检索结果-内蒙古大学图书馆

Breast cancer classification in point-of-care ultrasound imaging—the impact of training data

Journal of Medical Imaging 2025年第1期12卷 014502页

作者： Karlsson, Jennie Arvidsson, Ida Sahlin, Freja Åström, Kalle Overgaard, Niels Christian Lång, Kristina Heyden, Anders Lund University Centre for Mathematical Sciences Division of Computer Vision and Machine Learning Lund Sweden Lund University Division of Diagnostic Radiology Department of Translational Medicine Lund Sweden Skåne University Hospital Unilabs Mammography Unit Malmö Sweden

Purpose: The survival rate of breast cancer for women in low- and middle-income countries is poor compared with that in high-income countries. Point-of-care ultrasound (POCUS) combined with deep learning could potentially be a suitable solution enabling early detection of breast cancer. We aim to improve a classification network dedicated to classifying POCUS images by comparing different techniques for increasing the amount of training data. Approach: Two data sets consisting of breast tissue images were collected, one captured with POCUS and another with standard ultrasound (US). The data sets were expanded by using different techniques, including augmentation, histogram matching, histogram equalization, and cycle-consistent adversarial networks (CycleGANs). A classification network was trained on different combinations of the original and expanded data sets. Different types of augmentation were investigated and two different CycleGAN approaches were implemented. Results: Almost all methods for expanding the data sets significantly improved the classification results compared with solely using POCUS images during the training of the classification network. When training the classification network on POCUS and CycleGAN-generated POCUS images, it was possible to achieve an area under the receiver operating characteristic curve of 95.3% (95% confidence interval 93.4% to 97.0%). Conclusions: Applying augmentation during training showed to be important and increased the performance of the classification network. Adding more data also increased the performance, but using standard US images or CycleGAN-generated POCUS images gave similar results. © The Authors.

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

Pulmofusion: Advancing Pulmonary Health with Efficient Multi-Modal Fusion

Pulmofusion: Advancing Pulmonary Health with Efficient Multi...

引用

IEEE International Symposium on Biomedical Imaging

作者： Ahmed Sharshar Yasser Attia Mohammad Yaqub Mohsen Guizani Department of Computer Vision MBZUAI UAE Department of Machine Learning MBZUAI UAE

ISBN: (数字)9798331520526

ISBN: (纸本)9798331520533

Traditional remote spirometry lacks the precision required for effective pulmonary monitoring. We present a novel, non-invasive approach using multimodal predictive models that integrate RGB or thermal video data with patient meta-data. Our method leverages energy-efficient Spiking Neural Networks (SNNs) for the regression of Peak Expiratory Flow (PEF) and classification of Forced Expiratory Volume (FEVl) and Forced Vital Capacity (FVC), using lightweight CNNs to overcome SNN limitations in regression tasks. Multimodal data integration is improved with a Multi-Head Attention Layer, and we employ K-Fold validation and en-semble learning to boost robustness. Using thermal data, our SNN models achieve 92% ± 2% accuracy on a breathing-cycle basis and 99.5% ± 0.5% patient-wise. PEF regression models attain Relative RMSEs of 0.11 ± 0.05 (thermal) and 0.26 ± 0.07 (RGB), with an MAE of 4.52% for FEV1/FVC predictions, establishing state-of-the-art performance. 1 1 Code and dataset can be found on https://***-sharshar/***

关键词： Spirometry Accuracy Lungs Scalability Spiking neural networks Infrared imaging Predictive models Metadata Robustness Monitoring

来源：评论

学校读者我要写书评

暂无评论

PULMOFUSION: ADVANCING PULMONARY HEALTH WITH EFFICIENT MULTI-MODAL FUSION

arXiv

引用

arXiv 2025年

作者： Sharshar, Ahmed Attia, Yasser Yaqub, Mohammad Guizani, Mohsen Department of Computer Vision MBZUAI United Arab Emirates Department of Machine Learning MBZUAI United Arab Emirates

