检索结果-内蒙古大学图书馆

Machine learning predicts long-term mortality after acute myocardial infarction using systolic time intervals and routinely collected clinical data

学校读者我要写书评

暂无评论

Intelligent Medicine 2024年第3期4卷 170-176页

作者： Bijan Roudini Boshra Khajehpiri Hamid Abrishami Moghaddam Mohamad Forouzanfar Department of Systems Engineering School of Advanced TechnologyUniversity of QuebecMontrealCanada Machine Vision and Medical Image Processing(MVMIP)Laboratory Faculty of Electrical and Computer EngineeringK.N.Toosi University of TechnologyTehranIran Research Center of the Montreal University Institute of Geriatrics MontrealCanada

Background Precise estimation of current and future comorbidities of patients with cardiovascular disease is an important factor in prioritizing continuous physiological monitoring and new *** learning(ML)models have shown satisfactory performance in short-term mortality prediction in patients with heart disease,whereas their utility in long-term predictions is *** study aimed to investigate the performance of tree-based ML models on long-term mortality prediction and effect of two recently introduced biomarkers on long-term *** This study used publicly available data from the Collaboration Center of Health Information Appli-cation at the Ministry of Health and Welfare,Taiwan,*** collected data were from patients admitted to the cardiac care unit for acute myocardial infarction(AMI)between November 2003 and September *** collected and analyzed mortality data up to December *** records were used to gather demo-graphic and clinical data,including age,gender,body mass index,percutaneous coronary intervention status,and comorbidities such as hypertension,dyslipidemia,ST-segment elevation myocardial infarction,and non-ST-segment elevation myocardial *** the data,collected from 139 patients with AMI,from medical and demographic records as well as two recently introduced biomarkers,brachial pre-ejection period(bPEP)and brachial ejection time(bET),we investigated the performance of advanced ensemble tree-based ML algorithms(random forest,AdaBoost,and XGBoost)to predict all-cause mortality within 14 years.A nested cross-validation was performed to evaluate and compare the performance of our developed models precisely with that of the conventional logistic regression(LR)as the baseline *** The developed ML models achieved significantly better performance compared to the baseline LR(C-Statistic,0.80 for random forest,0.79 for AdaBoost,and 0.78 for XGBoost,vs.0.77 for LR)(PRF<0.001,PAdaBoost<0.001,a

关键词： Electrocardiogram Predication Mortality prediction Machine learning

Dermoscopic image Classification Using Attention Mechanism and Ensemble Learning Approaches

学校读者我要写书评

暂无评论

Dermoscopic Image Classification Using Attention Mechanism a...

2023 IEEE International Conference on Big Data, BigData 2023

作者： Huang, Shanchuan Lei, Hongwei Jin, Liuhan Yang, Jinzhu Jiang, Tao Yao, Yudong Grzegorzek, Marcin Li, Chen Northeastern University Microscopic Image and Medical Image Analysis Group College of Medicine and Biological Information Engineering China Northeastern University Key Laboratory of Intelligent Computing in Medical Image Ministry of Education Liaoning Shenyang China Chengdu University of Traditional Chinese Medicine School of Intelligent Medicine Chengdu China Stevens Institute of Technology Department of Electrical and Computer Engineering United States Institute of Medical Informatics University of Luebeck Luebeck Germany

ISBN: (纸本)9798350324457

Background and purpose: Skin tumours have become one of the most common diseases worldwide. While benign ones are not usually a threat to human health, malignant ones can develop into skin cancer and become life-threatening if left untreated. Early detection of the disease is important for the treatment of patients with skin tumours and dermoscopy is the most effective means of diagnosing skin tumours. However, the complexity of skin tumour cells makes the diagnosis somewhat erroneous for doctors. Therefore, a dermoscopic classification network based on deep learning and computer-aided diagnostic techniques is needed to obtain a high diagnostic accuracy rate for skin tumours. Methods: In this paper, Deep-skin, a model for dermoscopic image classification is proposed, which is based on both attention mechanism and ensemble learning. Considering the characteristics of dermoscopic images, embedding different attention mechanisms on top of Inception-V3 has been suggested to obtain more potential features. We then improve the classification performance by late fusion of the different models. To demonstrate the effectiveness of Deep-skin, experiments and evaluations are performed on the publicly available dataset Skin Cancer: Malignant vs. Benign and compare the performance of Deep-skin with other classification models. Results: The experimental results indicate that Deep-skin performs well on the dataset in comparison to other models, achieving a maximum accuracy of 87.8%.Conclusion: In this paper, the Deep-skin model is proposed for the classification of dermoscopic images and has shown better performance. In the future, we intend to investigate better classification models for automatic diagnosis of skin tumours. Such models can potentially assist physicians and patients in clinical settings. © 2023 IEEE.

