2019 IEEE International Conference on Imaging Systems and Techniques (IST)最新文献_第3页

Pollen Grain Classification using Geometrical and Textural Features 基于几何和纹理特征的花粉粒分类

2019 IEEE International Conference on Imaging Systems and Techniques (IST) Pub Date : 2019-12-01 DOI: 10.1109/IST48021.2019.9010563

Georgios C. Manikis, K. Marias, E. Alissandrakis, L. Perrotto, E. Savvidaki, N. Vidakis

{"title":"Pollen Grain Classification using Geometrical and Textural Features","authors":"Georgios C. Manikis, K. Marias, E. Alissandrakis, L. Perrotto, E. Savvidaki, N. Vidakis","doi":"10.1109/IST48021.2019.9010563","DOIUrl":"https://doi.org/10.1109/IST48021.2019.9010563","url":null,"abstract":"This study presents an image analysis framework coupled with machine learning algorithms for the classification of microscopy pollen grain images. Pollen grain classification has received notable attention concerning a wide range of applications such as paleontology and honey certification, forecasting of allergies caused of airborne pollen and food technology. It requires an extensive qualitative process that is mostly performed manually by an expert. Although manual classification shows satisfactory performance, it may suffer from intra and inter-observer variability and it is time consuming. This study benefits from the advances of image processing and machine learning and proposes a fully-automated analysis pipeline aiming to: A) calculate morphological characteristics from the images using a cost-effective microscope, and b) classify images into 6 pollen classes. A private dataset from the Department of Agriculture of the Hellenic Mediterranean University in Crete containing 564 images was used in this study. A Random Forest (RF) classifier was utilized to classify images. A repeated nested cross-validation (nested-CV) schema was used to estimate the generalization performance and prevent overfitting. Image preprocessing, extraction of geometric and textural characteristics and feature selection were implemented prior to the assessment of the classification performance and a mean accuracy of 88.24% was reported.","PeriodicalId":117219,"journal":{"name":"2019 IEEE International Conference on Imaging Systems and Techniques (IST)","volume":"53 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125908413","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: 4

An Accurate System for Prostate Cancer Localization from Diffusion-Weighted MRI 基于弥散加权MRI的前列腺癌精确定位系统

2019 IEEE International Conference on Imaging Systems and Techniques (IST) Pub Date : 2019-12-01 DOI: 10.1109/IST48021.2019.9010552

Islam R. Abdelmaksoud, M. Ghazal, A. Shalaby, M. Elmogy, A. Aboulfotouh, M. El-Ghar, R. Keynton, A. El-Baz

{"title":"An Accurate System for Prostate Cancer Localization from Diffusion-Weighted MRI","authors":"Islam R. Abdelmaksoud, M. Ghazal, A. Shalaby, M. Elmogy, A. Aboulfotouh, M. El-Ghar, R. Keynton, A. El-Baz","doi":"10.1109/IST48021.2019.9010552","DOIUrl":"https://doi.org/10.1109/IST48021.2019.9010552","url":null,"abstract":"This paper proposes a computer-aided diagnosis (CAD) system for localizing prostate cancer from diffusion-weighted magnetic resonance imaging (DW-MRI). This system uses DW-MRI data sets that were acquired at four b-values: 100, 200, 300, and 400 smm −2. The first step in the proposed system is prostate segmentation using a level set method. The evolution of this level set is guided not only by the intensity of the prostate voxels but also the shape prior of the prostate and the voxels spatial relationships. The second step in the proposed system calculates the apparent diffusion coefficient (ADC) maps of the prostate regions as a discriminating feature between malignant and healthy cases. These ADC maps are used in the last step of the CAD system to fine-tune a pretrained convolutional neural network (CNN) to identify the ADC maps with malignant tumors. The accuracy of the proposed system was evaluated using 40% of the ADC maps while the other 60% are used to fine-tune the pretrained CNN model. The proposed CAD system resulted in an average area under the curve (AUC) of 0.95 at the four b-values.","PeriodicalId":117219,"journal":{"name":"2019 IEEE International Conference on Imaging Systems and Techniques (IST)","volume":"8 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130633405","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

Effect of stimulation patterns on bladder volume measurement based on fringe effect of EIT sensors 基于EIT传感器条纹效应的刺激模式对膀胱体积测量的影响

2019 IEEE International Conference on Imaging Systems and Techniques (IST) Pub Date : 2019-12-01 DOI: 10.1109/IST48021.2019.9010111

