNAs in HCC show heterogeneous results. We hypothesized that part of this heterogeneity might be attributable to variations of miRNA expression deriving from the HCC capsule or the fibrotic septa within the peritumoral tissue used as controls. Tissue from surgically resected hepatitis C–associated HCC from six well-matched patients was microdissected using laser microdissection and pressure catapulting technique. Four distinct histologic compartments were isolated: tumor parenchyma (TP), fibrous capsule of the tumor (TC), tumor-adjacent liver parenchyma (LP), and cirrhotic septa of the tumor-adjacent liver (LC). MiRNA expression profiling analysis of 1105 mature miRNAs and precursors was performed using miRNA microarray. Principal component analysis and consecutive pairwise supervised comparisons demonstrated distinct patterns of expressed miRNAs not only for TP versus LP (e.g., intratumoral down-regulation of miR-214, miR-199a, miR-146a, and miR-125a; P< .05) but also for TC versus LC (including down-regulation within TC of miR-126, miR-99a/100, miR-26a, and miR-125b; P< .05). The tumor capsule therefore demonstrates a tumor-like phenotype with down-regulation of well-known tumor-suppressive miRNAs. Variations of co-analyzed fibrotic tissue within the tumor or in controls may have profound influence on miRNA expression analyses in HCC. Several miRNAs, which are proposed to be HCC specific, may indeed be rather associated to the tumor capsule. As miRNAs evolve to be important biomarkers in liver tumors, the presented data have important translational implications on diagnostics and treatment in patients with HCC.
Introduction and Objective: Identifying patients that benefit from cisplatin-based adjuvant chemotherapy is a major issue in the management of muscle-invasive bladder cancer (MIBC). The purpose of this study is to correlate “luminal” and “basal” type protein expression with histological subtypes, to investigate the prognostic impact on survival after adjuvant chemotherapy and to define molecular consensus subtypes of “double negative” patients (i.e., without expression of CK5/6 or GATA3).
Materials and Methods: We performed immunohistochemical (IHC) analysis of CK5/6 and GATA3 for surrogate molecular subtyping in 181 MIBC samples. The mRNA expression profiles for molecular consensus classification were determined in CK5/6 and GATA3 (double) negative cases using a transcriptome panel with 19.398 mRNA targets (HTG Molecular Diagnostics). Data of 110 patients undergoing radical cystectomy were available for survival analysis.
Results: The expression of CK5/6 correlated with squamous histological subtype (96%) and expression of GATA3 was associated with micropapillary histology (100%). In the multivariate Cox-regression model, patients receiving adjuvant chemotherapy had a significant survival benefit (hazard ratio [HR]: 0.19 95% confidence interval [CI]: 0.1–0.4, p < 0.001) and double-negative cases had decreased OS (HR: 4.07; 95% CI: 1.5–10.9, p = 0.005). Double negative cases were classified as NE-like (30%), stroma-rich (30%), and Ba/Sq (40%) consensus molecular subtypes and displaying different histological subtypes.
In gastric cancer (GC), there are four molecular subclasses that indicate whether patients respond to chemotherapy or immunotherapy, according to the TCGA. In clinical practice, however, not every patient undergoes molecular testing. Many laboratories have used well-implemented in situ techniques (IHC and EBER-ISH) to determine the subclasses in their cohorts. Although multiple stains are used, we show that a staining approach is unable to correctly discriminate all subclasses. As an alternative, we trained an ensemble convolutional neuronal network using bagging that can predict the molecular subclass directly from hematoxylin–eosin histology. We also identified patients with predicted intra-tumoral heterogeneity or with features from multiple subclasses, which challenges the postulated TCGA-based decision tree for GC subtyping. In the future, deep learning may enable targeted testing for molecular subtypes and targeted therapy for a broader group of GC patients. © 2022 The Authors. The Journal of Pathology published by John Wiley & Sons Ltd on behalf of The Pathological Society of Great Britain and Ireland.
Objectives: To analyze the performance of radiological assessment categories and quantitative computational analysis of apparent diffusion coefficient (ADC) maps using variant machine learning algorithms to differentiate clinically significant versus insignificant prostate cancer (PCa). Methods: Retrospectively, 73 patients were included in the study. The patients (mean age, 66.3 ± 7.6 years) were examined with multiparametric MRI (mpMRI) prior to radical prostatectomy (n = 33) or targeted biopsy (n = 40). The index lesion was annotated in MRI ADC and the equivalent histologic slides according to the highest Gleason Grade Group (GrG). Volumes of interest (VOIs) were determined for each lesion and normal-appearing peripheral zone. VOIs were processed by radiomic analysis. For the classification of lesions according to their clinical significance (GrG ≥ 3), principal component (PC) analysis, univariate analysis (UA) with consecutive support vector machines, neural networks, and random forest analysis were performed. Results: PC analysis discriminated between benign and malignant prostate tissue. PC evaluation yielded no stratification of PCa lesions according to their clinical significance, but UA revealed differences in clinical assessment categories and radiomic features. We trained three classification models with fifteen feature subsets. We identified a subset of shape features which improved the diagnostic accuracy of the clinical assessment categories (maximum increase in diagnostic accuracy ΔAUC = + 0.05, p < 0.001) while also identifying combinations of features and models which reduced overall accuracy. Conclusions: The impact of radiomic features to differentiate PCa lesions according to their clinical significance remains controversial. It depends on feature selection and the employed machine learning algorithms. It can result in improvement or reduction of diagnostic performance.
Spinocerebellar ataxia type 2 (SCA2) is caused by polyglutamine expansion in Ataxin-2 (ATXN2). This factor binds RNA/proteins to modify metabolism after stress, and to control calcium (Ca2+) homeostasis after stimuli. Cerebellar ataxias and corticospinal motor neuron degeneration are determined by gain/loss in ATXN2 function, so we aimed to identify key molecules in this atrophic process, as potential disease progression markers. Our Atxn2-CAG100-Knock-In mouse faithfully models features observed in patients at pre-onset, early and terminal stages. Here, its cerebellar global RNA profiling revealed downregulation of signaling cascades to precede motor deficits. Validation work at mRNA/protein level defined alterations that were independent of constant physiological ATXN2 functions, but specific for RNA/aggregation toxicity, and progressive across the short lifespan. The earliest changes were detected at three months among Ca2+ channels/transporters (Itpr1, Ryr3, Atp2a2, Atp2a3, Trpc3), IP3 metabolism (Plcg1, Inpp5a, Itpka), and Ca2+-Calmodulin dependent kinases (Camk2a, Camk4). CaMKIV–Sam68 control over alternative splicing of Nrxn1, an adhesion component of glutamatergic synapses between granule and Purkinje neurons, was found to be affected. Systematic screening of pre/post-synapse components, with dendrite morphology assessment, suggested early impairment of CamKIIα abundance together with the weakening of parallel fiber connectivity. These data reveal molecular changes due to ATXN2 pathology, primarily impacting excitability and communication.