Evaluation of myocardial work changes after lung resection-the significance of surgical approach: an echocardiographic comparison between VATS and thoracotomy.

OBJECTIVE: Considering the controversial benefits of video-assisted thoracoscopic surgery (VATS), we intended to evaluate the impact of surgical approach on cardiac function after lung resection using myocardial work analysis. METHODS: Echocardiographic data of 48 patients (25 thoracotomy vs. 23 VATS) were retrospectively analyzed. All patients underwent transthoracic echocardiography (TTE) within 2 weeks before and after surgery, including two-dimensional speckle tracking and tissue Doppler imaging. RESULTS: No notable changes in left ventricular (LV) function, assessed mainly using the LV global longitudinal strain (GLS), global myocardial work index (GMWI), and global work efficiency (GWE), were observed. Right ventricular (RV) TTE values, including tricuspid annular plane systolic excursion (TAPSE), tricuspid annular systolic velocity (TASV), right ventricular global longitudinal strain (RVGLS), and RV free-wall GLS (RVFWGLS), indicated greater RV function impairment in the thoracotomy group than in the VATS group [TAPSE(mm) 17.90 ± 3.80 vs. 21.00 ± 3.48, p = 0.006; d = 0.84; TASV(cm/s): 12.40 ± 2.90 vs. 14.70 ± 2.40, p = 0.004, d = 0.86; RVGLS(%): - 16.00 ± 4.50 vs. - 19.40 ± 2.30, p = 0.012, d = 0.20; RVFWGLS(%): - 11.50 ± 8.50 vs. - 18.31 ± 5.40, p = 0.009, d = 0.59; respectively]. CONCLUSIONS: Unlike RV function, LV function remained preserved after lung resection. The thoracotomy group exhibited greater RV function impairment than did the VATS group. Further studies should evaluate the long-term impact of surgical approach on cardiac function.

Deep learning innovations in diagnosing diabetic retinopathy: The potential of transfer learning and the DiaCNN model.

Diabetic retinopathy (DR) is a significant cause of vision impairment, emphasizing the critical need for early detection and timely intervention to avert visual deterioration. Diagnosing DR is inherently complex, as it necessitates the meticulous examination of intricate retinal images by experienced specialists. This makes the early diagnosis of DR essential for effective treatment and prevention of eventual blindness. Traditional diagnostic methods, relying on human interpretation of medical images, face challenges in terms of accuracy and efficiency. In the present research, we introduce a novel method that offers superior precision in DR diagnosis, compared to traditional methods, by employing advanced deep learning techniques. Central to this approach is the concept of transfer learning. This entails the utilization of pre-existing, well-established models, specifically InceptionResNetv2 and Inceptionv3, to extract features and fine-tune selected layers to cater to the unique requirements of this specific diagnostic task. Concurrently, we also present a newly devised model, DiaCNN, which is tailored for the classification of eye diseases. To prove the efficacy of the proposed methodology, we leveraged the Ocular Disease Intelligent Recognition (ODIR) dataset, which comprises eight different eye disease categories. The results are promising. The InceptionResNetv2 model, incorporating transfer learning, registered an impressive 97.5% accuracy in both the training and testing phases. Its counterpart, the Inceptionv3 model, achieved an even more commendable 99.7% accuracy during training, and 97.5% during testing. Remarkably, the DiaCNN model showcased unparalleled precision, achieving 100% accuracy in training and 98.3% in testing. These figures represent a significant leap in classification accuracy when juxtaposed with existing state-of-the-art diagnostic methods. Such advancements hold immense promise for the future, emphasizing the potential of our proposed technique to revolutionize the accuracy of DR and other eye disease diagnoses. By facilitating earlier detection and more timely interventions, this approach stands poised to significantly reduce the incidence of blindness associated with DR, thus heralding a new era of improved patient outcomes. Therefore, this work, through its novel approach and stellar results, not only pushes the boundaries of DR diagnostic accuracy but also promises a transformative impact in early detection and intervention, aiming to substantially diminish DR-induced blindness and champion enhanced patient care.

