A novel breast cancer detection architecture based on a CNN-CBR system for mammogram classification.

This paper presents a novel framework for breast cancer detection using mammogram images. The proposed solution aims to output an explainable classification from a mammogram image. The classification approach uses a Case-Based Reasoning system (CBR). CBR accuracy strongly depends on the quality of the extracted features. To achieve relevant classification, we propose a pipeline that includes image enhancement and data augmentation to improve the quality of extracted features and provide a final diagnosis. An efficient segmentation method based on a U-Net architecture is used to extract Regions of interest (RoI) from mammograms. The purpose is to combine deep learning (DL) with CBR to improve classification accuracy. DL provides accurate mammogram segmentation, while CBR gives an explainable and accurate classification. The proposed approach was tested on the CBIS-DDSM dataset and achieved high performance with an accuracy (Acc) of 86.71 % and a recall of 91.34 %, outperforming some well-known machine learning (ML) and DL approaches.

Explainable COVID-19 Detection Based on Chest X-rays Using an End-to-End RegNet Architecture.

COVID-19,which is caused by the severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2), is one of the worst pandemics in recent history. The identification of patients suspected to be infected with COVID-19 is becoming crucial to reduce its spread. We aimed to validate and test a deep learning model to detect COVID-19 based on chest X-rays. The recent deep convolutional neural network (CNN) RegNetX032 was adapted for detecting COVID-19 from chest X-ray (CXR) images using polymerase chain reaction (RT-PCR) as a reference. The model was customized and trained on five datasets containing more than 15,000 CXR images (including 4148COVID-19-positive cases) and then tested on 321 images (150 COVID-19-positive) from Montfort Hospital. Twenty percent of the data from the five datasets were used as validation data for hyperparameter optimization. Each CXR image was processed by the model to detect COVID-19. Multi-binary classifications were proposed, such as: COVID-19 vs. normal, COVID-19 + pneumonia vs. normal, and pneumonia vs. normal. The performance results were based on the area under the curve (AUC), sensitivity, and specificity. In addition, an explainability model was developed that demonstrated the high performance and high generalization degree of the proposed model in detecting and highlighting the signs of the disease. The fine-tuned RegNetX032 model achieved an overall accuracy score of 96.0%, with an AUC score of 99.1%. The model showed a superior sensitivity of 98.0% in detecting signs from CXR images of COVID-19 patients, and a specificity of 93.0% in detecting healthy CXR images. A second scenario compared COVID-19 + pneumonia vs. normal (healthy X-ray) patients. The model achieved an overall score of 99.1% (AUC) with a sensitivity of 96.0% and specificity of 93.0% on the Montfort dataset. For the validation set, the model achieved an average accuracy of 98.6%, an AUC score of 98.0%, a sensitivity of 98.0%, and a specificity of 96.0% for detection (COVID-19 patients vs. healthy patients). The second scenario compared COVID-19 + pneumonia vs. normal patients. The model achieved an overall score of 98.8% (AUC) with a sensitivity of 97.0% and a specificity of 96.0%. This robust deep learning model demonstrated excellent performance in detecting COVID-19 from chest X-rays. This model could be used to automate the detection of COVID-19 and improve decision making for patient triage and isolation in hospital settings. This could also be used as a complementary aid for radiologists or clinicians when differentiating to make smart decisions.

Deep Learning Methods for Chest Disease Detection Using Radiography Images.

X-ray images are the most widely used medical imaging modality. They are affordable, non-dangerous, accessible, and can be used to identify different diseases. Multiple computer-aided detection (CAD) systems using deep learning (DL) algorithms were recently proposed to support radiologists in identifying different diseases on medical images. In this paper, we propose a novel two-step approach for chest disease classification. The first is a multi-class classification step based on classifying X-ray images by infected organs into three classes (normal, lung disease, and heart disease). The second step of our approach is a binary classification of seven specific lungs and heart diseases. We use a consolidated dataset of 26,316 chest X-ray (CXR) images. Two deep learning methods are proposed in this paper. The first is called DC-ChestNet. It is based on ensembling deep convolutional neural network (DCNN) models. The second is named VT-ChestNet. It is based on a modified transformer model. VT-ChestNet achieved the best performance overcoming DC-ChestNet and state-of-the-art models (DenseNet121, DenseNet201, EfficientNetB5, and Xception). VT-ChestNet obtained an area under curve (AUC) of 95.13% for the first step. For the second step, it obtained an average AUC of 99.26% for heart diseases and an average AUC of 99.57% for lung diseases.

