Showing papers in "Diagnostics in 2023"
TL;DR: In this article , the authors show that using machine learning-based bioinformatics tools has improved the accuracy of variant and CNV calling for thalassemia detection, especially for CNV and the homologous HBA and HBG genes.
Abstract: Thalassemia is one of the most heterogeneous diseases, with more than a thousand mutation types recorded worldwide. Molecular diagnosis of thalassemia by conventional PCR-based DNA analysis is time- and resource-consuming owing to the phenotype variability, disease complexity, and molecular diagnostic test limitations. Moreover, genetic counseling must be backed-up by an extensive diagnosis of the thalassemia-causing phenotype and the possible genetic modifiers. Data coming from advanced molecular techniques such as targeted sequencing by next-generation sequencing (NGS) and third-generation sequencing (TGS) are more appropriate and valuable for DNA analysis of thalassemia. While NGS is superior at variant calling to TGS thanks to its lower error rates, the longer reads nature of the TGS permits haplotype-phasing that is superior for variant discovery on the homologous genes and CNV calling. The emergence of many cutting-edge machine learning-based bioinformatics tools has improved the accuracy of variant and CNV calling. Constant improvement of these sequencing and bioinformatics will enable precise thalassemia detections, especially for the CNV and the homologous HBA and HBG genes. In conclusion, laboratory transiting from conventional DNA analysis to NGS or TGS and following the guidelines towards a single assay will contribute to a better diagnostics approach of thalassemia.
9 citations
TL;DR: In this paper , the authors systematically reviewed recent studies that used AI for mpox-related research and selected 34 studies with the following subject categories: diagnostic testing of MPox, epidemiological modeling of mpox infection spread, drug and vaccine discovery, and media risk management.
Abstract: Monkeypox or Mpox is an infectious virus predominantly found in Africa. It has spread to many countries since its latest outbreak. Symptoms such as headaches, chills, and fever are observed in humans. Lumps and rashes also appear on the skin (similar to smallpox, measles, and chickenpox). Many artificial intelligence (AI) models have been developed for accurate and early diagnosis. In this work, we systematically reviewed recent studies that used AI for mpox-related research. After a literature search, 34 studies fulfilling prespecified criteria were selected with the following subject categories: diagnostic testing of mpox, epidemiological modeling of mpox infection spread, drug and vaccine discovery, and media risk management. In the beginning, mpox detection using AI and various modalities was described. Other applications of ML and DL in mitigating mpox were categorized later. The various machine and deep learning algorithms used in the studies and their performance were discussed. We believe that a state-of-the-art review will be a valuable resource for researchers and data scientists in developing measures to counter the mpox virus and its spread.
9 citations
TL;DR: Wang et al. as mentioned in this paper presented an effective COVID-19 detection and classification approach using the Shufflenet CNN by employing three types of images, i.e., chest radiograph, CT-scan, and ECG-trace images.
Abstract: Early and precise COVID-19 identification and analysis are pivotal in reducing the spread of COVID-19. Medical imaging techniques, such as chest X-ray or chest radiographs, computed tomography (CT) scan, and electrocardiogram (ECG) trace images are the most widely known for early discovery and analysis of the coronavirus disease (COVID-19). Deep learning (DL) frameworks for identifying COVID-19 positive patients in the literature are limited to one data format, either ECG or chest radiograph images. Moreover, using several data types to recover abnormal patterns caused by COVID-19 could potentially provide more information and restrict the spread of the virus. This study presents an effective COVID-19 detection and classification approach using the Shufflenet CNN by employing three types of images, i.e., chest radiograph, CT-scan, and ECG-trace images. For this purpose, we performed extensive classification experiments with the proposed approach using each type of image. With the chest radiograph dataset, we performed three classification experiments at different levels of granularity, i.e., binary, three-class, and four-class classifications. In addition, we performed a binary classification experiment with the proposed approach by classifying CT-scan images into COVID-positive and normal. Finally, utilizing the ECG-trace images, we conducted three experiments at different levels of granularity, i.e., binary, three-class, and five-class classifications. We evaluated the proposed approach with the baseline COVID-19 Radiography Database, SARS-CoV-2 CT-scan, and ECG images dataset of cardiac and COVID-19 patients. The average accuracy of 99.98% for COVID-19 detection in the three-class classification scheme using chest radiographs, optimal accuracy of 100% for COVID-19 detection using CT scans, and average accuracy of 99.37% for five-class classification scheme using ECG trace images have proved the efficacy of our proposed method over the contemporary methods. The optimal accuracy of 100% for COVID-19 detection using CT scans and the accuracy gain of 1.54% (in the case of five-class classification using ECG trace images) from the previous approach, which utilized ECG images for the first time, has a major contribution to improving the COVID-19 prediction rate in early stages. Experimental findings demonstrate that the proposed framework outperforms contemporary models. For example, the proposed approach outperforms state-of-the-art DL approaches, such as Squeezenet, Alexnet, and Darknet19, by achieving the accuracy of 99.98 (proposed method), 98.29, 98.50, and 99.67, respectively.
7 citations
TL;DR: In this article , a two-dimensional convolutional neural network (CNN) consisting of four CNN layers was applied for the detection of monkeypox and chickenpox using digital skin images of patients with suspected monkeypox.
