检索结果-内蒙古大学图书馆

Medical Technologies National Conference (TIPTEKNO)

作者： Reyhan Dede Gokhan Bilgin Department of Computer Engineering Signal and Image Processing Lab. (SIMPLAB) at YTU Yildiz Technical University (YTU) Istanbul Turkey

ISBN: (数字)9798331529819

ISBN: (纸本)9798331529826

This paper introduces a novel deep learning framework for the discovery of breast cancer stages, which integrates GAN-generated synthetic images with multi-omics data. By employing StyleGAN3 for the generation of realistic histopathological images and Swin Transformer for classification, the model draws upon both visual and biological data to enhance the accuracy of cancer staging predictions. The proposed methodology entails the generation of high-quality synthetic images using StyleGAN3, with a Fréchet Inception Distance (FID) score of 35, indicating a reasonable degree of similarity to real images. The images, in conjunction with RNA, miRNA, and clinical data, are integrated into a Swin Transformer-based classifier, resulting in an accuracy of 95.03 %, a precision of 95.00 %, and an F1 score of 95.00 %. A threshold-based softmax probability analysis was employed during the inference stage to explore the potential discovery of new cancer stages. The preliminary observation-based threshold of 30 % may be optimized through further experimentation. In the event that the model exhibited a confidence level for a given class below the specified threshold, the image was identified as a potential candidate for a previously unidentified stage. This study underscores the potential of multimodal data integration in enhancing breast cancer staging and offers insights into leveraging deep learning models for generating and classifying histopathological data, alongside identifying novel disease stages.

关键词： Deep learning Visualization Accuracy RNA Data integration Predictive models Transformers Breast cancer Data models Biomedical imaging

来源：评论

学校读者我要写书评

暂无评论

A novel segmentation framework for uveal melanoma in magnetic resonance imaging based on class activation maps 2

A novel segmentation framework for uveal melanoma in magneti...

引用

2nd International Conference on Medical Imaging with Deep Learning, MIDL 2019

作者： Nguyen, Huu-Giao Pica, Alessia Hrbacek, Jan Weber, Damien C. La Rosa, Francesco Schalenbourg, Ann Sznitman, Raphael Cuadra, Meritxell Bach Proton Therapy Center Paul Scherrer Institut ETH Domain Villigen Switzerland Ophthalmic Technology Lab. ARTORG Center University of Bern Switzerland Switzerland Radiation Oncology Department Inselspital University of Bern Switzerland Signal Processing Lab. Ecole Polytechnique Fédérale de Lausanne Switzerland Adult Ocular Oncology Unit Jules-Gonin Eye Hospital Lausanne Switzerland Medical Image Analysis Laboratory CIBM University of Lausanne Switzerland

An automatic and accurate eye tumor segmentation from Magnetic Resonance images (MRI) could have a great clinical contribution for the purpose of diagnosis and treatment planning of intra-ocula cancer. For instance, the characterization of uveal melanoma (UM) tumors would allow the integration of 3D information for the radiotherapy and would also support further radiomics studies. In this work, we tackle two major challenges of UM segmentation: 1) the high heterogeneity of tumor characterization in respect to location, size and appearance and, 2) the difficulty in obtaining ground-truth delineations of medical experts for training. We propose a thorough segmentation pipeline consisting of a combination of two Convolutional Neural Networks (CNN). First, we consider the class activation maps (CAM) output from a Resnet classification model and the combination of Dense Conditional Random Field (CRF) with a prior information of sclera and lens from an Active Shape Model (ASM) to automatically extract the tumor location for all MRIs. Then, these immediate results will be inputted into a 2D-Unet CNN whereby using four encoder and decoder layers to produce the tumor segmentation. A clinical data set of 1.5T T1-w and T2-w images of 28 healthy eyes and 24 UM patients is used for validation. We show experimentally in two different MRI sequences that our weakly 2D-Unet approach outperforms previous state-of-the-art methods for tumor segmentation and that it achieves equivalent accuracy as when manual lab.ls are used for training. These results are promising for further large-scale analysis and for introducing 3D ocular tumor information in the therapy planning. © 2019 H.-G. Nguyen, A. Pica, J. Hrbacek, D. Weber, F.L. Rosa, A. Schalenbourg, R. Sznitman & M. Bach Cuadra.

