Explore the vast range of titles available.

In today’s world, a brain tumor is one of the most serious diseases. If it is detected at an advanced stage, it might lead to a very limited survival rate. Therefore, brain tumor classification is crucial for appropriate therapeutic planning to improve patient life quality. This research investigates a deep-feature-trained brain tumor detection and differentiation model using classical/linear machine learning classifiers (MLCs). In this study, transfer learning is used to obtain deep brain magnetic resonance imaging (MRI) scan features from a constructed convolutional neural network (CNN). First, multiple layers (19, 22, and 25) of isolated CNNs are constructed and trained to evaluate the performance. The developed CNN models are then utilized for training the multiple MLCs by extracting deep features via transfer learning. The available brain MRI datasets are employed to validate the proposed approach. The deep features of pre-trained models are also extracted to evaluate and compare their performance with the proposed approach. The proposed CNN deep-feature-trained support vector machine model yielded higher accuracy than other commonly used pre-trained deep-feature MLC training models. The presented approach detects and distinguishes brain tumors with 98% accuracy. It also has a good classification rate (97.2%) for an unknown dataset not used to train the model. Following extensive testing and analysis, the suggested technique might be helpful in assisting doctors in diagnosing brain tumors.

Brain tumors reduce life expectancy due to the lack of a cure. Moreover, their diagnosis involves complex and costly procedures such as magnetic resonance imaging (MRI) and lengthy, careful examination to determine their severity. However, the timely diagnosis of brain tumors in their early stages may save a patient’s life. Therefore, this work utilizes MRI with a machine learning approach to diagnose brain tumor severity (glioma, meningioma, no tumor, and pituitary) in a timely manner. MRI Gaussian and nonlinear scale features are extracted due to their robustness over rotation, scaling, and noise issues, which are common in image processing features such as texture, local binary patterns, histograms of oriented gradient, etc. For the features, each MRI is broken down into multiple small 8 × 8-pixel MR images to capture small details. To counter memory issues, the strongest features based on variance are selected and segmented into 400 Gaussian and 400 nonlinear scale features, and these features are hybridized against each MRI. Finally, classical machine learning classifiers are utilized to check the performance of the proposed hybrid feature vector. An available online brain MRI image dataset is utilized to validate the proposed approach. The results show that the support vector machine-trained model has the highest classification accuracy of 95.33%, with a low computational time. The results are also compared with the recent literature, which shows that the proposed model can be helpful for clinicians/doctors for the early diagnosis of brain tumors.

Worldwide, COVID-19 is a highly contagious epidemic that has affected various fields. Using Artificial Intelligence (AI) and particular feature selection approaches, this study evaluates the aspects affecting the health of students throughout the COVID-19 lockdown time. The research presented in this paper plays a vital role in indicating the factor affecting the health of students during the lockdown in the COVID-19 pandemic. The research presented in this article investigates COVID-19’s impact on student health using feature selections. The Filter feature selection technique is used in the presented work to statistically analyze all the features in the dataset, and for better accuracy. ReliefF (TuRF) filter feature selection is tuned and utilized in such a way that it helps to identify the factors affecting students’ health from a benchmark dataset of students studying during COVID-19. Random Forest (RF), Gradient Boosted Decision Trees (GBDT), Support Vector Machine (SVM), and 2- layer Neural Network (NN), helps in identifying the most critical indicators for rapid intervention. Results of the approach presented in the paper identified that the students who maintained their weight and kept themselves busy in health activities in the pandemic, such student’s remained healthy through this pandemic and study from home in a positive manner. The results suggest that the 2- layer NN machine-learning algorithm showed better accuracy (90%) to predict the factors affecting on health issues of students during COVID-19 lockdown time.

