Pub Date : 2017-06-15DOI: 10.1109/ISBI.2017.7950702
T. Yin, N. Chiu
The partial volume effect (PVE) due to the low resolution of SPECT in brain SPECT volumes can be modeled as a convolution of a three-dimensional point-spread function (PSF) with the underlying true radioactivity. In this paper, a deconvolution guided by the edge locations in the geometric transfer matrix (GTM) method as a weighted regularization, denoted as RGTM, was proposed to take into account both the discrepancy from the convolution and the regional-homogeneity prior information in the correction of the PVE (PVC). Two steps were conducted: GTM and then a weighted regularization. Twenty digital phantom simulations were made to compare the performance of RGTM with those of Van-Cittert deconvolution (VC), GTM, and the region-based voxel-wise correction (RBV). Clinical data from eighty-four healthy adults with 99mTc-TRODAT-1 SPECT and MRI scans were also tested. Because the proposed RGTM was good in both constant and non-constant ROIs, its robustness is better than other methods if the distribution of the underlying radioactivity is not known exactly.
{"title":"Correction of partial volume effect in 99mTc-TRODAT-1 brain SPECT images using an edge-preserving weighted regularization","authors":"T. Yin, N. Chiu","doi":"10.1109/ISBI.2017.7950702","DOIUrl":"https://doi.org/10.1109/ISBI.2017.7950702","url":null,"abstract":"The partial volume effect (PVE) due to the low resolution of SPECT in brain SPECT volumes can be modeled as a convolution of a three-dimensional point-spread function (PSF) with the underlying true radioactivity. In this paper, a deconvolution guided by the edge locations in the geometric transfer matrix (GTM) method as a weighted regularization, denoted as RGTM, was proposed to take into account both the discrepancy from the convolution and the regional-homogeneity prior information in the correction of the PVE (PVC). Two steps were conducted: GTM and then a weighted regularization. Twenty digital phantom simulations were made to compare the performance of RGTM with those of Van-Cittert deconvolution (VC), GTM, and the region-based voxel-wise correction (RBV). Clinical data from eighty-four healthy adults with 99mTc-TRODAT-1 SPECT and MRI scans were also tested. Because the proposed RGTM was good in both constant and non-constant ROIs, its robustness is better than other methods if the distribution of the underlying radioactivity is not known exactly.","PeriodicalId":6547,"journal":{"name":"2017 IEEE 14th International Symposium on Biomedical Imaging (ISBI 2017)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2017-06-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"78501946","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 : 2017-06-15DOI: 10.1109/ISBI.2017.7950550
Sharib Ali, K. Rohr, M. Axer, K. Amunts, R. Eils, S. Wörz
The structural analysis of nerve fibers of the human brain is an important topic in current neuroscience. To obtain information about neural connections with micrometer resolution, polarized light imaging (3D PLI) of histological brain sections is well suited. In our application, both high-resolution (HR, 64µm in-plane pixel size) and ultra-high resolution (ultra-HR, 1.3µm) 3D PLI data of human brain sections are acquired. However, due to arbitrary translations and rotations caused by the sectioning and mounting process, spatial coherence between sections is lost and image registration is necessary. We introduce a new feature-based approach for registration of ultra-HR 3D PLI data to their corresponding HR images. The approach is based on a novel multi-scale salient feature detection method that is well suited for 3D PLI data. We have successfully evaluated the approach and applied it to 83 sections of a human brain. An experimental comparison with previous state-of-the-art feature detectors demonstrates the superior performance of our approach.