Traditional remote spirometry lacks the precision required for effective pulmonary monitoring. We present a novel, non-invasive approach using multimodal predictive models that integrate RGB or thermal video data with patient metadata. Our method leverages energy-efficient Spiking Neural Networks (SNNs) for the regression of Peak Expiratory Flow (PEF) and classification of Forced Expiratory Volume (FEV1) and Forced Vital Capacity (FVC), using lightweight CNNs to overcome SNN limitations in regression tasks. Multimodal data integration is improved with a Multi-Head Attention Layer, and we employ K-Fold validation and ensemble learning to boost robustness. Using thermal data, our SNN models achieve 92% ± 2% accuracy on a breathing-cycle basis and 99.5% ± 0.5% patient-wise. PEF regression models attain Relative RMSEs of 0.11 ± 0.05 (thermal) and 0.26 ± 0.07 (RGB), with an MAE of 4.52% for FEV1/FVC predictions, establishing state-of-the-art performance.1 © 2025, CC BY.

关键词： Lung cancer

来源：评论

学校读者我要写书评

暂无评论

Optimizing 7-DOF Robot Manipulator Path Using Deep Reinforcement learning Techniques

Optimizing 7-DOF Robot Manipulator Path Using Deep Reinforce...

引用

International Workshop on Robot Sensing (ROSE)

作者： Mariam Kashkash Abdulmotaleb El Saddik Mohsen Guizani Machine Learning Department MBZUAI UAE University of Ottawa Canada Computer Vision Department MBZUAI UAE

ISBN: (数字)9798350362367

ISBN: (纸本)9798350362374

This paper proposes three different Deep Rein-forcement learning (DRL) techniques to find a free-obstacle path for a 7-DOF Robot Manipulator (RM). The robot is the Kinova Jaco Assistive Robot arm; its DH parameters and kinematics are presented. The suggested DRL methods are Deep Q-Network (DQN), Actor-Critic (AC), and Proximal Policy Optimization (PPO) algorithms. The environment, state space, action space, and reward function are defined to suit all proposed methods. The experiment is run to validate the performance of these methods in finding the path for the RM in two different environments. These environments differ in obstacles and complexity. The reward and average reward evaluation were used to evaluate the proposed methods. The results showed that the three models found the path in the suggested environments. The comparison between these methods is presented and discussed in this paper. The result discussion clarified the superiority of the PPO method in finding the free-obstacle path in a complex environment.

关键词： Kinematics Manipulators Assistive robots Robot sensing systems Deep reinforcement learning Complexity theory Sensors

来源：评论

学校读者我要写书评

暂无评论

Underwater Object Detection Enhancement via Channel Stabilization

Underwater Object Detection Enhancement via Channel Stabiliz...

引用

2022 International Conference on Digital Image Computing: Techniques and Applications, DICTA 2022

作者： Ali, Muhammad Khan, Salman Department of Machine Learning Mohamed bin Zayed University of AI Abu Dhabi UAE Department of Computer Vision Mohamed bin Zayed University of AI Abu Dhabi UAE

ISBN: (纸本)9781665456425

The complex marine environment exacerbates the challenges of object Abstract-The complex marine environment exacerbates the challenges of object detection manifold. With the advent of the modern era, marine trash presents a danger to the aquatic ecosystem, and it has always been challenging to address this issue with complete grip. Therefore, there is a significant need to precisely detect marine deposits and locate them accurately in challenging aquatic surroundings. To ensure the safety of the marine environment caused by waste, the deployment of underwater object detection is a crucial tool to mitigate the harm of such waste. Our work explains the image enhancement strategies used and experiments exploring the best detection obtained after applying these methods. Specifically, we evaluate Detectron 2's backbones performance using different base models and configurations for the underwater detection task. We first propose a channel stabilization technique on top of a simplified image enhancement model to help reduce haze and colour cast in training images. The proposed procedure shows improved results on multi-scale size objects present in the data set. After processing the images, we explore various backbones in Detectron2 to give the best detection accuracy for these images. In addition, we use a sharpening filter with augmentation techniques. This highlights the profile of the object which helps us recognize it easily. We demonstrate our results by verifying these on TrashCan Data set, both instance and material version. We then explore the best-performing backbone method for this setting. We apply our channel stabilization and augmentation methods to the best-performing technique. We also compare our detection results from Detectron2 using the best backbones with those from Deformable Transformer. The detection result for small size objects in the Instance-version of TRASHCAN 1.0 gives us a 9.53box we get the absolute gain of 7to the baseline. © 2022 IEEE.

