Circulating levels of FoxP3, M2 (sCD163) and IGF-1 as potential biomarkers associated with Laryngeal Squamous Cell Carcinoma in Tunisian patients.

We aim to assess the clinical impact of circulating levels of sCD163, FoxP3, IGF-1 in LSCC patients (Laryngeal Squamous Cell Carcinoma). The concentrations of sCD163, FoxP3, and IGF-1 were measured using ELISA test in the serum samples collected from 70 pretreatment LSCC patients and 70 age and sex-matched healthy controls. Statistical analysis was performed using ANOVA to compare the two groups, and the correlation between markers and clinical parameters. Receiver-Operator Characteristic (ROC) curve analysis was conducted to determine the optimal cutoff values and evaluate the diagnostic impact of these markers. Significant differences in the levels of sCD163, FoxP3, and IGF-1 were observed between LSCC patients and the control group, with respective p-values of 0.01, 0.022, <0.0001. The determined cutoff values for sCD163, FoxP3, IGF-1 concentrations were 314.55 ng/mL, 1.69 ng/mL, and 1.69 ng/mL, respectively. The corresponding area under the curve (AUC) values were 0.67 (95% CI: 0.57-0.76), 0.70 (95% CI: 0.61-0.80), 0.84 (95% CI: 0.76-0.92), respectively. Furthermore, it was found that IGF-1 concentrations exceeding 125.20 ng/mL were positively correlated with lymph node metastasis. Elevated serum levels of sCD163, FoxP3 and IGF-1 are associated with the diagnosis of LSCC. IGF-1 appears to be the most promising indicator for the LSCC progression.

[Reversed polarity high-cell carcinoma of the breast: A case report]. / Carcinome à cellules hautes et à polarité inversée du sein : à propos d'un cas.

Reverse polarity high-cell carcinoma of the breast, formerly known as reverse polarity solid papillary carcinoma, is a rare entity recently introduced into the latest edition of the WHO classification of breast tumors. Its phenotype is triple-negative, and its diagnosis difficult. Although few cases have been reported in the literature, knowledge of this breast tumor is essential to distinguish it from other triple-negative carcinomas, which have a poorer prognosis. We report a case of high-cell, inverted-polarity carcinoma of the breast in a 43-year-old female patient with no history of breast neoplasia and no palpable mass on clinical examination. The tumour was discovered following a screening echomammogram, which revealed a lesion classified ACR 4b. A microbiopsy of this lesion concluded that it was a papillary proliferation that should be removed. A lumpectomy was performed. Histopathological and immunohistochemical studies of the surgical specimen confirmed the diagnosis of high-cell, reverse-polarity carcinoma expressing calretinin and IDH1. Given the rarity of this entity, there is no standard treatment. In our case, a mastectomy without lymph node curage was performed. The extension work-up was negative and the patient received no adjuvant treatment. After 12 months, the patient is in complete remission. In this case report, we describe the histopathological, immunohistochemical and molecular features of this rare entity.

Deep Neural Decision Forest (DNDF): A Novel Approach for Enhancing Intrusion Detection Systems in Network Traffic Analysis.

Intrusion detection systems, also known as IDSs, are widely regarded as one of the most essential components of an organization's network security. This is because IDSs serve as the organization's first line of defense against several cyberattacks and are accountable for accurately detecting any possible network intrusions. Several implementations of IDSs accomplish the detection of potential threats throughout flow-based network traffic analysis. Traditional IDSs frequently struggle to provide accurate real-time intrusion detection while keeping up with the changing landscape of threat. Innovative methods used to improve IDSs' performance in network traffic analysis are urgently needed to overcome these drawbacks. In this study, we introduced a model called a deep neural decision forest (DNDF), which allows the enhancement of classification trees with the power of deep networks to learn data representations. We essentially utilized the CICIDS 2017 dataset for network traffic analysis and extended our experiments to evaluate the DNDF model's performance on two additional datasets: CICIDS 2018 and a custom network traffic dataset. Our findings showed that DNDF, a combination of deep neural networks and decision forests, outperformed reference approaches with a remarkable precision of 99.96% by using the CICIDS 2017 dataset while creating latent representations in deep layers. This success can be attributed to improved feature representation, model optimization, and resilience to noisy and unbalanced input data, emphasizing DNDF's capabilities in intrusion detection and network security solutions.

An Evidence Theory Based Embedding Model for the Management of Smart Water Environments.

