Related references
Note: Only part of the references are listed.
Article
Computer Science, Theory & Methods
Haroon Wahab et al.
Summary: Video capsule endoscopy (VCE) is a revolutionary technology for early diagnosis of gastric disorders, but manual interpretation of VCE videos is time-consuming due to the high redundancy and subtle manifestation of anomalies. Several machine learning methods have been adopted to improve VCE analysis, but their clinical impact is yet to be explored. This survey aimed to bridge the gap between existing ML-based research and clinically significant rules established by gastroenterologists. A framework for interpreting raw frames and merging findings with meta-data was proposed. The challenges and opportunities for VCE analysis were discussed, and the importance of maximizing the discriminative power of features, creating large datasets, and ensuring explainability and reliability of ML-based diagnostics in VCE was emphasized.
FUTURE GENERATION COMPUTER SYSTEMS-THE INTERNATIONAL JOURNAL OF ESCIENCE
(2023)
Article
Computer Science, Theory & Methods
Gianni D'Angelo et al.
Summary: Diabetes mellitus is a global health problem, and its most debilitating complication, diabetic foot, increases the risk of hospitalization, morbidity, and mortality. This study presents a Genetic Programming-based approach called X-GPC, which provides a global interpretation of the diabetic foot ulcer diagnosis through a mathematical model. It also offers a consultable 3D graph for medical staff to understand patients' situations and make decisions for their healing. Experimental results show that the proposal achieves 100% accuracy in diagnosing diabetic foot, outperforming other state-of-the-art techniques.
FUTURE GENERATION COMPUTER SYSTEMS-THE INTERNATIONAL JOURNAL OF ESCIENCE
(2023)
Article
Computer Science, Theory & Methods
Sung-Jong Eun et al.
Summary: Recently, therapeutic exercise serious games have been conducted to enhance cognitive decline in dementia and aid physical rehabilitation. This study aims to design a digital healthcare application to improve the elderly's physical and cognitive functions. The study used an AI-based personalized system of difficulty level adjustment and relative scoring to motivate the user to keep playing the game. The study also conducted a three-month empirical assessment on user satisfaction and performance, showing higher immersion, satisfaction, and performance records compared to existing games.
FUTURE GENERATION COMPUTER SYSTEMS-THE INTERNATIONAL JOURNAL OF ESCIENCE
(2023)
Article
Computer Science, Theory & Methods
Yi Zhou et al.
Summary: This paper proposes a hybrid hard-soft label learning mechanism and consistency regularization to enhance a single model's disease detection capability. Experiments on public datasets show that the proposed model outperforms state-of-the-art methods with consistent improvements. The mean AUC on the CheXpert dataset is increased by 2.44%, and the Q.W. Kappa on the KaggleDR+ and FGADR datasets is increased by 5.65% and 4.66% respectively. The classification accuracy on the Clothing 1M dataset is increased by 4.47%.
FUTURE GENERATION COMPUTER SYSTEMS-THE INTERNATIONAL JOURNAL OF ESCIENCE
(2023)
Article
Computer Science, Theory & Methods
Jiatao Li et al.
Summary: With the increasing sales of the medical device market, the article proposes a solution for the growing medical incidents caused by passive devices in the medical device supply chain. By combining the traditional RBAC model and the ABAC model, the access control management in the supply chain can overcome limitations and achieve granular and dynamic permissions management. The implementation of the access control model in blockchain's smart contract ensures security and privacy while using blockchain technology's features for eliminating passive and inferior medical equipment sales activities.
FUTURE GENERATION COMPUTER SYSTEMS-THE INTERNATIONAL JOURNAL OF ESCIENCE
(2023)
Article
Computer Science, Theory & Methods
Xin Su et al.
Summary: The development of intelligent healthcare systems has increased the value of digital medical data. Federated learning shows promise in future digital healthcare by harnessing digital medical data for diagnosis assistance. However, the computing and storage constraints, as well as privacy risks, faced by federated nodes deployed at the edge of intelligent healthcare systems pose challenges. To address these challenges, this paper proposes a cloud-edge collaboration framework that combines federated learning and blockchain. It introduces a bi-level optimization scheduling model for intelligent healthcare systems, considering the large-scale access requirement of distributed generation, energy storage, and controllable load. Simulation results demonstrate reduced execution delay and power consumption, as well as improved interest coordination among stakeholders.