关键词： Attention mechanism Ensemble learning image classification Late fusion Skin Cancer

GEM: Context-Aware Gaze EstiMation with Visual Search Behavior Matching for Chest Radiograph

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Liu, Shaonan Chen, Wenting Liu, Jie Luo, Xiaoling Shen, Linlin Computer Vision Institute College of Computer Science and Software Engineering Shenzhen University China Department of Electrical Engineering City University of Hong Kong Hong Kong AI Research Center for Medical Image Analysis and Diagnosis Shenzhen University China Guangdong Provincial Key Laboratory of Intelligent Information Processing China

Gaze estimation is pivotal in human scene comprehension tasks, particularly in medical diagnostic analysis. Eye-tracking technology facilitates the recording of physicians’ ocular movements during image interpretation, thereby elucidating their visual attention patterns and information-processing strategies. In this paper, we initially define the context-aware gaze estimation problem in medical radiology report settings. To understand the attention allocation and cognitive behavior of radiologists during the medical image interpretation process, we propose a context-aware Gaze EstiMation (GEM) network that utilizes eye gaze data collected from radiologists to simulate their visual search behavior patterns throughout the image interpretation process. It consists of a context-awareness module, visual behavior graph construction, and visual behavior matching. Within the context-awareness module, we achieve intricate multimodal registration by establishing connections between medical reports and images. Subsequently, for a more accurate simulation of genuine visual search behavior patterns, we introduce a visual behavior graph structure, capturing such behavior through high-order relationships (edges) between gaze points (nodes). To maintain the authenticity of visual behavior, we devise a visual behavior-matching approach, adjusting the high-order relationships between them by matching the graph constructed from real and estimated gaze points. Extensive experiments on four publicly available datasets demonstrate the superiority of GEM over existing methods and its strong generalizability, which also provides a new direction for the effective utilization of diverse modalities in medical image interpretation and enhances the interpretability of models in the field of medical imaging. https://***/Tiger-SN/GEM. Copyright © 2024, The Authors. All rights reserved.

关键词： Eye movements

Bi-Directional MS Lesion Filling and Synthesis Using Denoising Diffusion Implicit Model-based Lesion Repainting

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Zhang, Jinwei Zuo, Lianrui Liu, Yihao Remedios, Samuel Landman, Bennett A. Prince, Jerry L. Carass, Aaron Image Analysis and Communications Laboratory Department of Electrical and Computer Engineering Johns Hopkins University BaltimoreMD21218 United States Department of Electrical and Computer Engineering Vanderbilt University NashvilleTN37235 United States Department of Computer Science Johns Hopkins University BaltimoreMD21218 United States

Automatic magnetic resonance (MR) image processing pipelines are widely used to study people with multiple sclerosis (PwMS), encompassing tasks such as lesion segmentation and brain parcellation. However, the presence of lesion often complicates these analysis, particularly in brain parcellation. Lesion filling is commonly used to mitigate this issue, but existing lesion filling algorithms often fall short in accurately reconstructing realistic lesion-free images, which are vital for consistent downstream analysis. Additionally, the performance of lesion segmentation algorithms is often limited by insufficient data with lesion delineation as training labels. In this paper, we propose a novel approach leveraging Denoising Diffusion Implicit Models (DDIMs) for both MS lesion filling and synthesis based on image inpainting. Our modified DDIM architecture, once trained, enables both MS lesion filing and synthesis. Specifically, it can generate lesion-free T1-weighted or FLAIR images from those containing lesions;Or it can add lesions to T1-weighted or FLAIR images of healthy subjects. The former is essential for downstream analyses that require lesion-free images, while the latter is valuable for augmenting training datasets for lesion segmentation tasks. We validate our approach through initial experiments in this paper and demonstrate promising results in both lesion filling and synthesis, paving the way for future work. Our code is available at https://***/IACL/UponAcceptance. © 2024, CC BY.

