检索结果-内蒙古大学图书馆

arXiv 2024年

作者： Atad, Matan Schinz, David Moeller, Hendrik Graf, Robert Wiestler, Benedikt Rueckert, Daniel Navab, Nassir Kirschke, Jan S. Keicher, Matthias Department of Diagnostic and Interventional Neuroradiology Klinikum rechts der Isar Technical University of Munich Germany Institute for Artificial Intelligence and Computer Science in Medicine Technical University of Munich Germany Computer Aided Medical Procedures Technical University of Munich Germany AI for Image-Guided Diagnosis and Therapy Technical University of Munich Germany

Counterfactual explanations (CEs) aim to enhance the interpretability of machine learning models by illustrating how alterations in input features would affect the resulting predictions. Common CE approaches require an additional model and are typically constrained to binary counterfactuals. In contrast, we propose a novel method that operates directly on the latent space of a generative model, specifically a Diffusion Autoencoder (DAE). This approach offers inherent interpretability by enabling the generation of CEs and the continuous visualization of the model’s internal representation across decision boundaries. Our method leverages the DAE’s ability to encode images into a semantically rich latent space in an unsupervised manner, eliminating the need for labeled data or separate feature extraction models. We show that these latent representations are helpful for medical condition classification and the ordinal regression of severity pathologies, such as vertebral compression fractures (VCF) and diabetic retinopathy (DR). Beyond binary CEs, our method supports the visualization of ordinal CEs using a linear model, providing deeper insights into the model’s decision-making process and enhancing interpretability. Experiments across various medical imaging datasets demonstrate the method’s advantages in interpretability and versatility. The linear manifold of the DAE’s latent space allows for meaningful interpolation and manipulation, making it a powerful tool for exploring medical image properties. Our code is available at https://***/10.5281/zenodo.13859266. © 2024, CC BY.

关键词： Labeled data

来源：评论

学校读者我要写书评

暂无评论

E-Buddy for Rescue Child Labour

E-Buddy for Rescue Child Labour

引用

BIT Conference (BITCON), International

作者： Ajmeera Kiran Prithiviraj Ananth P Veera Prakash N. Kumareshan Ramesh Kumar Ayyasamy P. Chinnasamy Department of Computer Science and Engineering MLR Institute of Technology Hyderabad India Department of CSE Sona College of Technology Salem Dept of CSE Srinivasa Ramanujan Institute of Technology (Autonomous) Ananthapuramu Andhra Pradesh Department of ECE Professor/Centre for Advances in Signal Processing and Sensor Networks Sri Eshwar College of Engineering Coimbatore Faculty of Information and Communication Technology Universiti Tunku Abdul Rahman (UTAR) Kampar Malaysia Department of Computer Science and Engineering School of Computing Kalasalingam Academy of Research and Education Tamilnadu India

ISBN: (数字)9798331518394

ISBN: (纸本)9798331518400

Ebuddy is a ground breaking platform dedicated to rescuing and rehabilitating child laboures. By leveraging advanced technology, this initiative effectively connects with at-risk children, providing them with crucial education and support services. With a mission to break the vicious cycle of poverty and exploitation, Ebuddy collaborates with local communities and organizations to raise awareness about child labor and advocate for policies that safeguard children's rights. This platform offers comprehensive support services aimed at addressing the children's physical, emotional, and psychological well-being. By providing counseling, rehabilitation, and necessary medical assistance, Ebuddy empowers children to leave their past behind and embrace a better future.

关键词： Employee welfare Pediatrics Education Psychology Morphology Organizations

来源：评论

学校读者我要写书评

暂无评论

AN AUTOMATED PIPELINE FOR TUMOUR-INFILTRATING LYMPHOCYTE SCORING IN BREAST CANCER

arXiv

引用

arXiv 2023年

作者： Shephard, Adam J. Jahanifar, Mostafa Wang, Ruoyu Dawood, Muhammad Graham, Simon Sidlauskas, Kastytis Khurram, Syed Ali Rajpoot, Nasir M. Ahmed Raza, Shan E. Tissue Image Analytics Centre Department of Computer Science University of Warwick United Kingdom Barts Cancer Institute Queen Mary University of London United Kingdom School of Clinical Dentistry University of Sheffield United Kingdom