Having access to safe water and using it properly is crucial for human well-being, sustainable development, and environmental conservation. Nonetheless, the increasing disparity between human demands and natural freshwater resources is causing water scarcity, negatively impacting agricultural and industrial efficiency, and giving rise to numerous social and economic issues. Understanding and managing the causes of water scarcity and water quality degradation are essential steps toward more sustainable water management and use. In this context, continuous Internet of Things (IoT)-based water measurements are becoming increasingly crucial in environmental monitoring. However, these measurements are plagued by uncertainty issues that, if not handled correctly, can introduce bias and inaccuracy into our analysis, decision-making processes, and results. To cope with uncertainty issues related to sensed water data, we propose combining network representation learning with uncertainty handling methods to ensure rigorous and efficient modeling management of water resources. The proposed approach involves accounting for uncertainties in the water information system by leveraging probabilistic techniques and network representation learning. It creates a probabilistic embedding of the network, enabling the classification of uncertain representations of water information entities, and applies evidence theory to enable decision making that is aware of uncertainties, ultimately choosing appropriate management strategies for affected water areas.

[Sex cord tumors with annular tubules: About 4 cases and literature review]. / Les tumeurs des cordons sexuels à tubules annelés : à propos de 4 cas et revue de la littérature.

Sex cord tumor with annular tubules (SCTAT) is a rare ovarian tumor. It belongs to sex cord and stromal tumor of the ovary and represents less than 1% of cases. It includes two forms: the first one associated with Peuz-Jeghers syndrome and the second sporadic. We report 4 cases of SCTAT collected at the department of pathology of Salah Azaiez Institute of Tunis over the 12 last years. The age ranged from 10 to 32 years. Symptoms were non specific except for one case revealed by precocious puberty. One patient had Peutz-Jeghers syndrome associated. Tumors were unilateral. Gross findings showed often a solid tumor with yellow cut surface. Their size ranged from 0.5cm to 28cm. Their morphological features were characteristic. Immunohistochemistry showed that tumor cells expressed inhibin and claretinin. The treatment was surgical, often conservative. The diagnosis of malignancy wasn't focused on histological features, but on tumor extension, clinical course, and presence of metastases. Evolution was often favorable. We also performed a systematic review of the literature that identified 166 cases. Features of these cases were studied. We also compared these features between sporadic and syndromic forms and between benign and malignant forms. In conclusion, SCTAT is a rare tumor, usually benign. Its diagnosis is based on histological examination. There is a malignant potential especially in sporadic forms, estimated at 20%. Treatment is most often conservative, based on oophorectomy.

Association of ZEB1 and Vimentin with poor prognosis in metaplastic breast cancer.

Zinc finger E-box binding homeobox factor 1 (ZEB1) is a transcription factor involved in the epithelial to mesenchymal transition (EMT) process of metaplastic breast cancer (MBC). This study aimed to assess the expression of ZEB1 in MBC and explore its association with clinicopathological factors and prognosis. We analyzed the immunohistochemical expression of ZEB1 in 50 MBC tissue samples. ZEB1 was overexpressed in 36% (18/50) of cases. ZEB1 overexpression was significantly correlated to fibromatosis-like and spindle cell sarcoma subtypes (P < 0.001) and tended to be correlated to metastatic status (P = 0.069). Using the Kaplan-Meier method, ZEB1 expression was significantly associated with poor 5-years overall survival (OS) (P = 0.001) and relapse-free survival (RFS) (P = 0.0001). The multivariate Cox regression analysis showed that ZEB1 positive remained a significantly independent adverse prognostic factor for RFS and OS (HR = 4.9 [2.14-11.53]; P < 0.0001) and (HR = 4 [1.05-15.18]; P = 0.042), while Vimentin was an independent poor prognostic factor only for RFS (HR = 5.69 [1.79-18.11], P = 0.003). Our results indicated that ZEB1 and Vimentin overexpression might serve as adverse prognostic factors and potential therapeutic targets for MBC patients.

A Novel Detection and Multi-Classification Approach for IoT-Malware Using Random Forest Voting of Fine-Tuning Convolutional Neural Networks.