Abstract: Monkeypox is a zoonotic viral disease caused by the monkeypox virus. After its recent outbreak, it has become clear that a rapid, accurate, and reliable diagnosis may help reduce the risk of a future outbreak. The presence of skin lesions is one of the most prominent symptoms of the disease. However, this symptom is also peculiar to chickenpox. The resemblance in skin lesions in the human subject may disrupt effective diagnosis and, as a result, lead to misdiagnosis. Such misdiagnosis can lead to the further spread of the disease as it is a communicable disease and can eventually result in an outbreak. As deep learning (DL) algorithms have recently been regarded as a promising technique in medical fields, we have been attempting to integrate a well-trained DL algorithm to assist in the early detection and classification of skin lesions in human subjects. This study used two open-sourced digital skin images for monkeypox and chickenpox. A two-dimensional convolutional neural network (CNN) consisting of four convolutional layers was applied. Afterward, three MaxPooling layers were used after the second, third, and fourth convolutional layers. Finally, we evaluated the performance of our proposed model with state-of-the-art deep-learning models for skin lesions detection. Our proposed CNN model outperformed all DL models with a test accuracy of 99.60%. In addition, a weighted average precision, recall, F1 score of 99.00% was recorded. Subsequently, Alex Net outperformed other pre-trained models with an accuracy of 98.00%. The VGGNet consisting of VGG16 and VGG19 performed least well with an accuracy of 80.00%. Due to the uniqueness of the proposed model and image augmentation techniques applied, the proposed CNN model is generalized and avoids over-fitting. This model would be helpful for the rapid and accurate detection of monkeypox using digital skin images of patients with suspected monkeypox.
7 citations
TL;DR: In this article , the Segment Anything Model (SAM) was examined on medical images and reported both quantitative and qualitative zero-shot segmentation results on nine medical image segmentation benchmarks, covering various imaging modalities, such as optical coherence tomography (OCT), magnetic resonance imaging (MRI), and computed tomography, as well as different applications including dermatology, ophthalmology, and radiology.
Abstract: Medical image analysis plays an important role in clinical diagnosis. In this paper, we examine the recent Segment Anything Model (SAM) on medical images, and report both quantitative and qualitative zero-shot segmentation results on nine medical image segmentation benchmarks, covering various imaging modalities, such as optical coherence tomography (OCT), magnetic resonance imaging (MRI), and computed tomography (CT), as well as different applications including dermatology, ophthalmology, and radiology. Those benchmarks are representative and commonly used in model development. Our experimental results indicate that while SAM presents remarkable segmentation performance on images from the general domain, its zero-shot segmentation ability remains restricted for out-of-distribution images, e.g., medical images. In addition, SAM exhibits inconsistent zero-shot segmentation performance across different unseen medical domains. For certain structured targets, e.g., blood vessels, the zero-shot segmentation of SAM completely failed. In contrast, a simple fine-tuning of it with a small amount of data could lead to remarkable improvement of the segmentation quality, showing the great potential and feasibility of using fine-tuned SAM to achieve accurate medical image segmentation for a precision diagnostics. Our study indicates the versatility of generalist vision foundation models on medical imaging, and their great potential to achieve desired performance through fine-turning and eventually address the challenges associated with accessing large and diverse medical datasets in support of clinical diagnostics.
7 citations
TL;DR: In this paper , a machine learning algorithm model was proposed for early imaging prediction of idiopathic pulmonary fibrosis (IPF) in respiratory diseases, which can effectively prolong the life of patients.
Abstract: Machine Learning (ML) is an algorithm based on big data, which learns patterns from the previously observed data through classifying, predicting, and optimizing to accomplish specific tasks. In recent years, there has been rapid development in the field of ML in medicine, including lung imaging analysis, intensive medical monitoring, mechanical ventilation, and there is need for intubation etiology prediction evaluation, pulmonary function evaluation and prediction, obstructive sleep apnea, such as biological information monitoring and so on. ML can have good performance and is a great potential tool, especially in the imaging diagnosis of interstitial lung disease. Idiopathic pulmonary fibrosis (IPF) is a major problem in the treatment of respiratory diseases, due to the abnormal proliferation of fibroblasts, leading to lung tissue destruction. The diagnosis mainly depends on the early detection of imaging and early treatment, which can effectively prolong the life of patients. If the computer can be used to assist the examination results related to the effects of fibrosis, a timely diagnosis of such diseases will be of great value to both doctors and patients. We also previously proposed a machine learning algorithm model that can play a good clinical guiding role in early imaging prediction of idiopathic pulmonary fibrosis. At present, AI and machine learning have great potential and ability to transform many aspects of respiratory medicine and are the focus and hotspot of research. AI needs to become an invisible, seamless, and impartial auxiliary tool to help patients and doctors make better decisions in an efficient, effective, and acceptable way. The purpose of this paper is to review the current application of machine learning in various aspects of respiratory diseases, with the hope to provide some help and guidance for clinicians when applying algorithm models.
6 citations
TL;DR: GabROP as mentioned in this paper is an automated CAD tool based on Gabor wavelets and multiple deep learning (DL) models, which can demonstrate significant texture information that can help artificial intelligence (AI) based models to improve diagnostic accuracy.
Abstract: One of the most serious and dangerous ocular problems in premature infants is retinopathy of prematurity (ROP), a proliferative vascular disease. Ophthalmologists can use automatic computer-assisted diagnostic (CAD) tools to help them make a safe, accurate, and low-cost diagnosis of ROP. All previous CAD tools for ROP diagnosis use the original fundus images. Unfortunately, learning the discriminative representation from ROP-related fundus images is difficult. Textural analysis techniques, such as Gabor wavelets (GW), can demonstrate significant texture information that can help artificial intelligence (AI) based models to improve diagnostic accuracy. In this paper, an effective and automated CAD tool, namely GabROP, based on GW and multiple deep learning (DL) models is proposed. Initially, GabROP analyzes fundus images using GW and generates several sets of GW images. Next, these sets of images are used to train three convolutional neural networks (CNNs) models independently. Additionally, the actual fundus pictures are used to build these networks. Using the discrete wavelet transform (DWT), texture features retrieved from every CNN trained with various sets of GW images are combined to create a textural-spectral-temporal demonstration. Afterward, for each CNN, these features are concatenated with spatial deep features obtained from the original fundus images. Finally, the previous concatenated features of all three CNN are incorporated using the discrete cosine transform (DCT) to lessen the size of features caused by the fusion process. The outcomes of GabROP show that it is accurate and efficient for ophthalmologists. Additionally, the effectiveness of GabROP is compared to recently developed ROP diagnostic techniques. Due to GabROP’s superior performance compared to competing tools, ophthalmologists may be able to identify ROP more reliably and precisely, which could result in a reduction in diagnostic effort and examination time.
