检索结果-内蒙古大学图书馆

Unsupervised many-to-many stain translation for histological image augmentation to improve classification accuracy

Journal of Pathology Informatics 2023年 14卷 100195-100195页

作者： Berijanian, Maryam Schaadt, Nadine S. Huang, Boqiang Lotz, Johannes Feuerhake, Friedrich Merhof, Dorit Department of Computational Mathematics Science and Engineering (CMSE) Michigan State University East Lansing United States Institute for Pathology Hannover Medical School Hannover Germany Institute of Image Analysis and Computer Vision Faculty of Informatics and Data Science University of Regensburg Regensburg Germany Fraunhofer Institute for Digital Medicine MEVIS Lübeck Germany Institute for Neuropathology University Clinic Freiburg Freiburg Germany Fraunhofer Institute for Digital Medicine MEVIS Bremen Germany Fraunhofer Institute for Digital Medicine MEVIS Bremen Germany

Background: Deep learning tasks, which require large numbers of images, are widely applied in digital pathology. This poses challenges especially for supervised tasks since manual image annotation is an expensive and laborious process. This situation deteriorates even more in the case of a large variability of images. Coping with this problem requires methods such as image augmentation and synthetic image generation. In this regard, unsupervised stain translation via GANs has gained much attention recently, but a separate network must be trained for each pair of source and target domains. This work enables unsupervised many-to-many translation of histopathological stains with a single network while seeking to maintain the shape and structure of the tissues. Methods: StarGAN-v2 is adapted for unsupervised many-to-many stain translation of histopathology images of breast tissues. An edge detector is incorporated to motivate the network to maintain the shape and structure of the tissues and to have an edge-preserving translation. Additionally, a subjective test is conducted on medical and technical experts in the field of digital pathology to evaluate the quality of generated images and to verify that they are indistinguishable from real images. As a proof of concept, breast cancer classifiers are trained with and without the generated images to quantify the effect of image augmentation using the synthetized images on classification accuracy. Results: The results show that adding an edge detector helps to improve the quality of translated images and to preserve the general structure of tissues. Quality control and subjective tests on our medical and technical experts show that the real and artificial images cannot be distinguished, thereby confirming that the synthetic images are technically plausible. Moreover, this research shows that, by augmenting the training dataset with the outputs of the proposed stain translation method, the accuracy of breast cancer classifie

关键词： Adversarial networks Breast cancer classifier Deep learning Digital pathology Stain translation Unsupervised

来源：评论

学校读者我要写书评

暂无评论

Optimization of eigenvalue bounds for the independence and chromatic number of graph powers

arXiv

引用

arXiv 2020年

作者： Abiad, Aida Coutinho, Gabriel Fiol, Miquel Angel Nogueira, Bruno D. Zeijlemaker, Sjanne Department of Mathematics and Computer Science Eindhoven University of Technology Eindhoven Netherlands Department of Mathematics: Analysis Logic and Discrete Mathematics Ghent University Ghent Belgium Department of Mathematics and Data Science Vrije Universiteit Brussels Brussels Belgium Department of Computer Science Federal University of Minas Gerais Belo Horizonte Brazil Departament of Mathematics Polytechnic University of Catalonia Barcelona Graduate School of Mathematics Barcelona Spain

The kth power of a graph G = (V, E), Gk, is the graph whose vertex set is V and in which two distinct vertices are adjacent if and only if their distance in G is at most k. This article proves various eigenvalue bounds for the independence number and chromatic number of Gk which purely depend on the spectrum of G, together with a method to optimize them. Our bounds for the k-independence number also work for its quantum counterpart, which is not known to be a computable parameter in general, thus justifying the use of integer programming to optimize them. Some of the bounds previously known in the literature follow as a corollary of our main results. Infinite families of graphs where the bounds are sharp are presented as well. Copyright © 2020, The Authors. All rights reserved.

