检索结果-内蒙古大学图书馆

38th Conference on Neural Information Processing Systems, NeurIPS 2024

作者： Chen, Yenho Mudrik, Noga Johnsen, Kyle A. Alagapan, Sankaraleengam Charles, Adam S. Rozell, Christopher J. Machine Learning Center Georgia Institute of Technology United States School of Electrical and Computer Engineering Georgia Institute of Technology United States Coulter Dept. of Biomedical Engineering Emory University Georgia Institute of Technology United States Department of Biomedical Engineering Mathematical Institute for Data Science Center for Imaging Science Kavli Neuroscience Discovery Institute Johns Hopkins University United States

Time-varying linear state-space models are powerful tools for obtaining mathematically interpretable representations of neural signals. For example, switching and decomposed models describe complex systems using latent variables that evolve according to simple locally linear dynamics. However, existing methods for latent variable estimation are not robust to dynamical noise and system nonlinearity due to noise-sensitive inference procedures and limited model formulations. This can lead to inconsistent results on signals with similar dynamics, limiting the model's ability to provide scientific insight. In this work, we address these limitations and propose a probabilistic approach to latent variable estimation in decomposed models that improves robustness against dynamical noise. Additionally, we introduce an extended latent dynamics model to improve robustness against system nonlinearities. We evaluate our approach on several synthetic dynamical systems, including an empirically-derived brain-computer interface experiment, and demonstrate more accurate latent variable inference in nonlinear systems with diverse noise conditions. Furthermore, we apply our method to a real-world clinical neurophysiology dataset, illustrating the ability to identify interpretable and coherent structure where previous models cannot. © 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

Denoising Diffusion Models for Anomaly Localization in Medical Images

arXiv

引用

arXiv 2024年

作者： Bercea, Cosmin I. Cattin, Philippe C. Schnabel, Julia A. Wolleb, Julia School of Computation Information and Technology Technical University of Munich Germany Institute of Machine Learning in Biomedical Imaging and Helmholtz AI Helmholtz Munich Germany Department of Biomedical Engineering University of Basel Allschwil Switzerland Institute of Machine Learning in Biomedical Imaging Helmholtz Munich Germany School of Biomedical Engineering and Imaging Sciences King’s College London United Kingdom

This chapter explores anomaly localization in medical images using denoising diffusion models. After providing a brief methodological background of these models, including their application to image reconstruction and their conditioning using guidance mechanisms, we provide an overview of available datasets and evaluation metrics suitable for their application to anomaly localization in medical images. In this context, we discuss supervision schemes ranging from fully supervised segmentation to semi-supervised, weakly supervised, self-supervised, and unsupervised methods, and provide insights into the effectiveness and limitations of these approaches. Furthermore, we highlight open challenges in anomaly localization, including detection bias, domain shift, computational cost, and model interpretability. Our goal is to provide an overview of the current state of the art in the field, outline research gaps, and highlight the potential of diffusion models for robust anomaly localization in medical images. Copyright © 2024, The Authors. All rights reserved.

关键词： Image denoising

来源：评论

学校读者我要写书评

暂无评论

Semantic Alignment of Unimodal Medical Text and Vision Representations

arXiv

引用

arXiv 2025年

作者： Di Folco, Maxime Chan, Emily Hasny, Marta Bercea, Cosmin I. Schnabel, Julia A. Institute of Machine Learning in Biomedical Imaging Helmholtz Munich Germany School of Computation Information and Technology Technical University of Munich Germany School of Biomedical Engineering & Imaging Sciences King’s College London United Kingdom

General-purpose AI models, particularly those designed for text and vision, demonstrate impressive versatility across a wide range of deep-learning tasks. However, they often underperform in specialised domains like medical imaging, where domain-specific solutions or alternative knowledge transfer approaches are typically required. Recent studies have noted that general-purpose models can exhibit similar latent spaces when processing semantically related data, although this alignment does not occur naturally. Building on this insight, it has been shown that applying a simple transformation - at most affine - estimated from a subset of semantically corresponding samples, known as anchors, enables model stitching across diverse training paradigms, architectures, and modalities. In this paper, we explore how semantic alignment - estimating transformations between anchors - can bridge general-purpose AI with specialised medical knowledge. Using multiple public chest X-ray datasets, we demonstrate that model stitching across model architectures allows general models to integrate domain-specific knowledge without additional training, leading to improved performance on medical tasks. Furthermore, we introduce a novel zero-shot classification approach for unimodal vision encoders that leverages semantic alignment across modalities. Our results show that our method not only outperforms general multimodal models but also approaches the performance levels of fully trained, medical-specific multimodal solutions. Code will be available upon acceptance. © 2025, CC BY-NC-ND.