6 citations
TL;DR: In this paper , the authors proposed three different approaches for early identification and diagnosis of pneumonia and tuberculosis using X-ray images: VGG16 + support vector machine (SVM), ResNet18 + SVM, and ANN based on features extracted by local binary pattern (LBP), DWT and GLCM.
Abstract: An infectious disease called tuberculosis (TB) exhibits pneumonia-like symptoms and traits. One of the most important methods for identifying and diagnosing pneumonia and tuberculosis is X-ray imaging. However, early discrimination is difficult for radiologists and doctors because of the similarities between pneumonia and tuberculosis. As a result, patients do not receive the proper care, which in turn does not prevent the disease from spreading. The goal of this study is to extract hybrid features using a variety of techniques in order to achieve promising results in differentiating between pneumonia and tuberculosis. In this study, several approaches for early identification and distinguishing tuberculosis from pneumonia were suggested. The first proposed system for differentiating between pneumonia and tuberculosis uses hybrid techniques, VGG16 + support vector machine (SVM) and ResNet18 + SVM. The second proposed system for distinguishing between pneumonia and tuberculosis uses an artificial neural network (ANN) based on integrating features of VGG16 and ResNet18, before and after reducing the high dimensions using the principal component analysis (PCA) method. The third proposed system for distinguishing between pneumonia and tuberculosis uses ANN based on integrating features of VGG16 and ResNet18 separately with handcrafted features extracted by local binary pattern (LBP), discrete wavelet transform (DWT) and gray level co-occurrence matrix (GLCM) algorithms. All the proposed systems have achieved superior results in the early differentiation between pneumonia and tuberculosis. An ANN based on the features of VGG16 with LBP, DWT and GLCM (LDG) reached an accuracy of 99.6%, sensitivity of 99.17%, specificity of 99.42%, precision of 99.63%, and an AUC of 99.58%.
6 citations
TL;DR: In this article , the authors proposed a hybrid system based on the advantages of fused CNN models, which achieved promising results for diagnosing dermatoscopic images of the ISIC 2019 data set and distinguishing skin cancer from other skin lesions.
Abstract: Melanoma is one of the deadliest types of skin cancer that leads to death if not diagnosed early. Many skin lesions are similar in the early stages, which causes an inaccurate diagnosis. Accurate diagnosis of the types of skin lesions helps dermatologists save patients’ lives. In this paper, we propose hybrid systems based on the advantages of fused CNN models. CNN models receive dermoscopy images of the ISIC 2019 dataset after segmenting the area of lesions and isolating them from healthy skin through the Geometric Active Contour (GAC) algorithm. Artificial neural network (ANN) and Random Forest (Rf) receive fused CNN features and classify them with high accuracy. The first methodology involved analyzing the area of skin lesions and diagnosing their type early using the hybrid models CNN-ANN and CNN-RF. CNN models (AlexNet, GoogLeNet and VGG16) receive lesions area only and produce high depth feature maps. Thus, the deep feature maps were reduced by the PCA and then classified by ANN and RF networks. The second methodology involved analyzing the area of skin lesions and diagnosing their type early using the hybrid CNN-ANN and CNN-RF models based on the features of the fused CNN models. It is worth noting that the features of the CNN models were serially integrated after reducing their high dimensions by Principal Component Analysis (PCA). Hybrid models based on fused CNN features achieved promising results for diagnosing dermatoscopic images of the ISIC 2019 data set and distinguishing skin cancer from other skin lesions. The AlexNet-GoogLeNet-VGG16-ANN hybrid model achieved an AUC of 94.41%, sensitivity of 88.90%, accuracy of 96.10%, precision of 88.69%, and specificity of 99.44%.
6 citations
TL;DR: In this paper , a systematic literature review on the deep learning-based methods for breast cancer detection is presented, which can guide practitioners and researchers in understanding the challenges and new trends in the field.
Abstract: Breast cancer is one of the precarious conditions that affect women, and a substantive cure has not yet been discovered for it. With the advent of Artificial intelligence (AI), recently, deep learning techniques have been used effectively in breast cancer detection, facilitating early diagnosis and therefore increasing the chances of patients’ survival. Compared to classical machine learning techniques, deep learning requires less human intervention for similar feature extraction. This study presents a systematic literature review on the deep learning-based methods for breast cancer detection that can guide practitioners and researchers in understanding the challenges and new trends in the field. Particularly, different deep learning-based methods for breast cancer detection are investigated, focusing on the genomics and histopathological imaging data. The study specifically adopts the Preferred Reporting Items for Systematic Reviews and Meta-Analyses (PRISMA), which offer a detailed analysis and synthesis of the published articles. Several studies were searched and gathered, and after the eligibility screening and quality evaluation, 98 articles were identified. The results of the review indicated that the Convolutional Neural Network (CNN) is the most accurate and extensively used model for breast cancer detection, and the accuracy metrics are the most popular method used for performance evaluation. Moreover, datasets utilized for breast cancer detection and the evaluation metrics are also studied. Finally, the challenges and future research direction in breast cancer detection based on deep learning models are also investigated to help researchers and practitioners acquire in-depth knowledge of and insight into the area.
