2022 IEEE Western New York Image and Signal Processing Workshop (WNYISPW)最新文献

On Deep Learning for Dorsal Hand Vein Recognition 手背静脉识别的深度学习研究

2022 IEEE Western New York Image and Signal Processing Workshop (WNYISPW) Pub Date : 2022-11-04 DOI: 10.1109/WNYISPW57858.2022.9982726

Sougato Bagchi, Geetartho Chanda, Akshay Agarwal, N. Ratha

{"title":"On Deep Learning for Dorsal Hand Vein Recognition","authors":"Sougato Bagchi, Geetartho Chanda, Akshay Agarwal, N. Ratha","doi":"10.1109/WNYISPW57858.2022.9982726","DOIUrl":"https://doi.org/10.1109/WNYISPW57858.2022.9982726","url":null,"abstract":"The use of biometrics has been one of the most effective solutions for a person’s identification and verification. Traditional biometric modalities such as fingerprint, iris, and face recognition have been successfully employed and have shown tremendous success in providing a secure access mechanism. On top of that, the success of deep learning algorithms has showcased that automated biometrics recognition has the potential of surpassing human-level accuracy. Another relatively unexplored biometric modality namely Dorsal Hand Vein (DHV) recently has gained traction in the industry and among researchers from academia. In this paper, we have designed an end-to-end pipeline for DHV biometric authentication that includes image enhancement, region of interest (ROI) extraction, and finally deep learning models for DHV recognition. Three deep learning models namely a custom convolutional neural network (CNN), a Siamese network, and a Triplet Network are trained on publicly available images of DHV datasets. Later, these models are used as feature extractors and tested on images of unseen subjects for authentication. We find that the simple CNN model learns a better feature representation than the Triplet network, which outperforms the Siamese network. One potential reason for such behavior is the limited availability of the datasets used in training.","PeriodicalId":427869,"journal":{"name":"2022 IEEE Western New York Image and Signal Processing Workshop (WNYISPW)","volume":"3 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-11-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124443082","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: 0

Effect of Inter-User Segmentation Differences on Ischemic Stroke Radiomics from CTA and NCCT 用户间分割差异对CTA和NCCT缺血性脑卒中放射组学的影响

2022 IEEE Western New York Image and Signal Processing Workshop (WNYISPW) Pub Date : 2022-11-04 DOI: 10.1109/WNYISPW57858.2022.9983487

T. Patel, Munjal Shah, S. Veeturi, A. Monteiro, A. Siddiqui, V. Tutino

{"title":"Effect of Inter-User Segmentation Differences on Ischemic Stroke Radiomics from CTA and NCCT","authors":"T. Patel, Munjal Shah, S. Veeturi, A. Monteiro, A. Siddiqui, V. Tutino","doi":"10.1109/WNYISPW57858.2022.9983487","DOIUrl":"https://doi.org/10.1109/WNYISPW57858.2022.9983487","url":null,"abstract":"Radiomics is emerging as a promising tool for analyzing variations in signal intensities among different imaging modalities. For this technique, variations in medical images are quantified into a high dimensional space using automated data-characterization algorithms. Such radiomic features (RFs) are then used in advanced mathematical analyses of medical images for the prediction of treatment outcomes, disease prognoses, and pathology detection. In the field of acute ischemic stroke intervention and management, the procedural outcomes of mechanical thrombectomy have been associated with RF subsets according to several published studies. However, sensitivity of these features to key radiomics parameters in the determination of the RFs and the effect of inter-user segmentation accuracy remains unexplored but is an important consideration to the standardization of radiomics-based image biomarkers. In this study, we collected clots and corresponding non-contrast CT (NCCT) and CT angiography (CTA) images from 17 patients undergoing mechanical thrombectomy for large vessel stroke. Clot image regions were then segmented by 3 observers and radiomics feature were extracted for each. In total, 200 RFs were extracted. Sensitivity analysis was conducted across 4 binwidths (2, 4, 8, and 16) for all RFs, and a binwidth of 2 was found to maximum agreeability between users. Interrater reliability was calculated using the interclass correlation coefficient (ICC) for RFs from the 3 segmentations. Observers showed lower reliability in RFs for CTA compared to NCCT RFs. However, observers had good agreement with ICC>0.75 for 67 and 43 RFs from NCCT and CTA clot regions respectively, several of which have been shown to be predictive of thrombectomy outcomes in previous studies.","PeriodicalId":427869,"journal":{"name":"2022 IEEE Western New York Image and Signal Processing Workshop (WNYISPW)","volume":"133 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-11-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122547675","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: 0