Discovery of a Small-Molecule Inhibitor Targeting the Androgen Receptor N-Terminal Domain for Castration-Resistant Prostate Cancer.

The current mainstay therapeutic strategy for advanced prostate cancer is to suppress androgen receptor (AR) signaling. However, castration-resistant prostate cancer (CRPC) invariably arises with restored AR signaling activity. To date, the AR ligand-binding domain (LBD) is the only targeted region for all clinically available AR signaling antagonists, such as enzalutamide (ENZ). Major resistance mechanisms have been uncovered to sustain the AR signaling in CRPC despite these treatments, including AR amplification, AR LBD mutants, and the emergence of AR splice variants (AR-Vs) such as AR-V7. AR-V7 is a constitutively active truncated form of AR that lacks the LBD; thus, it can not be inhibited by AR LBD-targeting drugs. Therefore, an approach to inhibit AR through the regions outside of LBD is urgently needed. In this study, we have discovered a novel small molecule SC428, which directly binds to the AR N-terminal domain (NTD) and exhibits pan-AR inhibitory effect. SC428 potently decreased the transactivation of AR-V7, ARv567es, as well as full-length AR (AR-FL) and its LBD mutants. SC428 substantially suppressed androgen-stimulated AR-FL nuclear translocation, chromatin binding, and AR-regulated gene transcription. Moreover, SC428 also significantly attenuated AR-V7-mediated AR signaling that does not rely on androgen, hampered AR-V7 nuclear localization, and disrupted AR-V7 homodimerization. SC428 inhibited in vitro proliferation and in vivo tumor growth of cells that expressed a high level of AR-V7 and were unresponsive to ENZ treatment. Together, these results indicated the potential therapeutic benefits of AR-NTD targeting for overcoming drug resistance in CRPC.

Vision Transformers for Lung Segmentation on CXR Images.

Accurate segmentation of the lungs in CXR images is the basis for an automated CXR image analysis system. It helps radiologists in detecting lung areas, subtle signs of disease and improving the diagnosis process for patients. However, precise semantic segmentation of lungs is considered a challenging case due to the presence of the edge rib cage, wide variation of lung shape, and lungs affected by diseases. In this paper, we address the problem of lung segmentation in healthy and unhealthy CXR images. Five models were developed and used in detecting and segmenting lung regions. Two loss functions and three benchmark datasets were employed to evaluate these models. Experimental results showed that the proposed models were able to extract salient global and local features from the input CXR images. The best performing model achieved an F1 score of 97.47%, outperforming recent published models. They proved their ability to separate lung regions from the rib cage and clavicle edges and segment varying lung shape depending on age and gender, as well as challenging cases of lungs affected by anomalies such as tuberculosis and the presence of nodules.

DCTable: A Dilated CNN with Optimizing Anchors for Accurate Table Detection.

With the widespread use of deep learning in leading systems, it has become the mainstream in the table detection field. Some tables are difficult to detect because of the likely figure layout or the small size. As a solution to the underlined problem, we propose a novel method, called DCTable, to improve Faster R-CNN for table detection. DCTable came up to extract more discriminative features using a backbone with dilated convolutions in order to improve the quality of region proposals. Another main contribution of this paper is the anchors optimization using the Intersection over Union (IoU)-balanced loss to train the RPN and reduce the false positive rate. This is followed by a RoI Align layer, instead of the ROI pooling, to improve the accuracy during mapping table proposal candidates by eliminating the coarse misalignment and introducing the bilinear interpolation in mapping region proposal candidates. Training and testing on a public dataset showed the effectiveness of the algorithm and a considerable improvement of the F1-score on ICDAR 2017-Pod, ICDAR-2019, Marmot and RVL CDIP datasets.

