检索结果-内蒙古大学图书馆

11th Biomedical Engineering International Conference (BMEiCON)

作者： Pepe, Antonio Trotta, Gianpaolo Francesco Gsaxner, Christina Wallner, Jurgen Egger, Jan Schmalstieg, Dieter Bevilacqua, Vitoantonio Graz Univ Technol Inst Comp Graph & Vis Graz Austria Polytech Univ Bari Dept Mech Math & Management Bari Italy Comp Algorithms Med Lab Graz Austria Med Univ Graz Dept Oral & Maxillofacial Surg Graz Austria Polytech Univ Bari Dept Elect & Informat Engn Bari Italy

ISBN: (纸本)9781538657249

Maxillofacial tumor resection is often dependent on the expertise of the surgeon performing the operation. This study wants to be a first exploration of the role that commercial mixed reality headsets could have in this field. With this purpose in mind, a mixed reality Head Mounted Display (HMD) application is proposed to ease this task and provide a training tool. Due to the invasiveness of the operation, a marker-less registration has been considered as advantageous and therefore a pattern recognition algorithm has been adopted for properly placing a segmented PET-CT scan over the target face. To document the validity and appreciation rate of such a system, groups of physicians and engineers were asked to evaluate and assess the resulting prototype according to the standard ISO-9241/110. The application showed a noticeable accuracy of millimeters, consistent with other biomedical studies, due to intrinsic limitations of the device. Nonetheless, the remarkably positive feedbacks collected from both groups suggest high interest in further work.

关键词： Mixed Reality Human-computer Interaction Maxillofacial Surgery Head and Neck Cancer medical Imaging Microsoft HoloLens PET-CT

来源：评论

学校读者我要写书评

暂无评论

Exploit ¹⁸F-FDG Enhanced Urinary Bladder in PET Data for Deep Learning Ground Truth Generation in CT Scans

Exploit <SUP>18</SUP>F-FDG Enhanced Urinary Bladder in PET D...

引用

SPIE Conference on medical Imaging - Biomedical Applications in Molecular, Structural, and Functional Imaging

作者： Gsaxner, Christina Pfarrkirchner, Birgit Lindner, Lydia Jakse, Norbert Wallner, Juergen Schmalstieg, Dieter Egger, Jan Graz Univ Technol Inst Comp Graph & Vis Inffeldgasse 16c-2 A-8010 Graz Austria Comp Algorithms Med Cafe Lab A-8010 Graz Styria Austria Med Univ Graz Dept Maxillofacial Surg Auenbruggerpl 12 A-8036 Graz Austria BioTechMed Graz Krenngasse 37-1 A-8010 Graz Austria

ISBN: (数字)9781510616462

ISBN: (纸本)9781510616462

Accurate segmentation of medical images is a key step in medical image processing. As the amount of medical images obtained in diagnostics, clinical studies and treatment planning increases, automatic segmentation algorithms become increasingly more important. Therefore, we plan to develop an automatic segmentation approach for the urinary bladder in computed tomography (CT) images using deep learning. For training such a neural network, a large amount of labeled training data is needed. However, public data sets of medical images with segmented ground truth are scarce. We overcome this problem by generating binary masks of images of the F-18-FDG enhanced urinary bladder obtained from a multi-modal scanner delivering registered CT and positron emission tomography (PET) image pairs. Since PET images offer good contrast, a simple thresholding algorithm suffices for segmentation. We apply data augmentation to these datasets to increase the amount of available training data. In this contribution, we present algorithms developed with the medical image processing and visualization platform MeVislab to achieve our goals. With the proposed methods, accurate segmentation masks of the urinary bladder could be generated, and given datasets could be enlarged by a factor of up to 2500.

关键词： medical Image Segmentation Urinary Bladder Deep Learning Combined PET/CT F-18-FDG Data Augmentation

来源：评论

学校读者我要写书评

暂无评论

Learning to Rearrange Voxels in Binary Segmentation Masks for Smooth Manifold Triangulation 1

引用

2nd Conference on AutoImplant Cranial Implant Design Challenge (AutoImplant)

作者： Li, Jianning Pepe, Antonio Gsaxner, Christina Jin, Yuan Egger, Jan Graz Univ Technol Inst Comp Graph & Vis Inffeldgasse 16 A-8010 Graz Austria Comp Algorithms Med Lab Cafe Lab A-8010 Graz Austria Med Univ Graz Res Unit Expt Neurotraumatol Dept Neurosurg Auenbruggerpl 22 A-8036 Graz Austria Univ Hosp Essen Inst AI Med IKIM Girardetstr 2 D-45131 Essen Germany Zhejiang Lab Res Ctr Connected Healthcare Big Data Hangzhou 311121 Zhejiang Peoples R China