关键词： Image enhancement

来源：评论

学校读者我要写书评

暂无评论

Pruning neural network models for gene regulatory dynamics using data and domain knowledge 38

Pruning neural network models for gene regulatory dynamics u...

引用

38th Conference on Neural Information Processing Systems, NeurIPS 2024

作者： Hossain, Intekhab Fischer, Jonas Burkholz, Rebekka Quackenbush, John Department of Biostatistics Harvard T.H. Chan School of Public Health BostonMA02115 United States Dep. for Computer Vision and Machine Learning Max Planck Institute for Informatics Saarbrücken Germany Helmholtz Center CISPA for Information Security Saarbrücken Germany

The practical utility of machine learning models in the sciences often hinges on their interpretability. It is common to assess a model's merit for scientific discovery, and thus novel insights, by how well it aligns with already available domain knowledge-a dimension that is currently largely disregarded in the comparison of neural network models. While pruning can simplify deep neural network architectures and excels in identifying sparse models, as we show in the context of gene regulatory network inference, state-of-the-art techniques struggle with biologically meaningful structure learning. To address this issue, we propose DASH‡, a generalizable framework that guides network pruning by using domain-specific structural information in model fitting and leads to sparser, better interpretable models that are more robust to noise. Using both synthetic data with ground truth information, as well as real-world gene expression data, we show that DASH, using knowledge about gene interaction partners within the putative regulatory network, outperforms general pruning methods by a large margin and yields deeper insights into the biological systems being studied. © 2024 Neural information processing systems foundation. All rights reserved.

关键词：

来源：评论

学校读者我要写书评

暂无评论

An Enhancement of Object Detection Using YOLO V8 and Mobile Net in Challenging Conditions

引用

SN computer Science 2025年第4期6卷 1-20页

作者： Pasupuleti, Shailaja Ramalakshmi, K. Gunasekaran, Hemalatha Arokiaraj, Rex Macedo Debnath, Saswati Jebaseeli, T. Jemima Department of Computer Science and Engineering Alliance University Karnataka Anekal Bangalore India AU-Centre of Excellence Department of Computer Vision Alliance University Karnataka Anekal Bangalore India College of Computing and Information Sciences University of Technology and Applied Sciences Ibri Oman Department of Information Technology College of Computing and Information Sciences University of Technology and Applied Sciences Ibri Oman Department of Computer Science and Engineering Alliance University Karnataka Bangalore India Division of Artificial Intelligence and Machine Learning Karunya Institute of Technology and Sciences Coimbatore India

Autonomous drones and deep learning neural networks are becoming popular tools to revolutionize aircraft operations by partially automating visual inspection processes in aircraft maintenance. The research aims to provide a trustworthy method for locating and classifying surface flaws on aircraft, such as dents, fractures, corrosion, and a few other anomalies. To assess the model performance with and without a lightweight network integration, the implementation merges YOLOv8 and Mobile Net architectures, using dropout regularization and data augmentation approaches. To guarantee the model's performance in low-light situations, the dataset has been carefully selected to contain images replicating such settings. Annotation, environment setup, model training, and online dataset scraping are all covered by the thorough technique. A web-scraped dataset is used to train and validate two popular semantic segmentation algorithms, YOLOv8 and Mobile Net, which show enough performance for segmenting and grading aircraft surface problems in practical settings. The results show that precision and recall values are improved using a hybrid technique that ensembles trained Mobile Net and YOLOv8 models. Using COCO metrics, in the proposed approach an assessment of Ensemble WBF, Mobile Net-YOLO, and YOLOv8 outcomes on test and validation sets, guaranteed reliable object recognition and classification abilities. © The Author(s), under exclusive licence to Springer Nature Singapore Pte Ltd. 2025.