E-liquid alters oral epithelial cell function to promote epithelial to mesenchymal transition and invasiveness in preclinical oral squamous cell carcinoma.

The gaining popularity of tobacco and nicotine delivery products, such as electronic cigarettes (e-cigarettes) being perceived as relatively safe is of a medical concern. The long-term safety of these new products remains uncertain for oral health. In this study, in vitro effects of e-liquid were assessed in a panel of normal oral epithelium cell lines (NOE and HMK), oral squamous cell carcinoma (OSCC) human cell lines (CAL27 and HSC3), and a mouse oral cancer cell line (AT84) using cell proliferation, survival/cell death, and cell invasion assays. In addition, signaling pathways underlying the pro-invasive activity of e-cigarettes were evaluated by gene and protein expression analysis. We demonstrated that e-liquid promotes proliferation and anchorage-independent growth of OSCC and induces morphological changes associated with enhanced motility and invasive phenotypes. Furthermore, e-liquid-exposed cells express significantly reduced cell viability, regardless of e-cigarette flavour content. At the gene expression level, e-liquid induces changes in gene expression consistent with epithelial to mesenchymal transition (EMT) revealed by reduced expression of cell epithelial markers such as E-cadherin and enhanced expression of mesenchymal proteins like vimentin and B-catenin seen both in OSCC cell lines and normal oral epithelium cells. In summary, the ability of e-liquid to induce proliferative and invasive properties along the activation of the EMT process can contribute to the development of tumorigenesis in normal epithelial cells and promote aggressive phenotype in pre-existing oral malignant cells.

A Review of Recent Advances in Deep Learning Models for Chest Disease Detection Using Radiography.

Chest X-ray radiography (CXR) is among the most frequently used medical imaging modalities. It has a preeminent value in the detection of multiple life-threatening diseases. Radiologists can visually inspect CXR images for the presence of diseases. Most thoracic diseases have very similar patterns, which makes diagnosis prone to human error and leads to misdiagnosis. Computer-aided detection (CAD) of lung diseases in CXR images is among the popular topics in medical imaging research. Machine learning (ML) and deep learning (DL) provided techniques to make this task more efficient and faster. Numerous experiments in the diagnosis of various diseases proved the potential of these techniques. In comparison to previous reviews our study describes in detail several publicly available CXR datasets for different diseases. It presents an overview of recent deep learning models using CXR images to detect chest diseases such as VGG, ResNet, DenseNet, Inception, EfficientNet, RetinaNet, and ensemble learning methods that combine multiple models. It summarizes the techniques used for CXR image preprocessing (enhancement, segmentation, bone suppression, and data-augmentation) to improve image quality and address data imbalance issues, as well as the use of DL models to speed-up the diagnosis process. This review also discusses the challenges present in the published literature and highlights the importance of interpretability and explainability to better understand the DL models' detections. In addition, it outlines a direction for researchers to help develop more effective models for early and automatic detection of chest diseases.

Genetic Mutations Associated with Inflammatory Response Caused by HPV Integration in Oropharyngeal Squamous Cell Carcinoma.

