Unbox the black-box for the medical explainable AI via multi-modal and multi-centre data fusion: A mini-review, two showcases and beyond

Information Fusion, Journal Year: 2021, Volume and Issue: 77, P. 29 - 52

Published: July 31, 2021

Explainable Artificial Intelligence (XAI) is an emerging research topic of machine learning aimed at

Language: Английский

---

TransMed: Transformers Advance Multi-Modal Medical Image Classification

Diagnostics, Journal Year: 2021, Volume and Issue: 11(8), P. 1384 - 1384

Published: July 31, 2021

Over the past decade, convolutional neural networks (CNN) have shown very competitive performance in medical image analysis tasks, such as disease classification, tumor segmentation, and lesion detection. CNN has great advantages extracting local features of images. However, due to locality convolution operation, it cannot deal with long-range relationships well. Recently, transformers been applied computer vision achieved remarkable success large-scale datasets. Compared natural images, multi-modal images explicit important dependencies, effective fusion strategies can greatly improve deep models. This prompts us study transformer-based structures apply them Existing network architectures require datasets achieve better performance. imaging are relatively small, which makes difficult pure analysis. Therefore, we propose TransMed for classification. combines transformer efficiently extract low-level establish dependencies between modalities. We evaluated our model on two datasets, parotid gland tumors classification knee injury Combining contributions, an improvement 10.1% 1.9% average accuracy, respectively, outperforming other state-of-the-art CNN-based The results proposed method promising tremendous potential be a large number tasks. To best knowledge, this is first work

Language: Английский

---

A Review on Deep Learning Techniques for the Diagnosis of Novel Coronavirus (COVID-19)

IEEE Access, Journal Year: 2021, Volume and Issue: 9, P. 30551 - 30572

Published: Jan. 1, 2021

Novel coronavirus (COVID-19) outbreak, has raised a calamitous situation all over the world and become one of most acute severe ailments in past hundred years. The prevalence rate COVID-19 is rapidly rising every day throughout globe. Although no vaccines for this pandemic have been discovered yet, deep learning techniques proved themselves to be powerful tool arsenal used by clinicians automatic diagnosis COVID-19. This paper aims overview recently developed systems based on using different medical imaging modalities like Computer Tomography (CT) X-ray. review specifically discusses provides insights well-known data sets train these networks. It also highlights partitioning various performance measures researchers field. A taxonomy drawn categorize recent works proper insight. Finally, we conclude addressing challenges associated with use methods detection probable future trends research area. aim facilitate experts (medical or otherwise) technicians understanding ways are regard how they can potentially further utilized combat outbreak

Language: Английский

---

Applications of artificial intelligence in battling against covid-19: A literature review

Chaos Solitons & Fractals, Journal Year: 2020, Volume and Issue: 142, P. 110338 - 110338

Published: Oct. 3, 2020

Language: Английский

---

Novel Feature Selection and Voting Classifier Algorithms for COVID-19 Classification in CT Images

IEEE Access, Journal Year: 2020, Volume and Issue: 8, P. 179317 - 179335

Published: Jan. 1, 2020

Diagnosis is a critical preventive step in Coronavirus research which has similar manifestations with other types of pneumonia. CT scans and X-rays play an important role that direction. However, processing chest images using them to accurately diagnose COVID-19 computationally expensive task. Machine Learning techniques have the potential overcome this challenge. This article proposes two optimization algorithms for feature selection classification COVID-19. The proposed framework three cascaded phases. Firstly, features are extracted from Convolutional Neural Network (CNN) named AlexNet. Secondly, algorithm, Guided Whale Optimization Algorithm (Guided WOA) based on Stochastic Fractal Search (SFS), then applied followed by balancing selected features. Finally, voting classifier, WOA Particle Swarm (PSO), aggregates different classifiers' predictions choose most voted class. increases chance individual classifiers, e.g. Support Vector (SVM), Networks (NN), k-Nearest Neighbor (KNN), Decision Trees (DT), show significant discrepancies. Two datasets used test model: containing clinical findings positive negative algorithm (SFS-Guided compared widely recent literature validate its efficiency. classifier (PSO-Guided-WOA) achieved AUC (area under curve) 0.995 superior classifiers terms performance metrics. Wilcoxon rank-sum, ANOVA, T-test statistical tests statistically assess quality as well.