ISBN: (数字)9783030926526

ISBN: (纸本)9783030926526;9783030926519

medical images, especially volumetric images, are of high resolution and often exceed the capacity of standard desktop GPUs. As a result, most deep learning-based medical image analysis tasks require the input images to be downsampled, often substantially, before these can be fed to a neural network. However, downsampling can lead to a loss of image quality, which is undesirable especially in reconstruction tasks, where the fine geometric details need to be preserved. In this paper, we propose that high-resolution images can be reconstructed in a coarse-to-fine fashion, where a deep learning algorithm is only responsible for generating a coarse representation of the image, which consumes moderate GPU memory. For producing the high-resolution outcome, we propose two novel methods: learned voxel rearrangement of the coarse output and hierarchical image synthesis. compared to the coarse output, the high-resolution counterpart allows for smooth surface triangulation, which can be 3D-printed in the highest possible quality. Experiments of this paper are carried out on the dataset of AutoImplant 2021 (https://***/), a MICCAI challenge on cranial implant design. The dataset contains high-resolution skulls that can be viewed as 2D manifolds embedded in a 3D space. Codes associated with this study can be accessed at https://***/ Jianningli/voxel rearrangement.

关键词： Skull reconstruction Cranial implant design Deep learning Manifold Sparse CNN Nearest neighbor search (NNS) Hash table Super resolution Hamming distance 3D printing

来源：评论

学校读者我要写书评

暂无评论

Lower Jawbone Data Generation for Deep Learning Tools under MeVislab

Lower Jawbone Data Generation for Deep Learning Tools under ...

引用

SPIE Conference on medical Imaging - Biomedical Applications in Molecular, Structural, and Functional Imaging

作者： Pfarrkirchner, Birgit Gsaxner, Christina Lindner, Lydia Jakse, Norbert Wallner, Juergen Schmalstieg, Dieter Egger, Jan Graz Univ Technol Inst Comp Graph & Vis ICG Inffeldgasse 16c-2 A-8010 Graz Styria Austria Comp Algorithms Med Cafe Lab A-8010 Graz Styria Austria Med Univ Graz Dept Maxillofacial Surg Auenbruggerpl 12 A-8036 Graz Styria Austria BioTechMed Graz Krenngasse 37-1 A-8010 Graz Styria Austria

ISBN: (数字)9781510616462

ISBN: (纸本)9781510616462

In this contribution, the preparation of data for training deep learning networks that are used to segment the lower jawbone in computed tomography (CT) images is proposed. To train a neural network, we had initially only ten CT datasets of the head-neck region with a diverse number of image slices from the clinical routine of a maxillofacial surgery department. In these cases, facial surgeons segmented the lower jawbone in each image slice to generate the ground truth for the segmentation task. Since the number of present images was deemed insufficient to train a deep neural network efficiently, the data was augmented with geometric transformations and added noise. Flipping, rotating and scaling images as well as the addition of various noise types (uniform, Gaussian and salt-and-pepper) were connected within a global macro module under MeVislab. Our macro module can prepare the data for general deep learning data in an automatic and flexible way. Augmentation methods for segmentation tasks can easily be incorporated.

关键词： Data Augmentation Lower Jawbone MeVislab Deep Learning medical Image Segmentation computed Tomography (CT)

来源：评论

学校读者我要写书评

暂无评论

Magnetic energy-based feature extraction for low-quality fingerprint images

引用

SIGNAL IMAGE AND VIDEO PROCESSING 2018年第8期12卷 1471-1478页

作者： Hassanat, Ahmad B. A. Prasath, V. B. Surya Al-kasassbeh, Mouhammd Tarawneh, Ahmad S. Al-shamailh, Ahmad J. Mutah Univ Dept Informat Technol Al Karak Jordan Eotvos Lorand Univ Dept Algorithms & Their Applicat Budapest Hungary Univ Missouri Columbia Computat Imaging & VisAnal CIVA Lab Dept Comp Sci Columbia MO 65211 USA Cincinnati Childrens Hosp Med Ctr Div Biomed Informat Cincinnati OH 45229 USA Univ Cincinnati Dept Biomed Informat Coll Med Cincinnati OH 45220 USA

In fingerprint recognition systems, feature extraction is an important part because of its impact on the final performance of the overall system, particularly, in the case of low-quality images, which poses significant challenges to traditional fingerprint feature extraction methods. In this work, we make two major contributions: First, a novel feature extraction method for low-quality fingerprints images is proposed, which mimics the magnetic energy when attracting iron fillings, and this method is based on image energies attracting uniformly distributed points to form the final features that can describe a fingerprint. Second, we created a new low-quality fingerprints image database to evaluate the proposed method. We used a mobile phone camera to capture the fingerprints of 136 different persons, with five samples for each to obtain 680 fingerprint images in total. To match the computed features, we used the dynamic time warping and evaluated the performance of our system based on k-nearest neighbor classifier. Further, we represent the features using their probability density functions to evaluate the method using some other classifiers. The highest identification accuracy recorded by several experiments reached 95.11% using our in-house database. The experimental results show that the proposed method can be used as a general feature extraction method for other applications.