Tumour-infiltrating lymphocytes (TILs) are considered as a valuable prognostic markers in both triple-negative and human epidermal growth factor receptor 2 (HER2) breast cancer. In this study, we introduce an innovative deep learning pipeline based on the Efficient-UNet architecture to compute a TILs score for breast cancer whole slide images. Our pipeline first segments tumour-stroma regions and generates a tumour bulk mask. Subsequently, it detects TILs within the tumour-associated stroma, generating a TILs score by closely mirroring the pathologist’s workflow. Our method exhibits state-of-the-art performance in segmenting tumour/stroma areas and TILs detection, as demonstrated by internal cross-validation on the TiGER Challenge training dataset and evaluation on the final leaderboards. Additionally, our TILs score proves competitive in predicting survival outcomes within the same challenge, underscoring the clinical relevance and potential of our automated TILs scoring system as a breast cancer prognostic tool. © 2023, CC BY-NC-SA.

关键词： Tumors

来源：评论

学校读者我要写书评

暂无评论

To Make Yourself Invisible with Adversarial Semantic Contours

arXiv

引用

arXiv 2023年

作者： Zhang, Yichi Zhu, Zijian Su, Hang Zhu, Jun Zheng, Shibao He, Yuan Xue, Hui Department of Computer Science and Technology Institute for Artificial Intelligence THBI Lab Tsinghua University Beijing100084 China Institute of Image Communication and Network Engineering Shanghai Jiao Tong University Shanghai200240 China Alibaba Group Hangzhou311121 China

Modern object detectors are vulnerable to adversarial examples, which may bring risks to real-world applications. The sparse attack is an important task which, compared with the popular adversarial perturbation on the whole image, needs to select the potential pixels that is generally regularized by an 0-norm constraint, and simultaneously optimize the corresponding texture. The non-differentiability of 0 norm brings challenges and many works on attacking object detection adopted manually-designed patterns to address them, which are meaningless and independent of objects, and therefore lead to relatively poor attack performance. In this paper, we propose Adversarial Semantic Contour (ASC), an MAP estimate of a Bayesian formulation of sparse attack with a deceived prior of object contour. The object contour prior effectively reduces the search space of pixel selection and improves the attack by introducing more semantic bias. Extensive experiments demonstrate that ASC can corrupt the prediction of 9 modern detectors with different architectures (e.g., one-stage, two-stage and Transformer) by modifying fewer than 5% of the pixels of the object area in COCO in white-box scenario and around 10% of those in black-box scenario. We further extend the attack to datasets for autonomous driving systems to verify the effectiveness. We conclude with cautions about contour being the common weakness of object detectors with various architecture and the care needed in applying them in safety-sensitive scenarios. © 2023, CC BY.

关键词： Semantics

来源：评论

学校读者我要写书评

暂无评论

Transclaw U-Net: Claw U-Net With Transformers for Medical image Segmentation

Transclaw U-Net: Claw U-Net With Transformers for Medical Im...

引用

IEEE International Conference on Information Communication and Signal processing (ICICSP)

作者： Chang Yao Menghan Hu Qingli Li Guangtao Zhai Xiao-Ping Zhang Shanghai Key Laboratory of Multidimensional Information Processing East China Normal University Shanghai China Institute of Image Communication and Information Processing Shanghai Jiao Tong University Shanghai China Department of Electrical Computer and Biomedical Engineering Ryerson University Toronto Canada

In medical image analysis, the long-range spatial features are often not accurately obtained by the traditional convolutional neural networks. Hence, we propose a TransClaw U-Net network structure. The transformer part is added after three convolution operations to fuse shallow features extracted by convolution operations for maximally encoding the long-range spatial features between patches. The “Claw” in TransClaw U-net means that we add the bottom upsampling part to retain the deepest feature information for detail segmentation. In addition, the modified three-channel global attention mechanism to blend the outputs of three channels (the encoding part, the bottom upsampling part and the decoding part) to effectively extract image contours. The experimental results on Synapse Multi-organ Segmentation Dataset show that TransClaw U-Net performs better than other networks. The results of ablation experiments prove the effectiveness of the three improved components of the network and influence of input image size and skip-connection numbers on network performance. The source code will be publicly available once the paper is accepted.

