Mohammad Ebrahim Shiri Ahmadabadi

Bio: Mohammad Ebrahim Shiri Ahmadabadi is an academic researcher from Amirkabir University of Technology. The author has contributed to research in topics: Statistical classification & Image segmentation. The author has an hindex of 2, co-authored 2 publications receiving 4 citations.

Developing an Artificial Intelligence Model for Tumor Grading and Classification, Based on MRI Sequences of Human Brain Gliomas

Abstract: Background: Artificial intelligence (AI) models have provided advanced applications to many scientific areas, including the prediction of the pathologic grade of tumors, utilizing radiology techniques. Gliomas are among the malignant brain tumors in human adults, and their efficient diagnosis is of high clinical significance. Objectives: Given the contribution of AI to medical diagnoses, we investigated the role of deep learning in the differential diagnosis and grading of human brain gliomas. Methods: This study developed a new AI diagnostic model, i.e., EfficientNetB0, to grade and classify human brain gliomas, using sequences from magnetic resonance imaging (MRI). Results: We validated the new AI model, using a standard dataset (BraTS-2019) and demonstrated that the AI components, i.e., convolutional neural networks and transfer learning, provided excellent performance for classifying and grading glioma images at 98.8% accuracy. Conclusions: The proposed model, EfficientNetB0, is capable to classify and grade glioma from MRI sequences at high accuracy, validity, and specificity. It can provide better performance and diagnostic results for human glioma images than models developed by previous studies.

Fully Unsupervised Salient Object Detection

Abstract: Object detection is one of the most important components of machine vision. Today, object detection is used in a variety of areas, including guidance, driving, industry, and other key areas. For this reason, many algorithms have been proposed in this regard, with the aim of increasing the quality of detecting objects in an image. Since the correct representation of the object in the image is considered an essential requirement, in this article, a five-step algorithm is proposed for object detection. Experiments are performed on a given database in comparison with other methods in this area. In this algorithm, a color space is used to extract the feature and from self-encoder to remove the noise in the property matrix. Then, by scoring the clusters created based on the features, using the mean shift algorithm, the maximum pixels of the object are detected and separated from the background. The results of the experiments show performance of the proposed method in dealing with photos that involve challenges from multiple objects to changes the image.

An Accurate Classification Algorithm With Genetic Algorithm Approach

Abstract: The importance of employing classifiers with high accuracy in many applications in real life is important. Developmental process to construct the high accuracy classification rules by using the features associated with noisy information and duplication is avoided. Our algorithm is compared with 7 known classification algorithms in 9 different areas of application. Experimental results using several non-parametric statistical tests that are used in classification are investigated.The results show that our algorithm achieves the best competitive accuracy and that’s why it can be recognized as an accurate classifier.

Convolutional Neural Network Techniques for Brain Tumor Classification (from 2015 to 2022): Review, Challenges, and Future Perspectives

Abstract: Convolutional neural networks (CNNs) constitute a widely used deep learning approach that has frequently been applied to the problem of brain tumor diagnosis. Such techniques still face some critical challenges in moving towards clinic application. The main objective of this work is to present a comprehensive review of studies using CNN architectures to classify brain tumors using MR images with the aim of identifying useful strategies for and possible impediments in the development of this technology. Relevant articles were identified using a predefined, systematic procedure. For each article, data were extracted regarding training data, target problems, the network architecture, validation methods, and the reported quantitative performance criteria. The clinical relevance of the studies was then evaluated to identify limitations by considering the merits of convolutional neural networks and the remaining challenges that need to be solved to promote the clinical application and development of CNN algorithms. Finally, possible directions for future research are discussed for researchers in the biomedical and machine learning communities. A total of 83 studies were identified and reviewed. They differed in terms of the precise classification problem targeted and the strategies used to construct and train the chosen CNN. Consequently, the reported performance varied widely, with accuracies of 91.63–100% in differentiating meningiomas, gliomas, and pituitary tumors (26 articles) and of 60.0–99.46% in distinguishing low-grade from high-grade gliomas (13 articles). The review provides a survey of the state of the art in CNN-based deep learning methods for brain tumor classification. Many networks demonstrated good performance, and it is not evident that any specific methodological choice greatly outperforms the alternatives, especially given the inconsistencies in the reporting of validation methods, performance metrics, and training data encountered. Few studies have focused on clinical usability.

