2019 IEEE 16th International Symposium on Biomedical Imaging (ISBI 2019)最新文献_第9页

Multicenter Validation Of Population-Based Input Function With Non-Linear Mixed Effect Modeling For Voxel-Wise Quantification Of [18F]Fdg Metabolic Rate 基于种群的输入函数非线性混合效应建模多中心验证[18F]Fdg代谢率体素量化

2019 IEEE 16th International Symposium on Biomedical Imaging (ISBI 2019) Pub Date : 2019-04-01 DOI: 10.1109/ISBI.2019.8759190

Matteo Tonietto, F. Zanderigo, A. Bertoldo, D. Devanand, J. Mann, B. Bodini, B. Stankoff

{"title":"Multicenter Validation Of Population-Based Input Function With Non-Linear Mixed Effect Modeling For Voxel-Wise Quantification Of [18F]Fdg Metabolic Rate","authors":"Matteo Tonietto, F. Zanderigo, A. Bertoldo, D. Devanand, J. Mann, B. Bodini, B. Stankoff","doi":"10.1109/ISBI.2019.8759190","DOIUrl":"https://doi.org/10.1109/ISBI.2019.8759190","url":null,"abstract":"Population-based input function (PBF) methods provide a less-invasive approach to the quantification of dynamic positron emission tomography (PET) images. PBF methods require the a priori creation of an input function template from a group of subjects who underwent full arterial blood sampling with the same radiotracer. The template is then calibrated using one or two blood samples from the subject under analysis. In this study we propose to generate the PBF template from a group of 8 subjects using a non-linear mixed effect approach and a new input function model. We validated our PBF approach using an independent[18F] FDG dataset of 25 subjects acquired in a different PET center. Results showed a high correlation (> 0.98) and low bias (mean percentage error=1.0 ± 3.1%) between the voxel-wise estimates of [18F] FDG net uptake rate (Ki) obtained with the measured input function and those obtained with the proposed PBF, supporting its use for the quantification of [18F] FDG images acquired in different PET centers.","PeriodicalId":119935,"journal":{"name":"2019 IEEE 16th International Symposium on Biomedical Imaging (ISBI 2019)","volume":"76 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-04-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127081703","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 2

Multi-anatomy localization in fetal echocardiography videos 胎儿超声心动图影像的多解剖定位

2019 IEEE 16th International Symposium on Biomedical Imaging (ISBI 2019) Pub Date : 2019-04-01 DOI: 10.1109/ISBI.2019.8759551

A. Patra, J. Noble

引用次数: 11

Ink Removal from Histopathology Whole Slide Images by Combining Classification, Detection and Image Generation Models 结合分类、检测和图像生成模型的组织病理学全切片图像油墨去除

2019 IEEE 16th International Symposium on Biomedical Imaging (ISBI 2019) Pub Date : 2019-04-01 DOI: 10.1109/ISBI.2019.8759322

Sharib Ali, N. K. Alham, C. Verrill, J. Rittscher

{"title":"Ink Removal from Histopathology Whole Slide Images by Combining Classification, Detection and Image Generation Models","authors":"Sharib Ali, N. K. Alham, C. Verrill, J. Rittscher","doi":"10.1109/ISBI.2019.8759322","DOIUrl":"https://doi.org/10.1109/ISBI.2019.8759322","url":null,"abstract":"Histopathology slides are routinely marked by pathologists using permanent ink markers that should not be removed as they form part of the medical record. Often tumour regions are marked up for the purpose of highlighting features or other downstream processing such an gene sequencing. Once digitised there is no established method for removing this information from the whole slide images limiting its usability in research and study. Removal of marker ink from these high-resolution whole slide images is non-trivial and complex problem as they contaminate different regions and in an inconsistent manner. We propose an efficient pipeline using convolution neural networks that results in ink-free images without compromising information and image resolution. Our pipeline includes a sequential classical convolution neural network for accurate classification of contaminated image tiles, a fast region detector and a domain adaptive cycle consistent adversarial generative model for restoration of foreground pixels. Both quantitative and qualitative results on four different whole slide images show that our approach yields visually coherent ink-free whole slide images.","PeriodicalId":119935,"journal":{"name":"2019 IEEE 16th International Symposium on Biomedical Imaging (ISBI 2019)","volume":"29 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-04-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124992536","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 15

