Breast cancer classification based on convolutional neural network and image fusion approaches using ultrasound images.

Deep learning and image processing are used to classify and segment breast tumor images, specifically in ultrasound (US) modalities, to support clinical decisions and improve healthcare quality. However, directly using US images can be challenging due to noise and diverse imaging modalities. In this study, we developed a three-step image processing scheme involving speckle noise filtering using a block-matching three-dimensional filtering technique, region of interest highlighting, and RGB fusion. This method enhances the generalization of deep-learning models and achieves better performance. We used a deep learning model (VGG19) to perform transfer learning on three datasets: BUSI (780 images), Dataset B (162 images), and KAIMRC (5693 images). When tested on the BUSI and KAIMRC datasets using a fivefold cross-validation mechanism, the model with the proposed preprocessing step performed better than without preprocessing for each dataset. The proposed image processing approach improves the performance of the breast cancer deep learning classification model. Multiple diverse datasets (private and public) were used to generalize the model for clinical application.

Machine Learning and Deep Learning Techniques for Optic Disc and Cup Segmentation - A Review.

Background: Globally, glaucoma is the second leading cause of blindness. Detecting glaucoma in the early stages is essential to avoid disease complications, which lead to blindness. Thus, computer-aided diagnosis systems are powerful tools to overcome the shortage of glaucoma screening programs. Methods: A systematic search of public databases, including PubMed, Google Scholar, and other sources, was performed to identify relevant studies to overview the publicly available fundus image datasets used to train, validate, and test machine learning and deep learning methods. Additionally, existing machine learning and deep learning methods for optic cup and disc segmentation were surveyed and critically reviewed. Results: Eight fundus images datasets were publicly available with 15,445 images labeled with glaucoma or non-glaucoma, and manually annotated optic disc and cup boundaries were found. Five metrics were identified for evaluating the developed models. Finally, three main deep learning architectural designs were commonly used for optic disc and optic cup segmentation. Conclusion: We provided future research directions to formulate robust optic cup and disc segmentation systems. Deep learning can be utilized in clinical settings for this task. However, many challenges need to be addressed before using this strategy in clinical trials. Finally, two deep learning architectural designs have been widely adopted, such as U-net and its variants.

ChromoEnhancer: An Artificial-Intelligence-Based Tool to Enhance Neoplastic Karyograms as an Aid for Effective Analysis.

Cytogenetics laboratory tests are among the most important procedures for the diagnosis of genetic diseases, especially in the area of hematological malignancies. Manual chromosomal karyotyping methods are time consuming and labor intensive and, hence, expensive. Therefore, to alleviate the process of analysis, several attempts have been made to enhance karyograms. The current chromosomal image enhancement is based on classical image processing. This approach has its limitations, one of which is that it has a mandatory application to all chromosomes, where customized application to each chromosome is ideal. Moreover, each chromosome needs a different level of enhancement, depending on whether a given area is from the chromosome itself or it is just an artifact from staining. The analysis of poor-quality karyograms, which is a difficulty faced often in preparations from cancer samples, is time consuming and might result in missing the abnormality or difficulty in reporting the exact breakpoint within the chromosome. We developed ChromoEnhancer, a novel artificial-intelligence-based method to enhance neoplastic karyogram images. The method is based on Generative Adversarial Networks (GANs) with a data-centric approach. GANs are known for the conversion of one image domain to another. We used GANs to convert poor-quality karyograms into good-quality images. Our method of karyogram enhancement led to robust routine cytogenetic analysis and, therefore, to accurate detection of cryptic chromosomal abnormalities. To evaluate ChromoEnahancer, we randomly assigned a subset of the enhanced images and their corresponding original (unenhanced) images to two independent cytogeneticists to measure the karyogram quality and the elapsed time to complete the analysis, using four rating criteria, each scaled from 1 to 5. Furthermore, we compared the enhanced images with our method to the original ones, using quantitative measures (PSNR and SSIM metrics).

Risk factors of SARS-CoV-2 infection in cancer patients pre- and post-vaccination.

BACKGROUND: Severe complications from COVID-19 and poor responses to SARS-CoV-2 vaccination were commonly reported in cancer patients compared to those without cancer. Therefore, the identification of predisposing factors to SARS-CoV-2 infection in cancer patients would assist in the prevention of COVID-19 and improve vaccination strategies. The literature lacks reports on this topic from the Kingdom of Saudi Arabia (KSA). Therefore, we studied clinical and laboratory data of 139 cancer patients from King Abdulaziz Medical City, Riyadh, KSA. METHODS: The cancer patients fall into three categories; (i) uninfected with SARS-CoV-2 pre-vaccination and remained uninfected post-vaccination (control group; n = 114; 81%), (ii) pre-vaccination infected group (n = 16; 11%), or (iii) post-vaccination infected group (n = 9; 6%). Next, the clinical and lab data of the three groups of patients were investigated. RESULTS: Comorbidity factors like diabetes and hemodialysis were associated with the risk of infection in cancer patients before the vaccination (p<0.05). In contrast to breast cancer, papillary thyroid cancer was more prevalent in the infected patients pre- and post-vaccination (p<0.05). Pre-vaccination infected group had earlier cancer stages compared with the control group (p = 0.01). On the other hand, combined therapy was less commonly administrated to the infected groups versus the control group (p<0.05). Neutrophil to lymphocyte ratio was lower in the post-vaccination infected group compared to the control group (p = 0.01). CONCLUSION: Collectively, this is the first study from KSA to report potential risk factors of SARS-CoV-2 infection in cancer patients pre- and post-vaccination. Further investigations on these risk factors in a larger cohort are worthwhile to draw a definitive conclusion about their roles in predisposing cancer patients to the infection.