关键词： Aircraft Classification Mobile-Net Object detection Weighted Box Fusion YOLOv8

来源：评论

学校读者我要写书评

暂无评论

Sailing in high-dimensional spaces: Low-dimensional embeddings through angle preservation

arXiv

引用

arXiv 2024年

作者： Fischer, Jonas Ma, Rong Department for Computer Vision and Machine Learning Max Planck Institute for Informatics Saarbrücken Germany Department for Biostatistics Harvard University BostonMA United States

Low-dimensional embeddings (LDEs) of high-dimensional data are ubiquitous in science and engineering. They allow us to quickly understand the main properties of the data, identify outliers and processing errors, and inform the next steps of data analysis. As such, LDEs have to be faithful to the original high-dimensional data, i.e., they should represent the relationships that are encoded in the data, both at a local as well as global scale. The current generation of LDE approaches focus on reconstructing local distances between any pair of samples correctly, often outperforming traditional approaches aiming at all distances. For these approaches, global relationships are, however, usually strongly distorted, often argued to be an inherent trade-off between local and global structure learning for embeddings. We suggest a new perspective on LDE learning, reconstructing angles between data points. We show that this approach, MERCAT, yields good reconstruction across a diverse set of experiments and metrics, and preserve structures well across all scales. Compared to existing work, our approach also has a simple formulation, facilitating future theoretical analysis and algorithmic improvements. © 2024, CC BY.

关键词： Embeddings

来源：评论

学校读者我要写书评

暂无评论

MRIShift: Disentangled Representation learning for 3D MRI Lesion Segmentation Under Distributional Shifts

MRIShift: Disentangled Representation Learning for 3D MRI Le...

引用

European Workshop on Visual Information Processing (EUVIP)

作者： Umaima Rahman Guangyi Chen Kun Zhang Computer Vision Department Mohamed Bin Zayed University of Artificial Intelligence Abu Dhabi UAE Machine Learning Department Carnegie Mellon University Pittsburgh PA USA

ISBN: (数字)9798350391145

ISBN: (纸本)9798350391152

In the clinical environment, heterogeneity of data coming from different centers poses challenges where the data may not conform to the assumption of being independent and identically distributed (i.i.d). As a result, it is essential to develop an approach that can generate better predictions even on samples it did not encounter during training. In this paper, we propose an unsupervised domain adaptation approach using disentangled representation learning to enhance the transferability of the 3D segmentation model for medical samples belonging to different distributions unseen during training. When dealing with medical image segmentation, it is essential to understand how features relate to voxel-wise labels. To achieve this, we focus on minimizing changes between data from different sources. This involves organizing the data into two categories: invariant components that remain consistent across different sources, and variant components that exhibit changes. By ensuring that domain shifts primarily affect the changing components, we aim to preserve the identifiability of latent variables. This helps in identifying joint data-label distributions within the target domain. We also introduce a new loss function that integrates image and feature level reconstruction with segmentation loss, enhancing the model's performance. Our experiments on real-world medical data demonstrate improved segmentation accuracy within known distributions and a notable 5% enhancement in handling out-of-distribution samples. Additionally, our method enhances the robustness of the model as demonstrated by the improvement in performance metrics such as R-AUC.

关键词： Training Image segmentation Adaptation models Visualization Three-dimensional displays Accuracy Disentangled representation learning Distributed databases Lesions Biomedical imaging

来源：评论

学校读者我要写书评

暂无评论

How to Choose a Reinforcement-learning Algorithm

arXiv

引用

arXiv 2024年

作者： Bongratz, Fabian Golkov, Vladimir Mautner, Lukas Libera, Luca Della Heetmeyer, Frederik Czaja, Felix Rodemann, Julian Cremers, Daniel Computer Vision Group Technical University of Munich Germany Munich Center for Machine Learning Germany Department of Statistics Ludwig-Maximilians-Universität Munich Germany

The field of reinforcement learning offers a large variety of concepts and methods to tackle sequential decision-making problems. This variety has become so large that choosing an algorithm for a task at hand can be challenging. In this work, we streamline the process of choosing reinforcement-learning algorithms and action-distribution families. We provide a structured overview of existing methods and their properties, as well as guidelines for when to choose which methods. An interactive version of these guidelines is available online at https://***/.MSC Codes 62M45 © 2024, CC BY-NC-SA.

关键词： Adversarial machine learning

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：