Are ML Image Classifiers Robust to Medical Image Quality Degradation? ML图像分类器对医学图像质量退化具有鲁棒性吗?

2022 IEEE Western New York Image and Signal Processing Workshop (WNYISPW) Pub Date : 2022-11-04 DOI: 10.1109/WNYISPW57858.2022.9983488

Sergei Chuprov, Akshaya Nandkishor Satam, L. Reznik

{"title":"Are ML Image Classifiers Robust to Medical Image Quality Degradation?","authors":"Sergei Chuprov, Akshaya Nandkishor Satam, L. Reznik","doi":"10.1109/WNYISPW57858.2022.9983488","DOIUrl":"https://doi.org/10.1109/WNYISPW57858.2022.9983488","url":null,"abstract":"Classification of medical images plays an important role in medical assisting applications, as it helps in performing routine patients diagnostics. In many cases, the images are transferred over a network to the cloud-based service that might result in their corruption. In this paper, we investigate how the ML medical image classification performance can be affected by the network Quality of Service (QoS) and Data Quality (DQ) degradation. In our study, we employ real-world X-ray image scans of lungs diseases and real life networks. As ML medical image classification systems, we employ well-known industrial VVG16, ResNet50, and InceptionV3 models, analyze and compare their performance. We leverage the POWDER platform to establish real wireless network between the two nodes. We transfer our X-ray scans between these nodes with various packet losses to obtain images corrupted due to network QoS degradation. We test our ML image classifiers on the obtained X-ray scans of various corruption degree and evaluate their performance. Our study demonstrates that even small packet losses of 2-5% can significantly deteriorate the ML classifier performance reducing the recognition accuracy from 90 to about 70-80 % that will make the cloud-based classification unacceptable for medical-related applications.","PeriodicalId":427869,"journal":{"name":"2022 IEEE Western New York Image and Signal Processing Workshop (WNYISPW)","volume":"15 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-11-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124758123","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

Selecting Optimal Substrate Mounts in Terahertz Time Domain Spectroscopic Imaging of Murine Radiation-Treated Pancreatic Ductal Adenocarcinoma 放射治疗小鼠胰腺导管腺癌太赫兹时域光谱成像选择最佳底物支架

2022 IEEE Western New York Image and Signal Processing Workshop (WNYISPW) Pub Date : 2022-11-04 DOI: 10.1109/WNYISPW57858.2022.9983490

D. Chakraborty, Bradley N. Mills, Jing Cheng, I. Komissarov, Scott Gerber, R. Sobolewski

引用次数: 1

Opportunistic Temporal Spectrum Coexistence of Passive Radiometry and Active Wireless Networks 无源辐射测量和有源无线网络的机会时间频谱共存

2022 IEEE Western New York Image and Signal Processing Workshop (WNYISPW) Pub Date : 2022-11-04 DOI: 10.1109/WNYISPW57858.2022.9983493