关键词： image segmentation

Unsupervised learning of spatially varying regularization for diffeomorphic image registration

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Chen, Junyu Wei, Shuwen Liu, Yihao Bian, Zhangxing He, Yufan Carass, Aaron Bai, Harrison Du, Yong Department of Radiology and Radiological Science Johns Hopkins School of Medicine MD United States Image Analysis and Communications Laboratory Department of Electrical and Computer Engineering Johns Hopkins University MD United States Department of Electrical and Computer Engineering Vanderbilt University TN United States NVIDIA Corporation BethesdaMD United States

Spatially varying regularization accommodates the deformation variations that may be necessary for different anatomical regions during deformable image registration. Historically, optimization-based registration models have harnessed spatially varying regularization to address anatomical subtleties. However, most modern deep learning-based models tend to gravitate towards spatially invariant regularization, wherein a homogenous regularization strength is applied across the entire image, potentially disregarding localized variations. In this paper, we propose a hierarchical probabilistic model that integrates a prior distribution on the deformation regularization strength, enabling the end-to-end learning of a spatially varying deformation regularizer directly from the data. The proposed method is straightforward to implement and easily integrates with various registration network architectures. Additionally, automatic tuning of hyperparameters is achieved through Bayesian optimization, allowing efficient identification of optimal hyperparameters for any given registration task. Comprehensive evaluations on publicly available datasets demonstrate that the proposed method significantly improves registration performance and enhances the interpretability of deep learning-based registration, all while maintaining smooth deformations. Copyright © 2024, The Authors. All rights reserved.

关键词： image registration

ISGAN: Unsupervised Domain Adaptation With Improved Symmetric GAN for Cross-Modality Multi-Organ Segmentation

学校读者我要写书评

暂无评论

IEEE Journal of Biomedical and Health Informatics 2024年第6期29卷 3874-3885页

作者： Jiapeng Li Yifan Zhang Lisheng Xu Yudong Yao Lin Qi College of Medicine and Biological Information Engineering Northeastern University Shenyang China Engineering Research Center of Medical Imaging and Intelligent Analysis Ministry of Education Shenyang China Key Laboratory of Medical Image Computing Ministry of Education Northeastern University Shenyang China Department of Electrical and Computer Engineering Stevens Institute of Technology Hoboken NJ USA

The differences between cross-modality medical images are significant, so several studies are working on unsupervised domain adaptation (UDA) segmentation, which aims to adapt a segmentation model trained on a labeled source domain to an unlabeled target domain. The conventional UDA segmentation strategy aims to integrate image generation and segmentation. However, conventional image generation modules only consider information from a single domain (source or target), resulting in visual inconsistencies. The image generation module may also lack anatomical constraints, leading to incorrect pseudo-label generation. To address these issues, we propose an improved symmetric generative adversarial network (ISGAN). Unlike conventional approaches that perform domain adaptation only in the source or target domain, ISGAN adopts a symmetric architecture using two-path domain adaptation to reduce the visual difference. In addition, ISGAN adopts a bidirectional training strategy to optimize the image generation and segmentation modules. The bidirectional training strategy introduces the anatomical constraints into the image generation module, thereby reducing the generation of incorrect pseudo labels. Finally, we validate ISGAN on two cross-modality datasets (the MMWHS cardiac dataset and Abdomen dataset). ISGAN delivers promising segmentation and generalization performance compared with state-of-the-art UDA methods.

关键词： image segmentation Training Biomedical imaging image synthesis Magnetic resonance imaging Computed tomography Feature extraction Generative adversarial networks Generators Diffusion models

Beyond MR image Harmonization: Resolution Matters Too

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Hays, Savannah P. Remedios, Samuel W. Zuo, Lianrui Mowry, Ellen M. Newsome, Scott D. Calabresi, Peter A. Carass, Aaron Dewey, Blake E. Prince, Jerry L. Image Analysis and Communications Laboratory Department of Electrical and Computer Engineering Johns Hopkins University BaltimoreMD21218 United States Department of Computer Science Johns Hopkins University BaltimoreMD21218 United States Department of Electrical and Computer Engineering Vanderbilt University NashvilleTN37235 United States Department of Neurology Johns Hopkins School of Medicine BaltimoreMD21287 United States

