Are deep learning classification results obtained on CT scans fair and interpretable?

Following the great success of various deep learning methods in image and object classification, the biomedical image processing society is also overwhelmed with their applications to various automatic diagnosis cases. Unfortunately, most of the deep learning-based classification attempts in the literature solely focus on the aim of extreme accuracy scores, without considering interpretability, or patient-wise separation of training and test data. For example, most lung nodule classification papers using deep learning randomly shuffle data and split it into training, validation, and test sets, causing certain images from the Computed Tomography (CT) scan of a person to be in the training set, while other images of the same person to be in the validation or testing image sets. This can result in reporting misleading accuracy rates and the learning of irrelevant features, ultimately reducing the real-life usability of these models. When the deep neural networks trained on the traditional, unfair data shuffling method are challenged with new patient images, it is observed that the trained models perform poorly. In contrast, deep neural networks trained with strict patient-level separation maintain their accuracy rates even when new patient images are tested. Heat map visualizations of the activations of the deep neural networks trained with strict patient-level separation indicate a higher degree of focus on the relevant nodules. We argue that the research question posed in the title has a positive answer only if the deep neural networks are trained with images of patients that are strictly isolated from the validation and testing patient sets.

Placenta microRNA profile of patient with Obstetric Antiphospholipid Syndrome.

The onset of obstetric antiphospholipid syndrome (APS) occurs when antiphospholipid antibodies act upon the placenta. During pregnancy, APS exhibits traits such as vascular thrombosis, inflammation, and hindered trophoblast implantation. The involvement of microRNA expression has been proposed as a genetic factor contributing to the syndrome's development. MicroRNAs play a role in regulating gene expression in various cellular processes, including the formation of placental tissue. Therefore, additional research is needed to explore the control of placental miRNA in APS. In this study, we aimed to profile miRNA expressions from placenta tissue of patients with APS. Differentially expressed miRNAs were determined for its targeted genes and pathways. Agilent microarray platform was used to measure placental microRNA expressions between normal placental tissue and those obtained from patients with APS. Differentially expressed miRNAs were detected using GeneSpring GX software 14.2 and sequences were mapped using TargetScan software to generate the predicted target genes. Pathway analysis for the genes was then performed on PANTHER and REACTOME software. Selected miRNAs and their associated genes of interest were validated using qPCR. Microarray findings revealed, 9 downregulated and 21 upregulated miRNAs expressed in placenta of patients with APS. Quantitative expressions of 3 selected miRNAs were in agreement with the microarray findings, however only miR-525-5p expression was statistically significant. Pathway analysis revealed that the targeted genes of differentially expressed miRNAs were involved in several hypothesised signalling pathways such as the vascular endothelial (VE) growth factor (VEGF) and inflammatory pathways. VE-cadherin, ras homolog member A (RHOA) and tyrosine kinase receptor (KIT) showed significant downregulation while Retinoblastoma gene (RET), Dual specificity protein phosphatase 10 (DUSP10) and B-lymphocyte kinase (BLK) genes were significantly upregulated. These preliminary findings suggest the involvement of miRNAs and identified novel associated genes involvement in the mechanism of obstetric APS, particularly through the alteration of vascular-associated regulators and the inflammatory signalling cascade.

Gastric Schwannoma in an elderly man: A case report.

Schwannomas are mesenchymal tumors that are characteristically benign and slow growing, which originate from any nerve with Schwann cell sheath. Gastrointestinal schwannomas are rare with distinct morphologic features as compared to schwannomas of soft tissue or central nervous system. A 77-year-old male patient was diagnosed with gastrointestinal stromal tumor based on radiological findings and clinical impression when he presented with worsening abdominal discomfort and pain. He underwent distal gastrectomy however histopathological examination of the tumour revealed schwannoma. This case report presents a rare case of a symptomatic gastric schwannoma, whose definitive diagnosis was established by histopathological and immunohistochemical findings postoperatively.

RNA protein kinase SNP at -226 C

BACKGROUND: RNA-dependant protein kinase R (PKR) is a primary mediator in the defence mechanism of interferon against viral replication and pathogenesis during Hepatitis C virus (HCV) infection. In the present study, we have examined the role of Single Nucleotide Polymorphisms (SNPs) in the promoter region of PKR and the serum level of the same protein on the outcome of HCV-infected Egyptian patients. PATIENTS AND METHODS: Genomic DNA was extracted from a total of 135 subjects, including 15 healthy controls, 40 HCV spontaneous resolvers (SRs), and 80 patients with chronic HCV infection. PKR genotyping was assessed using DNA sequencing. Finally, serum levels of PKR, TNF-α, INF-γ, and IL-10 were measured using ELISA technique. RESULTS: Serum levels of PKR, TNF-α, and INF-γ showed a significant increase in SRs as compared to chronic HCV patients. On the other hand, serum levels of IL-10 were significantly higher in chronic HCV patients compared to SRs. The present study demonstrated two novel SNPs in the PKR promoter region: at -226 C/T and -141 C/G. The PKR SNP at -226 C < T correlated with HCV-infected patients (genotype 4a) outcome among Egyptians. Our data showed the unique presence of the TT genotype in SRs group (three patients: 7.5%) in PKR -226 C/T. Interestingly, subjects with the TT genotype were more likely to clear their HCV infection than those with the CC genotype. CONCLUSION: Our work provides more detail about PKR gene polymorphism in HCV genotype 4a as a new clinical tool for anticipating HCV-4a infection outcome.

Prevalence of hepatitis E virus in Egyptian children presented with minor hepatic disorders.

UNLABELLED: Hepatitis E virus (HEV) is considered as one of the common causes of particular hepatitis in developing countries. It is transmitted in a fecal-oral manner. It causes sporadic infections and large epidemics. To estimate the prevalence of anti-HEV IgG and IgM antibodies to ORF3 peptide of Hepatitis E virus genome in an age of children, study subjects (100 children) between 6 months and 10 years with minor, hepatic illnesses were recruited for the study during the period from September 2004 to September 2005. Serum anti-HEV IgG and anti-HEV IgM antibodies were screened in all subjects, anti-HEV IgM antibodies were assayed as an indicator of recent infection. Serum transaminases (AST and ALT) were estimated in positive subjects. Out of 100 subjects recruited, 26 subjects (26%) demonstrated anti-HEV IgG and 6 (6 %) were anti-HEV IgM and IgG positive. Anti-HEV IgG were present since the first year of age till 10 years of age and increased with advancing age. Serum transaminases were raised in one (17%) of subjects with anti-HEV IgM antibodies. CONCLUSIONS: Children are susceptible to HEV infection since early infancy. Seropositivity to HEV antibodies increased by over 2 times beyond 4 years of age as compared to younger age.