关键词： Fingerprint recognition Low-quality images Feature extraction Magnetic energy Smartphone camera

来源：评论

学校读者我要写书评

暂无评论

CranGAN: Adversarial Point Cloud Reconstruction for patient-specific Cranial Implant Design 44

CranGAN: Adversarial Point Cloud Reconstruction for patient-...

引用

44th Annual International Conference of the IEEE-Engineering-in-medicine-and-Biology-Society (EMBC)

作者： Sulakhe, Harsh Li, Jianning Egger, Jan Goyal, Poonam BITS Pilani Birla Inst Technol & Sci Pilani Rajasthan India Comp Algorithms Med Lab Graz Austria Univ Hosp Essen Inst AI Med IKIM D-45131 Essen Germany Graz Univ Technol Inst Comp Graph & Vis Inffeldgasse 16 A-8010 Graz Austria Univ Med Essen Canc Res Ctr Cologne Essen CCCE Hufelandstr 55 D-45147 Essen Germany

ISBN: (数字)9781728127828

ISBN: (纸本)9781728127828

Automatizing cranial implant design has become an increasingly important avenue in biomedical research. Benefits in terms of financial resources, time and patient safety necessitate the formulation of an efficient and accurate procedure for the same. This paper attempts to provide a new research direction to this problem, through an adversarial deep learning solution. Specifically, in this work, we present CranGAN - a 3D Conditional Generative Adversarial Network designed to reconstruct a 3D representation of a complete skull given its defective counterpart. A novel solution of employing point cloud representations instead of conventional 3D meshes and voxel grids is proposed. We provide both qualitative and quantitative analysis of our experiments with three separate GAN objectives, and compare the utility of two 3D reconstruction loss functions viz. Hausdorff Distance and Chamfer Distance. We hope that our work inspires further research in this direction.

关键词： Point cloud compression Deep learning Three-dimensional displays Statistical analysis Implants Generative adversarial networks Skull

来源：评论

学校读者我要写书评

暂无评论

Deep Learning and Particle Filter-based Aortic Dissection Vessel Tree Segmentation

Deep Learning and Particle Filter-based Aortic Dissection Ve...

引用

Conference on medical Imaging - Biomedical Applications in Molecular, Structural, and Functional Imaging

作者： Jin, Yuan Pepe, Antonio Li, Jianning Gsaxner, Christina Egger, Jan Graz Univ Technol Inst Comp Graph & Vis Inffeldgasse 16c-2 A-8010 Graz Austria Comp Algorithms Med Lab A-8010 Graz Austria Leibniz Univ Hannover Inst Informat Verarbeitung Appelstr 9A D-30167 Hannover Germany Med Univ Graz Dept Oral & Maxillofacial Surg Auenbruggerpl 5-1 A-8036 Graz Austria

ISBN: (纸本)9781510640306

Aortic dissections (AD) are injuries of the inner vessel wall of the (human) aorta. As this disease poses a significant threat to a patient's life, it is crucial to observe and analyze the progression of the dissection over the course of the disease. The clinical examinations are usually performed with the application of computed Tomography (CT) or computed Tomography Angiography (CTA), based on which, automated post-processing procedures would be beneficial for the management of critical pathologies. One of the main tasks during post-processing is aorta segmentation. Different methods have been developed for the segmentation of aorta, including the tracking methods, the active contour/surface methods and the deep learning methods. In this study, a method for the automatic segmentation of aorta and its branches from original thorax CT and CTA images is introduced. The aorta is segmented based on deep learning algorithm and afterwards the branches are tracked based on particle filter algorithm.

关键词： Aortic Dissection computed Tomography Angiography Segmentation Deep Learning V-Net Particle Filter

来源：评论

学校读者我要写书评

暂无评论

A Cloud-based Centerline Algorithm for Studierfenster

A Cloud-based Centerline Algorithm for Studierfenster

引用

Conference on medical Imaging - Imaging Informatics for Healthcare, Research, and Applications

作者： Dionysio, Christina Wild, Daniel Pepe, Antonio Gsaxner, Christina Li, Jianning Alvarez, Luis Egger, Jan Graz Univ Technol Inst Comp Graph & Vis Inffeldgasse 16c-II A-8010 Graz Austria Comp Algorithms Med Lab Graz Austria Med Univ Graz Dept Oral & Maxillofacial Surg Auenbruggerpl 5 A-8036 Graz Austria Univ Las Palmas Gran Canaria Dept Informat & Sistemas CTIM Las Palmas Gran Canaria 35017 Spain