6 citations
TL;DR: In this article, a deep learning model using Deep convolutional autoencoder-Bidirectional Long Short Memory for Epileptic Seizure Detection (DCAE-ESD-Bi-LSTM) for automatic detection of seizures using EEG data.
Abstract: Detecting brain disorders using deep learning methods has received much hype during the last few years. Increased depth leads to more computational efficiency, accuracy, and optimization and less loss. Epilepsy is one of the most common chronic neurological disorders characterized by repeated seizures. We have developed a deep learning model using Deep convolutional Autoencoder—Bidirectional Long Short Memory for Epileptic Seizure Detection (DCAE-ESD-Bi-LSTM) for automatic detection of seizures using EEG data. The significant feature of our model is that it has contributed to the accurate and optimized diagnosis of epilepsy in ideal and real-life situations. The results on the benchmark (CHB-MIT) dataset and the dataset collected by the authors show the relevance of the proposed approach over the baseline deep learning techniques by achieving an accuracy of 99.8%, classification accuracy of 99.7%, sensitivity of 99.8%, specificity and precision of 99.9% and F1 score of 99.6%. Our approach can contribute to the accurate and optimized detection of seizures while scaling the design rules and increasing performance without changing the network’s depth.
TL;DR: In this article , the authors proposed a deep learning approach to the detection of chest abnormalities with the X-ray modality using the EfficientDet (CXray-EffDet) model.
Abstract: The competence of machine learning approaches to carry out clinical expertise tasks has recently gained a lot of attention, particularly in the field of medical-imaging examination. Among the most frequently used clinical-imaging modalities in the healthcare profession is chest radiography, which calls for prompt reporting of the existence of potential anomalies and illness diagnostics in images. Automated frameworks for the recognition of chest abnormalities employing X-rays are being introduced in health departments. However, the reliable detection and classification of particular illnesses in chest X-ray samples is still a complicated issue because of the complex structure of radiographs, e.g., the large exposure dynamic range. Moreover, the incidence of various image artifacts and extensive inter- and intra-category resemblances further increases the difficulty of chest disease recognition procedures. The aim of this study was to resolve these existing problems. We propose a deep learning (DL) approach to the detection of chest abnormalities with the X-ray modality using the EfficientDet (CXray-EffDet) model. More clearly, we employed the EfficientNet-B0-based EfficientDet-D0 model to compute a reliable set of sample features and accomplish the detection and classification task by categorizing eight categories of chest abnormalities using X-ray images. The effective feature computation power of the CXray-EffDet model enhances the power of chest abnormality recognition due to its high recall rate, and it presents a lightweight and computationally robust approach. A large test of the model employing a standard database from the National Institutes of Health (NIH) was conducted to demonstrate the chest disease localization and categorization performance of the CXray-EffDet model. We attained an AUC score of 0.9080, along with an IOU of 0.834, which clearly determines the competency of the introduced model.
TL;DR: In this paper , the authors proposed a new automated computerized framework for breast cancer classification, which improves the contrast using a novel enhancement technique called haze-reduced local-global, and the enhanced images are later employed for the dataset augmentation.
Abstract: One of the most frequent cancers in women is breast cancer, and in the year 2022, approximately 287,850 new cases have been diagnosed. From them, 43,250 women died from this cancer. An early diagnosis of this cancer can help to overcome the mortality rate. However, the manual diagnosis of this cancer using mammogram images is not an easy process and always requires an expert person. Several AI-based techniques have been suggested in the literature. However, still, they are facing several challenges, such as similarities between cancer and non-cancer regions, irrelevant feature extraction, and weak training models. In this work, we proposed a new automated computerized framework for breast cancer classification. The proposed framework improves the contrast using a novel enhancement technique called haze-reduced local-global. The enhanced images are later employed for the dataset augmentation. This step aimed at increasing the diversity of the dataset and improving the training capability of the selected deep learning model. After that, a pre-trained model named EfficientNet-b0 was employed and fine-tuned to add a few new layers. The fine-tuned model was trained separately on original and enhanced images using deep transfer learning concepts with static hyperparameters’ initialization. Deep features were extracted from the average pooling layer in the next step and fused using a new serial-based approach. The fused features were later optimized using a feature selection algorithm known as Equilibrium-Jaya controlled Regula Falsi. The Regula Falsi was employed as a termination function in this algorithm. The selected features were finally classified using several machine learning classifiers. The experimental process was conducted on two publicly available datasets—CBIS-DDSM and INbreast. For these datasets, the achieved average accuracy is 95.4% and 99.7%. A comparison with state-of-the-art (SOTA) technology shows that the obtained proposed framework improved the accuracy. Moreover, the confidence interval-based analysis shows consistent results of the proposed framework.
TL;DR: Zhang et al. as discussed by the authors proposed a new intelligent auxiliary framework for the medical image segmentation of bone malignant tumor lesions, which consists of a supervised edge-attention guidance segmentation network (SEAGNET).
Abstract: Bone malignant tumors are metastatic and aggressive, with poor treatment outcomes and prognosis. Rapid and accurate diagnosis is crucial for limb salvage and increasing the survival rate. There is a lack of research on deep learning to segment bone malignant tumor lesions in medical images with complex backgrounds and blurred boundaries. Therefore, we propose a new intelligent auxiliary framework for the medical image segmentation of bone malignant tumor lesions, which consists of a supervised edge-attention guidance segmentation network (SEAGNET). We design a boundary key points selection module to supervise the learning of edge attention in the model to retain fine-grained edge feature information. We precisely locate malignant tumors by instance segmentation networks while extracting feature maps of tumor lesions in medical images. The rich contextual-dependent information in the feature map is captured by mixed attention to better understand the uncertainty and ambiguity of the boundary, and edge attention learning is used to guide the segmentation network to focus on the fuzzy boundary of the tumor region. We implement extensive experiments on real-world medical data to validate our model. It validates the superiority of our method over the latest segmentation methods, achieving the best performance in terms of the Dice similarity coefficient (0.967), precision (0.968), and accuracy (0.996). The results prove the important contribution of the framework in assisting doctors to improve the accuracy of diagnosis and clinical efficiency.