关键词： Knowledge representation

来源：评论

学校读者我要写书评

暂无评论

Selective Test-Time Adaptation for Unsupervised Anomaly Detection using Neural Implicit Representations

arXiv

引用

arXiv 2024年

作者： Ambekar, Sameer Schnabel, Julia A. Bereca, Cosmin School of Computation Information and Technology Technical University of Munich Germany Institute of Machine Learning in Biomedical Imaging Helmholtz Munich Germany School of Biomedical Engineering and Imaging Sciences King's College London United Kingdom

Deep learning models in medical imaging often encounter challenges when adapting to new clinical settings unseen during training. Test-time adaptation offers a promising approach to optimize models for these unseen domains, yet its application in anomaly detection (AD) remains largely unexplored. AD aims to efficiently identify deviations from normative distributions;however, full adaptation, including pathological shifts, may inadvertently learn the anomalies it intends to detect. We introduce a novel concept of selective test-time adaptation that utilizes the inherent characteristics of deep pre-trained features to adapt selectively in a zero-shot manner to any test image from an unseen domain. This approach employs a model-agnostic, lightweight multi-layer perceptron for neural implicit representations, enabling the adaptation of outputs from any reconstruction-based AD method without altering the source-trained model. Rigorous validation in brain AD demonstrated that our strategy substantially enhances detection accuracy for multiple conditions and different target distributions. Specifically, our method improves the detection rates by up to 78% for enlarged ventricles and 24% for edemas. Our code is available: https://***/compai-lab/2024-miccai-adsmi-ambekar. © 2024, CC BY.

关键词： Zero-shot learning

来源：评论

学校读者我要写书评

暂无评论

DiENTeS: Dynamic ENTity Segmentation with Local-Global Transformers 2nd

DiENTeS: Dynamic ENTity Segmentation with Local-Global Tran...

引用

2nd International ToothFairy2: Multi-Structure Segmentation in CBCT Volumes, ToothFairy 2024, 3D Teeth Landmarks Detection Challenge, 3DTeethLand 2024, Semi-supervised Teeth Segmentation, STS 2024 held in conjunction with the 27th International Conference on Medical Image Computing and Computer-Assisted Intervention, MICCAI 2024

作者： Daza, Laura Schnabel, Julia Institute of Machine Learning in Biomedical Imaging Helmholtz Munich Neuherberg Germany School of Computation Information and Technology Technical University of Munich Munich Germany School of Biomedical Engineering and Imaging Sciences King’s College London London United Kingdom

ISBN: (纸本)9783031889769

Semantic segmentation is crucial for accurately identifying anatomical structures and pathological anomalies in medical images, playing a vital role in diagnostics, treatment planning, and disease progression monitoring. Despite significant advancements, the development of flexible and generalizable algorithms that can adapt to the diverse shapes, sizes, and textures of various anatomical regions remains challenging. In this work, we introduce the Dynamic ENTity Segmentation (DiENTeS) model, which leverages Local-global Transformers for 3D medical segmentation. Our model utilizes a transformer-based backbone to extract localized features and propagate them to form a comprehensive global representation. Additionally, we incorporate language features to guide the segmentation process, enabling the generation of specialized convolutional kernels for each category. This approach allows DiENTeS to tackle semantic segmentation as a class-agnostic entity segmentation problem. We validate our method using the ToothFairy2 Challenge, demonstrating its effectiveness in segmenting multiple structures in the maxillofacial region. We will make our code and models publicly available. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2025.