Mohammad Koosha, Nicholas Mastronarde

{"title":"Opportunistic Temporal Spectrum Coexistence of Passive Radiometry and Active Wireless Networks","authors":"Mohammad Koosha, Nicholas Mastronarde","doi":"10.1109/WNYISPW57858.2022.9983493","DOIUrl":"https://doi.org/10.1109/WNYISPW57858.2022.9983493","url":null,"abstract":"There is insufficient wireless frequency spectrum to support the continued growth of active wireless technologies and devices. This has provoked extensive research on spectrum coexistence. One case that has gained limited attention in this course is using currently banned frequency bands for active wireless communications. One such option is the 27 MHz-wide narrowband portion of the L-band from 1.400 to 1.427 GHz, which is exclusively devoted to space-borne passive radiometry for remote sensing and radio astronomy. Radio regulations currently prohibit active wireless communications and radars from operating in this band to avoid radio frequency interference (RFI) on highly noise-sensitive passive radiometry equipment. The National Aeronautics and Space Administration’s (NASA’s) Soil Moisture Active Passive (SMAP) satellite is one of the latest space-borne remote sensing missions that evaluates global soil moisture by passive scanning of the thermal emissions of the earth in this frequency band. In this paper, we investigate the opportunistic temporal use of this 27 MHz-wide passive radiometry band for active wireless transmissions when there is no Line of Sight (LoS) between SMAP and a terrestrial wireless network. We use MATLAB simulations to determine the fraction of time that SMAP has LoS (and non-LoS) with a terrestrial wireless cell at different Earth latitudes based on SMAP’s orbital characteristics. We also investigate the severity of RFI induced on SMAP in the presence of a terrestrial cluster of 5G cells with LoS.","PeriodicalId":427869,"journal":{"name":"2022 IEEE Western New York Image and Signal Processing Workshop (WNYISPW)","volume":"384 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-11-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114959459","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: 3

Iris recognition using curvelet transform and accuracy maximization by particle swarm optimization 基于曲线变换和粒子群优化的虹膜识别

2022 IEEE Western New York Image and Signal Processing Workshop (WNYISPW) Pub Date : 2022-11-04 DOI: 10.1109/WNYISPW57858.2022.9983494

A. Ahamed, Syed Irfan Ali Meerza

引用次数: 0

Tracking Evolving Geometric Data by Local Graph Laplacian Operators 局部图拉普拉斯算子跟踪几何数据演化

2022 IEEE Western New York Image and Signal Processing Workshop (WNYISPW) Pub Date : 2022-11-04 DOI: 10.1109/WNYISPW57858.2022.9983489

Hsun-Hsien Shane Chang

{"title":"Tracking Evolving Geometric Data by Local Graph Laplacian Operators","authors":"Hsun-Hsien Shane Chang","doi":"10.1109/WNYISPW57858.2022.9983489","DOIUrl":"https://doi.org/10.1109/WNYISPW57858.2022.9983489","url":null,"abstract":"Geometric data are samples on geometric surfaces of physical or abstract objects. When the underlying objects evolve over time, their geometric data change as well. Tracking their evolution is critical to many emerging areas, such as autonomous driving, edge computing networks, and drug interactions. Lacking well-defined grids in geometric data prohibits easy temporal matching for tracking evolution of geometric data. This paper considers the framework of graph signal processing to exploit spectral analysis on geometric surfaces to achieve the tracking task.This paper begins with modeling an underlying geometric surface by a graph, followed by using the spectra of local graph Laplacians to detect graph patches corresponding to regions of high curvatures on the geometric surfaces. The Laplacian spectra of feature graph patches and the structural information of graphs are analyzed together to perform temporal matching across times. Sparse temporal transforms are reconstructed based on the matched feature graph patches, and extrapolating the transforms to the full-scale graph derives the estimation of geometric evolution.","PeriodicalId":427869,"journal":{"name":"2022 IEEE Western New York Image and Signal Processing Workshop (WNYISPW)","volume":"36 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-11-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125065343","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: 0

Modeling Bessel Acoustic Radiation Force Impulse Imaging with the k-Wave MATLAB Toolbox 用k波MATLAB工具箱建模贝塞尔声辐射力脉冲成像

2022 IEEE Western New York Image and Signal Processing Workshop (WNYISPW) Pub Date : 2022-11-04 DOI: 10.1109/WNYISPW57858.2022.9983492