关键词： Measurement image segmentation image coding Convolution Fuses Source coding Transformers

来源：评论

学校读者我要写书评

暂无评论

Style Content Decomposition-based Data Augmentation for Domain Generalizable Medical image Segmentation

arXiv

引用

arXiv 2025年

作者： Shen, Zhiqiang Cao, Peng Yang, Jinzhu Zaiane, Osmar R. Chen, Zhaolin School of Computer Science and Engineering Northeastern University Shenyang China Key Laboratory of Intelligent Computing in Medical Image Ministry of Education Shenyang China Alberta Machine Intelligence Institute University of Alberta EdmontonAB Canada Monash Biomedical Imaging Monash University Australia Department of Data Science and AI Monash University Australia

Due to the domain shifts between training and testing medical images, learned segmentation models often experience significant performance degradation during deployment. In this paper, we first decompose an image into its style code and content map and reveal that domain shifts in medical images involve: style shifts (i.e., differences in image appearance) and content shifts (i.e., variations in anatomical structures), the latter of which has been largely overlooked. To this end, we propose StyCona, a style content decomposition-based data augmentation method that innovatively augments both image style and content within the rank-one space, for domain generalizable medical image segmentation. StyCona is a simple yet effective plug-and-play module that substantially improves model generalization without requiring additional training parameters or modifications to the segmentation model architecture. Experiments on cross-sequence, cross-center, and cross-modality medical image segmentation settings with increasingly severe domain shifts, demonstrate the effectiveness of StyCona and its superiority over state-of-the-arts. The code is available at https://***/Senyh/StyCona. Copyright © 2025, The Authors. All rights reserved.

关键词： Medical imaging

来源：评论

学校读者我要写书评

暂无评论

Automatic License Plate Detection Using Information processing System Vision and Deep Learning

Automatic License Plate Detection Using Information Processi...

引用

Recent Trends in Microelectronics, Automation, Computing and Communications Systems (ICMACC), International Conference on

作者： Avinash Sharma Ishita Dwivedi Divya Dawar Rini Saxena Tarkcshwar Barua Parul Goyel Department of information processing system Science and Engineering Chandigarh Engineering Chandigarh Group of Colleges Mohali India Department of CSE(AIML) Chandigarh Engineering Chandigarh Group of Colleges Mohali India Computer Science & Engineering Department Roorkee Institute of Technology Roorkee India CSE Department M. M. Engineering College Maharishi Markandeshwar University Mullana Ambala Haryana India

ISBN: (数字)9798350366570

ISBN: (纸本)9798350366587

The content of this probe is to overcome the current cognitive content with ALPR playacting, with a special accent on developing a dead and impelling playacting for distinguishing License plates from video film. The study attempts to ameliorate the presentation norms of ALPR technology by utilizing the powerful accumulation of optical character identification (OCR)[20] and deep learning based object detection algorithmic program. The core of this occupation is the use of the cutting-edge YOLOv8. object distinguishing hypothesis, which has been pains taking and disciplined on an unequaled dataset premeditated with License plate detection in mind. Focusing on quality and efficiency, the YOLOv8 model accomplish an amazing 99.8 quality rate when it comes to accurately localization and categorization License plates[18] inside video frames. This occupation aims to formalize the willingness and dependability of the advisable ALPR playacting through extensive scientific research. The project aims to intensify ALPR technology and determinant the forthcoming of transport and police investigation playactings[18] by breaking through current obstruction and establishing new presentation norms.

关键词： Deep learning YOLO Pain Streaming media Real-time systems Microelectronics Object recognition Optical films Probes License plate recognition

来源：评论

学校读者我要写书评

暂无评论

EWT: Efficient Wavelet-Transformer for Single image Denoising

arXiv

引用

arXiv 2023年

作者： Li, Juncheng Cheng, Bodong Chen, Ying Gao, Guangwei Zeng, Tieyong The School of Communication & Information Engineering Shanghai University Shanghai China Jiangsu Key Laboratory of Image and Video Understanding for Social Safety Nanjing University of Science and Technology Nanjing China The School of Computer Science and Technology Xidian University Xian China The Department of Cyberspace Security Beijing Electronic Science & Technology Institute Beijing China The Institute of Advanced Technology Nanjing University of Posts and Telecommunications Nanjing China The Provincial Key Laboratory for Computer Information Processing Technology Soochow University Suzhou China The Department of Mathematics The Chinese University of Hong Kong New Territories Hong Kong