COVID-19 is a profoundly contagious pandemic that has taken the world by storm and has afflicted different fields of life with negative effects. It has had a substantial impact on education which is evident from the transition from Face-to-Face (F2F) teaching to online mode of education and the rigid implementation of lockdown across the globe. This study examines the factors impacting the performance of teachers during the lockdown period of COVID-19 using various feature selection algorithms and Artificial Intelligence techniques. In this paper, we have proposed a novel multilevel feature selection for the prediction of the factors affecting the teachers’ satisfaction with online teaching and learning in COVID-19. The proposed multilevel feature selection is composed of the Fast Correlation Based Filter (FCBF), Mutual Information (MI), Relieff, and Particle Swarm Optimization (PSO) feature selection. The performance of the proposed feature selection approach is evaluated through the teachers’ benchmark dataset. We used a range of measures like accuracy, precision, f-measure, and recall to evaluate the performance of the proposed approach. We applied different machine learning approaches (SVM, LGBM, and ANN) with the proposed multilevel feature selection technique. The performance of the proposed approach is also compared with existing feature selection algorithms, and the results show the improvement in the performance of feature selection in terms of accuracy, precision, recall, and F-Measure. Proposed feature selection provides more than 80% accuracy with Light Weight Gradient Boosting Machine (LGBM).

For the precise preoperative evaluation of complex congenital heart diseases (CHDs) with reduced radiation dose exposure, we assessed the diagnostic validity and reliability of low-dose prospective ECG-gated cardiac CT (CCT). Forty-two individuals with complex CHDs who underwent preoperative CCT as part of a prospective study were included. Each CCT image was examined independently by two radiologists. The primary reference for assessing the diagnostic validity of the CCT was the post-operative data. Infants and neonates were the most common age group suffering from complex CHDs. The mean volume of the CT dose index was 1.44 ± 0.47 mGy, the mean value of the dose-length product was 14.13 ± 5.4 mGy*cm, and the mean value of the effective radiation dose was 0.58 ± 0.13 mSv. The sensitivity, specificity, PPV, NPV, and accuracy of the low-dose prospective ECG-gated CCT for identifying complex CHDs were 95.6%, 98%, 97%, 97%, and 97% for reader 1 and 92.6%, 97%, 95.5%, 95.1%, and 95.2% for reader 2, respectively. The overall inter-reader agreement for interpreting the cardiac CCTs was good (κ = 0.74). According to the results of our investigation, low-dose prospective ECG-gated CCT is a useful and trustworthy method for assessing coronary arteries and making a precise preoperative diagnosis of complex CHDs.

Carpal tunnel syndrome (CTS) is a common condition characterized by compression of the median nerve (MN) within the carpal tunnel. Accurate diagnosis and assessment of CTS severity are crucial for appropriate management decisions. This study aimed to investigate the combined diagnostic utility of B-mode ultrasound (US) and shear wave elastography (SWE) for assessing the severity of CTS in comparison to electrodiagnostic tests (EDT). This prospective observational study was conducted over 9-month periods at a tertiary care hospital. A total of 48 patients (36 females, 12 males; mean age 44 ± 10.9 years; age range 28-57 years) with clinically suspected CTS were enrolled. All patients underwent EDT, US, and SWE. Based on the EDT results, CTS cases were categorized into four groups: mild, moderate, severe, and negative. The cross-sectional area (CSA) and elasticity (E) of the MN were measured at the tunnel inlet (CSAu and Eu) and pronator quadratus region (CSAo and Eo). The differences (CSAu-CSAo and Eu-Eo) were calculated. The primary outcomes were the diagnostic performance of CSAu, CSAu-CSAo, Eu, and Eu-Eo in differentiating moderate/severe from mild/negative CTS compared to EDT findings. Secondary outcomes included a correlation of US/SWE parameters with EDT grades and between each other. ANOVA, correlation, regression, and receiver operating characteristic (ROC) curve analyses were performed. CSAu and CSAu-CSAo increased progressively with worsening CTS severity. E measurements were significantly higher in moderate-to-severe CTS compared to mild or negative cases. The combined metric of CSAu-CSAo at a 5 mm threshold exhibited enhanced performance, with a higher sensitivity (83.3%), specificity (100%), and area under the curve (AUC) (0.98), surpassing the results of CSAu when used independently. Similarly, the SWE measurements indicated that Eu-Eo at a 56.1kPa cutoff achieved an AUC of 0.95, with a sensitivity of 93.3% and specificity of 94.4%, outperforming the metrics for Eu when used alone, which had an AUC of 0.93, with identical sensitivity and specificity values (93.3% and 94.4%, respectively). The integration of ultrasound, shear wave elastography, and electrodiagnostic tests provides a comprehensive approach to evaluate anatomical and neurological changes and guide management decisions for CTS.