关键词： Integer programming

来源：评论

学校读者我要写书评

暂无评论

Skeleton Recall Loss for Connectivity Conserving and Resource Efficient Segmentation of Thin Tubular Structures

arXiv

引用

arXiv 2024年

作者： Kirchhoff, Yannick Rokuss, Maximilian R. Roy, Saikat Kovacs, Balint Ulrich, Constantin Wald, Tassilo Zenk, Maximilian Vollmuth, Philipp Kleesiek, Jens Isensee, Fabian Maier-Hein, Klaus Heidelberg Division of Medical Image Computing Germany Faculty of Mathematics and Computer Science Heidelberg University Germany HIDSS4Health - Helmholtz Information and Data Science School for Health Heidelberg Karlsruhe Germany Medical Faculty Heidelberg Heidelberg University Heidelberg Germany Helmholtz Imaging German Cancer Research Center Heidelberg Germany Clinic for Neuroradiology University Hospital Bonn Bonn Germany Medical Faculty Bonn University of Bonn Bonn Germany University Hospital Essen Essen Germany West German Cancer Center Essen University Hospital Essen Essen Germany Pattern Analysis and Learning Group Department of Radiation Oncology Heidelberg University Hospital Germany

Accurately segmenting thin tubular structures, such as vessels, nerves, roads or concrete cracks, is a crucial task in computer vision. Standard deep learning-based segmentation loss functions, such as Dice or Cross-Entropy, focus on volumetric overlap, often at the expense of preserving structural connectivity or topology. This can lead to segmentation errors that adversely affect downstream tasks, including flow calculation, navigation, and structural inspection. Although current topology-focused losses mark an improvement, they introduce significant computational and memory overheads. This is particularly relevant for 3D data, rendering these losses infeasible for larger volumes as well as increasingly important multi-class segmentation problems. To mitigate this, we propose a novel Skeleton Recall Loss, which effectively addresses these challenges by circumventing intensive GPU-based calculations with inexpensive CPU operations. It demonstrates overall superior performance to current state-of-the-art approaches on five public datasets for topology-preserving segmentation, while substantially reducing computational overheads by more than 90%. In doing so, we introduce the first multi-class capable loss function for thin structure segmentation, excelling in both efficiency and efficacy for topology-preservation. Our code is available to the community, providing a foundation for further advancements, at: https://***/MIC-DKFZ/Skeleton-Recall. © 2024, CC BY.

关键词： Topology

来源：评论

学校读者我要写书评

暂无评论

A new cognitive clock matching phenotypic and epigenetic ages (vol 12, 364, 2022)

引用

TRANSLATIONAL PSYCHIATRY 2022年第1期12卷 364页

作者： Krivonosov, M. I. Kondakova, E. V. Bulanov, N. A. Polevaya, S. A. Franceschi, C. Ivanchenko, M. V. Vedunova, M. V. Institute of Biology and Biomedicine Department of Neurotechnology N. I. Lobachevsky State University Nizhny Novgorod Russia. krivonosov@itmm.unn.ru. Laboratory of Systems Medicine of Healthy Aging Institute of Biology and Biomedicine N. I. Lobachevsky State University Nizhny Novgorod Russia. Faculty of Computer Science School of Data Analysis and Artificial Intelligence HSE University Moscow Russia. Faculty of Social Sciences Department of Psychophysiology N. I. Lobachevsky State University Nizhny Novgorod Russia. Institute of Information Technology Mathematics and Mechanics Department of Applied Mathematics N. I. Lobachevsky State University Nizhny Novgorod Russia.

Cognitive abilities decline with age, constituting a major manifestation of aging. The quantitative biomarkers of this process, as well as the correspondence to different biological clocks, remain largely an open problem. In this paper we employ the following cognitive tests: 1. differentiation of shades (campimetry); 2. evaluation of the arithmetic correctness and 3. detection of reversed letters and identify the most significant age-related cognitive indices. Based on their subsets we construct a machine learning-based Cognitive Clock that predicts chronological age with a mean absolute error of 8.62 years. Remarkably, epigenetic and phenotypic ages are predicted by Cognitive Clock with an even better accuracy. We also demonstrate the presence of correlations between cognitive, phenotypic and epigenetic age accelerations that suggests a deep connection between cognitive performance and aging status of an individual.