The Internet of Things (IoT) is prone to malware assaults due to its simple installation and autonomous operating qualities. IoT devices have become the most tempting targets of malware due to well-known vulnerabilities such as weak, guessable, or hard-coded passwords, a lack of secure update procedures, and unsecured network connections. Traditional static IoT malware detection and analysis methods have been shown to be unsatisfactory solutions to understanding IoT malware behavior for mitigation and prevention. Deep learning models have made huge strides in the realm of cybersecurity in recent years, thanks to their tremendous data mining, learning, and expression capabilities, thus easing the burden on malware analysts. In this context, a novel detection and multi-classification vision-based approach for IoT-malware is proposed. This approach makes use of the benefits of deep transfer learning methodology and incorporates the fine-tuning method and various ensembling strategies to increase detection and classification performance without having to develop the training models from scratch. It adopts the fusion of 3 CNNs, ResNet18, MobileNetV2, and DenseNet161, by using the random forest voting strategy. Experiments are carried out using a publicly available dataset, MaleVis, to assess and validate the suggested approach. MaleVis contains 14,226 RGB converted images representing 25 malware classes and one benign class. The obtained findings show that our suggested approach outperforms the existing state-of-the-art solutions in terms of detection and classification performance; it achieves a precision of 98.74%, recall of 98.67%, a specificity of 98.79%, F1-score of 98.70%, MCC of 98.65%, an accuracy of 98.68%, and an average processing time per malware classification of 672 ms.

Information Fusion in Autonomous Vehicle Using Artificial Neural Group Key Synchronization.

Information fusion in automated vehicle for various datatypes emanating from many resources is the foundation for making choices in intelligent transportation autonomous cars. To facilitate data sharing, a variety of communication methods have been integrated to build a diverse V2X infrastructure. However, information fusion security frameworks are currently intended for specific application instances, that are insufficient to fulfill the overall requirements of Mutual Intelligent Transportation Systems (MITS). In this work, a data fusion security infrastructure has been developed with varying degrees of trust. Furthermore, in the V2X heterogeneous networks, this paper offers an efficient and effective information fusion security mechanism for multiple sources and multiple type data sharing. An area-based PKI architecture with speed provided by a Graphic Processing Unit (GPU) is given in especially for artificial neural synchronization-based quick group key exchange. A parametric test is performed to ensure that the proposed data fusion trust solution meets the stringent delay requirements of V2X systems. The efficiency of the suggested method is tested, and the results show that it surpasses similar strategies already in use.

Future Forecasting of COVID-19: A Supervised Learning Approach.

A little over a year after the official announcement from the WHO, the COVID-19 pandemic has led to dramatic consequences globally. Today, millions of doses of vaccines have already been administered in several countries. However, the positive effect of these vaccines will probably be seen later than expected. In these circumstances, the rapid diagnosis of COVID-19 still remains the only way to slow the spread of this virus. However, it is difficult to predict whether a person is infected or not by COVID-19 while relying only on apparent symptoms. In this context, we propose to use machine learning (ML) algorithms in order to diagnose COVID-19 infected patients more effectively. The proposed diagnosis method takes into consideration several symptoms, such as flu symptoms, throat pain, immunity status, diarrhea, voice type, body temperature, joint pain, dry cough, vomiting, breathing problems, headache, and chest pain. Based on these symptoms that are modelled as ML features, our proposed method is able to predict the probability of contamination with the COVID-19 virus. This method is evaluated using different experimental analysis metrics such as accuracy, precision, recall, and F1-score. The obtained experimental results have shown that the proposed method can predict the presence of COVID-19 with over 97% accuracy.

Deep Learning for the Industrial Internet of Things (IIoT): A Comprehensive Survey of Techniques, Implementation Frameworks, Potential Applications, and Future Directions.

The Industrial Internet of Things (IIoT) refers to the use of smart sensors, actuators, fast communication protocols, and efficient cybersecurity mechanisms to improve industrial processes and applications. In large industrial networks, smart devices generate large amounts of data, and thus IIoT frameworks require intelligent, robust techniques for big data analysis. Artificial intelligence (AI) and deep learning (DL) techniques produce promising results in IIoT networks due to their intelligent learning and processing capabilities. This survey article assesses the potential of DL in IIoT applications and presents a brief architecture of IIoT with key enabling technologies. Several well-known DL algorithms are then discussed along with their theoretical backgrounds and several software and hardware frameworks for DL implementations. Potential deployments of DL techniques in IIoT applications are briefly discussed. Finally, this survey highlights significant challenges and future directions for future research endeavors.