Language: Английский

---

Applications of artificial intelligence in COVID-19 pandemic: A comprehensive review

Expert Systems with Applications, Journal Year: 2021, Volume and Issue: 185, P. 115695 - 115695

Published: Aug. 4, 2021

Language: Английский

---

COVID-19 CT Image Synthesis With a Conditional Generative Adversarial Network

IEEE Journal of Biomedical and Health Informatics, Journal Year: 2020, Volume and Issue: 25(2), P. 441 - 452

Published: Dec. 4, 2020

Coronavirus disease 2019 (COVID-19) is an ongoing global pandemic that has spread rapidly since December 2019. Real-time reverse transcription polymerase chain reaction (rRT-PCR) and chest computed tomography (CT) imaging both play important role in COVID-19 diagnosis. Chest CT offers the benefits of quick reporting, a low cost, high sensitivity for detection pulmonary infection. Recently, deep-learning-based computer vision methods have demonstrated great promise use medical applications, including X-rays, magnetic resonance imaging, imaging. However, training deep-learning model requires large volumes data, staff faces risk when collecting data due to infectivity disease. Another issue lack experts available labeling. In order meet requirements we propose image synthesis approach based on conditional generative adversarial network can effectively generate high-quality realistic images tasks. Experimental results show proposed method outperforms other state-of-the-art with generated indicates promising various machine learning applications semantic segmentation classification.

Language: Английский

---

Deep learning for diagnosis of COVID-19 using 3D CT scans

Computers in Biology and Medicine, Journal Year: 2021, Volume and Issue: 132, P. 104306 - 104306

Published: March 10, 2021

Language: Английский

---

Review on COVID‐19 diagnosis models based on machine learning and deep learning approaches

Expert Systems, Journal Year: 2021, Volume and Issue: 39(3)

Published: July 28, 2021

COVID-19 is the disease evoked by a new breed of coronavirus called severe acute respiratory syndrome 2 (SARS-CoV-2). Recently, has become pandemic infecting more than 152 million people in over 216 countries and territories. The exponential increase number infections rendered traditional diagnosis techniques inefficient. Therefore, many researchers have developed several intelligent techniques, such as deep learning (DL) machine (ML), which can assist healthcare sector providing quick precise diagnosis. this paper provides comprehensive review most recent DL ML for studies are published from December 2019 until April 2021. In general, includes 200 that been carefully selected publishers, IEEE, Springer Elsevier. We classify research tracks into two categories: present public datasets established extracted different countries. measures used to evaluate methods comparatively analysed proper discussion provided. conclusion, diagnosing outbreak prediction, SVM widely mechanism, CNN mechanism. Accuracy, sensitivity, specificity measurements previous studies. Finally, will guide community on upcoming development inspire their works future development. This

Language: Английский

---

Advanced Meta-Heuristics, Convolutional Neural Networks, and Feature Selectors for Efficient COVID-19 X-Ray Chest Image Classification

IEEE Access, Journal Year: 2021, Volume and Issue: 9, P. 36019 - 36037

Published: Jan. 1, 2021

The chest X-ray is considered a significant clinical utility for basic examination and diagnosis. human lung area can be affected by various infections, such as bacteria viruses, leading to pneumonia. Efficient reliable classification method facilities the diagnosis of infections. Deep transfer learning has been introduced pneumonia detection from X-rays in different models. However, there still need further improvements feature extraction advanced stages. This paper proposes with two stages classify cases images based on proposed Advanced Squirrel Search Optimization Algorithm (ASSOA). first stage processes Convolutional Neural Network (CNN) model named ResNet-50 image augmentation dropout processes. ASSOA algorithm then applied extracted features selection process. Finally, Multi-layer Perceptron (MLP) Network's connection weights are optimized (using selected features) input cases. A Kaggle (Pneumonia) dataset consists 5,863 employed experiments. compared (SS) optimization algorithm, Grey Wolf Optimizer (GWO), Genetic (GA) validate its efficiency. (ASSOA + MLP) also other classifiers, (SS MLP), (GWO (GA performance metrics. achieved mean accuracy (99.26%). MLP (99.7%) COVID-19 tested GitHub. results statistical tests demonstrate high effectiveness determining infected

Language: Английский

---