Performance evaluation of salient object detection techniques

Abstract: Abstract Recently, the detection and segmentation of salient objects that attract the attention of human visual in images is determined by using salient object detection (SOD) techniques. As an essential computer vision problem, SOD has increasingly attracted the researchers’ interest over the years. While a lot of SOD models and applications have been proposed, there is still a lack of deep understanding of the issues and achievements. A comprehensive study on the recent techniques of SOD is provided in this paper. Precisely, this paper presents a review of SOD techniques from various perspectives. Various image segmentation techniques are presented such as segmentation based on machine learning or deep learning, the second perspective concentrates on classifying them into supervised and unsupervised learning techniques and the last one based on manual approach, semi-automatic approach, and fully automatic approach and so on. Then, the paper presents a summarization of datasets used for SOD. Finally, analyses of SOD models and comparison results are presented.

A mix-supervised unified framework for salient object detection

Abstract: Recently, although deep learning network has shown its advantages in supervised salient object detection, supervised models often require massive pixel-wise annotations and learnable parameters, which seriously manacle training and testing of models. In this paper, we present a mix-supervised unified framework for salient object detection to avoid the insufficient training labels and speed training and testing up, which is composed of a region-wise stream and a pixel-wise stream. In the region-wise stream, to avoid the requirement of expensive pixel-wise annotations, an improved energy equation based manifold learning algorithm is employed, by which accurate object location and prior knowledge are introduced by the unsupervised learning. In the pixel-wise stream, to alleviate the problem of time-consuming, a simplified bi-directional reuse network is introduced, which can obtain clear object contour and competitive performance with fewer parameters. To relieve the bottleneck pressure of parallel training and testing, each steam is directly connected to its pre-processed color feature and post-processing refinement. Extensive experiments demonstrate that each component contributes to the final results and complement each other perfectly.

Artificial Intelligence and Precision Medicine: A New Frontier for the Treatment of Brain Tumors

Abstract: Brain tumors are a widespread and serious neurological phenomenon that can be life- threatening. The computing field has allowed for the development of artificial intelligence (AI), which can mimic the neural network of the human brain. One use of this technology has been to help researchers capture hidden, high-dimensional images of brain tumors. These images can provide new insights into the nature of brain tumors and help to improve treatment options. AI and precision medicine (PM) are converging to revolutionize healthcare. AI has the potential to improve cancer imaging interpretation in several ways, including more accurate tumor genotyping, more precise delineation of tumor volume, and better prediction of clinical outcomes. AI-assisted brain surgery can be an effective and safe option for treating brain tumors. This review discusses various AI and PM techniques that can be used in brain tumor treatment. These new techniques for the treatment of brain tumors, i.e., genomic profiling, microRNA panels, quantitative imaging, and radiomics, hold great promise for the future. However, there are challenges that must be overcome for these technologies to reach their full potential and improve healthcare.

Attention Deep Feature Extraction from Brain MRIs in Explainable Mode: DGXAINet

Abstract: Artificial intelligence models do not provide information about exactly how the predictions are reached. This lack of transparency is a major drawback. Particularly in medical applications, interest in explainable artificial intelligence (XAI), which helps to develop methods of visualizing, explaining, and analyzing deep learning models, has increased recently. With explainable artificial intelligence, it is possible to understand whether the solutions offered by deep learning techniques are safe. This paper aims to diagnose a fatal disease such as a brain tumor faster and more accurately using XAI methods. In this study, we preferred datasets that are widely used in the literature, such as the four-class kaggle brain tumor dataset (Dataset I) and the three-class figshare brain tumor dataset (Dataset II). To extract features, a pre-trained deep learning model is chosen. DenseNet201 is used as the feature extractor in this case. The proposed automated brain tumor detection model includes five stages. First, training of brain MR images with DenseNet201, the tumor area was segmented with GradCAM. The features were extracted from DenseNet201 trained using the exemplar method. Extracted features were selected with iterative neighborhood component (INCA) feature selector. Finally, the selected features were classified using support vector machine (SVM) with 10-fold cross-validation. An accuracy of 98.65% and 99.97%, were obtained for Datasets I and II, respectively. The proposed model obtained higher performance than the state-of-the-art methods and can be used to aid radiologists in their diagnosis.