关键词：

来源：评论

学校读者我要写书评

暂无评论

atTRACTive: Semi-automatic white matter tract segmentation using active learning

arXiv

引用

arXiv 2023年

作者： Peretzke, Robin Maier-Hein, Klaus Bohn, Jonas Kirchhoff, Yannick Roy, Saikat Oberli-Palma, Sabrina Becker, Daniela Lenga, Pavlina Neher, Peter Heidelberg Germany Medical Faculty Heidelberg Heidelberg University Heidelberg Germany Partner Site Heidelberg Germany NCT Heidelberg a Partnership Between DKFZ University Medical Center Heidelberg Germany Pattern Analysis and Learning Group Heidelberg University Hospital Heidelberg Germany HIDSS4Health - Helmholtz Information and Data Science School for Health Karlsruhe Heidelberg Germany Faculty of Mathematics and Computer Science Heidelberg University Heidelberg Germany Faculty of Bioscience Heidelberg University Heidelberg Germany Department of Neurosurgery Heidelberg University Hospital Heidelberg Germany IU International University of Applied Sciences Erfurt Germany

Accurately identifying white matter tracts in medical images is essential for various applications, including surgery planning and tract-specific analysis. Supervised machine learning models have reached state-of-the-art solving this task automatically. However, these models are primarily trained on healthy subjects and struggle with strong anatomical aberrations, e.g. caused by brain tumors. This limitation makes them unsuitable for tasks such as preoperative planning, wherefore time-consuming and challenging manual delineation of the target tract is typically employed. We propose semi-automatic entropy-based active learning for quick and intuitive segmentation of white matter tracts from whole-brain tractography consisting of millions of streamlines. The method is evaluated on 21 openly available healthy subjects from the Human Connectome Project and an internal dataset of ten neurosurgical cases. With only a few annotations, the proposed approach enables segmenting tracts on tumor cases comparable to healthy subjects (dice = 0.71), while the performance of automatic methods, like TractSeg dropped substantially (dice = 0.34) in comparison to healthy subjects. The method is implemented as a prototype named atTRACTive in the freely available software MITK Diffusion. Manual experiments on tumor data showed higher efficiency due to lower segmentation times compared to traditional ROI-based segmentation. © 2023, CC BY-NC-ND.

关键词： Tumors

来源：评论

学校读者我要写书评

暂无评论

Improved Graphical analysis of Atrial Fibrillation Based on Holter Measurement data 29

Improved Graphical Analysis of Atrial Fibrillation Based on ...

引用

29th International Scientific Symposium "Metrology and Metrology Assurance", MMA 2019

作者： Sokol, Yevgen Shyshkin, Mykhailo Olha, Butova Olena, Akhiiezer Olha, Dunaievska National Technical University Kharkiv Polytechnic Institute Department of Industrial and Biomedical Electronics Kharkiv Ukraine National Technical University Kharkiv Polytechnic Institute Department of Computer Mathematics and Data Analysis Kharkiv Ukraine

ISBN: (纸本)9781728122137

Today, one of the most actual problems of cardiology is to obtain comprehensive data in everyday life to determine current cardiac states, including hidden pathologies, their interpretation and analysis. This article proposes a new method for processing measurements obtained during Holter monitoring and using only the value of the intervals between R peaks of ECG. These peaks have the biggest amplitude and their determination does not present technical difficulties. The improved graphical analysis method proposed by the authors, 'Speed Spot', allows to take into account not only the data of heart rate variability, but also includes an integral characteristic of the rate of change of the variability components. The method was used to determine the type of pathology as atrial fibrillation (AF). To confirm the effectiveness of the proposed method for the detection of arrhythmias, the Atrial Fibrillation database of *** was used, containing records of both normal and arrhythmic signals. A comparative analysis of the SS with Poincaré clouds for five patients with AF showed that this method is more sensitive and requires less data to determine the controlled cardiovascular state compared to similar ones. The criteria for estimating the degree of HRV (instability) by the 'Speed Spot' can be the geometrical dimensions of an ellipse: the length and width and the coordinate of its center. The proposed method, due to the symmetry of the distribution of cloud points with respect to the x-axis, provides more opportunities for use in systems for automatic tracking of heart rate disturbances. Practical application of the method to automatically determine the degree and type of arrhythmia is an object for further research. Further development of the method involves applying it to other types of hidden cardiopathology. © 2019 IEEE.