人脑神经纤维的结构分析是当前神经科学的一个重要课题。为了获得微米级分辨率的神经连接信息，脑组织切片偏振光成像(3D PLI)非常适合。在我们的应用中，获得了高分辨率(HR, 64µm平面内像素尺寸)和超高分辨率(ultra-HR, 1.3µm)人脑切片的3D PLI数据。然而，由于切片和安装过程中引起的任意平移和旋转，切片之间的空间一致性丢失，需要图像配准。我们介绍了一种新的基于特征的方法，用于将超HR 3D PLI数据配准到相应的HR图像。该方法基于一种新颖的多尺度显著特征检测方法，该方法非常适合于三维PLI数据。我们已经成功地评估了这种方法，并将其应用于人类大脑的83个部分。与以前最先进的特征检测器的实验比较表明了我们的方法的优越性能。
{"title":"Registration of ultra-high resolution 3D PLI data of human brain sections to their corresponding high-resolution counterpart","authors":"Sharib Ali, K. Rohr, M. Axer, K. Amunts, R. Eils, S. Wörz","doi":"10.1109/ISBI.2017.7950550","DOIUrl":"https://doi.org/10.1109/ISBI.2017.7950550","url":null,"abstract":"The structural analysis of nerve fibers of the human brain is an important topic in current neuroscience. To obtain information about neural connections with micrometer resolution, polarized light imaging (3D PLI) of histological brain sections is well suited. In our application, both high-resolution (HR, 64µm in-plane pixel size) and ultra-high resolution (ultra-HR, 1.3µm) 3D PLI data of human brain sections are acquired. However, due to arbitrary translations and rotations caused by the sectioning and mounting process, spatial coherence between sections is lost and image registration is necessary. We introduce a new feature-based approach for registration of ultra-HR 3D PLI data to their corresponding HR images. The approach is based on a novel multi-scale salient feature detection method that is well suited for 3D PLI data. We have successfully evaluated the approach and applied it to 83 sections of a human brain. An experimental comparison with previous state-of-the-art feature detectors demonstrates the superior performance of our approach.","PeriodicalId":6547,"journal":{"name":"2017 IEEE 14th International Symposium on Biomedical Imaging (ISBI 2017)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2017-06-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"89151056","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 : 2017-06-15DOI: 10.1109/ISBI.2017.7950489
X. Li, M. Guindani, C. Ng, B. Hobbs
Radiomics, an emerging field of quantitative imaging, encompasses a broad class of analytical techniques. Recent literature have interrogated associations between quantitatively derived GLCM-based texture features and clinical/pathology information using machine learning algorithms in many cancer settings, but often fail to elucidate the predictive power of these features. Moreover, for many cancers characterized by complex histopathological profiles, such as adrenocortical carcinoma, reducing the multivariate functional structure of GLCM to a set of summary statistics is potentially reductive, masking the patterns that distinguish malignancy from benignity. We develop a Bayesian probabilistic framework for predictive classification of lesion types, based on the entire GLCM. Our method, which uses a spatial Gaussian random field to model dependencies among neighboring cells of the GLCMs, was applied in a cancer detection context to discriminant malignant from benign adrenal lesions using GLCMs arising from non-contrast CT scans. Our method is shown to yield improved predictive power both in simulations as well as the adrenal CT application when compared to state-of-the-art diagnostic algorithms that use GLCM derived features.
{"title":"Classification of adrenal lesions through spatial Bayesian modeling of GLCM","authors":"X. Li, M. Guindani, C. Ng, B. Hobbs","doi":"10.1109/ISBI.2017.7950489","DOIUrl":"https://doi.org/10.1109/ISBI.2017.7950489","url":null,"abstract":"Radiomics, an emerging field of quantitative imaging, encompasses a broad class of analytical techniques. Recent literature have interrogated associations between quantitatively derived GLCM-based texture features and clinical/pathology information using machine learning algorithms in many cancer settings, but often fail to elucidate the predictive power of these features. Moreover, for many cancers characterized by complex histopathological profiles, such as adrenocortical carcinoma, reducing the multivariate functional structure of GLCM to a set of summary statistics is potentially reductive, masking the patterns that distinguish malignancy from benignity. We develop a Bayesian probabilistic framework for predictive classification of lesion types, based on the entire GLCM. Our method, which uses a spatial Gaussian random field to model dependencies among neighboring cells of the GLCMs, was applied in a cancer detection context to discriminant malignant from benign adrenal lesions using GLCMs arising from non-contrast CT scans. Our method is shown to yield improved predictive power both in simulations as well as the adrenal CT application when compared to state-of-the-art diagnostic algorithms that use GLCM derived features.","PeriodicalId":6547,"journal":{"name":"2017 IEEE 14th International Symposium on Biomedical Imaging (ISBI 2017)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2017-06-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"76261515","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 : 2017-06-15DOI: 10.1109/ISBI.2017.7950501
M. Almekkawy, E. Ebbini
Ultrasound speckle tracking provides a robust motion estimation of fine tissue displacements along the beam direction. Extensions to 2-D have been proposed in recent years. Due to relatively coarse lateral sampling, several solutions relied on lateral interpolation in order to achieve subsample accuracy. We introduce a new multi-dimensional speckle tracking method (MDST) with subsample accuracy in all dimensions. The proposed algorithm is based on solving a least squares problem to estimate the coefficients of a second order polynomial expansion to fit the magnitude of the two dimensional complex normalized correlation of the generalized analytic signal in the vicinity of the true peak. The generalization method utilizes the Riesz transform which is the multidimensional Hilbert transform. The displacement is estimated from acquired successive radio-frequency data frames of the region of interest. Field II simulation of flow data in a channel with a bench mark known displacement is generated to validate the accuracy of the method. In addition, the new MDST method is applied to imaging data from a flow phantom (ATS Model 524) to estimate the flow motion and pulsating channel wall. Simulations and experimental results demonstrate the effectiveness of the proposed technique.