Automated diagnosis of EEG abnormalities with different classification techniques.

Automatic seizure detection and prediction using clinical Electroencephalograms (EEGs) are challenging tasks due to factors such as low Signal-to-Noise Ratios (SNRs), high variance in epileptic seizures among patients, and limited clinical data constraints. To overcome these challenges, this paper presents two approaches for EEG signal classification. One of these approaches depends on Machine Learning (ML) tools. The used features are different types of entropy, higher-order statistics, and sub-band energies in the Hilbert Marginal Spectrum (HMS) domain. The classification is performed using Support Vector Machine (SVM), Logistic Regression (LR), and K-Nearest Neighbor (KNN) classifiers. Both seizure detection and prediction scenarios are considered. The second approach depends on spectrograms of EEG signal segments and a Convolutional Neural Network (CNN)-based residual learning model. We use 10000 spectrogram images for each class. In this approach, it is possible to perform both seizure detection and prediction in addition to a 3-state classification scenario. Both approaches are evaluated on the Children's Hospital Boston and the Massachusetts Institute of Technology (CHB-MIT) dataset, which contains 24 EEG recordings for 6 males and 18 females. The results obtained for the HMS-based model showed an accuracy of 100%. The CNN-based model achieved accuracies of 97.66%, 95.59%, and 94.51% for Seizure (S) versus Pre-Seizure (PS), Non-Seizure (NS) versus S, and NS versus S versus PS classes, respectively. These results demonstrate that the proposed approaches can be effectively used for seizure detection and prediction. They outperform the state-of-the-art techniques for automatic seizure detection and prediction. Block diagram of proposed epileptic seizure detection method using HMS with different classifiers.

Simultaneous Super-Resolution and Classification of Lung Disease Scans.

Acute lower respiratory infection is a leading cause of death in developing countries. Hence, progress has been made for early detection and treatment. There is still a need for improved diagnostic and therapeutic strategies, particularly in resource-limited settings. Chest X-ray and computed tomography (CT) have the potential to serve as effective screening tools for lower respiratory infections, but the use of artificial intelligence (AI) in these areas is limited. To address this gap, we present a computer-aided diagnostic system for chest X-ray and CT images of several common pulmonary diseases, including COVID-19, viral pneumonia, bacterial pneumonia, tuberculosis, lung opacity, and various types of carcinoma. The proposed system depends on super-resolution (SR) techniques to enhance image details. Deep learning (DL) techniques are used for both SR reconstruction and classification, with the InceptionResNetv2 model used as a feature extractor in conjunction with a multi-class support vector machine (MCSVM) classifier. In this paper, we compare the proposed model performance to those of other classification models, such as Resnet101 and Inceptionv3, and evaluate the effectiveness of using both softmax and MCSVM classifiers. The proposed system was tested on three publicly available datasets of CT and X-ray images and it achieved a classification accuracy of 98.028% using a combination of SR and InceptionResNetv2. Overall, our system has the potential to serve as a valuable screening tool for lower respiratory disorders and assist clinicians in interpreting chest X-ray and CT images. In resource-limited settings, it can also provide a valuable diagnostic support.

Efficient framework for brain tumor detection using different deep learning techniques.

The brain tumor is an urgent malignancy caused by unregulated cell division. Tumors are classified using a biopsy, which is normally performed after the final brain surgery. Deep learning technology advancements have assisted the health professionals in medical imaging for the medical diagnosis of several symptoms. In this paper, transfer-learning-based models in addition to a Convolutional Neural Network (CNN) called BRAIN-TUMOR-net trained from scratch are introduced to classify brain magnetic resonance images into tumor or normal cases. A comparison between the pre-trained InceptionResNetv2, Inceptionv3, and ResNet50 models and the proposed BRAIN-TUMOR-net is introduced. The performance of the proposed model is tested on three publicly available Magnetic Resonance Imaging (MRI) datasets. The simulation results show that the BRAIN-TUMOR-net achieves the highest accuracy compared to other models. It achieves 100%, 97%, and 84.78% accuracy levels for three different MRI datasets. In addition, the k-fold cross-validation technique is used to allow robust classification. Moreover, three different unsupervised clustering techniques are utilized for segmentation.