关键词： Pathology

来源：评论

学校读者我要写书评

暂无评论

Non-linear mediation analysis with high-dimensional mediators whose causal structure is unknown

arXiv

引用

arXiv 2020年

作者： Loh, Wen Wei Moerkerke, Beatrijs Loeys, Tom Vansteelandt, Stijn Department of Data Analysis Ghent University Gent Belgium Department of Applied Mathematics Computer Science and Statistics Ghent University Ghent Belgium Department of Medical Statistics London School of Hygiene and Tropical Medicine United Kingdom

With multiple possible mediators on the causal pathway from a treatment to an outcome, we consider the problem of decomposing the effects along multiple possible causal path(s) through each distinct mediator. Under Pearl's path-specific effects framework (Pearl, 2001;Avin et al., 2005), such fine-grained decompositions necessitate stringent assumptions, such as correctly specifying the causal structure among the mediators, and no unobserved confounding among the mediators. In contrast, interventional direct and indirect effects for multiple mediators (Vansteelandt and Daniel, 2017) can be identified under much weaker conditions, while providing scientifically relevant causal interpretations. Nonetheless, current estimation approaches require (correctly) specifying a model for the joint mediator distribution, which can be difficult when there is a high-dimensional set of possibly continuous and non-continuous mediators. In this article, we avoid the need to model this distribution, by developing a definition of interventional effects previously suggested by VanderWeele and Tchetgen Tchetgen (2017) for longitudinal mediation. We propose a novel estimation strategy that uses non-parametric estimates of the (counterfactual) mediator distributions. Noncontinuous outcomes can be accommodated using non-linear outcome models. Estimation proceeds via Monte Carlo integration. The procedure is illustrated using publicly available genomic data (Huang and Pan, 2016) to assess the causal effect of a microRNA expression on the three-month mortality of brain cancer patients that is potentially mediated by expression values of multiple genes. Copyright © 2020, The Authors. All rights reserved.

关键词： Regression analysis

来源：评论

学校读者我要写书评

暂无评论

A Survey for Large Language Models in Biomedicine

arXiv

引用

arXiv 2024年

作者： Wang, Chong Li, Mengyao He, Junjun Wang, Zhongruo Darzi, Erfan Chen, Zan Ye, Jin Li, Tianbin Su, Yanzhou Ke, Jing Qu, Kaili Li, Shuxin Yu, Yi Liò, Pietro Wang, Tianyun Wang, Yu Guang Shen, Yiqing School of Medical Engineering Xinxiang Medical University Xinxiang China Engineering Technology Research Center of Neurosense and Control of Henan Province Xinxiang China Henan International Joint Laboratory of Neural Information Analysis and Drug Intelligent Design Xinxiang China Shanghai AI Laboratory Shanghai China Amazon Palo AltoCA United States Boston Children's Hospital MA United States Harvard Medical School Harvard University MA United States Toursun Synbio Shanghai China Department of Data Science & AI Faculty of IT Monash University Melbourne Australia School of Electronic Information and Electrical Engineering Shanghai Jiao Tong University Shanghai China School of Computer Science and Engineering University of New South Wales Sydney Australia Department of Computer Science and Technology University of Cambridge Cambridge United Kingdom School of Basic Medical Sciences Xinxiang Medical University Xinxiang China Institute of Natural Sciences Shanghai Jiao Tong University Shanghai China School of Mathematics and Statistics University of New South Wales Sydney Australia Department of Computer Science Johns Hopkins University MD United States