Deep Attentive Feature Learning for Histopathology Image Classification 用于组织病理学图像分类的深度关注特征学习

2019 IEEE 16th International Symposium on Biomedical Imaging (ISBI 2019) Pub Date : 2019-04-01 DOI: 10.1109/ISBI.2019.8759267

Pengxiang Wu, Hui Qu, Jingru Yi, Qiaoying Huang, Chao Chen, Dimitris N. Metaxas

引用次数: 4

Iteratively-Reweighted Beamforming For High-Resolution Ultrasound Imaging 用于高分辨率超声成像的迭代重加权波束形成

2019 IEEE 16th International Symposium on Biomedical Imaging (ISBI 2019) Pub Date : 2019-04-01 DOI: 10.1109/ISBI.2019.8759495

A. Mahurkar, P. Pokala, C. Seelamantula

{"title":"Iteratively-Reweighted Beamforming For High-Resolution Ultrasound Imaging","authors":"A. Mahurkar, P. Pokala, C. Seelamantula","doi":"10.1109/ISBI.2019.8759495","DOIUrl":"https://doi.org/10.1109/ISBI.2019.8759495","url":null,"abstract":"Ultrasound imaging typically employs delay-and-sum (DAS) beamformers for image reconstruction. An apodization window is typically used to suppress the beam-pattern’s sidelobes. This approach introduces a trade-off between the mainlobe width versus the sidelobe attenuation and therefore offers limited performance. We consider a statistical framework for beamforming and present two variants. In the first one, the signal of interest is modeled as a Laplacian distributed random variable and the interference is modeled as additive and Gaussian distributed. A closed-form solution is obtained to this optimization problem. In the second variant, we propose an iteratively-reweighted (IR) beamforming algorithm, which solves a constrained optimization problem to determine the optimal apodization weights. This beamformer results in a sharper mainlobe that translates to a finer lateral resolution. The proposed method is compared with the standard DAS beamformer and a recently proposed statistically modeled beamformer, namely iMAP for different number of plane-wave (PW) insonifications. This algorithm is independent of the imaging modality employed and exhibits a superior performance in terms of lateral resolution.","PeriodicalId":119935,"journal":{"name":"2019 IEEE 16th International Symposium on Biomedical Imaging (ISBI 2019)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-04-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125805019","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 1

A Supervoxel-Based Approach for Unsupervised Abnormal Asymmetry Detection in Mr Images of the Brain 基于超体素的脑磁共振图像非监督异常不对称检测方法

2019 IEEE 16th International Symposium on Biomedical Imaging (ISBI 2019) Pub Date : 2019-04-01 DOI: 10.1109/ISBI.2019.8759166

S. B. Martins, Guilherme C. S. Ruppert, F. Reis, C. L. Yasuda, A. Falcão

引用次数: 11

Topology-Preserving Shape-Based Regression Of Retinal Layers In Oct Image Data Using Convolutional Neural Networks 基于卷积神经网络的Oct图像数据中视网膜层拓扑保持形状回归

2019 IEEE 16th International Symposium on Biomedical Imaging (ISBI 2019) Pub Date : 2019-04-01 DOI: 10.1109/ISBI.2019.8759261