TL;DR: In this paper , the use of Electrochemotherapy (ECT) in local treatment of primary and secondary liver tumours located at different sites and with different histologies was analyzed.
Abstract: The aim of the study was to analyse papers describing the use of Electrochemotherapy (ECT) in local treatment of primary and secondary liver tumours located at different sites and with different histologies. Other Local Ablative Therapies (LAT) are also discussed. Analyses of these papers demonstrate that ECT use is safe and effective in lesions of large size, independently of the histology of the treated lesions. ECT performed better than other thermal ablation techniques in lesions > 6 cm in size and can be safely used to treat lesions distant, close, or adjacent to vital structures. ECT spares vessel and bile ducts, is repeatable, and can be performed between chemotherapeutic cycles. ECT can fill the gap in local ablative therapies due to being lesions too large or localized in highly challenging anatomical sites.
TL;DR: A review of the history and science of the HPV vaccine, its efficacy, effectiveness and safety, and some of the considerations and challenges posed to the achievement of global HPV vaccination coverage and the consequent elimination of cervical cancer is presented in this article .
Abstract: Cervical cancer still poses a significant global challenge. Developed countries have mitigated this challenge by the introduction of structured screening programmes and, more recently, the HPV vaccine. Countries that have successfully introduced national HPV vaccination programmes are on course for cervical cancer elimination in a few decades. In developing countries that lack structured screening and HPV vaccination programmes, cervical cancer remains a major cause of morbidity and mortality. The HPV vaccine is key to addressing the disproportionate distribution of cervical cancer incidence, with much to be gained from increasing vaccine coverage and uptake globally. This review covers the history and science of the HPV vaccine, its efficacy, effectiveness and safety, and some of the considerations and challenges posed to the achievement of global HPV vaccination coverage and the consequent elimination of cervical cancer.
TL;DR: In this paper , the authors evaluated the correlation between body mass index (BMI), heart weight, coronary and valvular atherosclerosis, left ventricular morphology, and the thickness of the epicardial adipose tissue (EAT) in sudden cardiac deaths, establishing an increased thickness of EAT as a novel risk factor.
Abstract: Background: In sudden cardiac deaths (SCD), visceral adipose tissue has begun to manifest interest as a standalone cardiovascular risk factor. Studies have shown that epicardial adipose tissue can be seen as a viable marker of coronary atherosclerosis. This study aimed to evaluate, from a forensic perspective, the correlation between body mass index (BMI), heart weight, coronary and valvular atherosclerosis, left ventricular morphology, and the thickness of the epicardial adipose tissue (EAT) in sudden cardiac deaths, establishing an increased thickness of EAT as a novel risk factor. Methods: This is a retrospective case–control descriptive study that included 80 deaths that were autopsied, 40 sudden cardiac deaths, and 40 control cases who hanged themselves and had unknown pathologies prior to their death. In all the autopsies performed, the thickness of the epicardial adipose tissue was measured in two regions of the left coronary artery, and the left ventricular morphology, macro/microscopically quantified coronary and valvular atherosclerosis, and weight of the heart were evaluated. Results: This study revealed a higher age in the SCD group (58.82 ± 9.67 vs. 53.4 ± 13.00; p = 0.03), as well as a higher incidence in females (p = 0.03). In terms of heart and coronary artery characteristics, there were higher values of BMI (p = 0.0009), heart weight (p < 0.0001), EAT of the left circumflex artery (LCx) (p < 0.0001), and EAT of the left anterior descending artery (LAD) (p < 0.0001). In the multivariate analysis, a high baseline value of BMI (OR: 4.05; p = 0.004), heart weight (OR: 5.47; p < 0.001), EAT LCx (OR: 23.72; p < 0.001), and EAT LAD (OR: 21.07; p < 0.001) were strong independent predictors of SCD. Moreover, age over 55 years (OR: 2.53; p = 0.045), type Vb plaque (OR: 17.19; p < 0.001), mild valvular atherosclerosis (OR: 4.88; p = 0.002), and moderate left ventricle dilatation (OR: 16.71; p = 0.008) all act as predictors of SCD. Conclusions: The data of this research revealed that higher baseline values of BMI, heart weight, EAT LCx, and EAT LAD highly predict SCD. Furthermore, age above 55 years, type Vb plaque, mild valvular atherosclerosis, and left ventricle dilatation were all risk factors for SCD.
TL;DR: In this article , the authors used confocal microscopy and immunoblotting to characterize the pseudo-DFS immunofluorescence pattern and found that the target antigen associated with this pattern partially co-localized with DFS70/LEDGFp75 and its interacting partners H3K36me2, an active chromatin marker, and MLL, a transcription factor.
Abstract: The monospecific dense fine speckled (DFS) immunofluorescence assay (IFA) pattern is considered a potential marker to aid in exclusion of antinuclear antibody (ANA)-associated rheumatic diseases (AARD). This pattern is typically produced by autoantibodies against transcription co-activator DFS70/LEDGFp75, which are frequently found in healthy individuals and patients with miscellaneous inflammatory conditions. In AARD patients, these antibodies usually co-exist with disease-associated ANAs. Previous studies reported the occurrence of monospecific autoantibodies that generate a DFS-like or pseudo-DFS IFA pattern but do not react with DFS70/LEDGFp75. We characterized this pattern using confocal microscopy and immunoblotting. The target antigen associated with this pattern partially co-localized with DFS70/LEDGFp75 and its interacting partners H3K36me2, an active chromatin marker, and MLL, a transcription factor, in HEp-2 cells, suggesting a role in transcription. Immunoblotting did not reveal a common protein band immunoreactive with antibodies producing the pseudo-DFS pattern, suggesting they may recognize diverse proteins or conformational epitopes. Given the subjectivity of the HEp-2 IFA test, the awareness of pseudo-DFS autoantibodies reinforces recommendations for confirmatory testing when reporting patient antibodies producing a putative DFS pattern in a clinical setting. Future studies should focus on defining the potential diagnostic utility of the pseudo-DFS pattern and its associated antigen(s).