Xiaofeng Liang, Lijun Xu, W. Tian, Yuedong Xie, Jiangtao Sun

{"title":"Effect of stimulation patterns on bladder volume measurement based on fringe effect of EIT sensors","authors":"Xiaofeng Liang, Lijun Xu, W. Tian, Yuedong Xie, Jiangtao Sun","doi":"10.1109/IST48021.2019.9010111","DOIUrl":"https://doi.org/10.1109/IST48021.2019.9010111","url":null,"abstract":"Real-time monitoring of bladder volume is necessary for patients with bladder dysfunction. Electrical impedance tomography (EIT) has the potential to be used for bladder volume measurement due to its advantages of noninvasive and real-time sensing. To overcome the sensitiveness of conventional EIT measurement methods to the urine conductivity, fringe effect of EIT sensors is explored for bladder volume measurement. In order to find the best stimulation pattern, this paper simulates seven stimulation patterns (using an integer value A as indicator) with a 16-electrodes EIT sensor. Meanwhile, it is investigated how stimulation patterns act with two typical electrodes arrangement, i.e. ring and semicircle. Sensitivity distribution and characteristic values related to the fringe effect of EIT sensors are used as evaluation criteria. The results show that when A=2 and the electrodes arrangement is semicircle, the bladder region has the highest mean sensitivity. Using semicircle arrangement ensures that all stimulation patterns except A=6 and 7 have satisfactory measurement sensitivities and less errors under changes of urine conductivity.","PeriodicalId":117219,"journal":{"name":"2019 IEEE International Conference on Imaging Systems and Techniques (IST)","volume":"472 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122919391","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

Comparison of machine learning methods for multiphase flowrate prediction 多相流量预测的机器学习方法比较

2019 IEEE International Conference on Imaging Systems and Techniques (IST) Pub Date : 2019-12-01 DOI: 10.1109/IST48021.2019.9010450

Zhenyu Jiang, Haokun Wang, Yunjie Yang, Yi Li

引用次数: 1

GPU-accelerated Simulator for Optical Tomography applied to Two-Phase Flows 应用于两相流的gpu加速光学层析模拟器

2019 IEEE International Conference on Imaging Systems and Techniques (IST) Pub Date : 2019-12-01 DOI: 10.1109/IST48021.2019.9010472

R. S. Bernardelli, E. N. Santos, R. Morales, D. Pipa, M. J. Silva

引用次数: 2

Learning Adversarially Enhanced Heatmaps for Aorta Segmentation in CTA 学习对抗增强热图用于CTA主动脉分割

2019 IEEE International Conference on Imaging Systems and Techniques (IST) Pub Date : 2019-12-01 DOI: 10.1109/IST48021.2019.9010225

Wenji Wang, Haogang Zhu

{"title":"Learning Adversarially Enhanced Heatmaps for Aorta Segmentation in CTA","authors":"Wenji Wang, Haogang Zhu","doi":"10.1109/IST48021.2019.9010225","DOIUrl":"https://doi.org/10.1109/IST48021.2019.9010225","url":null,"abstract":"In this work, we propose a method to combine ADversarially enhanced HeatMaps (short for AD-HM) to segment the aorta from CTA (Computed Tomography Angiography). The intuition of the AD-HM is that heatmaps encompass rich information on locations of the targets. The positions of the aorta are relatively regular in CTA, thus training with heatmaps exploits the positional information to boost the segmentation results. The quality of heatmaps can be further enhanced with adversarial learning to refine the performance. The AD-HM can embed almost any state-of-the-art deep segmentation networks off the shelf. We collect 111 CTA volumes counting to 79082 slices to verify the effectiveness of our method. The training set is constituted of 104 volumes drawn from the dataset accounting to 74000 slices. The remaining 5082 slices from 7 CTA samples are reserved for validating the algorithm and the results are reported on the validation set. Our experiments with 7 state-of-the-art deep segmentation networks demonstrate the effectiveness of our method. The absolute improvement on IOU(Intersection-over-Union) of the aorta from the 7 models is 1.77% on average, with minimum improvement of 0.8% (UNet: 86.5%−> 87.3%) and maximum improvement of 3.4% (SegNet: 83.8%−> 87.2%).","PeriodicalId":117219,"journal":{"name":"2019 IEEE International Conference on Imaging Systems and Techniques (IST)","volume":"203 ","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114004808","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

Classification System with Capability to Reject Unknowns 具有拒绝未知能力的分类系统

2019 IEEE International Conference on Imaging Systems and Techniques (IST) Pub Date : 2019-12-01 DOI: 10.1109/IST48021.2019.9010169

Soma Shiraishi, Katsumi Kikuchi, K. Iwamoto

引用次数: 3

Design and Optimization of Liquid Level Sensor based on Electrical Tomography 基于电断层成像的液位传感器设计与优化

2019 IEEE International Conference on Imaging Systems and Techniques (IST) Pub Date : 2019-12-01 DOI: 10.1109/IST48021.2019.9010148

Jingdai Cheng, Shui Liu, Yi Li

引用次数: 2

Resolution Improvement in Ground-Mapping Car-Borne Radar Imaging Systems 地面测绘车载雷达成像系统分辨率的提高

2019 IEEE International Conference on Imaging Systems and Techniques (IST) Pub Date : 2019-12-01 DOI: 10.1109/IST48021.2019.9010537

D. Valuyskiy, S. Vityazev, V. Vityazev

引用次数: 0

Accurate motion plan of ultrasonic linear array transducer for non-destructive 3D endoscopy of iconic cultural heritage assets 标志性文物无损三维内窥镜超声线阵换能器的精确运动方案

2019 IEEE International Conference on Imaging Systems and Techniques (IST) Pub Date : 2019-12-01 DOI: 10.1109/IST48021.2019.9010447

G. Karagiannis, S. Amanatiadis, Evdoxios Mimis

引用次数: 2