(1) Background: Head and neck cancer (HNC) ranks as the sixth most prevalent cancer in the world. In addition to the traditional risk factors such as alcohol and tobacco consumption, the implication of the human papillomavirus (HPV) is becoming increasingly significant, particularly in oropharyngeal cancer (OPC). (2) Methods: This study is based on a review analysis of different articles and repositories investigating the mutation profile of HPV-related OPC and its impact on patient outcomes. (3) Results: By compiling data from 38 datasets involving 8311 patients from 12 countries, we identified 330 genes that were further analyzed. These genes were enriched for regulation of the inflammatory response (RB1, JAK2, FANCA, CYLD, SYK, ABCC1, SYK, BCL6, CEBPA, SRC, BAP1, FOXP1, FGR, BCR, LRRK2, RICTOR, IGF1, and ATM), among other biological processes. Hierarchical cluster analysis showed the most relevant biological processes were linked with the regulation of mast cell cytokine production, neutrophil activation and degranulation, and leukocyte activation (FDR < 0.001; p-value < 0.05), suggesting that neutrophils may be involved in the development and progression of HPV-related OPC. (4) Conclusions: The neutrophil infiltration and HPV status emerge as a potential prognostic factor for OPC. HPV-infected HNC cells could potentially lead to a decrease in neutrophil infiltration. By gaining a better molecular understanding of HPV-mediated neutrophil immunosuppression activity, it is possible to identify a meaningful target to boost antitumor immune response in HNC and hence to improve the survival of patients with HNC.

Applying Deep Learning for Breast Cancer Detection in Radiology.

Recent advances in deep learning have enhanced medical imaging research. Breast cancer is the most prevalent cancer among women, and many applications have been developed to improve its early detection. The purpose of this review is to examine how various deep learning methods can be applied to breast cancer screening workflows. We summarize deep learning methods, data availability and different screening methods for breast cancer including mammography, thermography, ultrasound and magnetic resonance imaging. In this review, we will explore deep learning in diagnostic breast imaging and describe the literature review. As a conclusion, we discuss some of the limitations and opportunities of integrating artificial intelligence into breast cancer clinical practice.

Implications and Emerging Therapeutic Avenues of Inflammatory Response in HPV+ Head and Neck Squamous Cell Carcinoma.

Head and neck squamous cell carcinomas (HNSCC) are a heterogeneous group of malignancies which have shown exponential incidence in the last two decades especially due to human papillomavirus (HPV) infection. The HPV family comprises more than 100 types of viruses with HPV16 and HPV18 being the most prevalent strains in HNSCC. Literature data reveal that the mutation profile as well as the response to chemotherapy and radiotherapy are distinct among HPV+ versus HPV-negative tumors. Furthermore, the presence of the virus induces activation of an immune response, in particular the recruitment of specific antiviral T lymphocytes to tumor sites. These T cells when activated produce soluble factors including cytokines and chemokines capable of modifying the local immune tumor microenvironment and impact on tumor response to the treatment. In this comprehensive review we investigated current knowledge on how the presence of an HPV can modify the inflammatory response systemically and within the tumor microenvironment's immunological responses, thereby impacting on disease prognosis and survival. We highlighted the research gaps and emerging approaches necessary to discover novel immunotherapeutic targets for HPV-associated HNSCC.

Therapeutic Vaccines for HPV-Associated Oropharyngeal and Cervical Cancer: The Next De-Intensification Strategy?

The rise in human papillomavirus (HPV)-associated oropharyngeal squamous cell carcinoma (OPSCC) has prompted a quest for further understanding of the role of high-risk HPV in tumor initiation and progression. Patients with HPV-positive OPSCC (HPV+ OPSCC) have better prognoses than their HPV-negative counterparts; however, current therapeutic strategies for HPV+ OPSCC are overly aggressive and leave patients with life-long sequalae and poor quality of life. This highlights a need for customized treatment. Several clinical trials of treatment de-intensification to reduce acute and late toxicity without compromising efficacy have been conducted. This article reviews the differences and similarities in the pathogenesis and progression of HPV-related OPSCC compared to cervical cancer, with emphasis on the role of prophylactic and therapeutic vaccines as a potential de-intensification treatment strategy. Overall, the future development of novel and effective therapeutic agents for HPV-associated head and neck tumors promises to meet the challenges posed by this growing epidemic.

Explainable Vision Transformers and Radiomics for COVID-19 Detection in Chest X-rays.

