Pub Date : 2010-04-14DOI: 10.1109/ISBI.2010.5490224
S. Ens, J. Ulrici, E. Hell, T. Buzug
Some computed tomography (CT) applications, for example micro- or dental-CT, have long acquisition sequences and consequently motion of the object is likely to occur. The common motion correction method, not using optical techniques for patient motion measurement, is data-driven motion-correction (DDMC). This method is based on subdivision of the projection data into motion free subsections. Therefore, motion positions have to be determined. In this work, an approach for motion position detection in cone-beam CT data is described. Distance metric values, computed from two successive projection images, provide information of the incorporation of movement. Quantitative evaluation of motion detection is possible due to utilization of CT data with known movement positions, using generated dental cone-beam CT datasets. The proposed method uses nothing but information contained in the cone-beam projections. Therefore, it is generally applicable for motion detection in cone-beam CT. A correct detection rate of 99.89% is achieved by using a structural similarity index as a distance measure.
{"title":"Automatic detection of patient motion in cone-beam computed tomography","authors":"S. Ens, J. Ulrici, E. Hell, T. Buzug","doi":"10.1109/ISBI.2010.5490224","DOIUrl":"https://doi.org/10.1109/ISBI.2010.5490224","url":null,"abstract":"Some computed tomography (CT) applications, for example micro- or dental-CT, have long acquisition sequences and consequently motion of the object is likely to occur. The common motion correction method, not using optical techniques for patient motion measurement, is data-driven motion-correction (DDMC). This method is based on subdivision of the projection data into motion free subsections. Therefore, motion positions have to be determined. In this work, an approach for motion position detection in cone-beam CT data is described. Distance metric values, computed from two successive projection images, provide information of the incorporation of movement. Quantitative evaluation of motion detection is possible due to utilization of CT data with known movement positions, using generated dental cone-beam CT datasets. The proposed method uses nothing but information contained in the cone-beam projections. Therefore, it is generally applicable for motion detection in cone-beam CT. A correct detection rate of 99.89% is achieved by using a structural similarity index as a distance measure.","PeriodicalId":250523,"journal":{"name":"2010 IEEE International Symposium on Biomedical Imaging: From Nano to Macro","volume":"8 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2010-04-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115491352","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}
Pub Date : 2010-04-14DOI: 10.1109/ISBI.2010.5490127
J. Sanches, I. Sousa, P. Figueiredo
Pulsed Arterial Spin Labeling (PASL) techniques potentially allow the absolute, non-invasive quantification of brain perfusion using Magnetic Resonance Imaging (MRI). This can be achieved by fitting a kinetic model to the data acquired at a number of inversion times (TI). Some model parameters such as the arterial transit time need to be estimated together with perfusion, while others are usually assumed to be known. The accuracy of the model estimation strongly depends on the distribution of the TI sampling points. Here, we propose a Bayesian framework for PASL perfusion estimation based on the Fisher information criterion, whereby the optimal sampling points can be determined taking into account the uncertainty of the model parameters as well as the amount of noise in the data. We show that the optimal sampling strategy for PASL depends on the a priori knowledge of the model parameters and this should therefore be taken into account.
{"title":"Bayesian fisher information criterion for sampling optimization in ASL-MRI","authors":"J. Sanches, I. Sousa, P. Figueiredo","doi":"10.1109/ISBI.2010.5490127","DOIUrl":"https://doi.org/10.1109/ISBI.2010.5490127","url":null,"abstract":"Pulsed Arterial Spin Labeling (PASL) techniques potentially allow the absolute, non-invasive quantification of brain perfusion using Magnetic Resonance Imaging (MRI). This can be achieved by fitting a kinetic model to the data acquired at a number of inversion times (TI). Some model parameters such as the arterial transit time need to be estimated together with perfusion, while others are usually assumed to be known. The accuracy of the model estimation strongly depends on the distribution of the TI sampling points. Here, we propose a Bayesian framework for PASL perfusion estimation based on the Fisher information criterion, whereby the optimal sampling points can be determined taking into account the uncertainty of the model parameters as well as the amount of noise in the data. We show that the optimal sampling strategy for PASL depends on the a priori knowledge of the model parameters and this should therefore be taken into account.","PeriodicalId":250523,"journal":{"name":"2010 IEEE International Symposium on Biomedical Imaging: From Nano to Macro","volume":"54 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2010-04-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115680981","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}
Boundary delineation is the fundamental basis of many sonographic image analyses. In sonographic breast lesion images, it's complicated and time consuming for physicians to delineate the lesion boundaries. When it comes to three dimensional sonographic breast lesions image, delineation of lesion boundary becomes much more complicated. Taking advantage of cell competition algorithm along with its good region structure, generated cells can be served as elegant nodes for graph cut. Further, a similar weight function plays an important role in the estimation of lesion boundary to avoid visible weak edge and isolated node in graph cut. The integration of cell competition and graph cut can be intuitively implemented in three dimensional images, in addition to the reduction of computational time. With efficiency and accuracy of lesion detection, a computer aided system was therefore developed to fulfill clinical applications.