TL;DR: An overview of the applications of AI for chest X-rays in the emergency setting, emphasizing the detection and evaluation of pneumothorax, pneumonia, heart failure, and pleural effusion is provided in this article .
Abstract: Due to its widespread availability, low cost, feasibility at the patient’s bedside and accessibility even in low-resource settings, chest X-ray is one of the most requested examinations in radiology departments. Whilst it provides essential information on thoracic pathology, it can be difficult to interpret and is prone to diagnostic errors, particularly in the emergency setting. The increasing availability of large chest X-ray datasets has allowed the development of reliable Artificial Intelligence (AI) tools to help radiologists in everyday clinical practice. AI integration into the diagnostic workflow would benefit patients, radiologists, and healthcare systems in terms of improved and standardized reporting accuracy, quicker diagnosis, more efficient management, and appropriateness of the therapy. This review article aims to provide an overview of the applications of AI for chest X-rays in the emergency setting, emphasizing the detection and evaluation of pneumothorax, pneumonia, heart failure, and pleural effusion.
TL;DR: In this article , the authors present 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.
Abstract: 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.
TL;DR: The NavDx® blood test analyzes tumor tissue modified viral (TTMV)-HPV DNA to provide a reliable means of detecting and monitoring HPV-driven cancers as mentioned in this paper .
Abstract: The NavDx® blood test analyzes tumor tissue modified viral (TTMV)-HPV DNA to provide a reliable means of detecting and monitoring HPV-driven cancers. The test has been clinically validated in a large number of independent studies and has been integrated into clinical practice by over 1000 healthcare providers at over 400 medical sites in the US. This Clinical Laboratory Improvement Amendments (CLIA), high complexity laboratory developed test, has also been accredited by the College of American Pathologists (CAP) and the New York State Department of Health. Here, we report a detailed analytical validation of the NavDx assay, including sample stability, specificity as measured by limits of blank (LOBs), and sensitivity illustrated via limits of detection and quantitation (LODs and LOQs). LOBs were 0–0.32 copies/μL, LODs were 0–1.10 copies/μL, and LOQs were <1.20–4.11 copies/μL, demonstrating the high sensitivity and specificity of data provided by NavDx. In-depth evaluations including accuracy and intra- and inter-assay precision studies were shown to be well within acceptable ranges. Regression analysis revealed a high degree of correlation between expected and effective concentrations, demonstrating excellent linearity (R2 = 1) across a broad range of analyte concentrations. These results demonstrate that NavDx accurately and reproducibly detects circulating TTMV-HPV DNA, which has been shown to aid in the diagnosis and surveillance of HPV-driven cancers.
TL;DR: In this article , the impact of anemia on cognitive performances, mood, functional and nutritional status, and comorbidities in a population of subjects aged 65 years or older was evaluated.
Abstract: Background: The primary aim of this study was to evaluate the impact of anemia—according to the WHO criteria—on cognitive performances, mood, functional and nutritional status, and comorbidities in a population of subjects aged 65 years or older. The secondary aim of this study was to understand if different hemoglobin cut-off levels are associated with a variation of the mentioned domains’ impairment. Methods: We designed a cross-sectional study, including subjects aged 65 or more consecutively evaluated in an outpatient setting from July 2013 to December 2019. A sum of 1698 subjects met the inclusion criteria. They were evaluated with: MMSE and CDT (cognitive assessment), GDS (mood), BADL, IADL, PPT, and POMA (autonomies), MNA (nutritional status), and CIRS (comorbidities). Results: According to the WHO criteria, non-anemic patients reported significantly better performances than the anemics in BADL (p < 0.0001), IADL (p = 0.0007), PPT (p = 0.0278), POMA (p = 0.0235), MNA, CIRS TOT, CIRS ICC, and CIRS ISC (p < 0.0001). The same tendency has been found by considering the 12 g/dL- and the 13 g/dL-cut-off level in the whole population. The multivariate analysis showed that, considering the 12 g/dL-cut-off level, age (OR: 1.03, p = 0.0072), CIRS (OR: 1.08, p < 0.0001), and gender (OR: 0.57, p = 0.0007) were significant regressors of anemia, while considering the 13 g/dL-cut-off level, age (OR: 1.04, p = 0.0001), POMA (OR: 1.03, p = 0.0172), MNA (OR = 0.95, p = 0.0036), CIRS (OR: 1.17, p < 0.0001), ICC (OR = 0.83, p = 0.018), and gender (OR = 0.48, p < 0.0001) were significant regressors of anemia, while the other CGA variables were excluded by the model (p > 0.01). Conclusions: Our study showed that anemia negatively impact on geriatric people’s general status, regardless of which hemoglobin cut-off level is considered. It also highlighted that hemoglobin concentrations < 13 g/dL, regardless of gender, have an association with the impairment of the affective-functional-nutritional state as well as an increase in comorbidities; therefore, it should be pursuable to consider the elderly person “anemic” if Hb < 13 g/dL regardless of gender.
TL;DR: In this article , a non-invasive, non-contact, computer-vision-based method for diagnosis of MPX by analyzing skin lesion images that are more smart and secure compared to traditional methods of diagnosis.
