Classification of H. pylori Infection from Histopathological Images Using Deep Learning.

Helicobacter pylori (H. pylori) is a widespread pathogenic bacterium, impacting over 4 billion individuals globally. It is primarily linked to gastric diseases, including gastritis, peptic ulcers, and cancer. The current histopathological method for diagnosing H. pylori involves labour-intensive examination of endoscopic biopsies by trained pathologists. However, this process can be time-consuming and may occasionally result in the oversight of small bacterial quantities. Our study explored the potential of five pre-trained models for binary classification of 204 histopathological images, distinguishing between H. pylori-positive and H. pylori-negative cases. These models include EfficientNet-b0, DenseNet-201, ResNet-101, MobileNet-v2, and Xception. To evaluate the models' performance, we conducted a five-fold cross-validation, ensuring the models' reliability across different subsets of the dataset. After extensive evaluation and comparison of the models, ResNet101 emerged as the most promising. It achieved an average accuracy of 0.920, with impressive scores for sensitivity, specificity, positive predictive value, negative predictive value, F1 score, Matthews's correlation coefficient, and Cohen's kappa coefficient. Our study achieved these robust results using a smaller dataset compared to previous studies, highlighting the efficacy of deep learning models even with limited data. These findings underscore the potential of deep learning models, particularly ResNet101, to support pathologists in achieving precise and dependable diagnostic procedures for H. pylori. This is particularly valuable in scenarios where swift and accurate diagnoses are essential.

The Application of Deep Learning for the Segmentation and Classification of Coronary Arteries.

In recent years, the prevalence of coronary artery disease (CAD) has become one of the leading causes of death around the world. Accurate stenosis detection of coronary arteries is crucial for timely treatment. Cardiologists use visual estimations when reading coronary angiography images to diagnose stenosis. As a result, they face various challenges which include high workloads, long processing times and human error. Computer-aided segmentation and classification of coronary arteries, as to whether stenosis is present or not, significantly reduces the workload of cardiologists and human errors caused by manual processes. Moreover, deep learning techniques have been shown to aid medical experts in diagnosing diseases using biomedical imaging. Thus, this study proposes the use of automatic segmentation of coronary arteries using U-Net, ResUNet-a, UNet++, models and classification using DenseNet201, EfficientNet-B0, Mobilenet-v2, ResNet101 and Xception models. In the case of segmentation, the comparative analysis of the three models has shown that U-Net achieved the highest score with a 0.8467 Dice score and 0.7454 Jaccard Index in comparison with UNet++ and ResUnet-a. Evaluation of the classification model's performances has shown that DenseNet201 performed better than other pretrained models with 0.9000 accuracy, 0.9833 specificity, 0.9556 PPV, 0.7746 Cohen's Kappa and 0.9694 Area Under the Curve (AUC).

COVID-19 Lung CT image segmentation using localization and enhancement methods with U-Net.

Segmentation of pneumonia lesions from Lung CT images has become vital for diagnosing the disease and evaluating the severity of the patients during the COVID-19 pandemic. Several AI-based systems have been proposed for this task. However, some low-contrast abnormal zones in CT images make the task challenging. The researchers investigated image preprocessing techniques to accomplish this problem and to enable more accurate segmentation by the AI-based systems. This study proposes a COVID-19 Lung-CT segmentation system based on histogram-based non-parametric region localization and enhancement (LE) methods prior to the U-Net architecture. The COVID-19-infected lung CT images were initially processed by the LE method, and the infected regions were detected and enhanced to provide more discriminative features to the deep learning segmentation methods. The U-Net is trained using the enhanced images to segment the regions affected by COVID-19. The proposed system achieved 97.75%, 0.85, and 0.74 accuracy, dice score, and Jaccard index, respectively. The comparison results suggested that the use of LE methods as a preprocessing step in CT Lung images significantly improved the feature extraction and segmentation abilities of the U-Net model by a 0.21 dice score. The results might lead to implementing the LE method in segmenting varied medical images.

The dual role of microRNA (miR)-20b in cancers: Friend or foe?

MicroRNAs, as non-coding transcripts, modulate gene expression through RNA silencing under normal physiological conditions. Their aberrant expression has strongly associated with tumorigenesis and cancer development. MiR-20b is one of the crucial miRNAs that regulate essential biological processes such as cell proliferation, apoptosis, autophagy, and migration. Deregulated levels of miR-20b contribute to the early- and advanced stages of cancer. On the other hand, investigations emphasize the tumor suppressor ability of miR-20b. High-throughput strategies are developed to identify miR-20b potential targets, providing the proper insight into its molecular mechanism of action. Moreover, accumulated results suggest that miR-20b exerts its effects through diverse signaling pathways, including PI3K/AKT/mTOR and ERK axes. Restoration of the altered expression levels of miR-20b induces cell apoptosis and reduces invasion and migration. Further, miR-20b can be used as a biomarker in cancer. The current comprehensive review could lead to a better understanding of the miR-20b in either tumorigenesis or tumor regression that may open new avenues for cancer treatment. Video Abstract.

Identify Biomarkers and Design Effective Multi-Target Drugs in Ovarian Cancer: Hit Network-Target Sets Model Optimizing.