Hybrid classification structures for automatic COVID-19 detection.

This paper explores the issue of COVID-19 detection from X-ray images. X-ray images, in general, suffer from low quality and low resolution. That is why the detection of different diseases from X-ray images requires sophisticated algorithms. First of all, machine learning (ML) is adopted on the features extracted manually from the X-ray images. Twelve classifiers are compared for this task. Simulation results reveal the superiority of Gaussian process (GP) and random forest (RF) classifiers. To extend the feasibility of this study, we have modified the feature extraction strategy to give deep features. Four pre-trained models, namely ResNet50, ResNet101, Inception-v3 and InceptionResnet-v2 are adopted in this study. Simulation results prove that InceptionResnet-v2 and ResNet101 with GP classifier achieve the best performance. Moreover, transfer learning (TL) is also introduced in this paper to enhance the COVID-19 detection process. The selected classification hierarchy is also compared with a convolutional neural network (CNN) model built from scratch to prove its quality of classification. Simulation results prove that deep features and TL methods provide the best performance that reached 100% for accuracy.

S100A8 (rs3806232) gene polymorphism and S100A8 serum level in psoriasis vulgaris patients: A preliminary study.

BACKGROUND: S100A8 single nucleotide polymorphism (SNP) and S100A8 blood level are related to many inflammatory disorders with no available conclusion in psoriasis. AIM: The aim of this study was to evaluate the possible role of S100A8 in psoriasis pathogenesis through analyzing its S100A8 (rs3806232) gene polymorphism and S100A8 serum level in psoriasis vulgaris patients, in addition to correlate the detected results with severity psoriasis in those patients. METHODS: This case-control study was conducted on 50 patients having psoriasis vulgaris, and 26 controls. Severity of psoriasis was evaluated using psoriasis area and severity index (PASI) score. S100A8 serum level and S100A8 (rs3806232) SNP were evaluated by ELISA and polymerase chain reaction-restriction fragment length polymorphism (PCR-RFLP) respectively. RESULTS: Serum S100A8 level was significantly higher in psoriatic patients than controls and was positively correlated with PASI score (r = 0.826, p < 0.001). S100A8 (rs3806232) AA genotype and A allele were significantly increased among psoriasis patients than controls (p < 0.001) increasing risk of psoriasis development by about 5, 12, and 6 times than AG, GG, and G alleles. AA genotype was significantly associated with psoriasis severity (p = 0.005) and high S100A8 serum levels (p = 0.018). CONCLUSIONS: Circulating S100A8 could associated with disease severity and have an active role in psoriasis pathogenesis. S100A8 (rs3806232) SNP (AA genotype and A allele) might contribute to development and severity of psoriasis in the Egyptian population.

Acute kidney injury in ventilated patients with coronavirus disease-2019 pneumonia: A single-center retrospective study.

BACKGROUND: Acute kidney injury (AKI) is repeatedly observed in ventilated critically ill patients with coronavirus disease-2019 (COVID-19) pneumonia. This study aimed to determine the incidence, risk factors, and consequences of AKI in the ventilated critically ill adult patients with COVID-19 pneumonia. METHODS: This retrospective study included all the ventilated critically ill adult patients with COVID-19 pneumonia from March 1, 2020, to June 1, 2020. Data were collected from the electronic medical system. AKI was diagnosed using the Kidney Disease: Improving Global Outcomes 2012 Clinical Practice definition. Patients were followed 90 days from the intensive care unit (ICU) admission time or to the date when they were discharged from the hospital. RESULTS: AKI occurred in 65.1% of patients, with 26.6% of these started on continuous renal replacement therapy (CRRT). Patients with AKI had higher comorbidity and illness severity scores (P < 0.001). Age and the vasopressor requirements were predictors of AKI (P= 0.016 and P = 0.041) and hypertension predicted AKI (P = 0.099) and its progression (P = 0.05). The renal recovery rate was 86.7% and was associated with the mean arterial pressure on ICU admission in the no-CRRT group (P = 0.014) and the hypoxic index in the CRRT group (P = 0.019). AKI was associated with higher mortality (P = 0.017) and significantly longer ICU length-of-stay (P = 0.001). Additionally, AKI patients were more often discharged to a long-term skilled nursing facility (P = 0.005). CONCLUSION: COVID-19-associated AKI was common and associated with poor outcome, with the specific mechanisms being the main driving factors.