{"title":"Cell-based graph cut for segmentation of 2D/3D sonographic breast images","authors":"Hsin-Hung Chiang, Jie-Zhi Cheng, Pei-Kai Hung, Chun-You Liu, C. Chung, Chung-Ming Chen","doi":"10.1109/ISBI.2010.5490384","DOIUrl":"https://doi.org/10.1109/ISBI.2010.5490384","url":null,"abstract":"Boundary delineation is the fundamental basis of many sonographic image analyses. In sonographic breast lesion images, it's complicated and time consuming for physicians to delineate the lesion boundaries. When it comes to three dimensional sonographic breast lesions image, delineation of lesion boundary becomes much more complicated. Taking advantage of cell competition algorithm along with its good region structure, generated cells can be served as elegant nodes for graph cut. Further, a similar weight function plays an important role in the estimation of lesion boundary to avoid visible weak edge and isolated node in graph cut. The integration of cell competition and graph cut can be intuitively implemented in three dimensional images, in addition to the reduction of computational time. With efficiency and accuracy of lesion detection, a computer aided system was therefore developed to fulfill clinical applications.","PeriodicalId":250523,"journal":{"name":"2010 IEEE International Symposium on Biomedical Imaging: From Nano to Macro","volume":"71 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2010-04-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116981891","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}
Pub Date : 2010-04-14DOI: 10.1109/ISBI.2010.5490280
M. Buchem, J. Grond, M. Versluis, M. Osch, W. Teeuwisse, H. Kan, A. Webb
Clinical applications of high field MR take advantage of the increased sensitivity to magnetic field inhomogeneity, spatial resolution, signal-to-noise, and spectral resolution. Examples of each facet are demonstrated for 7T patient neuroimaging and localized spectroscopy.
{"title":"High field clinical MRI neuroimaging","authors":"M. Buchem, J. Grond, M. Versluis, M. Osch, W. Teeuwisse, H. Kan, A. Webb","doi":"10.1109/ISBI.2010.5490280","DOIUrl":"https://doi.org/10.1109/ISBI.2010.5490280","url":null,"abstract":"Clinical applications of high field MR take advantage of the increased sensitivity to magnetic field inhomogeneity, spatial resolution, signal-to-noise, and spectral resolution. Examples of each facet are demonstrated for 7T patient neuroimaging and localized spectroscopy.","PeriodicalId":250523,"journal":{"name":"2010 IEEE International Symposium on Biomedical Imaging: From Nano to Macro","volume":"32 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2010-04-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124918532","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}
Pub Date : 2010-04-14DOI: 10.1109/ISBI.2010.5490079
Kai Liu, Jie Tian, Shouping Zhu, C. Qin, Xing Zhang, Dong Han
Bioluminescence imaging (BLI) and bioluminescence tomography (BLT) make it possible to elucidate cellular signatures to better understand the effects of human disease in small animal in vivo. However, to the best of our knowledge, the existing gradient-type reconstruction methods in BLT are not very efficient, and often require a relatively small volume of interest (VOI) for feasible results. In this paper, a fast graph cuts based reconstruction method for BLT is presented, which is to localize the bioluminescent source in heterogeneous mouse atlas via max-flow/min-cut algorithm. Since the original graph cuts theory can only handle graph-representable problem, the quadratic pseudo-boolean optimization is incorporated to make the graph tractable. The internal light source can be reconstructed from the whole domain, so a priori knowledge of VOI can be avoided in this method. In the experiments, the proposed method is validated in a heterogeneous mouse atlas, and the source can be localized reliably and efficiently by graph cuts; and compared with a gradient-type method, graph cuts is about 25–50 times faster.
