检索结果-内蒙古大学图书馆

Distinct but correct: generating diversified and entity-revised medical response

学校读者我要写书评

暂无评论

Science China(Information Sciences) 2024年第3期67卷 94-113页

作者： Bin LI Bin SUN Shutao LI Encheng CHEN Hongru LIU Yixuan WENG Yongping BAI Meiling HU College of Electrical and Information Engineering Hunan University School of Mathematics Sun Yat-sen University JD Technology National Laboratory of Pattern Recognition Institute of AutomationChinese Academy of Sciences Xiangya Hospital of Central South University Teaching and Research Section of Clinical Nursing Xiangya Hospital of Central South University

Medical dialogue generation(MDG) is applied for building medical dialogue systems for intelligent consultation. Such systems can communicate with patients in real time, thereby improving the efficiency of clinical diagnosis. However, predicting correct entities and correctly generating distinct responses remain a great challenge. Inspired by actual doctors' responses to patients, we consider MDG a two-stage task: entity prediction and dialogue generation. For entity prediction, we design an ent-mac post pre-training strategy by leveraging external medical entity knowledge to enhance the pre-trained model. For dialogue generation, we propose an entity-aware fusion MDG method in which predicted entities are integrated into the dialogue generation model through different encoding fusion mechanisms, using information from different sources. Because the diverse beam search algorithm can produce responses with entities that deviate from the predicted entities, an entity-revised diverse beam search is proposed to correct the entities entailed in the generated responses and make the generated responses more distinct. The experimental results on the China Conference on Knowledge Graph and Semantic Computing 2021(A/B tests) and the International Conference on Learning Representations 2021(online test) datasets show that the proposed method outperforms several state-of-the-art methods, which demonstrates its practicability and effectiveness.

关键词： medical entity prediction ent-mac post pre-training strategy entity-aware fusion medical dialogue generation encoding fusion mechanism entity-revised diverse beam search

Supervised scale-regularized linear convolutionary filters 28

学校读者我要写书评

暂无评论

Supervised scale-regularized linear convolutionary filters

28th British Machine Vision Conference, BMVC 2017

作者： Loog, Marco Lauze, François Pattern Recognition Laboratory Delft University of Technology Delft Netherlands Image Section University of Copenhagen Copenhagen Denmark

ISBN: (纸本)190172560X

We start by demonstrating that an elementary learning task—learning a linear filter from training data by means of regression—can be solved very efficiently for feature spaces of very high dimensionality. In a second step, firstly, acknowledging that such high-dimensional learning tasks typically benefit from some form of regularization and, secondly, arguing that the problem of scale has not been taken care of in a very satisfactory manner, we come to a combined resolution of both of these shortcomings by proposing a technique that we coin scale regularization. This regularization problem can also be solved relatively efficient. All in all, the idea is to properly control the scale of a trained filter, which we solve by introducing a specific regularization term into the overall objective function. We demonstrate, on an artificial filter learning problem, the capabilities of our basic filter. In particular, we demonstrate that it clearly outperforms the de facto standard Tikhonov regularization, which is the one employed in ridge regression or Wiener filtering. © 2017. The copyright of this document resides with its authors.

关键词： Regression analysis

Supervised Classification: Quite a Brief Overview

学校读者我要写书评

暂无评论

arXiv 2017年

作者： Loog, Marco Pattern Recognition Laboratory Delft University of Technology Netherlands Image Section University of Copenhagen Denmark

The original problem of supervised classification considers the task of automatically assigning objects to their respective classes on the basis of numerical measurements derived from these objects. Classifiers are the tools that implement the actual functional mapping from these measurements—also called features or inputs—to the so-called class label—or output. The fields of pattern recognition and machine learning study ways of constructing such classifiers. The main idea behind supervised methods is that of learning from examples: given a number of example input-output relations, to what extent can the general mapping be learned that takes any new and unseen feature vector to its correct class? This chapter provides a basic introduction to the underlying ideas of how to come to a supervised classification problem. In addition, it provides an overview of some specific classification techniques, delves into the issues of object representation and classifier evaluation, and (very) briefly covers some variations on the basic supervised classification task that may also be of interest to the practitioner. Copyright © 2017, The Authors. All rights reserved.