[Endometrial carcinoma: An histopathological and histoprognotic study about 62 patients in a center in the Tunisian north]. / Les carcinomes de l'endomètre : étude anatomopathologique et histopronostique à propos de 62 cas dans un centre du Nord tunisien.

Endometrial cancer is the most prevalent genital tract cancer in occident and the third most common cancer among women in Tunisia. It is dominated by carcinoma. The identification of prognostic factors allows a better understanding of its outcome and guides its therapeutic approach. We propose to describe the clinicopathological features and identify the histoprognostic factors of this cancer. It is a retrospective analysis of a series of 62 total hysterectomy specimens with bilateral salpingo-oophorectomy from women with primary carcinoma of the endometrium, colligated in Anatomy Laboratory and Pathology Salah Azaiz Institute of Tunis over a period of 5 years, from January 2003 to December 2007. The median age was 60 years. At the time of diagnosis, 25% of patients were nulliparous and 86% were menopaused. The endometrioid adenocarcinoma was the most common, accounting for 84% of cases (5% of them were grade 3). A myometrial invasion superior or equal to 50% was observed in 40% of cases. 42% of cases were classified as stage IA, 14% in stage IB, 16% in stage II, 18% stage III and 10% in stage IV. 22% of patients had nodal involvement. Overall survival at 5 years was 81%. In multivariate analysis, stage IV, nodal involvement and brachytherapy have influenced this rate. Event-free survival at 5 years was 71%. It was directly related to stage and nodal involvement. Stage, histological type, tumor grade, invasion of more than half of the myometrium and lymph node involvement were the most important adverse prognostic factors, dictating an appropriate management of these tumors.

Analysis of prognostic factors of nephroblastoma in a Tunisian cohort.

BACKGROUND: Nephroblastoma is the most common childhood abdominal malignancy. Many studies allowed a better understanding of prognostic factors and they permitted to adapt treatment according to a risk stratification approach. AIM: To assess the most significant factors influencing the survival of patients presenting nephroblastoma. METHODS: We conducted a retrospective study over a 10-year period between 2001 and 2010 including 42 nephrectomy specimens, assessed in the pathology department of Salah Azaiz Institute, from all children diagnosed with nephroblastoma. The tumors were subdivided into histological subtypes and histological risk groups according to the SIOP-2001 classification. Statistical analyses were performed using the Kaplan-Meir and the Cox regression methods. RESULTS: The median age was 38 months. The mixed type was the most common (40% of cases). The tumors were subdivided into intermediate histological risk group (81%) and high risk group (14%). The tumors were classified as stage I (38%), stage II (24%), stage III (9%), stage IV (17%) and stage V (12%). The four-year survival rate was 83% and the event free survival rate was 85%. Age, laterality, histological risk group, tumor volume, blastema volume, stage, capsular rupture and incomplete resection had a significant impact on survival. Predictive factors of relapse were: laterality, tumor volume, blastema volume, histological risk group, stage, capsular rupture and incomplete resection. CONCLUSION: Histological type and stage were identified as the most important prognostic factors in nephroblastoma. Further large studies are needed to establish the impact of absolute blastemal volume.

Stromal Expression of MARCKS Protein in Ovarian Carcinomas Has Unfavorable Prognostic Value.

Epithelial ovarian cancer (EOC) is the most lethal gynecological cancer. Identification of new therapeutic targets is crucial. MARCKS, myristoylated alanine-rich C-kinase substrate, has been implicated in aggressiveness of several cancers and MARCKS inhibitors are in development. Using immunohistochemistry (IHC), we retrospectively assessed MARCKS expression in epithelial and stromal cells of 118 pre-chemotherapy EOC samples and 40 normal ovarian samples from patients treated at Salah Azaiez Institute. We compared MARCKS expression in normal versus cancer samples, and searched for correlations with clinicopathological features, including overall survival (OS). Seventy-five percent of normal samples showed positive epithelial MARCKS staining versus 50% of tumor samples (p = 6.02 × 10-3). By contrast, stromal MARCKS expression was more frequent in tumor samples (77%) than in normal samples (22%; p = 1.41 × 10-9). There was no correlation between epithelial and stromal IHC MARCKS statutes and prognostic clinicopathological features. Stromal MARCKS expression was correlated with shorter poor OS in uni- and multivariate analyses. Stromal MARCKS overexpression in tumors might contribute to cancer-associated fibroblasts activation and to the poor prognosis of EOC, suggesting a potential therapeutic interest of MARCKS inhibition for targeting the cooperative tumor stroma.