Epithelial ovarian cancer (EOC) is highly aggressive with poor patient outcomes, and a deeper understanding of ovarian cancer tumorigenesis could help guide future treatment development. We proposed an optimized hit network-target sets model to systematically characterize the underlying pathological mechanisms and intra-tumoral heterogeneity in human ovarian cancer. Using TCGA data, we constructed an epithelial ovarian cancer regulatory network in this study. We use three distinct methods to produce different HNSs for identification of the driver genes/nodes, core modules, and core genes/nodes. Following the creation of the optimized HNS (OHNS) by the integration of DN (driver nodes), CM (core module), and CN (core nodes), the effectiveness of various HNSs was assessed based on the significance of the network topology, control potential, and clinical value. Immunohistochemical (IHC), qRT-PCR, and Western blotting were adopted to measure the expression of hub genes and proteins involved in epithelial ovarian cancer (EOC). We discovered that the OHNS has two key advantages: the network's central location and controllability. It also plays a significant role in the illness network due to its wide range of capabilities. The OHNS and clinical samples revealed the endometrial cancer signaling, and the PI3K/AKT, NER, and BMP pathways. MUC16, FOXA1, FBXL2, ARID1A, COX15, COX17, SCO1, SCO2, NDUFA4L2, NDUFA, and PTEN hub genes were predicted and may serve as potential candidates for new treatments and biomarkers for EOC. This research can aid in better capturing the disease progression, the creation of potent multi-target medications, and the direction of the therapeutic community in the optimization of effective treatment regimens by various research objectives in cancer treatment.

A comprehensive survey into the role of microRNAs in ovarian cancer chemoresistance; an updated overview.

Ovarian cancer (OC), a frequent malignant tumor that affects women, is one of the leading causes of cancer-related death in this group of individuals. For the treatment of ovarian cancer, systemic chemotherapy with platinum-based drugs or taxanes is the first-line option. However, drug resistance developed over time during chemotherapy medications worsens the situation. Since uncertainty exists for the mechanism of chemotherapy resistance in ovarian cancer, there is a need to investigate and overcome this problem. miRNAs are engaged in various signaling pathways that contribute to the chemotherapeutic resistance of ovarian cancer. In the current study, we have tried to shed light on the mechanisms by which microRNAs contribute to the drug resistance of ovarian cancer and the use of some microRNAs to combat this chemoresistance, leading to the worse outcome of ovarian cancer patients treated with systemic chemotherapeutics.

CRISPR/Cas9 application in cancer therapy: a pioneering genome editing tool.

The progress of genetic engineering in the 1970s brought about a paradigm shift in genome editing technology. The clustered regularly interspaced short palindromic repeats/CRISPR associated protein 9 (CRISPR/Cas9) system is a flexible means to target and modify particular DNA sequences in the genome. Several applications of CRISPR/Cas9 are presently being studied in cancer biology and oncology to provide vigorous site-specific gene editing to enhance its biological and clinical uses. CRISPR's flexibility and ease of use have enabled the prompt achievement of almost any preferred alteration with greater efficiency and lower cost than preceding modalities. Also, CRISPR/Cas9 technology has recently been applied to improve the safety and efficacy of chimeric antigen receptor (CAR)-T cell therapies and defeat tumor cell resistance to conventional treatments such as chemotherapy and radiotherapy. The current review summarizes the application of CRISPR/Cas9 in cancer therapy. We also discuss the present obstacles and contemplate future possibilities in this context.

Brain tumor segmentation in MRI images using nonparametric localization and enhancement methods with U-net.

PURPOSE: Segmentation is one of the critical steps in analyzing medical images since it provides meaningful information for the diagnosis, monitoring, and treatment of brain tumors. In recent years, several artificial intelligence-based systems have been developed to perform this task accurately. However, the unobtrusive or low-contrast occurrence of some tumors and similarities to healthy brain tissues make the segmentation task challenging. These yielded researchers to develop new methods for preprocessing the images and improving their segmentation abilities. METHODS: This study proposes an efficient system for the segmentation of the complete brain tumors from MRI images based on tumor localization and enhancement methods with a deep learning architecture named U-net. Initially, the histogram-based nonparametric tumor localization method is applied to localize the tumorous regions and the proposed tumor enhancement method is used to modify the localized regions to increase the visual appearance of indistinct or low-contrast tumors. The resultant images are fed to the original U-net architecture to segment the complete brain tumors. RESULTS: The performance of the proposed tumor localization and enhancement methods with the U-net is tested on benchmark datasets, BRATS 2012, BRATS 2019, and BRATS 2020, and achieved superior results as 0.94, 0.85, 0.87, 0.88 dice scores for the BRATS 2012 HGG-LGG, BRATS 2019, and BRATS 2020 datasets, respectively. CONCLUSION: The results and comparisons showed how the proposed methods improve the segmentation ability of the deep learning models and provide high-accuracy and low-cost segmentation of complete brain tumors in MRI images. The results might yield the implementation of the proposed methods in segmentation tasks of different medical fields.

In vitro genotoxic perspective of Tamiflu.

The aim of this study was to investigate the genotoxic and/or cytotoxic effects of Tamiflu, commercial form of the oseltamivir antiviral and most frequently prescribed for the treatment of influenza infections, on cultured human peripheral lymphocytes by using sister chromatid exchange (SCE), chromosomal aberration (CA), and cytokinesis-blocked micronucleus (CBMN) assays. Cells were treated with 0.5, 1, 2 µg/mL oseltamivir, the Tamiflu capsule ingredient, for 24 or 48 h in the absence or presence of an exogenous metabolic activation system (S9 mix). The test chemical did not demonstrate any genotoxic effect dose-dependently but it showed a weak cytotoxicity on cells in this study. On the other hand, some concentrations of Tamiflu (2 µg/mL without S9 mix for 48 h and 1 µg/mL with S9 mix) induced SCE and also decreased significantly the proliferation index (PI) (48 h period) and the nuclear division index (NDI) (24 h period) (P < 0.05) in the absence of S9 mix. Considering the results, Tamiflu did not induce significant increases of CA or micronucleated cells in vitro in cultured peripheral blood lymphocytes under the treatment conditions used but weak SCE induction was observed. On the other hand, the weak cytotoxic effects observed disappeared in the cultures treated in presence of the S9 mix.