超声散斑跟踪提供了沿光束方向精细组织位移的鲁棒运动估计。近年来已经提出了对二维的扩展。由于横向采样相对粗糙，一些解决方案依赖于横向插值来实现子样本精度。提出了一种新的多维散斑跟踪方法(MDST)，该方法在所有维度上都具有子样本精度。该算法基于求解最小二乘问题来估计二阶多项式展开的系数，以拟合广义解析信号在真峰附近的二维复归一化相关的大小。泛化方法利用了Riesz变换，即多维希尔伯特变换。位移是根据所获取的感兴趣区域的连续射频数据帧估计的。为了验证该方法的准确性，对具有已知基准位移的通道中的流动数据进行了现场模拟。此外，将新的MDST方法应用于流动模体(ATS Model 524)的成像数据，以估计流动运动和脉动通道壁面。仿真和实验结果验证了该方法的有效性。
{"title":"Two-dimensional speckle tracking using parabolic polynomial expansion with Riesz transform","authors":"M. Almekkawy, E. Ebbini","doi":"10.1109/ISBI.2017.7950501","DOIUrl":"https://doi.org/10.1109/ISBI.2017.7950501","url":null,"abstract":"Ultrasound speckle tracking provides a robust motion estimation of fine tissue displacements along the beam direction. Extensions to 2-D have been proposed in recent years. Due to relatively coarse lateral sampling, several solutions relied on lateral interpolation in order to achieve subsample accuracy. We introduce a new multi-dimensional speckle tracking method (MDST) with subsample accuracy in all dimensions. The proposed algorithm is based on solving a least squares problem to estimate the coefficients of a second order polynomial expansion to fit the magnitude of the two dimensional complex normalized correlation of the generalized analytic signal in the vicinity of the true peak. The generalization method utilizes the Riesz transform which is the multidimensional Hilbert transform. The displacement is estimated from acquired successive radio-frequency data frames of the region of interest. Field II simulation of flow data in a channel with a bench mark known displacement is generated to validate the accuracy of the method. In addition, the new MDST method is applied to imaging data from a flow phantom (ATS Model 524) to estimate the flow motion and pulsating channel wall. Simulations and experimental results demonstrate the effectiveness of the proposed technique.","PeriodicalId":6547,"journal":{"name":"2017 IEEE 14th International Symposium on Biomedical Imaging (ISBI 2017)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2017-06-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"85714227","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 : 2017-06-15DOI: 10.1109/ISBI.2017.7950720
Sharib Ali, K. Rohr, M. Axer, D. Gräßel, Philipp Schlömer, K. Amunts, R. Eils, S. Wörz
We introduce a new approach for the elastic registration of high-resolution 3D polarized light imaging (3D PLI) data of histological sections of the human brain. For accurate registration of different types of 3D PLI modalities, we propose a novel intensity similarity measure that is based on a least-squares formulation of normalized cross-correlation. Moreover, we present a fully automatic registration pipeline for rigid and elastic registration of high-resolution 3D PLI images with a blockface reference including a preprocessing step. We have successfully evaluated our approach using manually obtained ground truth for five sections of a human brain and experimentally compared it with previous approaches. We also present experimental results for 60 brain sections.