关键词： Magnetic resonance imaging

来源：评论

学校读者我要写书评

暂无评论

image normalization for quantitative immunohistochemistry in digital pathology

Image normalization for quantitative immunohistochemistry in...

引用

IEEE International Symposium on Biomedical Imaging

作者： Yves-Rémi Van Eycke Justine Allard Mélanie Derock Isabelle Salmon Olivier Debeir Christine Decaestecker Lab. of Image Signal processing & Acoustics Université Libre de Bruxelles (ULB) Brussels Belgium DIAPath Center for Microscopy and Molecular Imaging (ULB) Gosselies Belgium Department of Pathology Université Libre de Bruxelles (ULB) Brussels Belgium

ISBN: (纸本)9781479923519

We propose to adapt to immunohistochemistry (IHC) some methods proposed to normalize images from histological slices stained with hematoxylin-eosin (H&E). Our final aim is to provide a coherent quantitative characterization of IHC biomarkers across different IHC batches with possible staining variations. In contrast to H&E, IHC staining strongly varies with the tissue analyzed and the protein targeted, making image normalization challenging. To solve this problem, we added in each IHC batch a slice from a reference tissue microarray (TMA) and then digitalized it to establish an inter-batch normalization transform. A comparison of two methods adapted to the specificity of IHC-stained slides evidences some normalization requirements to make valid IHC biomarker quantification across different staining batches.

关键词： image color analysis Biological tissues Proteins Deconvolution Biomarkers Immune system Pathology

来源：评论

学校读者我要写书评

暂无评论

Heart Rate Monitoring During Physical Exercise Using Wrist-Type Photoplethysmographic (PPG) signals

Heart Rate Monitoring During Physical Exercise Using Wrist-T...

引用

Annual International Conference of the IEEE Engineering in Medicine and Biology Society

作者： Amirhosein Khas Ahmadi Parsa Moradi Mahan Malihi Sajjad Karimi Mohammad B. Shamsollahi Shamsollahi Biomedical Signal and Image Processing Lab. (BiSIPL) Department of Electrical Engineering Sharif University of Technology Tehran Iran Biomedical Signal and Image Processing Lab. (BiSIPL) Department of Electrical Engineering Sharif University of Technology Tehran Iran

ISBN: (纸本)9781424492695

Heart rate monitoring using wrist-type using photoplethysmographic (PPG) signals during subjects' intensive exercises is a challenging problem, since signals are strongly affected by motion artifacts caused by unexpected movements. This paper presents a method that uses both time and frequency characteristics of signals;using sparse signal reconstruction for high-resolution spectrum estimation. Experimental results on type data sets recorded from 12 subjects during fast running at peak speed of 15 km/hour. The results have a performance with the average absolute error being 1.80 beat per minute.

关键词： Photoplethysmographic (PPG) Sparse signal Reconstruction Regression Heart rate

来源：评论

学校读者我要写书评

暂无评论

Acoustic detection and tracking of UAS targets

引用

The Journal of the Acoustical Society of America 2016年第4_SUPPLEMENT期139卷 2020-2020页

作者： Christian G. Reiff Signal and Image Processing Army Res. Lab. 2800 Powder Mill Rd. RDRL-SES-P Adelphi MD 20783 christian.g.reiff.civ@mail.mil

Acoustic detection using a Minimum Variance Distortionless Response (MVDR) method and tracking of Unmanned Aircraft System (UAS) targets with the MVDR results over time will be presented. The acoustic environment was complex with surf noise, wind, road traffic, air traffic, and aircraft hangar noise. The targets were gas and electric fixed wing UAS as well as electric multi-rotor quadcopters. Scenarios with the UAS target leaving, incoming, and with multiple simultaneous targets are addressed. Tracking results are evaluated through comparison with GPS based UAS ground truth tracks.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Investigating the stability of fast iterative shrinkage thresholding algorithm for MR imaging reconstruction using compressed sensing

Investigating the stability of fast iterative shrinkage thre...