Magnetic resonance (MR) imaging is commonly used in the clinical setting to non-invasively monitor the body. There exists a large variability in MR imaging due to differences in scanner hardware, software, and protocol design. Ideally, a processing algorithm should perform robustly to this variability, but that is not always the case in reality. This introduces a need for image harmonization to overcome issues of domain shift when performing downstream analysis such as segmentation. Most image harmonization models focus on acquisition parameters such as inversion time or repetition time, but they ignore an important aspect in MR imaging—resolution. In this paper, we evaluate the impact of image resolution on harmonization using a pretrained harmonization algorithm. We simulate 2D acquisitions of various slice thicknesses and gaps from 3D acquired, 1mm3 isotropic MR images and demonstrate how the performance of a state-of-the-art image harmonization algorithm varies as resolution changes. We discuss the most ideal scenarios for image resolution including acquisition orientation when 3D imaging is not available, which is common for many clinical scanners. Our results show that harmonization on low-resolution images does not account for acquisition resolution and orientation variations. Super-resolution can be used to alleviate resolution variations but it is not always used. Our methodology can generalize to help evaluate the impact of image acquisition resolution for multiple tasks. Determining the limits of a pretrained algorithm is important when considering preprocessing steps and trust in the results. Copyright © 2024, The Authors. All rights reserved.

关键词： Magnetic resonance imaging

Feature Correlation Aggregation: on the Path to Better Graph Neural Networks

学校读者我要写书评

暂无评论

Feature Correlation Aggregation: on the Path to Better Graph...

Proceedings of the Digital image Computing: Technqiues and Applications (DICTA)

作者： Jieming Zhou Tong Zhang Pengfei Fang Lars Petersson Mehrtash Harandi College of Engineering and Computer Science Australian National University Canberra Australia Image and Visual Representation Laboratory EPFL Lausanne Switzerland Imaging and Computer Vision Group CSIRO Canberra Australia Department of Electrical and Computer Systems Engineering Monash University Melbourne Australia

Prior to the introduction of Graph Neural Networks (GNNs), modelling and analyzing irregular data, particularly graphs, was thought to be the Achilles’ heel of deep learning. The core concept of GNNs is to find a representation by recursively aggregating the representations of a central node and those of its neighbor, and many GNNs’ designs have demonstrated its success. However, most only focus on using the first-order information between a node and its neighbors. In this paper, we introduce a central node permutation variant function through a frustratingly simple and innocent-looking modification to the core operation of a GNN, namely the Feature cOrrelation aGgregation (FOG) module, which learns the second-order information from feature correlation between a node and its neighbors in the pipeline. By adding FOG into existing variants of GNNs, we empirically verify this second-order information complements the features generated by original GNNs across a broad set of benchmarks. A tangible boost in the model’s performance is observed where the model surpasses previous state-of-the-art results by a significant margin while employing fewer parameters. e.g., 26.202% improvement on a real-world molecular dataset using graph convolutional networks.

关键词：

Counterfactual Data Augmentation with Denoising Diffusion for Graph Anomaly Detection

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Xiao, Chunjing Pang, Shikang Xu, Xovee Li, Xuan Trajcevski, Goce Zhou, Fan The School of Computer and Information Engineering Henan University China The Henan Key Laboratory of Big Data Analysis and Processing Henan University Kaifeng475004 China The University of Electronic Science and Technology of China Sichuan Chengdu610054 China The National Key Laboratory of Fundamental Science on Synthetic Vision Sichuan University Chengdu610065 China The Department of Electrical and Computer Engineering Iowa State University AmesIA50011 United States

A critical aspect of Graph Neural Networks (GNNs) is to enhance the node representations by aggregating node neighborhood information. However, when detecting anomalies, the representations of abnormal nodes are prone to be averaged by normal neighbors, making the learned anomaly representations less distinguishable. To tackle this issue, we propose CAGAD - an unsupervised Counterfactual data Augmentation method for Graph Anomaly Detection - which introduces a graph pointer neural network as the heterophilic node detector to identify potential anomalies whose neighborhoods are normal-node-dominant. For each identified potential anomaly, we design a graph-specific diffusion model to translate a part of its neighbors, which are probably normal, into anomalous ones. At last, we involve these translated neighbors in GNN neighborhood aggregation to produce counterfactual representations of anomalies. Through aggregating the translated anomalous neighbors, counterfactual representations become more distinguishable and further advocate detection performance. The experimental results on four datasets demonstrate that CAGAD significantly outperforms strong baselines, with an average improvement of 2.35% on F1, 2.53% on AUC-ROC, and 2.79% on AUC-PR. Copyright © 2024, The Authors. All rights reserved.

关键词： Anomaly detection