Survey of Explainable AI Techniques in Healthcare

Sensors, Год журнала: 2023, Номер 23(2), С. 634 - 634

Опубликована: Янв. 5, 2023

Artificial intelligence (AI) with deep learning models has been widely applied in numerous domains, including medical imaging and healthcare tasks. In the field, any judgment or decision is fraught risk. A doctor will carefully judge whether a patient sick before forming reasonable explanation based on patient's symptoms and/or an examination. Therefore, to be viable accepted tool, AI needs mimic human interpretation skills. Specifically, explainable (XAI) aims explain information behind black-box model of that reveals how decisions are made. This paper provides survey most recent XAI techniques used related applications. We summarize categorize types, highlight algorithms increase interpretability topics. addition, we focus challenging problems applications provide guidelines develop better interpretations using concepts image text analysis. Furthermore, this future directions guide developers researchers for prospective investigations clinical topics, particularly imaging.

Язык: Английский

---

NAGNN: Classification of COVID‐19 based on neighboring aware representation from deep graph neural network

International Journal of Intelligent Systems, Год журнала: 2021, Номер 37(2), С. 1572 - 1598

Опубликована: Сен. 21, 2021

COVID-19 pneumonia started in December 2019 and caused large casualties huge economic losses. In this study, we intended to develop a computer-aided diagnosis system based on artificial intelligence automatically identify the chest computed tomography images. We utilized transfer learning obtain image-level representation (ILR) backbone deep convolutional neural network. Then, novel neighboring aware (NAR) was proposed exploit relationships between ILR vectors. To information feature space of ILRs, an graph generated k-nearest neighbors algorithm, which ILRs were linked with their ILRs. Afterward, NARs by fusion graph. On basis representation, end-to-end classification architecture called network (NAGNN) proposed. The private public data sets used for evaluation experiments. Results revealed that our NAGNN outperformed all 10 state-of-the-art methods terms generalization ability. Therefore, is effective detecting COVID-19, can be clinical diagnosis.

Язык: Английский

---

Automated detection and forecasting of COVID-19 using deep learning techniques: A review

Neurocomputing, Год журнала: 2024, Номер 577, С. 127317 - 127317

Опубликована: Янв. 26, 2024

Язык: Английский

---

Self-attention based progressive generative adversarial network optimized with momentum search optimization algorithm for classification of brain tumor on MRI image

Biomedical Signal Processing and Control, Год журнала: 2023, Номер 88, С. 105597 - 105597

Опубликована: Окт. 24, 2023

Язык: Английский

---

Fusion of transfer learning models with LSTM for detection of breast cancer using ultrasound images

Computers in Biology and Medicine, Год журнала: 2024, Номер 169, С. 107914 - 107914

Опубликована: Янв. 4, 2024

Язык: Английский

---

A Systematic Review of Graph Neural Network in Healthcare-Based Applications: Recent Advances, Trends, and Future Directions

IEEE Access, Год журнала: 2024, Номер 12, С. 15145 - 15170

Опубликована: Янв. 1, 2024

Graph neural network (GNN) is a formidable deep learning framework that enables the analysis and modeling of intricate relationships present in data structured as graphs. In recent years, burgeoning interest has arisen exploiting latent capabilities GNN for healthcare-based applications, capitalizing on their aptitude complex unearthing profound insights from graph-structured data. However, to best our knowledge, no study systemically reviewed studies conducted healthcare domain. This furnished an all-encompassing erudite overview prevailing cutting-edge research healthcare. Through assimilation studies, current trends, recurrent challenges, promising future opportunities applications have been identified. China emerged leading country conduct GNN-based domain, followed by USA, UK, Turkey. Among various aspects healthcare, disease prediction drug discovery emerge most prominent areas focus application, indicating potential advancing diagnostic therapeutic approaches. proposed questions regarding diverse domain addressed them through in-depth analysis. can provide practitioners researchers with into landscape guide institutes, researchers, governments demonstrating ways which contribute development effective efficient systems.