Deep convolutional neural networks for COVID-19 automatic diagnosis.

This article is mainly concerned with COVID-19 diagnosis from X-ray images. The number of cases infected with COVID-19 is increasing daily, and there is a limitation in the number of test kits needed in hospitals. Therefore, there is an imperative need to implement an efficient automatic diagnosis system to alleviate COVID-19 spreading among people. This article presents a discussion of the utilization of convolutional neural network (CNN) models with different learning strategies for automatic COVID-19 diagnosis. First, we consider the CNN-based transfer learning approach for automatic diagnosis of COVID-19 from X-ray images with different training and testing ratios. Different pre-trained deep learning models in addition to a transfer learning model are considered and compared for the task of COVID-19 detection from X-ray images. Confusion matrices of these studied models are presented and analyzed. Considering the performance results obtained, ResNet models (ResNet18, ResNet50, and ResNet101) provide the highest classification accuracy on the two considered datasets with different training and testing ratios, namely 80/20, 70/30, 60/40, and 50/50. The accuracies obtained using the first dataset with 70/30 training and testing ratio are 97.67%, 98.81%, and 100% for ResNet18, ResNet50, and ResNet101, respectively. For the second dataset, the reported accuracies are 99%, 99.12%, and 99.29% for ResNet18, ResNet50, and ResNet101, respectively. The second approach is the training of a proposed CNN model from scratch. The results confirm that training of the CNN from scratch can lead to the identification of the signs of COVID-19 disease.

Progranulin and beta-catenin in psoriasis: An immunohistochemical study.

BACKGROUND/OBJECTIVES: Progranulin (PGRN) is a secreted glycoprotein that was investigated in many skin diseases. It plays an important role in inflammatory response and autophagy which could be mediated through Wnt/ß-catenin pathway. However, the role of PGRN in pathogenesis of psoriasis has not been clearly well-known. Therefore, we aimed by this study to investigate the possible role of progranulin in psoriasis pathogenesis through evaluation of its immunohistochemical expression in lesional and perilesional skin of psoriasis patients and to investigate if its hypothesized role is mediated through ß-catenin or not. METHODS: This case-control study was carried out on 37 patients presented with variable degrees of psoriasis vulgaris severity vs 37 age and sex-matched apparently healthy volunteers. Psoriasis area and severity index (PASI) score was used to evaluate the severity of psoriasis. From all cases (lesional and perilesional) and controls, skin biopsies were taken for histopathological and immunohistochemical evaluation of PGRN and ß-catenin. RESULTS: There was a significant stepwise upregulation of PGRN from controls (76.2 ± 11.9) to perilesional (178.7 ± 11.8) and lesional (242.7 ± 12.7) psoriatic skin (P < 0.001). PGRN expression was significantly correlated with psoriasis severity (r = 0.61; P < 0.001). ß-catenin showed a significant stepwise downregulation from control (210.0 ± 19.3) to perilesional (131.4 ± 9.2) and lesional (97.3 ± 11.5) psoriatic skin(P < 0.001). There was a significant negative correlation between PGRN and ß-catenin expression in psoriatic skin (P < 0.001). CONCLUSIONS: Progranulin has a pro-inflammatory effect in the psoriasis pathogenesis, which could be mediated through a decreasing ß-catenin expression in psoriasis. PGRN may be used as a target for immunotherapy in psoriasis management program.