关键词： Semantic Segmentation

来源：评论

学校读者我要写书评

暂无评论

DEALing with Image Reconstruction: Deep Attentive Least Squares

arXiv

引用

arXiv 2025年

作者： Pourya, Mehrsa Kobler, Erich Unser, Michael Neumayer, Sebastian Biomedical Imaging Group EPFL Lausanne Switzerland Institute for Machine Learning LIT AI lab Institute for Virtual Morphology Johannes Kepler University Linz Austria Faculty of Mathematics TU Chemnitz Germany

State-of-the-art image reconstruction often relies on complex, highly parameterized deep architectures. We propose an alternative: a data-driven reconstruction method inspired by the classic Tikhonov regularization. Our approach iteratively refines intermediate reconstructions by solving a sequence of quadratic problems. These updates have two key components: (i) learned filters to extract salient image features, and (ii) an attention mechanism that locally adjusts the penalty of filter responses. Our method achieves performance on par with leading plug-and-play and learned regularizer approaches while offering interpretability, robustness, and convergent behavior. In effect, we bridge traditional regularization and deep learning with a principled reconstruction approach. © 2025, CC BY.

关键词： Image reconstruction

来源：评论

学校读者我要写书评

暂无评论

learning Physics-Inspired Regularization for Medical Image Registration with Hypernetworks

arXiv

引用

arXiv 2023年

作者： Reithmeir, Anna Schnabel, Julia A. Zimmer, Veronika A. School of Computation Information and Technology Technical University of Munich Munich Germany Munich Center for Machine Learning Munich Germany Institute of Machine Learning in Biomedical Imaging Helmholtz Munich Neuherberg Germany School of Biomedical Engineering and Imaging Sciences King’s College London London United Kingdom

Medical image registration aims to identify the spatial deformation between images of the same anatomical region and is fundamental to image-based diagnostics and therapy. To date, the majority of the deep learning-based registration methods employ regularizers that enforce global spatial smoothness, e.g., the diffusion regularizer. However, such regularizers are not tailored to the data and might not be capable of reflecting the complex underlying deformation. In contrast, physics-inspired regularizers promote physically plausible deformations. One such regularizer is the linear elastic regularizer, which models the deformation of elastic material. These regularizers are driven by parameters that define the material’s physical properties. For biological tissue, a wide range of estimations of such parameters can be found in the literature, and it remains an open challenge to identify suitable parameter values for successful registration. To overcome this problem and to incorporate physical properties into learning-based registration, we propose to use a hypernetwork that learns the effect of the physical parameters of a physics-inspired regularizer on the resulting spatial deformation field. In particular, we adapt the HyperMorph framework to learn the effect of the two elasticity parameters of the linear elastic regularizer. Our approach enables the efficient discovery of suitable, data-specific physical parameters at test time. To the best of our knowledge, we are the first to use a hypernetwork to learn physics-inspired regularization for medical image registration. We evaluate our approach on 3D intra-patient lung CT images. The results show that the linear elastic regularizer can yield comparable results to the diffusion regularizer in unsupervised learning-based registration while predicting deformations with fewer foldings. With our method, the adaptation of the physical parameters to the data can successfully be performed at test time. Our code is available

关键词： Physical properties

来源：评论

学校读者我要写书评

暂无评论

Preface–Introduction to the Special Issue for Chinese-Russian Workshop on Biophotonics and biomedical Optics

引用

Journal of Innovative Optical Health Sciences 2024年第5期17卷 1-3页

作者： Tingting Yu Dan Zhu Valery V.Tuchin Britton Chance Center for Biomedical Photonics-MoE Key Laboratory for Biomedical Photonics Advanced Biomedical Imaging FacilityWuhan National Laboratory for Optoelectronics–Advanced Biomedical Imaging FacilityHuazhong University of Science and TechnologyWuhan 430074China Department of Optics and Biophotonics Science Medical CenterSaratov State UniversitySaratov 410012Russia Laboratory of Laser Diagnostics of Technical and Living Systems Institute of Precision Mechanics and ControlFRC“Saratov Scientic Centre of the Russian Academy of Sciences”Saratov 410028Russia Laboratory of Laser Molecular Imaging and Machine Learning Tomsk State UniversityTomsk 634050Russia

The Chinese-Russian Workshop on Biophotonics and biomedical Optics 2023 was held online twice on 18–21 September and 25–26 September *** bilateral workshop brought together both Russian and Chinese scientists,engineers,and clinical researchers from a variety of disciplines engaged in applying optical science,photonics,and imaging technologies to problems in biology and *** the workshops,two plenary lectures and twenty invited presentations were *** special issue selects some papers from both Russian and Chinese sides,consisting of one review and seven original research articles.