Abstract: Monkeypox (MPX) is a disease caused by monkeypox virus (MPXV). It is a contagious disease and has associated symptoms of skin lesions, rashes, fever, and respiratory distress lymph swelling along with numerous neurological distresses. This can be a deadly disease, and the latest outbreak of it has shown its spread to Europe, Australia, the United States, and Africa. Typically, diagnosis of MPX is performed through PCR, by taking a sample of the skin lesion. This procedure is risky for medical staff, as during sample collection, transmission and testing, they can be exposed to MPXV, and this infectious disease can be transferred to medical staff. In the current era, cutting-edge technologies such as IoT and artificial intelligence (AI) have made the diagnostics process smart and secure. IoT devices such as wearables and sensors permit seamless data collection while AI techniques utilize the data in disease diagnosis. Keeping in view the importance of these cutting-edge technologies, this paper presents a non-invasive, non-contact, computer-vision-based method for diagnosis of MPX by analyzing skin lesion images that are more smart and secure compared to traditional methods of diagnosis. The proposed methodology employs deep learning techniques to classify skin lesions as MPXV positive or not. Two datasets, the Kaggle Monkeypox Skin Lesion Dataset (MSLD) and the Monkeypox Skin Image Dataset (MSID), are used for evaluating the proposed methodology. The results on multiple deep learning models were evaluated using sensitivity, specificity and balanced accuracy. The proposed method has yielded highly promising results, demonstrating its potential for wide-scale deployment in detecting monkeypox. This smart and cost-effective solution can be effectively utilized in underprivileged areas where laboratory infrastructure may be lacking.
TL;DR: In this article , a real-life study showed that LC-OCT can play an important role in helping the noninvasive diagnosis of malignant skin neoplasms and especially of basal cell carcinomas.
Abstract: Line-field confocal optical coherence tomography (LC-OCT) is a new, noninvasive imaging technique for the diagnosis of skin cancers. A total of 243 benign (54%) and malignant (46%) skin lesions were consecutively enrolled from 27 August 2020, to 6 October 2021 at the Dermatology Department of the University Hospital of Siena, Italy. Dermoscopic- and LC-OCT-based diagnoses were given by an expert dermatologist and compared with the ground truth. Considering all types of malignant skin tumours (79 basal cell carcinomas (BCCs), 22 squamous cell carcinomas, and 10 melanomas), a statistically significant increase (p = 0.013) in specificity was observed from dermoscopy (0.73, CI 0.64–0.81) to LC-OCT (0.87, CI 0.79–0.93) while sensitivity was the same with the two imaging techniques (0.95 CI 0.89–0.98 for dermoscopy and 0.95 CI 0.90–0.99 for LC-OCT). The increase in specificity was mainly driven by the ability of LC-OCT to differentiate BCCs from other diagnoses. In conclusion, our real-life study showed that LC-OCT can play an important role in helping the noninvasive diagnosis of malignant skin neoplasms and especially of BCCs. LC-OCT could be positioned after the dermoscopic examination, to spare useless biopsy of benign lesions without decreasing sensitivity.
TL;DR: Deep learning has been applied in OCT-A image analysis in recent years and achieved good performance for different tasks, such as image quality control, segmentation, and classification as mentioned in this paper .
Abstract: Optical coherence tomography angiography (OCT-A) provides depth-resolved visualization of the retinal microvasculature without intravenous dye injection. It facilitates investigations of various retinal vascular diseases and glaucoma by assessment of qualitative and quantitative microvascular changes in the different retinal layers and radial peripapillary layer non-invasively, individually, and efficiently. Deep learning (DL), a subset of artificial intelligence (AI) based on deep neural networks, has been applied in OCT-A image analysis in recent years and achieved good performance for different tasks, such as image quality control, segmentation, and classification. DL technologies have further facilitated the potential implementation of OCT-A in eye clinics in an automated and efficient manner and enhanced its clinical values for detecting and evaluating various vascular retinopathies. Nevertheless, the deployment of this combination in real-world clinics is still in the “proof-of-concept” stage due to several limitations, such as small training sample size, lack of standardized data preprocessing, insufficient testing in external datasets, and absence of standardized results interpretation. In this review, we introduce the existing applications of DL in OCT-A, summarize the potential challenges of the clinical deployment, and discuss future research directions.
TL;DR: In this paper , an enhanced chimpanzee optimization algorithm (EChOA) is used to select the features by minimizing the dimension of the retrieved features. And the softmax classifier is then used to perform the feature classification process.
Abstract: One of the top causes of mortality in people globally is a brain tumor. Today, biopsy is regarded as the cornerstone of cancer diagnosis. However, it faces difficulties, including low sensitivity, hazards during biopsy treatment, and a protracted waiting period for findings. In this context, developing non-invasive and computational methods for identifying and treating brain cancers is crucial. The classification of tumors obtained from an MRI is crucial for making a variety of medical diagnoses. However, MRI analysis typically requires much time. The primary challenge is that the tissues of the brain are comparable. Numerous scientists have created new techniques for identifying and categorizing cancers. However, due to their limitations, the majority of them eventually fail. In that context, this work presents a novel way of classifying multiple types of brain tumors. This work also introduces a segmentation algorithm known as Canny Mayfly. Enhanced chimpanzee optimization algorithm (EChOA) is used to select the features by minimizing the dimension of the retrieved features. ResNet-152 and the softmax classifier are then used to perform the feature classification process. Python is used to carry out the proposed method on the Figshare dataset. The accuracy, specificity, and sensitivity of the proposed cancer classification system are just a few of the characteristics that are used to evaluate its overall performance. According to the final evaluation results, our proposed strategy outperformed, with an accuracy of 98.85%.