{"title":"Elastic registration of high-resolution 3D PLI data of the human brain","authors":"Sharib Ali, K. Rohr, M. Axer, D. Gräßel, Philipp Schlömer, K. Amunts, R. Eils, S. Wörz","doi":"10.1109/ISBI.2017.7950720","DOIUrl":"https://doi.org/10.1109/ISBI.2017.7950720","url":null,"abstract":"We introduce a new approach for the elastic registration of high-resolution 3D polarized light imaging (3D PLI) data of histological sections of the human brain. For accurate registration of different types of 3D PLI modalities, we propose a novel intensity similarity measure that is based on a least-squares formulation of normalized cross-correlation. Moreover, we present a fully automatic registration pipeline for rigid and elastic registration of high-resolution 3D PLI images with a blockface reference including a preprocessing step. We have successfully evaluated our approach using manually obtained ground truth for five sections of a human brain and experimentally compared it with previous approaches. We also present experimental results for 60 brain sections.","PeriodicalId":6547,"journal":{"name":"2017 IEEE 14th International Symposium on Biomedical Imaging (ISBI 2017)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2017-06-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"89071888","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 : 2017-04-19DOI: 10.1109/ISBI.2017.7950719
Lukás Rucka, I. Peterlík
Fast and accurate registration of image data is a key component of computer-aided medical image analysis. Instead of performing the registration directly on the input images, many algorithms compute the transformation using a sparse representation extracted from the original data. However, in order to apply the resulting transformation onto the original images, a dense deformation field has to be reconstructed using a suitable inter-/extra-polation technique. In this paper, we employ the radial basis function (RBF) to reconstruct the dense deformation field from a sparse transformation computed by a model-based registration. Various kernels are tested using different scenario. The dense deformation field is used to warp the source image and compare it quantitatively to the target image using two different metrics. Moreover, the influence of the number and distribution of the control points required by the RBF is studied via two different scenarios. Beside the accuracy, the performance of the method accelerated using a GPU is reported.
{"title":"Fast reconstruction of image deformation field using radial basis function","authors":"Lukás Rucka, I. Peterlík","doi":"10.1109/ISBI.2017.7950719","DOIUrl":"https://doi.org/10.1109/ISBI.2017.7950719","url":null,"abstract":"Fast and accurate registration of image data is a key component of computer-aided medical image analysis. Instead of performing the registration directly on the input images, many algorithms compute the transformation using a sparse representation extracted from the original data. However, in order to apply the resulting transformation onto the original images, a dense deformation field has to be reconstructed using a suitable inter-/extra-polation technique. In this paper, we employ the radial basis function (RBF) to reconstruct the dense deformation field from a sparse transformation computed by a model-based registration. Various kernels are tested using different scenario. The dense deformation field is used to warp the source image and compare it quantitatively to the target image using two different metrics. Moreover, the influence of the number and distribution of the control points required by the RBF is studied via two different scenarios. Beside the accuracy, the performance of the method accelerated using a GPU is reported.","PeriodicalId":6547,"journal":{"name":"2017 IEEE 14th International Symposium on Biomedical Imaging (ISBI 2017)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2017-04-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"85981466","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 : 2017-04-18DOI: 10.1109/ISBI.2017.7950542
Xiaojie Huang, Junjie Shan, V. Vaidya
We propose a new computer-aided detection system that uses 3D convolutional neural networks (CNN) for detecting lung nodules in low dose computed tomography. The system leverages both a priori knowledge about lung nodules and confounding anatomical structures and data-driven machine-learned features and classifier. Specifically, we generate nodule candidates using a local geometric-model-based filter and further reduce the structure variability by estimating the local orientation. The nodule candidates in the form of 3D cubes are fed into a deep 3D convolutional neural network that is trained to differentiate nodule and non-nodule inputs. We use data augmentation techniques to generate a large number of training examples and apply regularization to avoid overfitting. On a set of 99 CT scans, the proposed system achieved state-of-the-art performance and significantly outperformed a similar hybrid system that uses conventional shallow learning. The experimental results showed benefits of using a priori models to reduce the problem space for data-driven machine learning of complex deep neural networks. The results also showed the advantages of 3D CNN over 2D CNN in volumetric medical image analysis.