Molecular Dynamics Simulations to Decipher the Role of Phosphorylation of SARS-CoV-2 Nonstructural Proteins (nsps) in Viral Replication.

Protein phosphorylation is a post-translational modification that enables various cellular activities and plays essential roles in protein interactions. Phosphorylation is an important process for the replication of Severe Acute Respiratory Syndrome Coronavirus 2 (SARS-CoV-2). To shed more light on the effects of phosphorylation, we used an ensemble of neural networks to predict potential kinases that might phosphorylate SARS-CoV-2 nonstructural proteins (nsps) and molecular dynamics (MD) simulations to investigate the effects of phosphorylation on nsps structure, which could be a potential inhibitory target to attenuate viral replication. Eight target candidate sites were found as top-ranked phosphorylation sites of SARS-CoV-2. During the process of molecular dynamics (MD) simulation, the root-mean-square deviation (RMSD) analysis was used to measure conformational changes in each nsps. Root-mean-square fluctuation (RMSF) was employed to measure the fluctuation in each residue of 36 systems considered, allowing us to evaluate the most flexible regions. These analysis shows that there are significant structural deviations in the residues namely nsp1 THR 72, nsp2 THR 73, nsp3 SER 64, nsp4 SER 81, nsp4 SER 455, nsp5 SER284, nsp6 THR 238, and nsp16 SER 132. The identified list of residues suggests how phosphorylation affects SARS-CoV-2 nsps function and stability. This research also suggests that kinase inhibitors could be a possible component for evaluating drug binding studies, which are crucial in therapeutic discovery research.

Active site prediction of phosphorylated SARS-CoV-2 N-Protein using molecular simulation.

The Severe Acute Respiratory Syndrome Coronavirus 2 (SARS-CoV-2) nucleocapsid protein (N-protein) is responsible for viral replication by assisting in viral RNA synthesis and attaching the viral genome to the replicase-transcriptase complex (RTC). Numerous studies suggested the N-protein as a drug target. However, the specific N-protein active sites for SARS-CoV-2 drug treatments are yet to be discovered. The purpose of this study was to determine active sites of the SARS-CoV-2 N-protein by identifying torsion angle classifiers for N-protein structural changes that correlated with the respective angle differences between the active and inactive N-protein. In the study, classifiers with a minimum accuracy of 80% determined from molecular simulation data were analyzed by Principal Component Analysis and cross-validated by Logistic Regression, Support Vector Machine, and Random Forest Classification. The ability of torsion angles ψ252 and φ375 to differentiate between phosphorylated and unphosphorylated structures suggested that residues 252 and 375 in the RNA binding domain might be important in N-protein activation. Furthermore, the φ and ψ angles of residue S189 correlated to a 90.7% structural determination accuracy. The key residues involved in the structural changes identified here might suggest possible important functional sites on the N-protein that could be the focus of further study to understand their potential as drug targets.

Peripapillary atrophy classification using CNN deep learning for glaucoma screening.

Glaucoma is the second leading cause of blindness worldwide, and peripapillary atrophy (PPA) is a morphological symptom associated with it. Therefore, it is necessary to clinically detect PPA for glaucoma diagnosis. This study was aimed at developing a detection method for PPA using fundus images with deep learning algorithms to be used by ophthalmologists or optometrists for screening purposes. The model was developed based on localization for the region of interest (ROI) using a mask region-based convolutional neural networks R-CNN and a classification network for the presence of PPA using CNN deep learning algorithms. A total of 2,472 images, obtained from five public sources and one Saudi-based resource (King Abdullah International Medical Research Center in Riyadh, Saudi Arabia), were used to train and test the model. First the images from public sources were analyzed, followed by those from local sources, and finally, images from both sources were analyzed together. In testing the classification model, the area under the curve's (AUC) scores of 0.83, 0.89, and 0.87 were obtained for the local, public, and combined sets, respectively. The developed model will assist in diagnosing glaucoma in screening programs; however, more research is needed on segmenting the PPA boundaries for more detailed PPA detection, which can be combined with optic disc and cup boundaries to calculate the cup-to-disc ratio.

The variant artificial intelligence easy scoring (VARIES) system.