{"title":"Fast localize the bioluminescent source via graph cuts","authors":"Kai Liu, Jie Tian, Shouping Zhu, C. Qin, Xing Zhang, Dong Han","doi":"10.1109/ISBI.2010.5490079","DOIUrl":"https://doi.org/10.1109/ISBI.2010.5490079","url":null,"abstract":"Bioluminescence imaging (BLI) and bioluminescence tomography (BLT) make it possible to elucidate cellular signatures to better understand the effects of human disease in small animal in vivo. However, to the best of our knowledge, the existing gradient-type reconstruction methods in BLT are not very efficient, and often require a relatively small volume of interest (VOI) for feasible results. In this paper, a fast graph cuts based reconstruction method for BLT is presented, which is to localize the bioluminescent source in heterogeneous mouse atlas via max-flow/min-cut algorithm. Since the original graph cuts theory can only handle graph-representable problem, the quadratic pseudo-boolean optimization is incorporated to make the graph tractable. The internal light source can be reconstructed from the whole domain, so a priori knowledge of VOI can be avoided in this method. In the experiments, the proposed method is validated in a heterogeneous mouse atlas, and the source can be localized reliably and efficiently by graph cuts; and compared with a gradient-type method, graph cuts is about 25–50 times faster.","PeriodicalId":250523,"journal":{"name":"2010 IEEE International Symposium on Biomedical Imaging: From Nano to Macro","volume":"89 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2010-04-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123691450","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}
Pub Date : 2010-04-14DOI: 10.1109/ISBI.2010.5490366
S. Klein, M. Loog, F. Lijn, T. Heijer, A. Hammers, Marleen de Bruijne, A. Lugt, R. Duin, M. Breteler, W. Niessen
This article studies the possibility of detecting dementia in an early stage, using nonrigid registration of MR brain scans in combination with dissimilarity-based pattern recognition techniques. Instead of focussing on the shape of a single brain structure, we take into account the shape differences within the entire brain. Imaging data was obtained from a longitudinal, population based study of the elderly. A set of 29 subjects was identified, who were asymptomatic at the time of scanning, but were diagnosed as having dementia within 0.7 to 5 years after the scan, and a set of 29 age and gender matched healthy controls were selected. Each subject was registered to all other subjects, using a nonrigid registration algorithm. Based on statistics of the deformation field in the brain, a dissimilarity measure was calculated between each pair of subjects, yielding a 58×58 dissimilarity matrix. A kNN classifier was trained on the dissimilarity matrix and the performance was tested in a leave-one-out experiment. A classification accuracy of 81% was attained (spec. 83%, sens. 79%). This demonstrates the potential of whole-brain intersubject dissimilarities to aid in early diagnosis of dementia.
{"title":"Early diagnosis of dementia based on intersubject whole-brain dissimilarities","authors":"S. Klein, M. Loog, F. Lijn, T. Heijer, A. Hammers, Marleen de Bruijne, A. Lugt, R. Duin, M. Breteler, W. Niessen","doi":"10.1109/ISBI.2010.5490366","DOIUrl":"https://doi.org/10.1109/ISBI.2010.5490366","url":null,"abstract":"This article studies the possibility of detecting dementia in an early stage, using nonrigid registration of MR brain scans in combination with dissimilarity-based pattern recognition techniques. Instead of focussing on the shape of a single brain structure, we take into account the shape differences within the entire brain. Imaging data was obtained from a longitudinal, population based study of the elderly. A set of 29 subjects was identified, who were asymptomatic at the time of scanning, but were diagnosed as having dementia within 0.7 to 5 years after the scan, and a set of 29 age and gender matched healthy controls were selected. Each subject was registered to all other subjects, using a nonrigid registration algorithm. Based on statistics of the deformation field in the brain, a dissimilarity measure was calculated between each pair of subjects, yielding a 58×58 dissimilarity matrix. A kNN classifier was trained on the dissimilarity matrix and the performance was tested in a leave-one-out experiment. A classification accuracy of 81% was attained (spec. 83%, sens. 79%). This demonstrates the potential of whole-brain intersubject dissimilarities to aid in early diagnosis of dementia.","PeriodicalId":250523,"journal":{"name":"2010 IEEE International Symposium on Biomedical Imaging: From Nano to Macro","volume":"136 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2010-04-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123696010","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}
Pub Date : 2010-04-14DOI: 10.1109/ISBI.2010.5490282
M. Ceresa, X. Artaechevarria, A. Muñoz-Barrutia, C. Ortíz-de-Solórzano
Accurately extracting the airway tree is of utmost importance to correctly analyze CT images of the lungs. A survey of published methods reveals the existence of a trade-off between sensitivity -number of airway branches found- and accuracy -how much parenchymal leakage occurs-. In this paper, we present an algorithm for robust airway segmentation that attains both high sensitivity and accuracy. This is accomplished by using an initial permissive voxel acceptance criterion followed by early leakage detection and correction using a novel leakage recovery algorithm. Our algorithm was tested by comparing it to manual segmentation of a large and diverse image data-set.