Malignant pleural effusion (MPE) is a manifestation of advanced cancer that requires a prompt and accurate diagnosis. Ultrasonography (US) and computed tomography (CT) are valuable imaging techniques for evaluating pleural effusions; however, their relative predictive ability for a malignant origin remains debatable. This prospective study aimed to compare chest US with CT findings as predictors of malignancy in patients with undiagnosed exudative pleural effusion. Fifty-four adults with undiagnosed exudative pleural effusions underwent comprehensive clinical evaluation including chest US, CT, and histopathologic biopsy. Blinded radiologists evaluated the US and CT images for features suggestive of malignancy, based on predefined criteria. Diagnostic performance measures were calculated using histopathology as a reference standard. Of the 54 patients, 33 (61.1%) had MPEs confirmed on biopsy. No significant differences between US and CT were found in detecting parietal pleural abnormalities, lung lesions, chest wall invasion, or liver metastasis. US outperformed CT in identifying diaphragmatic pleural thickening ≥10 mm (33.3% vs. 6.1%, p < 0.001) and nodularity (45.5% vs. 3%, p < 0.001), whereas CT was superior for mediastinal thickening (48.5% vs. 15.2%, p = 0.002). For diagnosing MPE, diaphragmatic nodularity detected by US had 45.5% sensitivity and 100% specificity, whereas CT mediastinal thickening had 48.5% sensitivity and 90.5% specificity. Both US and CT demonstrate reasonable diagnostic performance for detecting MPE, with particular imaging findings favoring a malignant origin. US may be advantageous for evaluating diaphragmatic pleural involvement, whereas CT is more sensitive to mediastinal abnormalities.

Understanding the consistency of pituitary macroadenomas is crucial for neurosurgeons planning surgery. This retrospective study aimed to evaluate the utility of diffusion-weighted imaging (DWI) and the apparent diffusion coefficient (ADC) as non-invasive imaging modalities for predicting the consistency of pituitary macroadenomas. This could contribute to appropriate surgical planning and therefore reduce the likelihood of incomplete resections. The study included 45 patients with pathologically confirmed pituitary macroadenomas. Conventional MRI sequences, DWIs, ADC maps, and pre- and post-contrast MRIs were performed. Two neuroradiologists assessed all of the images. Neurosurgeons assessed the consistency of the tumor macroscopically, and histopathologists examined it microscopically. The MRI findings were compared with postoperative data. According to the operative data, macroadenomas were divided into the two following categories based on their consistency: aspirable (n = 27) and non-aspirable tumors (n = 18). A statistically significant difference in DWI findings was found when comparing macroadenomas of different consistencies (p < 0.001). Most aspirable macroadenomas (66.7%) were hyperintense according to DWI and hypointense on ADC maps, whereas most non-aspirable macroadenomas (83.3%) were hypointense for DWI and hyperintense on ADC maps. At a cut-off value of 0.63 × 10−3 mm2/s, the ADC showed a sensitivity of 85.7% and a specificity of 75% for the detection of non-aspirable macroadenomas (AUC, 0.946). The study concluded that DWI should be routinely performed in conjunction with ADC measurements in the preoperative evaluation of pituitary macroadenomas. This approach may aid in surgical planning, ensure that appropriate techniques are utilized, and reduce the risk of incomplete resection.