关键词： Supervised learning

Scale-regularized filter learning: Calculus of variation meets learning

学校读者我要写书评

暂无评论

arXiv 2017年

作者： Loog, Marco Lauze, François Pattern Recognition Laboratory Delft University of Technology Netherlands Image Section University of Copenhagen Denmark

We start out by demonstrating that an elementary learning task, corresponding to the training of a single linear neuron in a convolutional neural network, can be solved for feature spaces of very high dimensionality. In a second step, acknowledging that such high-dimensional learning tasks typically benefit from some form of regularization and arguing that the problem of scale has not been taken care of in a very satisfactory manner, we come to a combined resolution of both of these shortcomings by proposing a form of scale regularization. Moreover, using variational method, this regularization problem can also be solved rather efficiently and we demonstrate, on an artificial filter learning problem, the capabilities of our basic linear neuron. From a more general standpoint, we see this work as prime example of how learning and variational methods could, or even should work to their mutual benefit. Copyright © 2017, The Authors. All rights reserved.

关键词： Ordinary differential equations

MITK-ModelFit: A generic open-source framework for model fits and their exploration in medical imaging - design, implementation and application on the example of DCE-MRI

学校读者我要写书评

暂无评论

arXiv 2018年

作者： Debus, Charlotte Floca, Ralf Ingrisch, Michael Kompan, Ina Maier-Hein, Klaus Abdollahi, Amir Nolden, Marco Heidelberg Germany Heidelberg Germany Heidelberg University Hospital Heidelberg Germany Heidelberg Germany Heidelberg Institute of Radiation Oncology [HIRO Division of Medical Image Computing German Cancer Research Center Dkfz Department of Radiology University Hospital Munich Ludwig-Maximilians-University Munich Section Pattern Recognition Department of Radiation Oncology Heidelberg University Hospital Heidelberg

Background: Many medical imaging techniques utilize fitting approaches for quantitative parameter estimation and analysis. Common examples are pharmacokinetic modeling in dynamic contrast-enhanced (DCE) magnetic resonance imaging (MRI)/computed tomography (CT), apparent diffusion coefficient calculations and intravoxel incoherent motion modeling in diffusion-weighted MRI and Z-spectra analysis in chemical exchange saturation transfer MRI. Most available software tools are limited to a special purpose and do not allow for own developments and extensions. Furthermore, they are mostly designed as stand-Alone solutions using external frameworks and thus cannot be easily incorporated natively in the analysis workflow. Results: We present a framework for medical image fitting tasks that is included in the Medical Imaging Interaction Toolkit MITK, following a rigorous open-source, well-integrated and operating system independent policy. Software engineering-wise, the local models, the fitting infrastructure and the results representation are abstracted and thus can be easily adapted to any model fitting task on image data, independent of image modality or model. Several ready-To-use libraries for model fitting and use-cases, including fit evaluation and visualization, were implemented. Their embedding into MITK allows for easy data loading, pre-and post-processing and thus a natural inclusion of model fitting into an overarching workflow. As an example, we present a comprehensive set of plug-ins for the analysis of DCE MRI data, which we validated on existing and novel digital phantoms, yielding competitive deviations between fit and ground truth. Conclusions: Providing a very flexible environment, our software mainly addresses developers of medical imaging software that includes model fitting algorithms and tools. Additionally, the framework is of high interest to users in the domain of perfusion MRI, as it offers feature-rich, freely available, validated tools to perform

关键词： Magnetic resonance imaging

Label stability in multiple instance learning

学校读者我要写书评

暂无评论

arXiv 2017年

作者： Cheplygina, Veronika Sørensen, Lauge Tax, David M.J. de Bruijne, Marleen Loog, Marco Pattern Recognition Laboratory Delft University of Technology Netherlands Image Section University of Copenhagen Copenhagen Denmark Biomedical Imaging Group Rotterdam Erasmus MC Rotterdam Netherlands