引用

International Conference on Fuzzy Systems and Knowledge Discovery (FSKD)

作者： Guishan Zhang Haitao Deng Yaowen Chen Zhiwei Shen Renhua Wu Key Lab. of Digital Signal and Image Processing of Guangdong Province Shantou University Shantou China Department of Medical Imaging 2nd Affiliated Hospital Medical College of Shantou University Shantou China

ISBN: (纸本)9781467376839

Compressed sensing (CS) has been applied to the field of sub-sampled magnetic resonance imaging (MRI) reconstruction (CS-MRI). Fast iterative shrinkage-thresholding algorithm (FISTA) is an effective method for CS-MR images reconstruction. To investigate the accuracy and efficiency of the proposed algorithm, we applied it to the under-sampling MR images gained by different MRI scanning sequences. We found the peak signal to noise ratio (PSNR) of reconstructed MRI with varying sampling ratios diminished from Axial T1 weighted images (Ax T1) (45.13±12.97 dB), Axial T2 weighted images (Ax T2) (42.8 ± 14.95 dB), FLAIR (41.74 ± 14.15 dB), Diffusion Weighted Imaging (DWI) (40.23 ±17.40 dB) and Sagittal T2 weighted images (Sag T2) (36.28±12.32 dB), but there was no significant difference among the groups. In addition, the changes to the elapsed time of them was minor, Ax T1 (1.09±0.13 s), Ax T2 (1.30±0.13s), FLAIR (1.02±0.12s), DWI (1.07±0.13s) and Sag T2 (1.12±0.07s). Our results confirmed the stability of the proposed fast MRI reconstruction method for different scanning sequences. Further efforts are still needed to design the clinical sequence with sub-sampled acquisition strategy which may be a developing technique with clinical value.

关键词： Compressed Sensing Magnetic Resonance Imaging PSNR Fast Iterative Shrinkage-thresholding Algorithm (FISTA)

来源：评论

学校读者我要写书评

暂无评论

Binary pattern flavored feature extractors for Facial Expression Recognition: An overview

Binary pattern flavored feature extractors for Facial Expres...

引用

Proceedings of the International Convention MIPRO

作者： Rasmus Lyngby Kristensen Zheng-Hua Tan Zhanyu Ma Jun Guo Section of Image Analysis and Computer Graphics Technical University of Denmark Kgs. Lyngby Denmark Signal and Information Processing section (SIP) Aalborg University Aalborg Denmark Pattern Recognition and Intelligent System Lab. Beijing University of Posts and Telecommunications Beijing China

ISBN: (纸本)9781479981748

This paper conducts a survey of modern binary pattern flavored feature extractors applied to the Facial Expression Recognition (FER) problem. In total, 26 different feature extractors are included, of which six are selected for in depth description. In addition, the paper unifies important FER terminology, describes open challenges, and provides recommendations to scientific evaluation of FER systems. Lastly, it studies the facial expression recognition accuracy and blur invariance of the Local Frequency Descriptor. The paper seeks to bring together disjointed studies, and the main contribution is to provide a solid overview for future research.

关键词： Feature extraction Face Face recognition Databases Three-dimensional displays Accuracy Gold

来源：评论

学校读者我要写书评

暂无评论

Robust Multimodal Biometric Identification System Using Finger-Knuckle-Print features

Robust Multimodal Biometric Identification System Using Fing...