The rapid spread of COVID-19 across the globe since its emergence has pushed many countries' healthcare systems to the verge of collapse. To restrict the spread of the disease and lessen the ongoing cost on the healthcare system, it is critical to appropriately identify COVID-19-positive individuals and isolate them as soon as possible. The primary COVID-19 screening test, RT-PCR, although accurate and reliable, has a long turn-around time. More recently, various researchers have demonstrated the use of deep learning approaches on chest X-ray (CXR) for COVID-19 detection. However, existing Deep Convolutional Neural Network (CNN) methods fail to capture the global context due to their inherent image-specific inductive bias. In this article, we investigated the use of vision transformers (ViT) for detecting COVID-19 in Chest X-ray (CXR) images. Several ViT models were fine-tuned for the multiclass classification problem (COVID-19, Pneumonia and Normal cases). A dataset consisting of 7598 COVID-19 CXR images, 8552 CXR for healthy patients and 5674 for Pneumonia CXR were used. The obtained results achieved high performance with an Area Under Curve (AUC) of 0.99 for multi-class classification (COVID-19 vs. Other Pneumonia vs. normal). The sensitivity of the COVID-19 class achieved 0.99. We demonstrated that the obtained results outperformed comparable state-of-the-art models for detecting COVID-19 on CXR images using CNN architectures. The attention map for the proposed model showed that our model is able to efficiently identify the signs of COVID-19.

NEDD9 links anaplastic thyroid cancer stemness to chromosomal instability through integrated centrosome asymmetry and DNA sensing regulation.

Stemness and chromosomal instability (CIN) are two common contributors to intratumor heterogeneity and therapy relapse in advanced cancer, but their interplays are poorly defined. Here, in anaplastic thyroid cancer (ATC), we show that ALDH+ stem-like cancer cells possess increased CIN-tolerance owing to transcriptional upregulation of the scaffolding protein NEDD9. Thyroid patient tissues and transcriptomic data reveals NEDD9/ALDH1A3 to be co-expressed and co-upregulated in ATC. Compared to bulk ALDH- cells, ALDH+ cells were highly efficient at propagating CIN due to their intrinsic tolerance of both centrosome amplification and micronuclei. ALDH+ cells mitigated the fitness-impairing effects of centrosome amplification by partially inactivating supernumerary centrosomes. Meanwhile, ALDH+ cells also mitigated cell death caused by micronuclei-mediated type 1 interferon secretion by suppressing the expression of the DNA-sensor protein STING. Both mechanisms of CIN-tolerance were lost upon RNAi-mediated NEDD9 silencing. Both in vitro and in vivo, NEDD9-depletion attenuated stemness, CIN, cell/tumor growth, while enhancing paclitaxel effectiveness. Collectively, these findings reveal that ATC progression can involve an ALDH1A3/NEDD9-regulated program linking their stemness to CIN-tolerance that could be leveraged for ATC treatment.

Deep Learning and Transformer Approaches for UAV-Based Wildfire Detection and Segmentation.

Wildfires are a worldwide natural disaster causing important economic damages and loss of lives. Experts predict that wildfires will increase in the coming years mainly due to climate change. Early detection and prediction of fire spread can help reduce affected areas and improve firefighting. Numerous systems were developed to detect fire. Recently, Unmanned Aerial Vehicles were employed to tackle this problem due to their high flexibility, their low-cost, and their ability to cover wide areas during the day or night. However, they are still limited by challenging problems such as small fire size, background complexity, and image degradation. To deal with the aforementioned limitations, we adapted and optimized Deep Learning methods to detect wildfire at an early stage. A novel deep ensemble learning method, which combines EfficientNet-B5 and DenseNet-201 models, is proposed to identify and classify wildfire using aerial images. In addition, two vision transformers (TransUNet and TransFire) and a deep convolutional model (EfficientSeg) were employed to segment wildfire regions and determine the precise fire regions. The obtained results are promising and show the efficiency of using Deep Learning and vision transformers for wildfire classification and segmentation. The proposed model for wildfire classification obtained an accuracy of 85.12% and outperformed many state-of-the-art works. It proved its ability in classifying wildfire even small fire areas. The best semantic segmentation models achieved an F1-score of 99.9% for TransUNet architecture and 99.82% for TransFire architecture superior to recent published models. More specifically, we demonstrated the ability of these models to extract the finer details of wildfire using aerial images. They can further overcome current model limitations, such as background complexity and small wildfire areas.