We address the problem of instance label stability in multiple instance learning (MIL) classifiers. These classifiers are trained only on globally annotated images (bags), but often can provide fine-grained annotations for image pixels or patches (instances). This is interesting for computer aided diagnosis (CAD) and other medical image analysis tasks for which only a coarse labeling is provided. Unfortunately, the instance labels may be unstable. This means that a slight change in training data could potentially lead to abnormalities being detected in different parts of the image, which is undesirable from a CAD point of view. Despite MIL gaining popularity in the CAD literature, this issue has not yet been addressed. We investigate the stability of instance labels provided by several MIL classifiers on 5 different datasets, of which 3 are medical image datasets (breast histopathology, diabetic retinopathy and computed tomography lung images). We propose an unsupervised measure to evaluate instance stability, and demonstrate that a performance-stability trade-off can be made when comparing MIL classifiers. Copyright © 2017, The Authors. All rights reserved.

关键词： Computer aided diagnosis

Active learning using uncertainty information

学校读者我要写书评

暂无评论

arXiv 2017年

作者： Yang, Yazhou Yang, Yazhou Loog, Marco Loog, Marco Pattern Recognition Laboratory Delft University of Technology Delft Netherlands College of Information System and Management National University of Defense Technology Changsha China Image Section University of Copenhagen Copenhagen Denmark

Many active learning methods belong to the retraining-based approaches, which select one unlabeled instance, add it to the training set with its possible labels, retrain the classification model, and evaluate the criteria that we base our selection on. However, since the true label of the selected instance is unknown, these methods resort to calculating the average-case or worse-case performance with respect to the unknown label. In this paper, we propose a different method to solve this problem. In particular, our method aims to make use of the uncertainty information to enhance the performance of retraining-based models. We apply our method to two state-of-the-art algorithms and carry out extensive experiments on a wide variety of realworld datasets. The results clearly demonstrate the effectiveness of the proposed method and indicate it can reduce human labeling efforts in many real-life applications. Copyright © 2017, The Authors. All rights reserved.

关键词： Classification (of information)

On Measuring and Quantifying Performance: Error Rates, Surrogate Loss, and an Example in SSL

学校读者我要写书评

暂无评论

arXiv 2017年

作者： Loog, Marco Krijthe, Jesse Jensen, Are C. Department of Molecular Epidemiology Leiden University Medical Center Netherlands Pattern Recognition Laboratory Delft University of Technology Netherlands Image Section University of Copenhagen Denmark Department of Informatics University of Oslo Norway

In various approaches to learning, notably in domain adaptation, active learning, learning under covariate shift, semi-supervised learning, learning with concept drift, and the like, one often wants to compare a baseline classifier to one or more advanced (or at least different) strategies. In this chapter, we basically argue that if such classifiers, in their respective training phases, optimize a so-called surrogate loss that it may also be valuable to compare the behavior of this loss on the test set, next to the regular classification error rate. It can provide us with an additional view on the classifiers’ relative performances that error rates cannot capture. As an example, limited but convincing empirical results demonstrates that we may be able to find semi-supervised learning strategies that can guarantee performance improvements with increasing numbers of unlabeled data in terms of log-likelihood. In contrast, the latter may be impossible to guarantee for the classification error rate. Copyright © 2017, The Authors. All rights reserved.

关键词： Supervised learning

Genomic landscape and molecularly informed therapy in thymic carcinoma and other advanced thymic epithelial tumors

