Search

Purpose To evaluate the value of convolutional neural network (CNN) in the diagnosis of human brain tumor or Alzheimer’s disease by MR spectroscopic imaging (MRSI) and to compare its Matthews correlation coefficient (MCC) score against that of other machine learning methods and previous evaluation of the same data. We address two challenges: 1) limited number of cases in MRSI datasets and 2) interpretability of results in the form of relevant spectral regions. Methods A shallow CNN with only one hidden layer and an ad-hoc loss function was constructed involving two branches for processing spectral and image features of a brain voxel respectively. Each branch consists of a single convolutional hidden layer. The output of the two convolutional layers is merged and fed to a classification layer that outputs class predictions for the given brain voxel. Results Our CNN method separated glioma grades 3 and 4 and identified Alzheimer’s disease patients using MRSI and complementary MRI data with high MCC score (Area Under the Curve were 0.87 and 0.91 respectively). The results demonstrated superior effectiveness over other popular methods as Partial Least Squares or Support Vector Machines. Also, our method automatically identified the spectral regions most important in the diagnosis process and we show that these are in good agreement with existing biomarkers from the literature. Conclusion Shallow CNNs models integrating image and spectral features improved quantitative and exploration and diagnosis of brain diseases for research and clinical purposes. Software is available at https://bitbucket.org/TeslaH2O/cnn_mrsi.

Contains fulltext : 155092.PDF (Publisher’s version ) (Open Access) PURPOSE: To determine the frequency and prognostic value of elevated microsatellite alterations at selected tetranucleotide repeats (EMAST) in metastatic colorectal cancer (mCRC) patients in relation to microsatellite instability (MSI) status and MSH3 protein expression. MATERIAL AND METHODS: The frequency of EMAST was evaluated in mCRC patients with MSI tumors and microsatellite stable (MSS) tumors. A literature overview was performed to compare the frequency of EMAST in our study with existing data. Immunohistochemistry for MSH3 was compared with EMAST status. Outcome was studied in terms of overall survival (OS) of mCRC patients with MSI and MSS tumors. RESULTS: EMAST was evaluated in 89 patients with MSI tumors (including 39 patients with Lynch syndrome) and 94 patients with MSS tumors. EMAST was observed in 45.9% (84 out of 183) of patients, with an increased frequency in MSI tumors (79.8% versus 13.8%, p < 0.001). We found no correlation between EMAST and MSH3 protein expression. There was no effect of EMAST on prognosis in patients with MSS tumors, but patients with MSI / non-EMAST tumors had a significantly better prognosis than patients with MSI / EMAST tumors (OS: HR 3.22, 95% CI 1.25-8.30). CONCLUSION: Frequency of EMAST was increased in mCRC patients with MSI tumors, compared to MSS tumors. Our data suggest that the presence of EMAST correlates with worse OS in these patients. There was no effect of EMAST on the prognosis of patients with MSS tumors. A limitation of our study is the small number of patients in our subgroup analysis.

Contains fulltext : 135873.pdf (Publisher’s version ) (Open Access) Lyophilisomes are a novel class of biodegradable proteinaceous nano/micrometer capsules with potential use as drug delivery carrier. Cell-penetrating peptides (CPPs) including the TAT peptide have been successfully implemented for intracellular delivery of a broad variety of cargos including various nanoparticulate pharmaceutical carriers. In the present study, lyophilisomes were modified using CPPs in order to achieve enhanced cellular uptake. Lyophilisomes were prepared by a freezing, annealing, and lyophilization method and a cystein-elongated TAT peptide was conjugated to the lyophilisomes using a heterobifunctional linker. Fluorescent-activated cell sorting (FACS) was utilized to acquire a lyophilisome population with a particle diameter smaller than 1000 nm. Cultured HeLa, OVCAR-3, Caco-2 and SKOV-3 cells were exposed to unmodified lyophilisomes and TAT-conjugated lyophilisomes and examined with FACS. HeLa cells were investigated in more detail using a trypan blue quenching assay, confocal microscopy, and transmission electron microscopy. TAT-conjugation strongly increased binding and cellular uptake of lyophilisomes in a time-dependent manner in vitro, as assessed by FACS. These results were confirmed by confocal microscopy. Transmission electron microscopy indicated rapid cellular uptake of TAT-conjugated lyophilisomes via phagocytosis and/or macropinocytosis. In conclusion, TAT-peptides conjugated to albumin-based lyophilisomes are able to enhance cellular uptake of lyophilisomes in HeLa cells.

Contains fulltext : 137803.pdf (Publisher’s version ) (Open Access) Facioscapulohumeral muscular dystrophy (FSHD) is an untreatable disease, characterized by asymmetric progressive weakness of skeletal muscle with fatty infiltration. Although the main genetic defect has been uncovered, the downstream mechanisms causing FSHD are not understood. The objective of this study was to determine natural disease state and progression in muscles of FSHD patients and to establish diagnostic biomarkers by quantitative MRI of fat infiltration and phosphorylated metabolites. MRI was performed at 3T with dedicated coils on legs of 41 patients (28 men/13 women, age 34-76 years), of which eleven were re-examined after four months of usual care. Muscular fat fraction was determined with multi spin-echo and T1 weighted MRI, edema by TIRM and phosphorylated metabolites by 3D (31)P MR spectroscopic imaging. Fat fractions were compared to clinical severity, muscle force, age, edema and phosphocreatine (PCr)/ATP. Longitudinal intramuscular fat fraction variation was analyzed by linear regression. Increased intramuscular fat correlated with age (p

Contains fulltext : 136606.pdf (Publisher’s version ) (Open Access) In the last few years, susceptibility loci have been identified for urinary bladder cancer (UBC) through candidate-gene and genome-wide association studies. Prognostic relevance of most of these loci is yet unknown. In this study, we used data of the Nijmegen Bladder Cancer Study (NBCS) to perform a comprehensive evaluation of the prognostic relevance of all confirmed UBC susceptibility loci. Detailed clinical data concerning diagnosis, stage, treatment, and disease course of a population-based series of 1,602 UBC patients were collected retrospectively based on a medical file survey. Kaplan-Meier survival analyses and Cox proportional hazard regression were performed, and log-rank tests calculated, to evaluate the association between 12 confirmed UBC susceptibility variants and recurrence and progression in non-muscle invasive bladder cancer (NMIBC) patients. Among muscle-invasive or metastatic bladder cancer (MIBC) patients, association of these variants with overall survival was tested. Subgroup analyses by tumor aggressiveness and smoking status were performed in NMIBC patients. In the overall NMIBC group (n = 1,269), a statistically significant association between rs9642880 at 8q24 and risk of progression was observed (GT vs. TT: HR = 1.08 (95% CI: 0.76-1.54), GG vs. TT: HR = 1.81 (95% CI: 1.23-2.66), P for trend = 2.6x10(-3)). In subgroup analyses, several other variants showed suggestive, though non-significant, prognostic relevance for recurrence and progression in NMIBC and survival in MIBC. This study provides suggestive evidence that genetic loci involved in UBC etiology may influence disease prognosis. Elucidation of the causal variant(s) could further our understanding of the mechanism of disease, could point to new therapeutic targets, and might aid in improvement of prognostic tools.