ISBN: (纸本)9781510640320

Aortic diseases are common these times, as people tend to eat unhealthier food and do fewer sports. As a consequence, more people have atherosclerosis, which can also lead to aortic aneurysms. A practical method to analyze blood vessels, like the aorta, is to calculate the vessel's centerline and evaluate its shape in a thoracic CT or CTA scan. The centerline of a diseased vessel will most likely look different from the healthy vessel's reference centerline. This contribution introduces a semi-automatic cloud-based centerline tool for the aorta, which computes an initial centerline from a CTA scan with two user given seed points. Afterwards, this initial centerline can be smoothed in a second step. The work done for this contribution was implemented into an existing platform-independent online tool for medical image analysis, called Studierfenster (http://***). In order to evaluate the outcome of this contribution, we tested the smoothed centerline computed within Studierfenster against 40 baseline centerlines from a public available CTA challenge dataset. In doing so, we computed a minimum, maximum, and mean distance between the two centerlines in mm for every data sample, resulting in the smallest distance of 0.59mm, an overall maximum distance of 14.18mm, and a mean distance for all samples of 3.86mm with a standard deviation of 0.99mm.

关键词： Centerline Calculation Tracking Client/Server Studierfenster Aorta

来源：评论

学校读者我要写书评

暂无评论

STonKGs: a sophisticated transformer trained on biomedical text and knowledge graphs

引用

BIOINFORMATICS 2022年第6期38卷 1648-1656页

作者： Balabin, Helena Hoyt, Charles Tapley Birkenbihl, Colin Gyori, Benjamin M. Bachman, John Kodamullil, Alpha Tom Ploeger, Paul G. Hofmann-Apitius, Martin Domingo-Fernandez, Daniel Fraunhofer Inst Algorithms & Sci Comp Dept Bioinformat D-53757 St Augustin Germany Univ Appl Sci Dept Bonn Rhein Sieg D-53757 St Augustin Germany Harvard Med Sch Lab Syst Pharmacol Boston MA 02115 USA Fraunhofer Ctr Machine Learning St Augustin Germany Enveda Biosci Boulder CO 80301 USA

Motivation: The majority of biomedical knowledge is stored in structured databases or as unstructured text in scientific publications. This vast amount of information has led to numerous machine learning-based biological applications using either text through natural language processing (NLP) or structured data through knowledge graph embedding models. However, representations based on a single modality are inherently limited. Results: To generate better representations of biological knowledge, we propose STonKGs, a Sophisticated Transformer trained on biomedical text and Knowledge Graphs (KGs). This multimodal Transformer uses combined input sequences of structured information from KGs and unstructured text data from biomedical literature to learn joint representations in a shared embedding space. First, we pre-trained STonKGs on a knowledge base assembled by the Integrated Network and Dynamical Reasoning Assembler consisting of millions of text-triple pairs extracted from biomedical literature by multiple NLP systems. Then, we benchmarked STonKGs against three baseline models trained on either one of the modalities (i.e. text or KG) across eight different classification tasks, each corresponding to a different biological application. Our results demonstrate that STonKGs outperforms both baselines, especially on the more challenging tasks with respect to the number of classes, improving upon the F1-score of the best baseline by up to 0.084 (i.e. from 0.881 to 0.965). Finally, our pre-trained model as well as the model architecture can be adapted to various other transfer learning applications.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Robust dynamical network structure reconstruction

引用

AUTOMATICA 2011年第6期47卷 1230-1235页

作者： Yuan, Ye Stan, Guy-Bart Warnick, Sean Goncalves, Jorge Univ Cambridge Dept Engn Control Grp Informat Engn Div Cambridge CB2 1TN England Univ London Imperial Coll Sci Technol & Med Dept Bioengn Ctr Synthet Biol & Innovat London SW7 2AZ England Brigham Young Univ Dept Comp Sci Informat & Decis Algorithms Labs Provo UT 84602 USA Brigham Young Univ Interdisciplinary Informat & Decis Algorithms Lab Provo UT 84602 USA Univ London Imperial Coll Sci Technol & Med EPSRC Funded Ctr Synthet Biol & Innovat London SW7 2AZ England

This paper addresses the problem of network reconstruction from data. Previous work identified necessary and sufficient conditions for network reconstruction of LTI systems, assuming perfect measurements (no noise) and perfect system identification. This paper assumes that the conditions for network reconstruction have been met but here we additionally take into account noise and unmodelled dynamics (including nonlinearities). In order to identify the network structure that generated the data, we compute the smallest distances between the measured data and the data that would have been generated by particular network structures. We conclude with biologically inspired network reconstruction examples which include noise and nonlinearities. (C) 2011 Elsevier Ltd. All rights reserved.

关键词： Robust network reconstruction Noise and unmodelled dynamics Systems biology

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：