Refine
Year of publication
Document Type
- Article (22)
- Doctoral Thesis (1)
- Preprint (1)
Has Fulltext
- yes (24)
Is part of the Bibliography
- no (24)
Keywords
- Hodgkin lymphoma (2)
- Machine learning (2)
- Prostate cancer (2)
- classical Hodgkin lymphoma (2)
- gene expression (2)
- Affymetrix (1)
- Artificial intelligence (1)
- B-cell immunology (1)
- B-cell lymphoma (1)
- BATF3 (1)
Institute
Background: Protective effects of vitamin D have been reported in autoimmune and malignant thyroid diseases, though little is known about the underlying mechanism. Sirtuin 1 histon deacethylase (SIRT1) links the vitamin D pathway with regulation of transcription factor FOXO3a, a key player in cell cycle regulation and apoptosis. Aim of the present study was to investigate common single nucleotide polymorphisms (SNP's) in FOXO3a gene in respect to thyroid diseases, as well as to evaluate the hypothesis of Sirtuin1-FOXO3a interaction being a mediator of anti-proliferative vitamin D effects.
Methods: The SNP's FOXO3a rs4946936/rs4945816/rs9400239 were genotyped in 257 patients with differentiated thyroid carcinoma (DTC), 139 patients with Hashimoto thyroiditis (HT) and 463 healthy controls (HC). Moreover, T-helper cells of HC and papillary thyroid cancer cell line BCPAP were incubated with 1,25(OH)2D3 and/or SIRT1 inhibitor Ex-527 in order to elucidate SIRT1- dependent vitamin D effects on cell proliferation and FOXO3a gene expression in vitro.
Results: Patients with DTC tended to carry more often allele C in FOXO3a rs4946936 in comparison to HC (pcorrected = pc = 0.08). FOXO3a rs9400239T and rs4945816C was more frequent in HT in comparison to HC (pc = 0.02 and pc = 0.01, respectively). In both DTC and HT, we could not find a correlation of FOXO3a SNP's with vitamin D status. However, on in vitro level, 1,25(OH)2D3 showed an anti-proliferative effect in both T-helper cells and BCPAP, that was blocked by SIRT1 inhibition (T-helper cells: p = 0.0059, BCPAP: p = 0.04) and accompanied by elevated FOXO3a gene expression in T-helper cells (p = 0.05).
Conclusions: FOXO3a rs9400239T and rs4945816C may constitute risk factors for HT, independent of the vitamin D status.This indicates the implication of FOXO3a in pathogenesis of autoimmune thyroid diseases. The dependency of anti-proliferative vitamin D effects on SIRT1 activity further suggests a key role of vitamin D-SIRT1-FOXO3a axis for protective vitamin D effects.
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.
Bioinformatics analysis quantifies neighborhood preferences of cancer cells in Hodgkin lymphoma
(2017)
Motivation Hodgkin lymphoma is a tumor of the lymphatic system and represents one of the most frequent lymphoma in the Western world. It is characterized by Hodgkin cells and Reed-Sternberg cells, which exhibit a broad morphological spectrum. The cells are visualized by immunohistochemical staining of tissue sections. In pathology, tissue images are mainly manually evaluated, relying on the expertise and experience of pathologists. Computational quantification methods become more and more essential to evaluate tissue images. In particular, the distribution of cancer cells is of great interest.
Results Here, we systematically quantified and investigated cancer cell properties and their spatial neighborhood relations by applying statistical analyses to whole slide images of Hodgkin lymphoma and lymphadenitis, which describes a non-cancerous inflammation of the lymph node. We differentiated cells by their morphology and studied the spatial neighborhood relation of more than 400,000 immunohistochemically stained cells. We found that, according to their morphological features, the cells exhibited significant preferences for and aversions to cells of specific profiles as nearest neighbor. We quantified differences between Hodgkin lymphoma and lymphadenitis concerning the neighborhood relations of cells and the sizes of cells. The approach can easily be applied to other cancer types.
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.