Deep Learning is the newest and the current trend of the machine learning field that paid a lot of the researchers' attention in the recent few years. As a proven powerful machine learning tool, deep learning was widely used in several applications for solving various complex problems that require extremely high accuracy and sensitivity, particularly in the medical field. In general, the brain tumor is one of the most common and aggressive malignant tumor diseases which is leading to a very short expected life if it is diagnosed at a higher grade. Based on that, brain tumor grading is a very critical step after detecting the tumor in order to achieve an effective treating plan. In this paper, we used Convolutional Neural Network (CNN) which is one of the most widely used deep learning architectures for classifying a dataset of 3064 T1 weighted contrast-enhanced brain MR images for grading (classifying) the brain tumors into three classes (Glioma, Meningioma, and Pituitary Tumor). The proposed CNN classifier is a powerful tool and its overall performance with an accuracy of 98.93% and sensitivity of 98.18% for the cropped lesions, while the results for the uncropped lesions are 99% accuracy and 98.52% sensitivity and the results for segmented lesion images are 97.62% for accuracy and 97.40% sensitivity.

Electrocardiogram (ECG) is one of the most important and effective tools in clinical routine to assess the cardiac arrhythmias. In this research higherorder spectral estimations, bispectrum and third-order cumulants, are evaluated, saved, and pre-trained using convolutional neural networks (CNN) algorithm. CNN is transferred in this study to carry out automatic ECG arrhythmia diagnostics after employing the higher-order spectral algorithms. Transfer learning strategies are applied on pre-trained convolutional neural network, namely AlexNet and GoogleNet, to carry out the final classification. Five different arrhythmias of ECG waveform are chosen from the MIT-BIH arrhythmia database to evaluate the proposed approach. The main contribution of this study is to utilize the pre-trained convolutional neural networks with a combination of higher-order spectral estimations of arrhythmias ECG signal to implement a reliable and applicable deep learning classification technique. The Highest average accuracy obtained is 97.8 % when using third cumulants and GoogleNet. As is evident from these results, the proposed approach is an efficient automatic cardiac arrhythmia classification method and provides a reliable recognition system based on well-established CNN architectures instead of training a deep CNN from scratch.

No abstract

Proteins are essential for many biological functions. For example, folding amino acid chains reveals their functionalities by maintaining tissue structure, physiology, and homeostasis. Note that quantifiable protein characteristics are vital for improving therapies and precision medicine. The automatic inference of a protein's properties from its amino acid sequence is called "basic structure". Nevertheless, it remains a critical unsolved challenge in bioinformatics, although with recent technological advances and the investigation of protein sequence data. Inferring protein function from amino acid sequences is crucial in biology. This study considers using raw sequencing to explain biological facts using a large corpus of protein sequences and the Globin-like superfamily to generate a vector representation. The power of two representations was used to identify each amino acid, and a coding technique was established for each sequence family. Subsequently, the encoded protein numerical sequences are transformed into an image using bispectral analysis to identify essential characteristics for discriminating between protein sequences and their families. A deep Convolutional Neural Network (CNN) classifies the resulting images and developed non-normalized and normalized encoding techniques. Initially, the dataset was split 70/30 for training and testing. Correspondingly, the dataset was utilized for 70% training, 15% validation, and 15% testing. The suggested methods are evaluated using accuracy, precision, and recall. The non-normalized method had 70% accuracy, 72% precision, and 71% recall. 68% accuracy, 67% precision, and 67% recall after validation. Meanwhile, the normalized approach without validation had 92.4% accuracy, 94.3% precision, and 91.1% recall. Validation showed 90% accuracy, 91.2% precision, and 89.7% recall. Note that both algorithms outperform the rest. The paper presents that bispectrum-based nonlinear analysis using deep learning models outperforms standard machine learning methods and other deep learning methods based on convolutional architecture. They offered the best inference performance as the proposed approach improves categorization and prediction. Several instances show successful multi-class prediction in molecular biology's massive data.

Complex proteins are needed for many biological activities. Folding amino acid chains reveals their properties and functions. They support healthy tissue structure, physiology, and homeostasis. Precision medicine and treatments require quantitative protein identification and function. Despite technical advances and protein sequence data exploration, bioinformatics' "basic structure" problem-the automatic deduction of a protein's properties from its amino acid sequence-remains unsolved. Protein function inference from amino acid sequences is the main biological data challenge. This study analyzes whether raw sequencing can characterize biological facts. A massive corpus of protein sequences and the Globin-like superfamily's related protein families generate a solid vector representation. A coding technique for each sequence in each family was devised using two representations to identify each amino acid precisely. A bispectral analysis converts encoded protein numerical sequences into images for better protein sequence and family discrimination. Training and validation employed 70% of the dataset, while 30% was used for testing. This paper examined the performance of multistage deep learning models for differentiating between sixteen protein families after encoding and representing each encoded sequence by a higher spectral representation image (Bispectrum). Cascading minimized false positive and negative cases in all phases. The initial stage focused on two classes (six groups and ten groups). The subsequent stages focused on the few classes almost accurately separated in the first stage and decreased the overlapping cases between families that appeared in single-stage deep learning classification. The singlestage technique had 64.2% +/− 22.8% accuracy, 63.3% +/− 17.1% precision, and a 63.2% +/19.4% F1-score. The two-stage technique yielded 92.2% +/− 4.9% accuracy, 92.7% +/− 7.0% precision, and a 92.3% +/− 5.0% F1-score. This work provides balanced, reliable, and precise forecasts for all families in all measures. It ensured that the new model was resilient to family variances and provided high-scoring results.