Recent breakthroughs in large language models (LLMs) offer unprecedented natural language understanding and generation capabilities. However, existing surveys on LLMs in biomedicine often focus on specific applications or model architectures, lacking a comprehensive analysis that integrates the latest advancements across various biomedical domains. This review, based on an analysis of 484 publications sourced from databases including PubMed, Web of Science, and arXiv, provides an in-depth examination of the current landscape, applications, challenges, and prospects of LLMs in biomedicine, distinguishing itself by focusing on the practical implications of these models in real-world biomedical contexts. Firstly, we explore the capabilities of LLMs in zero-shot learning across a broad spectrum of biomedical tasks, including diagnostic assistance, drug discovery, and personalized medicine, among others, with insights drawn from 137 key studies. Then, we discuss adaptation strategies of LLMs, including fine-tuning methods for both uni-modal and multi-modal LLMs to enhance their performance in specialized biomedical contexts where zero-shot fails to achieve, such as medical question answering and efficient processing of biomedical literature. Finally, we discuss the challenges that LLMs face in the biomedicine domain including data privacy concerns, limited model interpretability, issues with dataset quality, and ethics due to the sensitive nature of biomedical data, the need for highly reliable model outputs, and the ethical implications of deploying AI in healthcare. To address these challenges, we also identify future research directions of LLM in biomedicine including federated learning methods to preserve data privacy and integrating explainable AI methodologies to enhance the transparency of LLMs. As this field of LLM rapidly evolves, continued research and development are essential to fully harness the capabilities of LLMs in biomedicine while ensuring their respon

关键词： Federated learning

来源：评论

学校读者我要写书评

暂无评论

Confounder selection strategies targeting stable treatment effect estimators

arXiv

引用

arXiv 2020年

作者： Loh, Wen Wei Vansteelandt, Stijn Department of Data Analysis Ghent University Gent Belgium Department of Applied Mathematics Computer Science and Statistics Ghent University Ghent Belgium Department of Medical Statistics London School of Hygiene and Tropical Medicine United Kingdom

Inferring the causal effect of a treatment on an outcome in an observational study requires adjusting for observed baseline confounders to avoid bias. However, adjusting for all observed baseline covariates, when only a subset are confounders of the effect of interest, is known to yield potentially inefficient and unstable estimators of the treatment effect. Furthermore, it raises the risk of finite-sample bias and bias due to model misspecification. For these stated reasons, confounder (or covariate) selection is commonly used to determine a subset of the available covariates that is sufficient for confounding adjustment. In this article, we propose a confounder selection strategy that focuses on stable estimation of the treatment effect. In particular, when the propensity score model already includes covariates that are sufficient to adjust for confounding, then the addition of covariates that are associated with either treatment or outcome alone, but not both, should not systematically change the effect estimator. The proposal, therefore, entails first prioritizing covariates for inclusion in the propensity score model, then using a change-in-estimate approach to select the smallest adjustment set that yields a stable effect estimate. The ability of the proposal to correctly select confounders, and to ensure valid inference of the treatment effect following data-driven covariate selection, is assessed empirically and compared with existing methods using simulation studies. We demonstrate the procedure using three different publicly available datasets commonly used for causal inference. Copyright © 2020, The Authors. All rights reserved.

关键词： Sampling

来源：评论

学校读者我要写书评

暂无评论

An overview on deep learning-based approximation methods for partial differential equations

arXiv

引用

arXiv 2020年

作者： Beck, Christian Hutzenthaler, Martin Jentzen, Arnulf Kuckuck, Benno Department of Mathematics ETH Zurich Zurich Switzerland Applied Mathematics: Institute for Analysis and Numerics Faculty of Mathematics and Computer Science University of Münster Münster Germany Faculty of Mathematics University of Duisburg-Essen Essen Germany School of Data Science Shenzhen Research Institute of Big Data The Chinese University of Hong Kong Shenzhen China

It is one of the most challenging problems in applied mathematics to approximatively solve high-dimensional partial differential equations (PDEs). Recently, several deep learning-based approximation algorithms for attacking this problem have been proposed and tested numerically on a number of examples of high-dimensional PDEs. This has given rise to a lively field of research in which deep learning-based methods and related Monte Carlo methods are applied to the approximation of high-dimensional PDEs. In this article we offer an introduction to this field of research by revisiting selected mathematical results related to deep learning approximation methods for PDEs and reviewing the main ideas of their proofs. We also provide a short overview of the recent literature in this area of *** Codes 65M99 (Primary), 35-02, 65-02, 68T07 (Secondary) Copyright © 2020, The Authors. All rights reserved.

关键词： Partial differential equations

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：