Transformer-based image denoising methods have achieved encouraging results in the past year. However, it must uses linear operations to model long-range dependencies, which greatly increases model inference time and consumes GPU storage space. Compared with convolutional neural network-based methods, current Transformer-based image denoising methods cannot achieve a balance between performance improvement and resource consumption. In this paper, we propose an Efficient Wavelet Transformer (EWT) for image denoising. Specifically, we use Discrete Wavelet Transform (DWT) and Inverse Wavelet Transform (IWT) for downsampling and upsampling, respectively. This method can fully preserve the image features while reducing the image resolution, thereby greatly reducing the device resource consumption of the Transformer model. Furthermore, we propose a novel Dual-stream Feature Extraction Block (DFEB) to extract image features at different levels, which can further reduce model inference time and GPU memory usage. Experiments show that our method speeds up the original Transformer by more than 80%, reduces GPU memory usage by more than 60%, and achieves excellent denoising results. All code will be public. © 2023, CC BY.

关键词： image denoising

来源：评论

学校读者我要写书评

暂无评论

A Self-Supervised Model for Multi-modal Stroke Risk Prediction

arXiv

引用

arXiv 2024年

作者： Delgrange, Camille Demler, Olga Mora, Samia Menze, Bjoern de la Rosa, Ezequiel Davoudi, Neda Signal Processing Institute EPFL University Lausanne Switzerland Brigham and Women’s Hospital Harvard Medical School BostonMA United States Department of Quantitative Biomedicine University of Zurich Zurich Switzerland ETH AI Center Department of Computer Science Department of Quantitative Biomedicine University of Zurich Zurich Switzerland

Predicting stroke risk is a complex challenge that can be enhanced by integrating diverse clinically available data modalities. This study introduces a self-supervised multimodal framework that combines 3D brain imaging, clinical data, and image-derived features to improve stroke risk prediction prior to onset. By leveraging large unannotated clinical datasets, the framework captures complementary and synergistic information across image and tabular data modalities. Our approach is based on a contrastive learning framework that couples contrastive language-image pretraining with an image-tabular matching module, to better align multimodal data representations in a shared latent space. The model is trained on the UK Biobank, which includes structural brain MRI and clinical data. We benchmark its performance against state-of-the-art unimodal and multimodal methods using tabular, image, and image-tabular combinations under diverse frozen and trainable model settings. The proposed model outperformed self-supervised tabular (image) methods by 2.6% (2.6%) in ROC-AUC and by 3.3% (5.6%) in balanced accuracy. Additionally, it showed a 7.6% increase in balanced accuracy compared to the best multimodal supervised model. Through interpretable tools, our approach demonstrated better integration of tabular and image data, providing richer and more aligned embeddings. Gradient-weighted Class Activation Mapping heatmaps further revealed activated brain regions commonly associated in the literature with brain aging, stroke risk, and clinical outcomes. This robust self-supervised multimodal framework surpasses state-of-the-art methods for stroke risk prediction and offers a strong foundation for future studies integrating diverse data modalities to advance clinical predictive modeling. © 2024, CC BY-NC-SA.

关键词： Brain mapping

来源：评论

学校读者我要写书评

暂无评论

Incoherent Digital Holography using Spiral Rotating Point Spread Functions Created by Double-helix Beams

Incoherent Digital Holography using Spiral Rotating Point Sp...

引用

Digital Holography and Three-Dimensional Imaging, DH 2022

作者： Dubey, Nitin Anand, Vijayakumar Khonina, Svetlana Kumar, Ravi Reddy, Andra Naresh Kumar Rosen, Joseph School of Electrical and Computer Engineering Ben-Gurion University of the Negev P.O. Box 653 Beer-Sheva8410501 Israel Institute of Physics University of Tartu Tartu50411 Estonia School of Science Computing and Engineering Technologies Swinburne University of Technology Hawthorn MelbourneVIC3122 Australia Samara National Research University Samara443086 Russia Image Processing Systems Institute Branch of the Federal Scientific Research Centre "Crystallography and Photonics" of Russian Academy of Sciences Samara443001 Russia Hee Photonic Labs RigaLV-1002 Latvia Department of Physics of Complex Systems Weizmann Institute of Science Rehovot7610001 Israel

A new incoherent 3D imaging system with a rotating point spread function has been developed. Different computational reconstruction methods such as non-linear reconstruction and the Lucy-Richardson-Rosen algorithm wer... 详细信息

ISBN: (纸本)9781957171128

关键词： Optical transfer function

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：