学校读者我要写书评

暂无评论

Med

Med 2025年第6期6卷 100612页

作者： Möhrmann, Lino Rostock, Lysann Werner, Maximilian Oleś, Małgorzata Arnold, Jonas S. Paramasivam, Nagarajan Jöhrens, Korinna Rupp, Luise Schmitz, Marc Richter, Daniela Uhrig, Sebastian Fröhlich, Martina Hutter, Barbara Hüllein, Jennifer Jahn, Arne Arlt, Marie Möhrmann, Elena E. Hanf, Dorothea Gieldon, Laura Kreutzfeldt, Simon Heilig, Christoph E. Teleanu, Maria-Veronica Lipka, Daniel B. Beck, Katja Baude-Müller, Annika Mock, Andreas Jelas, Ivan Rieke, Damian T. Wiesweg, Marcel Brandts, Christian Boerries, Melanie Illert, Anna L. Desuki, Alexander Kindler, Thomas Krackhardt, Angela M. Westphalen, C. Benedikt Christopoulos, Petros Apostolidis, Leonidas Stenzinger, Albrecht Allgäuer, Michael Neumann, Olaf Kerle, Irina A. Horak, Peter Heining, Christoph Grosch, Heidrun Schröck, Evelin Hübschmann, Daniel Fröhling, Stefan Glimm, Hanno Computational Health Informatics Program Boston Children's Hospital Harvard Medical School Boston United States Department of Translational Medical Oncology National Center for Tumor Diseases (NCT) NCT Dresden a partnership between DKFZ Faculty of Medicine and University Hospital Carl Gustav Carus TUD Dresden University of Technology and Helmholtz-Zentrum Dresden-Rossendorf (HZDR) Germany Translational Medical Oncology Faculty of Medicine University Hospital Carl Gustav Carus TU Dresden University of Technology Dresden Germany German Cancer Consortium (DKTK) Dresden Germany Computational Oncology Group (CO) Molecular Precision Oncology Program (MPOP) German Cancer Research Center (DKFZ) Heidelberg Germany National Center for Tumor Diseases (NCT) NCT Heidelberg a partnership between DKFZ and Heidelberg University Hospital Heidelberg Germany Institute for Clinical Genetics University Hospital Carl Gustav Carus TU Dresden University of Technology Dresden Germany ERN GENTURIS Hereditary Cancer Syndrome Center Dresden Dresden Germany Max Planck Institute of Molecular Cell Biology and Genetics Dresden Germany Department of Pathology University Hospital Carl Gustav Carus Dresden Germany Institute of Immunology Faculty of Medicine Carl Gustav Carus TU Dresden University of Technology Dresden Germany Institute of Medical Genetics Carl von Ossietzky University Oldenburg Germany Division of Translational Medical Oncology DKFZ Heidelberg Germany NCT Heidelberg Heidelberg Germany Section Translational Cancer Epigenomics Department of Translational Medical Oncology NCT Heidelberg and DKFZ Heidelberg Germany Institute of Pathology Ludwig-Maximilians-Universität München (LMU) Munich Germany Charité Comprehensive Cancer Center Universitätsmedizin Berlin Freie Universität Berlin and Humboldt-Universität zu Berlin Berlin Germany Department of Medical Oncology West German Cancer Center University Hospital Essen University Duisburg-Essen Essen Germany Department of Med

Background: Thymic epithelial tumors (TETs) are rare malignancies with limited treatment options and underexplored molecular features. Methods: We examined the genomic landscape and therapeutic outcomes in 81 patients with advanced TETs, including thymic carcinomas (TCs), thymomas, and thymic neuroendocrine neoplasms (TNENs), who were enrolled in the MASTER trial, a prospective observational precision oncology trial. Findings: Using whole-genome-sequencing and whole-exome-sequencing analysis, transcriptome analysis, and methylome analysis, we identified distinct molecular features across TET subtypes, including a higher tumor mutational burden in TC and pathogenic germline variants in 18% of cases. We performed transcriptome- and methylome-based unsupervised clustering and were able to divide TCs into immunologically hot and cold subsets, with hot TCs exhibiting higher T cell infiltration and significantly longer overall survival. In 65 out of 76 (86%) patients, we recommended molecularly informed therapies, which were applied in 29 out of 65 (45%) cases, leading to a disease control rate of 62% and an objective response rate of 23% (both n = 26). The progression-free survival ratio (PFSr) was > 1.3 in 8 out of 24 (33%) patients, 7 of them having TC. Among TCs, patients achieved a mean PFSr of 1.4, indicating potential therapeutic advantages in this subgroup. The PFSr between the PFS of immune checkpoint inhibition and preceding therapies was significantly higher in the hot cluster compared to the cold cluster (median 1.7 vs. 0.3;p = 0.01945). Conclusions: Our findings expand the understanding of TET biology and emphasize the role of precision oncology in informing treatment decisions and improving outcomes for patients with advanced TETs, particularly in TCs. © 2025 The Author(s)

关键词： molecular profiling multiomics precision oncology prospective observational study targeted therapy thymic carcinoma thymic epithelial tumor thymic neuroendocrine neoplasm thymoma Translation to patients whole-genome sequencing