Hybrid evolutionary machine learning model for advanced intrusion detection architecture for cyber threat identification.

In response to the rapidly evolving threat landscape in network security, this paper proposes an Evolutionary Machine Learning Algorithm designed for robust intrusion detection. We specifically address challenges such as adaptability to new threats and scalability across diverse network environments. Our approach is validated using two distinct datasets: BoT-IoT, reflecting a range of IoT-specific attacks, and UNSW-NB15, offering a broader context of network intrusion scenarios using GA based hybrid DT-SVM. This selection facilitates a comprehensive evaluation of the algorithm's effectiveness across varying attack vectors. Performance metrics including accuracy, recall, and false positive rates are meticulously chosen to demonstrate the algorithm's capability to accurately identify and adapt to both known and novel threats, thereby substantiating the algorithm's potential as a scalable and adaptable security solution. This study aims to advance the development of intrusion detection systems that are not only reactive but also preemptively adaptive to emerging cyber threats." During the feature selection step, a GA is used to discover and preserve the most relevant characteristics from the dataset by using evolutionary principles. Through the use of this technology based on genetic algorithms, the subset of features is optimised, enabling the subsequent classification model to focus on the most relevant components of network data. In order to accomplish this, DT-SVM classification and GA-driven feature selection are integrated in an effort to strike a balance between efficiency and accuracy. The system has been purposefully designed to efficiently handle data streams in real-time, ensuring that intrusions are promptly and precisely detected. The empirical results corroborate the study's assertion that the IDS outperforms traditional methodologies.

Enhancing Early Alzheimer's Disease Detection Through Big Data and Ensemble Few-Shot Learning.

Alzheimer's disease is a severe brain disorder that causes harm in various brain areas and leads to memory damage. The limited availability of labeled medical data poses a significant challenge for accurate Alzheimer's disease detection. There is a critical need for effective methods to improve the accuracy of Alzheimer's disease detection, considering the scarcity of labeled data, the complexity of the disease, and the constraints related to data privacy. To address this challenge, our study leverages the power of Big Data in the form of pre-trained Convolutional Neural Networks (CNNs) within the framework of Few-Shot Learning (FSL) and ensemble learning. We propose an ensemble approach based on a Prototypical Network (ProtoNet), a powerful method in FSL, integrating various pre-trained CNNs as encoders. This integration enhances the richness of features extracted from medical images. Our approach also includes a combination of class-aware loss and entropy loss to ensure a more precise classification of Alzheimer's disease progression levels. The effectiveness of our method was evaluated using two datasets, the Kaggle Alzheimer dataset, and the ADNI dataset, achieving an accuracy of 99.72% and 99.86%, respectively. The comparison of our results with relevant state-of-the-art studies demonstrated that our approach achieved superior accuracy and highlighted its validity and potential for real-world applications in early Alzheimer's disease detection.

Inflammatory breast cancer: An overview about the histo-pathological aspect and diagnosis.

Inflammatory Breast Cancer (IBC) is a rare and aggressive form of locally advanced breast cancer, classified as stage T4d according to the tumor-node-metastasis staging criteria. This subtype of breast cancer is known for its rapid progression and significantly lower survival rates compared to other forms of breast cancer. Despite its distinctive clinical features outlined by the World Health Organization, the histopathological characteristics of IBC remain not fully elucidated, presenting challenges in its diagnosis and treatment. Histologically, IBC tumors often exhibit a ductal phenotype, characterized by emboli composed of pleomorphic cells with a high nuclear grade. These emboli are predominantly found in the papillary and reticular dermis of the skin overlaying the breast, suggesting a primary involvement of the lymphatic vessels. The tumor microenvironment in IBC is a complex network involving various cells such as macrophages, monocytes, and predominantly T CD8+ lymphocytes, and elements including blood vessels and extracellular matrix molecules, which play a pivotal role in the aggressive nature of IBC. A significant aspect of IBC is the frequent loss of expression of hormone receptors like estrogen and progesterone receptors, a phenomenon that is still under active investigation. Moreover, the overexpression of ERBB2/HER2 and TP53 in IBC cases is a topic of ongoing debate, with studies indicating a higher prevalence in IBC compared to non-inflammatory breast cancer. This overview seeks to provide a comprehensive understanding of the histopathological features and diagnostic approaches to IBC, emphasizing the critical areas that require further research.