{"title":"Automatic leakage detection and recovery for airway tree extraction in chest CT images","authors":"M. Ceresa, X. Artaechevarria, A. Muñoz-Barrutia, C. Ortíz-de-Solórzano","doi":"10.1109/ISBI.2010.5490282","DOIUrl":"https://doi.org/10.1109/ISBI.2010.5490282","url":null,"abstract":"Accurately extracting the airway tree is of utmost importance to correctly analyze CT images of the lungs. A survey of published methods reveals the existence of a trade-off between sensitivity -number of airway branches found- and accuracy -how much parenchymal leakage occurs-. In this paper, we present an algorithm for robust airway segmentation that attains both high sensitivity and accuracy. This is accomplished by using an initial permissive voxel acceptance criterion followed by early leakage detection and correction using a novel leakage recovery algorithm. Our algorithm was tested by comparing it to manual segmentation of a large and diverse image data-set.","PeriodicalId":250523,"journal":{"name":"2010 IEEE International Symposium on Biomedical Imaging: From Nano to Macro","volume":"10 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2010-04-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123708416","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}
Pub Date : 2010-04-14DOI: 10.1109/ISBI.2010.5490085
M. Freiman, S. Esses, Leo Joskowicz, J. Sosna
We present an iterative model-constrained graph-cut algorithm for the segmentation of Abdominal Aortic Aneurysm (AAA) thrombus. Given an initial segmentation of the aortic lumen, our method automatically segments the thrombus by iteratively coupling intensity-based graph min-cut segmentation and geometric parametric model fitting. The geometric model effectively constrains the graph min-cut segmentation from “leaking” to nearby veins and organs. Experimental results on 8 AAA CTA datasets yield robust segmentations of the AAA thrombus in 2 mins computer time with a mean absolute volume difference of 8.0% and mean volumetric overlap error of 12.9%, which is comparable to the interobserver error.
{"title":"AN iterative model-constrained graph-cut algorithm for Abdominal Aortic Aneurysm thrombus segmentation","authors":"M. Freiman, S. Esses, Leo Joskowicz, J. Sosna","doi":"10.1109/ISBI.2010.5490085","DOIUrl":"https://doi.org/10.1109/ISBI.2010.5490085","url":null,"abstract":"We present an iterative model-constrained graph-cut algorithm for the segmentation of Abdominal Aortic Aneurysm (AAA) thrombus. Given an initial segmentation of the aortic lumen, our method automatically segments the thrombus by iteratively coupling intensity-based graph min-cut segmentation and geometric parametric model fitting. The geometric model effectively constrains the graph min-cut segmentation from “leaking” to nearby veins and organs. Experimental results on 8 AAA CTA datasets yield robust segmentations of the AAA thrombus in 2 mins computer time with a mean absolute volume difference of 8.0% and mean volumetric overlap error of 12.9%, which is comparable to the interobserver error.","PeriodicalId":250523,"journal":{"name":"2010 IEEE International Symposium on Biomedical Imaging: From Nano to Macro","volume":"7 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2010-04-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125434719","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}
Pub Date : 2010-04-14DOI: 10.1109/ISBI.2010.5490304
Marc M. J. Koppert, P. Rongen, M. Prokop, B. H. Romeny, H. V. Assen
Catheter ablation is an increasingly important curative procedure for atrial fibrillation. Knowledge of the local wall thickness is essential to determine the proper ablation energy. This paper presents the first semi-automatic atrial wall thickness measurement method for ablation guidance. It includes both endocardial and epicardial atrial wall segmentation on CT image data. Segmentation is based on active contours, Otsu's multiple threshold method and hysteresis thresholding. Segmentation results were compared to contours manually drawn by two experts, using repeated measures analysis of variance. The root mean square differences between the semi-automatic and the manually drawn contours were comparable to intra-observer variation (endocardium: p = 0.23, epicardium: p = 0.18). Mean wall thickness difference is significant between one of the experts on one side, and the presented method and the other expert on the other side (p ≪ 0.001). Wall thicknesses found were in the range of 0.5–5.5mm, corresponding to values presented in literature.