The flutter-by effect: a comprehensive study of the fluttering cusps of the Perceval heart valve prosthesis.

OBJECTIVES: Sutureless aortic valve prostheses are gaining popularity due to the substantial reduction in cross-clamp time. In this study, we report our observations on the cusp-fluttering phenomenon of the Perceval bioprosthesis (LivaNova, London, UK) using a combination of technical and medical perspectives. METHODS: Between August 2014 and December 2016, a total of 108 patients (69% women) with a mean age of 78 years had aortic valve replacement using the Perceval bioprosthesis (34 combined procedures). All patients underwent transoesophageal echocardiography (TOE) intraoperatively. TOE was performed postoperatively to detect paravalvular leakage and to measure gradients, acceleration time, Doppler velocity indices (Vmax and LVOT/Vmax AV) and effective orifice area indices. In addition, a TOE examination was performed in 21 patients postoperatively. Data were collected retrospectively from our hospital database. RESULTS: The retrospective evaluation of the intraoperative TOE examinations revealed consistent fluttering in all patients with the Perceval bioprosthesis. The echocardiographic postoperative measurements showed a mean effective orifice area index of 0.91 ± 0.12 cm2/m2. The overall mean pressure and peak pressure gradients were in a higher range (13.5 ± 5.1 mmHg and 25.5 ± 8.6 mmHg, respectively), whereas acceleration time (62.8 ± 16.4 ms) and Doppler velocity indices (0.43 ± 0.11) were within the normal range according to the American Society of Echocardiography or european association of echocardiography (EAE) guidelines. The 2-dimensional TOE in Motion Mode (M-Mode) that was performed in patients with elevated lactate dehydrogenase (LDH) levels revealed remarkable fluttering of the cusps of the Perceval bioprosthesis. CONCLUSIONS: In our study cohort, we observed the fluttering phenomenon in all patients who received the Perceval bioprosthesis, which was correlated with elevated LDH levels and higher pressure gradients.

Are elevated serum haemolysis markers a harbinger of adverse events in HeartMate II patients?

OBJECTIVES: Haemolysis during left ventricular assist device support is associated with thrombosis. In this retrospective study, we analysed whether low-level haemolysis (LLH) as defined by simultaneously elevated lactate dehydrogenase (LDH) and free haemoglobin (fHb) levels had an impact on thromboembolic and bleeding events and on von Willebrand factor levels in HeartMate II patients. METHODS: After exclusion of patients with LDH >700 U/l and fHb >40 mg/dl at hospital discharge, 79 HeartMate II patients were included. LDH and fHb levels were measured at discharge and in 3 months interval. von Willebrand factor activity and antigen activity were measured 3 months postoperatively. Outcomes regarding ischaemic stroke (IS), pump thrombosis (PT) and gastrointestinal bleeding were recorded. Patients with LLH (400 < LDH ≤ 700 U/l and 30 < fHb ≤ 40 mg/dl) at discharge (pre-Hemolyzers) were compared with the rest of the cohort (non-Hemolyzers). Competing risk analysis and Cox regression were applied for the comparison between groups. RESULTS: In all, 20% of the patients were identified as pre-Hemolyzers. Of these, 5 patients had PT and 3 patients had IS compared with 2 PT and 2 IS in the non-Hemolyzers group (P = 0.003 and P = 0.053, respectively). Fifty percent of the pre-Hemolyzers suffered gastrointestinal bleeding compared with 42% of the non-Hemolyzers (P = 0.399). The cumulative risk of thromboembolic events (IS or PT) in the pre-Hemolyzers group was significantly higher compared with the non-Hemolyzers group (hazard ratio 11.8, 95% confidence interval 3.7-37.7; P = 0.005). LLH did not have an impact on von Willebrand factor and the incidence of gastrointestinal bleeding. CONCLUSIONS: LLH as assessed by elevated fHb and LDH values at discharge during HeartMate II support is associated with thromboembolic events.