Search

Our study presents MozzieNet, a customized CNN model aimed at improving the identification of malaria parasites in blood smear microscopic images. By optimizing hyperparameters and incorporating techniques like data augmentation, batch normalization, and dropout, our model enhances robustness and generalization, addressing overfitting issues. Using the open‐source NIH malaria dataset with 27,558 images, we achieve a classification accuracy of 96.73%, recall rate of 97.90%, precision of 95.67%, area under the curve (AUC) of 99.35%, and F1 score of 96.77%. We performed feature maps and Grad‐CAM analysis on our proposed MozzieNet model to visualize and examine the targeted regions that are crucial for accurate predictions. Statistical analysis shows that the proposed architecture achieves promising performance and is superior to pre‐trained models and existing methods for malaria detection. MozzieNet is designed for cloud and low‐end smartphones, enabling malaria diagnosis in remote areas, thereby assisting physicians in informed malaria diagnosis and decision‐making. [ABSTRACT FROM AUTHOR]

The computer‐aided diagnostic (CAD) method to detect human brain tumors relies heavily on automated tumor characterization. Although CAD method has been extensively researched, significant obstacles still exist. Magnetic resonance imaging (MRI) classifiers brain tumors into glioma, meningioma, and pituitary tumors. However, accurately distinguishing between these tumor types remains a complex challenge in medical imaging. The recently developed deep learning and machine learning (ML) techniques have shown immense potential in image classification. However, the low numbers of medical image archives also pose a problem for medical image classification. As a result, fewer medical images are available to use in deep learning research and development. To address this issue, we use three highly effective ML classifiers with deep convolutional learned features for medical image classification. The MRI images of the three distinct types of brain tumors may be found in an open dataset on Figshare, which tests the automated approach's efficacy. Features are extracted from brain MRI scans using the DenseNet169 model. Extracted features are fed into a multiclass three ML classifiers (RF, SVM, XGBoost) for improved performance. Results from testing and evaluation of the entire framework are promising, especially compared to the field's state‐of‐the art technique. The suggested model outperformed the state‐of‐the‐art technique, with an overall classification accuracy of 95.10%. To verify the enhanced performance of the proposed system, extensive tests are conducted on the brain MRI dataset available on Figshare. The optimal hyper‐parameter fading classifier is seen to outperform the Softmax classifier for the features when there is limited training data. [ABSTRACT FROM AUTHOR]

Coronavirus disease (COVID‐19) is a pandemic that has caused thousands of casualties and impacts all over the world. Most countries are facing a shortage of COVID‐19 test kits in hospitals due to the daily increase in the number of cases. Early detection of COVID‐19 can protect people from severe infection. Unfortunately, COVID‐19 can be misdiagnosed as pneumonia or other illness and can lead to patient death. Therefore, in order to avoid the spread of COVID‐19 among the population, it is necessary to implement an automated early diagnostic system as a rapid alternative diagnostic system. Several researchers have done very well in detecting COVID‐19; however, most of them have lower accuracy and overfitting issues that make early screening of COVID‐19 difficult. Transfer learning is the most successful technique to solve this problem with higher accuracy. In this paper, we studied the feasibility of applying transfer learning and added our own classifier to automatically classify COVID‐19 because transfer learning is very suitable for medical imaging due to the limited availability of data. In this work, we proposed a CNN model based on deep transfer learning technique using six different pre‐trained architectures, including VGG16, DenseNet201, MobileNetV2, ResNet50, Xception, and EfficientNetB0. A total of 3886 chest X‐rays (1200 cases of COVID‐19, 1341 healthy and 1345 cases of viral pneumonia) were used to study the effectiveness of the proposed CNN model. A comparative analysis of the proposed CNN models using three classes of chest X‐ray datasets was carried out in order to find the most suitable model. Experimental results show that the proposed CNN model based on VGG16 was able to accurately diagnose COVID‐19 patients with 97.84% accuracy, 97.90% precision, 97.89% sensitivity, and 97.89% of F1‐score. Evaluation of the test data shows that the proposed model produces the highest accuracy among CNNs and seems to be the most suitable choice for COVID‐19 classification. We believe that in this pandemic situation, this model will support healthcare professionals in improving patient screening. [ABSTRACT FROM AUTHOR]