Timo Kepp, J. Ehrhardt, M. Heinrich, G. Hüttmann, H. Handels

{"title":"Topology-Preserving Shape-Based Regression Of Retinal Layers In Oct Image Data Using Convolutional Neural Networks","authors":"Timo Kepp, J. Ehrhardt, M. Heinrich, G. Hüttmann, H. Handels","doi":"10.1109/ISBI.2019.8759261","DOIUrl":"https://doi.org/10.1109/ISBI.2019.8759261","url":null,"abstract":"Optical coherence tomography (OCT) is a non-invasive imaging modality that provides cross-sectional 3D images of biological tissue. Especially in ophthalmology OCT is used for the diagnosis of various eye diseases. Automatic retinal layer segmentation algorithms, which are increasingly based on deep learning techniques, can support diagnostics. However, topology properties, such as the order of retinal layers, are often not considered. In our work, we present an automatic segmentation approach based on shape regression using convolutional neural networks (CNNs). Here, shapes are represented by signed distance maps (SDMs) that assign the distance to the next object contour to each pixel. Thus, spatial regularization is introduced and plausible segmentations can be produced. Our method is evaluated on a public OCT dataset and is compared with two classification-based approaches. The results show that our method has fewer outliers with comparable segmentation performance. In addition, it has an improved topology preservation, which saves further post-processing.","PeriodicalId":119935,"journal":{"name":"2019 IEEE 16th International Symposium on Biomedical Imaging (ISBI 2019)","volume":"161 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-04-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116160269","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 11

Determining Ischemic Stroke From CT-Angiography Imaging Using Symmetry-Sensitive Convolutional Networks 利用对称敏感卷积网络从ct血管造影成像中确定缺血性卒中

2019 IEEE 16th International Symposium on Biomedical Imaging (ISBI 2019) Pub Date : 2019-04-01 DOI: 10.1109/ISBI.2019.8759475

Arko Barman, M. Inam, Songmi Lee, S. Savitz, S. Sheth, L. Giancardo

{"title":"Determining Ischemic Stroke From CT-Angiography Imaging Using Symmetry-Sensitive Convolutional Networks","authors":"Arko Barman, M. Inam, Songmi Lee, S. Savitz, S. Sheth, L. Giancardo","doi":"10.1109/ISBI.2019.8759475","DOIUrl":"https://doi.org/10.1109/ISBI.2019.8759475","url":null,"abstract":"Acute Ischemic Stroke (AIS) is the second leading cause of death worldwide in 2015, and 5th in the United States. Neuro-imaging is routinely used in the diagnosis and management of these patients. To create a decision support method for AIS, we propose a convolutional neural network for automated detection of ischemic stroke from CT Angiography (CTA), an imaging technique that is widely available and used routinely in stroke evaluations. The network has a novel design that makes it sensitive to changes in symmetry of vascular and brain tissue texture which allows it to detect ischemic stroke from CTA brain images. The proposed model is inspired from the paradigm of Siamese networks and applied to the two brain hemispheres in parallel. We tested the model on a clinical dataset of 217 subjects, 123 controls and 94 subjects imaged less than 24 hours after stroke onset. First, we tested the ability of the network in recognizing strokes with the original images, which contain asymmetries in both vascular structures and brain tissues. Then, we digitally removed the vasculature in order to evaluate the ability of the network to recognize strokes by analyzing brain tissue only. We achieved AUC 0.914 (CI 0.88-0.95) and AUC 0.899 (CI 0.86-0.94) on the two experiments respectively. The qualitative analysis of the network activation confirms that the model efficiently learns the vasculature and brain tissue structures in one hemisphere that does not appear in the opposite hemisphere.","PeriodicalId":119935,"journal":{"name":"2019 IEEE 16th International Symposium on Biomedical Imaging (ISBI 2019)","volume":"42 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-04-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122649339","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 27

Radiomic-Based Framework for Early Diagnosis of Lung Cancer 肺癌早期诊断的放射组学框架

2019 IEEE 16th International Symposium on Biomedical Imaging (ISBI 2019) Pub Date : 2019-04-01 DOI: 10.1109/ISBI.2019.8759540

A. Shaffie, A. Soliman, H. A. Khalifeh, M. Ghazal, F. Taher, Adel Said Elmaghraby, R. Keynton, A. El-Baz

引用次数: 15

Brain Image Parcellation Using Multi-Atlas Guided Adversarial Fully Convolutional Network 基于多图谱引导的对抗全卷积网络的脑图像分割

2019 IEEE 16th International Symposium on Biomedical Imaging (ISBI 2019) Pub Date : 2019-04-01 DOI: 10.1109/ISBI.2019.8759507

Xianli Liu, Haifeng Zhao, Shaojie Zhang, Zhenyu Tan

引用次数: 3