PURPOSE: Medical artificial intelligence (MAI) is artificial intelligence (AI) applied to the healthcare field. AI can be applied to many different aspects of genetics, such as variant classification. With little or no prior experience in AI coding, we share our experience with variant classification using the Variant Artificial Intelligence Easy Scoring (VARIES), an open-access platform, and the Automatic Machine Learning (AutoML) of the Google Cloud Platform. METHODS: We investigated exome sequencing data from a sample of 1410 individuals. The majority (80%) were used for training and 20% for testing. The user-friendly Google Cloud Platform was used to create the VARIES model, and the TRIPOD checklist to develop and validate the prediction model for the development of the VARIES system. RESULTS: The learning rate of the training dataset reached optimal results at an early stage of iteration, with a loss value near zero in approximately 4 min. For the testing dataset, the results for F1 (micro average) was 0.64, F1 (macro average) 0.34, micro-average area under the curve AUC (one-over-rest) 0.81 and the macro-average AUC (one-over-rest) 0.73. The overall performance characteristics of the VARIES model suggest the classifier has a high predictive ability. CONCLUSION: We present a systematic guideline to create a genomic AI prediction tool with high predictive power, using a graphical user interface provided by Google Cloud Platform, with no prior experience in creating the software programs required.

Haematological and radiological-based prognostic markers of COVID-19.

BACKGROUND: Acute Respiratory Syndrome Coronavirus 2 (SARS-CoV-2) has emerged in 2019 and caused a global pandemic in 2020, manifesting in the coronavirus disease 2019 (COVID-19). The majority of patients exhibit a mild form of the disease with no major complications; however, moderate to severe and fatal cases are of public health concerns. Predicting the potential prognosis of COVID-19 could assist healthcare workers in managing cases and controlling the pandemic in an effective way. Therefore, the objectives of the study were to search for biomarkers associated with COVID-19 mortality and predictors of the overall survival (OS). METHODS: Here, clinical data of 6026 adult COVID-19 patients admitted to two large centers in Saudi Arabia (Riyadh and Hafar Al-Batin cities) between April and June 2020 were retrospectively analysed. RESULTS: More than 23% of the study subjects with available data have died, enabling the prediction of mortality in our cohort. Markers that were significantly associated with mortality in this study were older age, increased d-dimer in the blood, higher counts of WBCs, higher percentage of neutrophil, and a higher chest X-ray (CXR) score. The CXR scores were also positively associated with age, d-dimer, WBC count, and percentage of neutrophil. This supports the utility of CXR scores in the absence of blood testing. Predicting mortality based on Ct values of RT-PCR was not successful, necessitating a more quantitative RT-PCR to determine virus quantity in samples. Our work has also identified age, d-dimer concentration, leukocyte parameters and CXR score to be prognostic markers of the OS of COVID-19 patients. CONCLUSION: Overall, this retrospective study on hospitalised cohort of COVID-19 patients presents that age, haematological, and radiological data at the time of diagnosis are of value and could be used to guide better clinical management of COVID-19 patients.

Early Prediction of COVID-19 Ventilation Requirement and Mortality from Routinely Collected Baseline Chest Radiographs, Laboratory, and Clinical Data with Machine Learning.

BACKGROUND: Coronavirus disease 2019 (COVID-19), caused by severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2), emerged in Wuhan, China, in late 2019 and created a global pandemic that overwhelmed healthcare systems. COVID-19, as of July 3, 2021, yielded 182 million confirmed cases and 3.9 million deaths globally according to the World Health Organization. Several patients who were initially diagnosed with mild or moderate COVID-19 later deteriorated and were reclassified to severe disease type. OBJECTIVE: The aim is to create a predictive model for COVID-19 ventilatory support and mortality early on from baseline (at the time of diagnosis) and routinely collected data of each patient (CXR, CBC, demographics, and patient history). METHODS: Four common machine learning algorithms, three data balancing techniques, and feature selection are used to build and validate predictive models for COVID-19 mechanical requirement and mortality. Baseline CXR, CBC, demographic, and clinical data were retrospectively collected from April 2, 2020, till June 18, 2020, for 5739 patients with confirmed PCR COVID-19 at King Abdulaziz Medical City in Riyadh. However, of those patients, only 1508 and 1513 have met the inclusion criteria for ventilatory support and mortalilty endpoints, respectively. RESULTS: In an independent test set, ventilation requirement predictive model with top 20 features selected with reliefF algorithm from baseline radiological, laboratory, and clinical data using support vector machines and random undersampling technique attained an AUC of 0.87 and a balanced accuracy of 0.81. For mortality endpoint, the top model yielded an AUC of 0.83 and a balanced accuracy of 0.80 using all features with balanced random forest. This indicates that with only routinely collected data our models can predict the outcome with good performance. The predictive ability of combined data consistently outperformed each data set individually for intubation and mortality. For the ventilator support, chest X-ray severity annotations alone performed better than comorbidity, complete blood count, age, or gender with an AUC of 0.85 and balanced accuracy of 0.79. For mortality, comorbidity alone achieved an AUC of 0.80 and a balanced accuracy of 0.72, which is higher than models that use either chest radiograph, laboratory, or demographic features only. CONCLUSION: The experimental results demonstrate the practicality of the proposed COVID-19 predictive tool for hospital resource planning and patients' prioritization in the current COVID-19 pandemic crisis.