Siladitya Khan, Fan Feng, Soumya Goswami, S. McAleavey

{"title":"Modeling Bessel Acoustic Radiation Force Impulse Imaging with the k-Wave MATLAB Toolbox","authors":"Siladitya Khan, Fan Feng, Soumya Goswami, S. McAleavey","doi":"10.1109/WNYISPW57858.2022.9983492","DOIUrl":"https://doi.org/10.1109/WNYISPW57858.2022.9983492","url":null,"abstract":"Shear wave elasticity imaging (SWEI) is a non-invasive technique to assess mechanical properties of tissue, including elasticity and viscoelasticity by introducing acoustic energy by introduction of a radiation force. Traditional Acoustic Radiation Force Impulse (ARFI) are produced by focused and unfocused beams. Due to diminished acoustic intensity outside the focal zone, focused ARFI posseses limited depth-of-field, beyond which elasticity estimates are unreliable. Imaging quality in unfocused beams on the other hand are limited to the Fraunhofer zone due to near-field oscillations of the pressure profile. We report a SWEI approach with Bessel apodized ARFI that can reduce diffraction in the Fresnel zone and at the same time retain a large high intensity focal illumination. We evaluate elastogram image quality produced by Gaussian focused and Bessel apodized ARF with time domain simulations using k-wave which is an open-source acoustic wave field toolbox. Our results show image quality evaluated by CNRdB improves from 6.04 in focused ARF SWEI images to 16.06 in Bessel ARF SWEI.","PeriodicalId":427869,"journal":{"name":"2022 IEEE Western New York Image and Signal Processing Workshop (WNYISPW)","volume":"21 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-11-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121695952","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: 0

Identifying Periodic Signal Patterns in Audio Streams 识别音频流中的周期信号模式

2022 IEEE Western New York Image and Signal Processing Workshop (WNYISPW) Pub Date : 2022-11-04 DOI: 10.1109/WNYISPW57858.2022.9983495

Henry Zelenak, Shahin Mehdipour Ataee

引用次数: 0

3D Mapping of Vessel Wall Enhancement could Assist in Robust Risk Stratification of Intracranial Aneurysms 血管壁增强三维成像有助于颅内动脉瘤的可靠风险分层

2022 IEEE Western New York Image and Signal Processing Workshop (WNYISPW) Pub Date : 2022-11-04 DOI: 10.1109/WNYISPW57858.2022.9983491

S. Veeturi, N. Pintér, A. Baig, A. Monteiro, H. Rai, T. Patel, Munjal Shah, A. Siddiqui, V. Tutino

{"title":"3D Mapping of Vessel Wall Enhancement could Assist in Robust Risk Stratification of Intracranial Aneurysms","authors":"S. Veeturi, N. Pintér, A. Baig, A. Monteiro, H. Rai, T. Patel, Munjal Shah, A. Siddiqui, V. Tutino","doi":"10.1109/WNYISPW57858.2022.9983491","DOIUrl":"https://doi.org/10.1109/WNYISPW57858.2022.9983491","url":null,"abstract":"Vessel Wall Enhancement (VWE) has emerged as a potential tool to aid clinicians in risk stratification of intracranial aneurysms (IAs). However, this is currently graded manually which introduces subjectivity. Herein, we evaluated the inter-user variability of clinicians in grading VWE manually and used an existing pipeline to derive quantitative first order metrics. These metrics were then used to build statistical models for more objective VWE quantification and characterization. We observed that clinicians agree on the presence of VWE in 75% of the cases but only on 54% of the cases for the type of VWE and this agreement decreases in smaller IAs. Through our automated pipeline, we mapped the VWE intensity on to the sac of the IA and computed 10 different first order metrics. We found that 8 of these 10 metrics were significantly different between IAs exhibiting VWE and IAs without VWE. Additionally, we found that statistical models built using these metrics have a good performance in predicting the presence of VWE (AUC=0.94) and the type of VWE (AUC=0.78). This pipeline can be used as a tool for more objective quantification and characterization of VWE.","PeriodicalId":427869,"journal":{"name":"2022 IEEE Western New York Image and Signal Processing Workshop (WNYISPW)","volume":"45 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-11-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124005045","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: 0