Язык: Английский

---

Epileptic Seizures Detection in EEG Signals Using Fusion Handcrafted and Deep Learning Features

Sensors, Год журнала: 2021, Номер 21(22), С. 7710 - 7710

Опубликована: Ноя. 19, 2021

Epilepsy is a brain disorder disease that affects people's quality of life. Electroencephalography (EEG) signals are used to diagnose epileptic seizures. This paper provides computer-aided diagnosis system (CADS) for the automatic seizures in EEG signals. The proposed method consists three steps, including preprocessing, feature extraction, and classification. In order perform simulations, Bonn Freiburg datasets used. Firstly, we band-pass filter with 0.5-40 Hz cut-off frequency removal artifacts datasets. Tunable-Q Wavelet Transform (TQWT) signal decomposition. second step, various linear nonlinear features extracted from TQWT sub-bands. this statistical, frequency, based on fractal dimensions (FDs) entropy theories. classification different approaches conventional machine learning (ML) deep (DL) discussed. CNN-RNN-based DL number layers applied. have been fed input CNN-RNN model, satisfactory results reported. K-fold cross-validation k = 10 employed demonstrate effectiveness procedure. revealed achieved an accuracy 99.71% 99.13%, respectively.

Язык: Английский

---

Multi-class disease detection using deep learning and human brain medical imaging

Biomedical Signal Processing and Control, Год журнала: 2023, Номер 85, С. 104875 - 104875

Опубликована: Март 31, 2023

Язык: Английский

---

Deep learning approach for brain tumor classification using metaheuristic optimization with gene expression data

International Journal of Imaging Systems and Technology, Год журнала: 2023, Номер 34(2)

Опубликована: Дек. 16, 2023

Abstract This study addresses the critical challenge of accurately classifying brain tumors using artificial intelligence. Early detection is crucial, as untreated can be fatal. Despite advances in AI, remains a challenging task. To address this challenge, we propose novel optimization approach called PSCS combined with deep learning for tumor classification. optimizes classification process by improving Particle Swarm Optimization (PSO) exploitation Cuckoo search (CS) algorithm. Next, classified gene expression data Deep Learning (DL) to identify different groups or classes related particular along technique. The proposed technique DL achieves much better accuracy than other existing and Machine models evaluation matrices such Recall, Precision, F1‐Score, confusion matrix. research contributes AI‐driven diagnosis classification, offering promising solution improved patient outcomes.

Язык: Английский

---

Advance brain tumor segmentation using feature fusion methods with deep U-Net model with CNN for MRI data

Journal of King Saud University - Computer and Information Sciences, Год журнала: 2023, Номер 35(9), С. 101793 - 101793

Опубликована: Окт. 1, 2023

In modern healthcare, the precision of medical image segmentation holds immense significance for diagnosis and treatment planning. Deep learning techniques, such as CNNs, UNETs, Transformers, have revolutionized this field by automating previously labor-intensive manual processes. However, challenges like intricate structures indistinct features persist, leading to accuracy issues. Researchers are diligently addressing these further unlock potential in healthcare transformation. To enhance brain tumor MRI segmentation, our study introduces three novel feature-enhanced hybrid UNet models (FE-HU-NET): FE1-HU-NET, FE2-HU-NET, FE3-HU-NET. Our approach encompasses main aspects. Initially, we emphasize feature enhancement during preprocessing stage. We apply distinct techniques—CLAHE, MHE, MBOBHE—to each model. Secondly, tailor architecture model results, focusing on a personalized layered design. Lastly, employ CNN post-processing refine outcomes through additional convolutional layers. The HU-Net module, shared across models, integrates customized layer CNN. also introduce an alternative variant, FE4-HU-NET, utilizing DeepLABv3 Incorporating CLAHE bolstered layers, variant offers approach. Rigorous experimentation underscores excellence proposed framework distinguishing complex tissues, surpassing current state-of-the-art models. Impressively, achieve rates exceeding 99% two publicly available datasets. Performance metrics Jaccard index, sensitivity, specificity substantiate effectiveness Hybrid U-Net

Язык: Английский

---