Prediction of Alzheimer's progression based on multimodal Deep-Learning-based fusion and visual Explainability of time-series data

Information Fusion, Journal Year: 2022, Volume and Issue: 92, P. 363 - 388

Published: Dec. 5, 2022

Language: Английский

---

A unifying view of class overlap and imbalance: Key concepts, multi-view panorama, and open avenues for research

Information Fusion, Journal Year: 2022, Volume and Issue: 89, P. 228 - 253

Published: Aug. 20, 2022

Language: Английский

---

Review of Machine Learning in Lung Ultrasound in COVID-19 Pandemic

Journal of Imaging, Journal Year: 2022, Volume and Issue: 8(3), P. 65 - 65

Published: March 5, 2022

Ultrasound imaging of the lung has played an important role in managing patients with COVID-19-associated pneumonia and acute respiratory distress syndrome (ARDS). During COVID-19 pandemic, ultrasound (LUS) or point-of-care (POCUS) been a popular diagnostic tool due to its unique capability logistical advantages over chest X-ray CT. Pneumonia/ARDS is associated sonographic appearances pleural line irregularities B-line artefacts, which are caused by interstitial thickening inflammation, increase number severity. Artificial intelligence (AI), particularly machine learning, increasingly used as critical that assists clinicians LUS image reading decision making. We conducted systematic review from academic databases (PubMed Google Scholar) preprints on arXiv TechRxiv state-of-the-art learning technologies for images diagnosis. Openly accessible datasets listed. Various architectures have employed evaluate showed high performance. This paper will summarize current development AI management outlook emerging trends combining AI-based robotics, telehealth, other techniques.

Language: Английский

---

CNN-KCL: Automatic myocarditis diagnosis using convolutional neural network combined with k-means clustering

Mathematical Biosciences & Engineering, Journal Year: 2022, Volume and Issue: 19(3), P. 2381 - 2402

Published: Jan. 1, 2022

Myocarditis is the form of an inflammation middle layer heart wall which caused by a viral infection and can affect muscle its electrical system. It has remained one most challenging diagnoses in cardiology. Myocardial prime cause unexpected death approximately 20% adults less than 40 years age. Cardiac MRI (CMR) been considered noninvasive golden standard diagnostic tool for suspected myocarditis plays indispensable role diagnosing various cardiac diseases. However, performance CMR depends heavily on clinical presentation features such as chest pain, arrhythmia, failure. Besides, other imaging factors like artifacts, technical errors, pulse sequence, acquisition parameters, contrast agent dose, more importantly qualitatively visual interpretation result diagnosis. This paper introduces new deep learning-based model called Convolutional Neural Network-Clustering (CNN-KCL) to diagnose Myocarditis. In this study, we used 47 subjects with total number 98,898 images disease. Our results demonstrate that proposed method achieves accuracy 97.41% based 10 fold-cross validation technique 4 clusters diagnosis To best our knowledge, research first use learning algorithms myocarditis.

Language: Английский

---

Uncertainty-driven ensembles of multi-scale deep architectures for image classification

Information Fusion, Journal Year: 2022, Volume and Issue: 89, P. 53 - 65

Published: Aug. 13, 2022

The use of automatic systems for medical image classification has revolutionized the diagnosis a high number diseases. These alternatives, which are usually based on artificial intelligence (AI), provide helpful tool clinicians, eliminating inter and intra-observer variability that diagnostic process entails. Convolutional Neural Network (CNNs) have proved to be an excellent option this purpose, demonstrating large performance in wide range contexts. However, it is also extremely important quantify reliability model's predictions order guarantee confidence classification. In work, we propose multi-level ensemble system Bayesian Deep Learning approach maximize while providing uncertainty each decision. This combines information extracted from different architectures by weighting their results according predictions. Performance evaluated real scenarios: first one, aim differentiate between pulmonary pathologies: controls vs bacterial pneumonia viral pneumonia. A two-level decision tree employed divide 3-class into two binary classifications, yielding accuracy 98.19%. second context, assessed Parkinson's disease, leading 95.31%. reduced preprocessing needed obtaining performance, addition provided about evidence applicability used as aid clinicians.

Language: Английский

---

Explanation-Driven HCI Model to Examine the Mini-Mental State for Alzheimer’s Disease

ACM Transactions on Multimedia Computing Communications and Applications, Journal Year: 2022, Volume and Issue: 20(2), P. 1 - 16

Published: April 1, 2022

Directing research on Alzheimer’s disease toward only early prediction and accuracy cannot be considered a feasible approach tackling ubiquitous degenerative today. Applying deep learning (DL), Explainable artificial intelligence, advancing the human-computer interface (HCI) model can leap forward in medical research. This aims to propose robust explainable HCI using SHAPley additive explanation, local interpretable model-agnostic explanations, DL algorithms. The use of algorithms—logistic regression (80.87%), support vector machine (85.8%), k -nearest neighbor (87.24%), multilayer perceptron (91.94%), decision tree (100%)—and explainability help exploring untapped avenues for sciences that mold future models. presented model’s results show improved by incorporating user-friendly computer into decision-making, implying high significance level context biomedical clinical

Language: Английский

---

Medical images classification using deep learning: a survey

Multimedia Tools and Applications, Journal Year: 2023, Volume and Issue: 83(7), P. 19683 - 19728

Published: July 28, 2023

Language: Английский

---

COVID-19-The Role of Artificial Intelligence, Machine Learning, and Deep Learning: A Newfangled

Archives of Computational Methods in Engineering, Journal Year: 2023, Volume and Issue: 30(4), P. 2667 - 2682

Published: Jan. 17, 2023

Language: Английский

---

Role of Artificial Intelligence in COVID-19 Detection

Sensors, Journal Year: 2021, Volume and Issue: 21(23), P. 8045 - 8045

Published: Dec. 1, 2021

The global pandemic of coronavirus disease (COVID-19) has caused millions deaths and affected the livelihood many more people. Early rapid detection COVID-19 is a challenging task for medical community, but it also crucial in stopping spread SARS-CoV-2 virus. Prior substantiation artificial intelligence (AI) various fields science encouraged researchers to further address this problem. Various imaging modalities including X-ray, computed tomography (CT) ultrasound (US) using AI techniques have greatly helped curb outbreak by assisting with early diagnosis. We carried out systematic review on state-of-the-art applied CT, US images detect COVID-19. In paper, we discuss approaches used authors significance these research efforts, potential challenges, future trends related implementation an system during pandemic.

Language: Английский

---

Pulmonary COVID-19: Learning Spatiotemporal Features Combining CNN and LSTM Networks for Lung Ultrasound Video Classification

Sensors, Journal Year: 2021, Volume and Issue: 21(16), P. 5486 - 5486

Published: Aug. 14, 2021

Deep Learning is a very active and important area for building Computer-Aided Diagnosis (CAD) applications. This work aims to present hybrid model classify lung ultrasound (LUS) videos captured by convex transducers diagnose COVID-19. A Convolutional Neural Network (CNN) performed the extraction of spatial features, temporal dependence was learned using Long Short-Term Memory (LSTM). Different types convolutional architectures were used feature extraction. The (CNN-LSTM) hyperparameters optimized Optuna framework. best composed an Xception pre-trained on ImageNet LSTM containing 512 units, configured with dropout rate 0.4, two fully connected layers 1024 neurons each, sequence 20 frames in input layer (20×2018). presented average accuracy 93% sensitivity 97% COVID-19, outperforming models based purely approaches. Furthermore, transfer learning provided comparable results LUS images. corroborate other studies showing that this classification can be tool fight against COVID-19 diseases.

Language: Английский

---