Novel Aurora A and Protein Kinase C (α, ß1, ß2, and θ) Multitarget Inhibitors: Impact of Selenium Atoms on the Potency and Selectivity.

Aurora kinases and protein kinase C (PKC) have been shown to be involved in different aspects of cancer progression. To date, no dual Aurora/PKC inhibitor with clinical efficacy and low toxicity is available. Here, we report the identification of compound 2e as a potent small molecule capable of selectively inhibiting Aurora A kinase and PKC isoforms α, ß1, ß2 and θ. Compound 2e demonstrated significant inhibition of the colony forming ability of metastatic breast cancer cells in vitro and metastasis development in vivo. In vitro kinase screening and molecular modeling studies revealed the critical role of the selenium-containing side chains within 2e, where selenium atoms were shown to significantly improve its selectivity and potency by forming additional interactions and modulating the protein dynamics. In comparison to other H-bonding heteroatoms such as sulfur, our studies suggested that these selenium atoms also confer more favorable PK properties.

Molecular prognostic indicators in HPV-positive oropharyngeal cancer: an updated review.

Infection with HPV virus and exposure to extrinsic carcinogens are the main causative factors for oropharyngeal squamous cell carcinoma (OPSCC). While HPV-related OPSCC typically shows a better prognosis and may be a candidate for de-intensification therapy, there is a subset of HPV-related cancers that show aggressive phenotype with frequent metastatic spread. The identification and refinement of molecular markers can better serve for prediction of prognosis and thus improve treatment decisions and outcome. We conducted a systematic review according to the PRISMA guidelines of all relevant studies addressing novel biomarkers in publications prior to July 2021. We identified studies that evaluated the association between molecular markers and prognosis in HPV-positive OPSCC. Full-text publications were entirely reviewed, classified, and selected if a clear predictive/prognostic value was seen in patients with HPV-positive OPSCC. Furthermore, a functional analysis of the target genes was conducted to understand biological processes and molecular pathways impacting on HPV-positive OPSCC outcomes. The systematic review yielded a total of 14 studies that matched the inclusion and exclusion criteria. Differential expression was identified for 31 different biomarkers. The first common pattern identified was the association of HPV-related circulating antibodies to activated immune function. Second, gene-gene interaction analysis further identified interacting gene networks tightly implicated in hypoxia tumor metabolism including the Warburg effect. Survival in HPV-positive OPSCC can be predicted by distinct selective biomarkers mainly indicative of immune host response and oxidative metabolism. Among these markers, some were identified to be unsuitable for HPV-positive de-escalation trials aimed at improving patients' quality of life.

Identification of R-Spondin Gene Signature Predictive of Metastatic Progression in BRAFV600E-Positive Papillary Thyroid Cancer.

Papillary thyroid carcinoma (PTC) is the most common malignancy of the thyroid gland and early stages are curable. However, a subset of PTCs shows an unusually aggressive phenotype with extensive lymph node metastasis and higher incidence of locoregional recurrence. In this study, we investigated a large cohort of PTC cases with an unusual aggressive phenotype using a high-throughput RNA sequencing (RNA-Seq) to identify differentially regulated genes associated with metastatic PTC. All metastatic PTC with mutated BRAF (V600E) but not BRAF wild-type expressed an up-regulation of R-Spondin Protein 4 (RSPO4) concomitant with an upregulation of genes involved in focal adhesion and cell-extracellular matrix signaling. Further immunohistochemistry validation confirmed the upregulation of these target genes in metastatic PTC cases. Preclinical studies using established PTC cell lines support that RSPO4 overexpression is associated with BRAF V600E mutation and is a critical upstream event that promote activation of kinases of focal adhesion signaling known to drive cancer cell locomotion and invasion. This finding opens up the potential of co-targeting B-Raf, RSPO and focal adhesion proteins as a pharmacological approach for aggressive BRAF V600E PTC.