TL;DR: In this article , a weighted average ensemble deep learning model is proposed for the classification of brain tumors, which can help increase the accuracy of classification by combining the strengths of multiple models and compensating for individual weaknesses.
Abstract: Brain tumor diagnosis at an early stage can improve the chances of successful treatment and better patient outcomes. In the biomedical industry, non-invasive diagnostic procedures, such as magnetic resonance imaging (MRI), can be used to diagnose brain tumors. Deep learning, a type of artificial intelligence, can analyze MRI images in a matter of seconds, reducing the time it takes for diagnosis and potentially improving patient outcomes. Furthermore, an ensemble model can help increase the accuracy of classification by combining the strengths of multiple models and compensating for their individual weaknesses. Therefore, in this research, a weighted average ensemble deep learning model is proposed for the classification of brain tumors. For the weighted ensemble classification model, three different feature spaces are taken from the transfer learning VGG19 model, Convolution Neural Network (CNN) model without augmentation, and CNN model with augmentation. These three feature spaces are ensembled with the best combination of weights, i.e., weight1, weight2, and weight3 by using grid search. The dataset used for simulation is taken from The Cancer Genome Atlas (TCGA), having a lower-grade glioma collection with 3929 MRI images of 110 patients. The ensemble model helps reduce overfitting by combining multiple models that have learned different aspects of the data. The proposed ensemble model outperforms the three individual models for detecting brain tumors in terms of accuracy, precision, and F1-score. Therefore, the proposed model can act as a second opinion tool for radiologists to diagnose the tumor from MRI images of the brain.
TL;DR: In this article , the authors conducted a scoping review with the primary objective of identifying the types, and examining the range, of available evidence of vertical transmission of SARS-CoV-2 from mother to newborn.
Abstract: Severe acute respiratory syndrome virus 2 (SARS-CoV-2), the virus that causes 2019 coronavirus disease (COVID-19), has been isolated from various tissues and body fluids, including the placenta, amniotic fluid, and umbilical cord of newborns. In the last few years, much scientific effort has been directed toward studying SARS-CoV-2, focusing on the different features of the virus, such as its structure and mechanisms of action. Moreover, much focus has been on developing accurate diagnostic tools and various drugs or vaccines to treat COVID-19. However, the available evidence is still scarce and consistent criteria should be used for diagnosing vertical transmission. Applying the PRISMA ScR guidelines, we conducted a scoping review with the primary objective of identifying the types, and examining the range, of available evidence of vertical transmission of SARS-CoV-2 from mother to newborn. We also aimed to clarify the key concepts and criteria for diagnosis of SARS-CoV-2 vertical infection in neonates and summarize the existing evidence and advance the awareness of SARS-CoV-2 vertical infection in pregnancy. Most studies we identified were case reports or case series (about 30% of poor quality and inconsistent reporting of the findings). Summarizing the existing classification criteria, we propose an algorithm for consistent diagnosis. Registration: INPLASY2022120093.
TL;DR: In this paper , the authors focus on two key visual disorders that are directly or indirectly connected to migraine: visual aura and visual snow syndrome (VSS) and discuss key clinical features of the two disorders, including pathophysiological mechanisms, their differential diagnoses and best treatment practices.
Abstract: Migraine is a severe and common primary headache disorder, characterized by pain as well as a plethora of non-painful symptoms. Among these, visual phenomena have long been known to be associated with migraine, to the point where they can constitute a hallmark of the disease itself. In this review we focus on two key visual disorders that are directly or indirectly connected to migraine: visual aura and visual snow syndrome (VSS). Visual aura is characterized by the transient presence of positive and negative visual symptoms, before, during or outside of a migraine attack. VSS is a novel stand-alone phenomenon which has been shown to be comorbid with migraine. We discuss key clinical features of the two disorders, including pathophysiological mechanisms, their differential diagnoses and best treatment practices. Our aim is to provide an aid for clinicians and researchers in recognizing these common visual phenomena, which can even appear simultaneously in patients with an underlying migraine biology.
TL;DR: In this paper , the effect of efflux inhibition on the penetration of rifampicin into E. coli bacterial cells was studied by tracking the changes in the characteristic peaks of cell wall components and intracellular proteins.
Abstract: Visualization of the interaction of drugs with biological cells creates new approaches to improving the bioavailability, selectivity, and effectiveness of drugs. The use of CLSM and FTIR spectroscopy to study the interactions of antibacterial drugs with latent bacterial cells localized in macrophages create prospects to solve the problems of multidrug resistance (MDR) and severe cases. Here, the mechanism of rifampicin penetration into E. coli bacterial cells was studied by tracking the changes in the characteristic peaks of cell wall components and intracellular proteins. However, the effectiveness of the drug is determined not only by penetration, but also by efflux of the drugs molecules from the bacterial cells. Here, the efflux effect was studied and visualized using FTIR spectroscopy, as well as CLSM imaging. We have shown that because of efflux inhibition, eugenol acting as an adjuvant for rifampicin showed a significant (more than three times) increase in the antibiotic penetration and the maintenance of its intracellular concentration in E. coli (up to 72 h in a concentration of more than 2 μg/mL). In addition, optical methods have been applied to study the systems containing bacteria localized inside of macrophages (model of the latent form), where the availability of bacteria for antibiotics is reduced. Polyethylenimine grafted with cyclodextrin carrying trimannoside vector molecules was developed as a drug delivery system for macrophages. Such ligands were absorbed by CD206+ macrophages by 60–70% versus 10–15% for ligands with a non-specific galactose label. Owing to presence of ligands with trimannoside vectors, the increase in antibiotic concentration inside macrophages, and thus, its accumulation into dormant bacteria, is observed. In the future, the developed FTIR+CLSM techniques would be applicable for the diagnosis of bacterial infections and the adjustment of therapy strategies.