引用

International Conference on Control, Engineering & Information Technology

作者： Abdallah Meraoumia Salim Chitroub Ahmed Bouridane Univ Ouargla Fac. des nouvelles technologies de l'information et de la communication Lab. de Genie Electrique Signal and Image Processing Laboratory Electronics and Computer Science Faculty USTHB School of Computing Engineering and Information Sciences Northumbria University

ISBN: (纸本)9781479982134

Automatic personal identification is becoming an increasingly important requirement in a variety of applications like access control, surveillance systems and physical buildings. In recent years, biometric systems are used in these fields, offering greater convenience and several advantages over traditional security. In this paper, we propose an efficient online personal identification system based on Finger-Knuckle-Print (FKP) images. In this study, the finger image is characterized by the two dimensional Bloc based Discrete Cosine Transform (2D-BDCT) coefficients. Then, we use the Hidden Markov Model (HMM) for modeling the observation vector. In addition, the same finger is transformed by the two dimensional Discrete Fourier Transform (2D-DFT). The response of this transformation is directly used to create another observation vector. Subsequently, the two sub-systems are integrated in order to construct an efficient multi-modal identification system based on matching score level fusion. The results on a medium-size database, 150 users, show good identification performance based on individual modalities as well as after fusing multiple finger types.

关键词： Biometrics Identification FKP 2D-BDCT 2D-DFT HMM Data fusion

来源：评论

学校读者我要写书评

暂无评论

Underwater video streaming using adaptive frame decimation

Underwater video streaming using adaptive frame decimation

引用

OCEANS - Europe

作者： Gilad Avrashi Shlomi Museri Yaakov Bucris Azriel Sinai Alon Amar Signal and Image Processing Lab. Technion Haifa Israel Signal Processing Department Acoustics Research Center Rafael Haifa Israel

We introduce a low data rate video compression scheme for underwater acoustic communication. Recently, multi-carrier based underwater acoustic modems have been proposed and tested for data rates of up to tens of kilobits-per-second for about 1-4 kilometers transmission range. Online transmission of video data using these rates requires extreme compression. Herein, we propose pre-encoder and post-decoder processing in order to reduce the data rate. This is done by exploiting the characteristics of underwater videos for excluding frames. The algorithm was tested and analyzed in simulation environment with several video samples taken by divers in shallow waters of the Mediterranean. We show that using this technique, increased performance is achieved compared to standard H.264/AVC based codecs in both objective and subjective terms.

关键词： Streaming media PSNR image edge detection Video coding Vectors Video compression Codecs

来源：评论

学校读者我要写书评

暂无评论

Robust human identity identification system by using hand biometric traits 26

Robust human identity identification system by using hand bi...

引用

2014 26th International Conference on Microelectronics, ICM 2014

作者： Meraoumia, Abdallah Chitroub, Salim Bouridane, Ahmed Univ Ouargla Fac. des Nouvelles Technologies de L'information et de la Communication Lab. de Génie Électrique Ouargla30 000 Algeria Signal and Image Processing Laboratory Electronics and Computer Science Faculty USTHB P.O. box 32 El Alia Bab Ezzouar Algiers16111 Algeria Department of Computer Science and Digital Technologies Northumbria University Newcastle Pandon Building Newcastle-upon-TyneNE2 1XE United Kingdom

ISBN: (纸本)9781479981533

Automatic personal identification has become an important issue in several applications, such as physical buildings and information systems. Nowadays, biometric techniques are an important and effective solution for automatic personal identification. One of the most popular biometric systems is based on the hand due to its ease of use. Hand has several modalities to be extracted, among them, Finger-Knuckle-Print (FKP) and PaLMprint (PLM), has attracted an increasing amount of attention. This paper investigates these modalities for elab.rating an efficient multimodal biometric identification system. For that, the texture information of FKP and PLM is characterized by the Local Binary Pattern (LBP). During the matching phase, an Euclidian distance score is employed to measure the similarity between templates. The proposed system is tested and evaluated using a database of 165 users. Our experimental results show the effectiveness and reliability of the proposed system, which brings high identification accuracy rate. © 2014 IEEE.

关键词： Biometrics

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：