FUTURE GENERATION COMPUTER SYSTEMS-THE INTERNATIONAL JOURNAL OF ESCIENCE
(2023)
Article
Computer Science, Theory & Methods
Helena Liz et al.
Summary: Convolutional neural networks (CNNs) have dominated computer vision field due to their feature extraction ability and excellent performance in classification problems. However, they are considered black-box algorithms and lack interpretability. This paper proposes a deep learning methodology for imbalanced, multilabel chest X-ray datasets, establishing a baseline for the underutilized PadChest dataset and introducing a new explainable AI technique based on heatmaps.
FUTURE GENERATION COMPUTER SYSTEMS-THE INTERNATIONAL JOURNAL OF ESCIENCE
(2023)
Article
Computer Science, Theory & Methods
Chenbin Ma et al.
Summary: This study proposes a novel spatial-temporal-spectral fusion neural network (STSNet) for multi-task fine-grained assessment of tremor severity. The model efficiently fuses complementary information from static handwriting images and dynamic multi-sensory fusion signals, providing objective and accurate scores for tremor assessment.
FUTURE GENERATION COMPUTER SYSTEMS-THE INTERNATIONAL JOURNAL OF ESCIENCE
(2023)
Article
Computer Science, Theory & Methods
Shaoyi Du et al.
Summary: In this paper, a curriculum classification network based on margin-balancing multi-loss and ensemble learning method is proposed to address the difficulties of classification in different age groups and uneven distances within age groups using orthopantomogram images. The proposed method includes a curriculum learning framework, a margin-balancing multi-loss, and an ensemble feature learning method to improve classification accuracy. Experimental results on orthopantomograms dataset demonstrate that the proposed method performs well on different networks and achieves precise age estimation.
FUTURE GENERATION COMPUTER SYSTEMS-THE INTERNATIONAL JOURNAL OF ESCIENCE
(2023)
Article
Computer Science, Theory & Methods
Yousheng Zhou et al.
Summary: With the popularity of smart wearable devices, online diagnosis has become a promising medical technology, promoting the progress of digital healthcare. Online diagnostic services utilize the cloud to relieve computing and storage requirements of wearable devices, enabling remote collaboration and data sharing, providing instant access to diagnostics, and saving time and costs. However, the security risks posed by wireless transmission of wearable devices highlight the need for serious consideration of the security of online diagnosis. This paper proposes privacy-preserving logistic regression based online disease diagnosis (LR-DDH), achieving efficient computation and communication while preserving the privacy of medical data.
FUTURE GENERATION COMPUTER SYSTEMS-THE INTERNATIONAL JOURNAL OF ESCIENCE
(2023)
Article
Computer Science, Theory & Methods
Dong Zhang et al.
Summary: The structural and functional analysis of coronary arteries in XRA images is crucial for intraoperative treatment of coronary artery disease. AngioSFA, an efficient framework, integrates structural analysis with functional analysis by utilizing DTSN for structural analysis and DSLN for functional analysis. Experimental results show that AngioSFA achieves high accuracy in both structural and functional analysis, indicating its great potential in the intraoperative treatment of coronary artery disease.
FUTURE GENERATION COMPUTER SYSTEMS-THE INTERNATIONAL JOURNAL OF ESCIENCE
(2023)
Article
Computer Science, Theory & Methods
Xuanwei Zeng et al.
Summary: Postoperative delirium is a common and preventable complication after cardiovascular surgery, with increased morbidity and mortality risk. Limited strategies exist for identifying at-risk patients. This observational study collected intraoperative electroencephalography data from 50 cardiothoracic surgery patients and found that those who experienced delirium postoperatively had enhanced causal effects in the default mode network (DMN), particularly in the delta band. Using these findings, the CatBoost classifier accurately distinguished between delirious and non-delirious patients with an 89.1% success rate. These results help explain disrupted information processing in delirious patients and aid in predicting postoperative delirium.
FUTURE GENERATION COMPUTER SYSTEMS-THE INTERNATIONAL JOURNAL OF ESCIENCE
(2023)
Article
Computer Science, Theory & Methods
Ahmed M. Anter et al.
Summary: Parkinson's disease (PD) is a degenerative neurological disease, and early diagnosis is crucial. Monitoring PD progression from voice records is a promising technique for IoT-based telemedicine in smart homes. However, selecting the most relevant voice features fast and accurately for early diagnosis is still an open question.
FUTURE GENERATION COMPUTER SYSTEMS-THE INTERNATIONAL JOURNAL OF ESCIENCE
(2023)