关键词： Russian photonics biomedical

来源：评论

学校读者我要写书评

暂无评论

Fair and Private CT Contrast Agent Detection 2nd

Fair and Private CT Contrast Agent Detection

引用

2nd International Workshop on Fairness of AI in Medical imaging, FAIMI 2024, and 3rd International Workshop on Ethical and Philosophical Issues in Medical imaging, EPIMI 2024, Held in Conjunction with the International Conference on Medical Image Computing and Computer Assisted Interventions, MICCAI 2024

作者： Kaess, Philipp Ziller, Alexander Mantz, Lea Rueckert, Daniel Fintelmann, Florian J. Kaissis, Georgios AI in Healthcare and Medicine Technical University of Munich Munich Germany Department of Radiology Massachusetts General Hospital Boston United States Department of Diagnostic and Interventional Radiology University Medical Center of the Johannes Gutenberg University Mainz Mainz Germany Department of Computing Imperial College London London United Kingdom Institute of Machine Learning in Biomedical Imaging Helmholtz Munich Germany

ISBN: (纸本)9783031727863

Intravenous (IV) contrast agents are an established medical tool to enhance the visibility of certain structures. However, their application substantially changes the appearance of Computed Tomography (CT) images, which - if unknown - can significantly deteriorate the diagnostic performance of neural networks. Artificial Intelligence (AI) can help to detect IV contrast, reducing the need for labour-intensive and error-prone manual labeling. However, we demonstrate that automated contrast detection can lead to discrimination against demographic subgroups. Moreover, it has been shown repeatedly that AI models can leak private training data. In this work, we analyse the fairness of conventional and privacy-preserving AI models during the detection of IV contrast on CT images. Specifically, we present models which are substantially fairer compared to a previously published baseline. For better comparability, we extend existing metrics to quantify the fairness of a model on a protected attribute in a single value. We provide a model, fulfilling a strict Differential Privacy protection of (Ε,δ)=(8,2.8·10-3), which with an accuracy of 97.42% performs 5%-points better than the baseline. Additionally, while confirming prior works, that strict privacy preservation increases the discrimination against underrepresented subgroups, the proposed model is fairer than the baseline over all metrics considering race and sex as protected attributes, which extends to age for a more relaxed privacy guarantee. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2025.

关键词： Differential privacy

来源：评论

学校读者我要写书评

暂无评论

Bounding Reconstruction Attack Success of Adversaries Without Data Priors

arXiv

引用

arXiv 2024年

作者： Ziller, Alexander Riess, Anneliese Schwethelm, Kristian Mueller, Tamara T. Rueckert, Daniel Kaissis, Georgios Technical University of Munich Munich Germany Institute of Machine Learning in Biomedical Imaging Helmholtz Munich Neuherberg Germany Department of Computing Imperial College London London United Kingdom

Reconstruction attacks on machine learning (ML) models pose a strong risk of leakage of sensitive data. In specific contexts, an adversary can (almost) perfectly reconstruct training data samples from a trained model using the model’s gradients. When training ML models with differential privacy (DP), formal upper bounds on the success of such reconstruction attacks can be provided. So far, these bounds have been formulated under worst-case assumptions that might not hold high realistic practicality. In this work, we provide formal upper bounds on reconstruction success under realistic adversarial settings against ML models trained with DP and support these bounds with empirical results. With this, we show that in realistic scenarios, (a) the expected reconstruction success can be bounded appropriately in different contexts and by different metrics, which (b) allows for a more educated choice of a privacy parameter. © 2024, CC BY.

关键词：

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：