{"title":"Cardiac left atrium CT image segmentation for ablation guidance","authors":"Marc M. J. Koppert, P. Rongen, M. Prokop, B. H. Romeny, H. V. Assen","doi":"10.1109/ISBI.2010.5490304","DOIUrl":"https://doi.org/10.1109/ISBI.2010.5490304","url":null,"abstract":"Catheter ablation is an increasingly important curative procedure for atrial fibrillation. Knowledge of the local wall thickness is essential to determine the proper ablation energy. This paper presents the first semi-automatic atrial wall thickness measurement method for ablation guidance. It includes both endocardial and epicardial atrial wall segmentation on CT image data. Segmentation is based on active contours, Otsu's multiple threshold method and hysteresis thresholding. Segmentation results were compared to contours manually drawn by two experts, using repeated measures analysis of variance. The root mean square differences between the semi-automatic and the manually drawn contours were comparable to intra-observer variation (endocardium: p = 0.23, epicardium: p = 0.18). Mean wall thickness difference is significant between one of the experts on one side, and the presented method and the other expert on the other side (p ≪ 0.001). Wall thicknesses found were in the range of 0.5–5.5mm, corresponding to values presented in literature.","PeriodicalId":250523,"journal":{"name":"2010 IEEE International Symposium on Biomedical Imaging: From Nano to Macro","volume":"32 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2010-04-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115200018","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}
Pub Date : 2010-04-14DOI: 10.1109/ISBI.2010.5490378
Xiujuan Zheng, Guangjian Tian, L. Wen, D. Feng
It has been recognized that dual-time FDG-PET imaging can facilitate the differentiation of malignancy from benign lesions for cancer diagnosis. However, dual-time imaging protocols with retention index (RI) as a criteria in the classification are usually defined empirically, which might lead to the low accuracy in differentiation. Recently, a new quantitative index (QI) has been proposed to improve diagnostic efficacy. In this paper, we propose a novel framework to derive generalized optimal QI and its associated optimal ranges of imaging protocol to further improve the performance of dual-time FDG-PET imaging in lung cancer diagnosis.
{"title":"Generalized optimal quantitative index of dual-time FDG-PET imaging in lung cancer diagnosis","authors":"Xiujuan Zheng, Guangjian Tian, L. Wen, D. Feng","doi":"10.1109/ISBI.2010.5490378","DOIUrl":"https://doi.org/10.1109/ISBI.2010.5490378","url":null,"abstract":"It has been recognized that dual-time FDG-PET imaging can facilitate the differentiation of malignancy from benign lesions for cancer diagnosis. However, dual-time imaging protocols with retention index (RI) as a criteria in the classification are usually defined empirically, which might lead to the low accuracy in differentiation. Recently, a new quantitative index (QI) has been proposed to improve diagnostic efficacy. In this paper, we propose a novel framework to derive generalized optimal QI and its associated optimal ranges of imaging protocol to further improve the performance of dual-time FDG-PET imaging in lung cancer diagnosis.","PeriodicalId":250523,"journal":{"name":"2010 IEEE International Symposium on Biomedical Imaging: From Nano to Macro","volume":"21 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2010-04-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116154617","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}
京公网安备 11010802042870号
京ICP备2023020795号-1
扫码关注我们
求助内容：
应助结果提醒方式：