{"title":"Lung nodule detection in CT using 3D convolutional neural networks","authors":"Xiaojie Huang, Junjie Shan, V. Vaidya","doi":"10.1109/ISBI.2017.7950542","DOIUrl":"https://doi.org/10.1109/ISBI.2017.7950542","url":null,"abstract":"We propose a new computer-aided detection system that uses 3D convolutional neural networks (CNN) for detecting lung nodules in low dose computed tomography. The system leverages both a priori knowledge about lung nodules and confounding anatomical structures and data-driven machine-learned features and classifier. Specifically, we generate nodule candidates using a local geometric-model-based filter and further reduce the structure variability by estimating the local orientation. The nodule candidates in the form of 3D cubes are fed into a deep 3D convolutional neural network that is trained to differentiate nodule and non-nodule inputs. We use data augmentation techniques to generate a large number of training examples and apply regularization to avoid overfitting. On a set of 99 CT scans, the proposed system achieved state-of-the-art performance and significantly outperformed a similar hybrid system that uses conventional shallow learning. The experimental results showed benefits of using a priori models to reduce the problem space for data-driven machine learning of complex deep neural networks. The results also showed the advantages of 3D CNN over 2D CNN in volumetric medical image analysis.","PeriodicalId":6547,"journal":{"name":"2017 IEEE 14th International Symposium on Biomedical Imaging (ISBI 2017)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2017-04-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"73200279","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 : 2017-04-18DOI: 10.1109/ISBI.2017.7950461
William Meiniel, P. Spinicelli, E. Angelini, A. Fragola, V. Loriette, F. Orieux, E. Sepúlveda, J. Olivo-Marin
In this work, we introduce an original strategy to apply the Compressed Sensing (CS) framework to a super-resolution Structured Illumination Microscopy (SIM) technique. We first define a framework for direct domain CS, that exploits the sparsity of fluorescence microscopy images in the Fourier domain. We then propose an application of this method to a fast 4-images SIM technique, which allows to reconstruct super-resolved fluorescence microscopy images using only 25% of the camera pixels for each acquisition.
{"title":"Reducing data acquisition for fast Structured Illumination Microscopy using Compressed Sensing","authors":"William Meiniel, P. Spinicelli, E. Angelini, A. Fragola, V. Loriette, F. Orieux, E. Sepúlveda, J. Olivo-Marin","doi":"10.1109/ISBI.2017.7950461","DOIUrl":"https://doi.org/10.1109/ISBI.2017.7950461","url":null,"abstract":"In this work, we introduce an original strategy to apply the Compressed Sensing (CS) framework to a super-resolution Structured Illumination Microscopy (SIM) technique. We first define a framework for direct domain CS, that exploits the sparsity of fluorescence microscopy images in the Fourier domain. We then propose an application of this method to a fast 4-images SIM technique, which allows to reconstruct super-resolved fluorescence microscopy images using only 25% of the camera pixels for each acquisition.","PeriodicalId":6547,"journal":{"name":"2017 IEEE 14th International Symposium on Biomedical Imaging (ISBI 2017)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2017-04-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"88875834","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 : 2017-04-18DOI: 10.1109/ISBI.2017.7950598
Carl Azzopardi, Y. Hicks, K. Camilleri
The segmentation of media-adventitia and lumen-intima boundaries of the Carotid Artery forms an essential part in assessing plaque morphology in Ultrasound Imaging. Manual methods are tedious and prone to variability and thus, developing automated segmentation algorithms is preferable. In this paper, we propose to use deep convolutional networks for automated segmentation of the media-adventitia boundary in transverse and longitudinal sections of carotid ultrasound images. Deep networks have recently been employed with good success on image segmentation tasks, and we thus propose their application on ultrasound data, using an encoder-decoder convolutional structure which allows the network to be trained end-to-end for pixel-wise classification. Concurrently, we evaluate the performance for various configurations, depths and filter sizes within the network. In addition, we further propose a novel fusion of envelope and phase congruency data as an input to the network, as the latter provides an intensity-invariant data source to the network. We show that this data fusion and the proposed network structure yields higher segmentation performance than the state-of-the-art techniques.
{"title":"Automatic Carotid ultrasound segmentation using deep Convolutional Neural Networks and phase congruency maps","authors":"Carl Azzopardi, Y. Hicks, K. Camilleri","doi":"10.1109/ISBI.2017.7950598","DOIUrl":"https://doi.org/10.1109/ISBI.2017.7950598","url":null,"abstract":"The segmentation of media-adventitia and lumen-intima boundaries of the Carotid Artery forms an essential part in assessing plaque morphology in Ultrasound Imaging. Manual methods are tedious and prone to variability and thus, developing automated segmentation algorithms is preferable. In this paper, we propose to use deep convolutional networks for automated segmentation of the media-adventitia boundary in transverse and longitudinal sections of carotid ultrasound images. Deep networks have recently been employed with good success on image segmentation tasks, and we thus propose their application on ultrasound data, using an encoder-decoder convolutional structure which allows the network to be trained end-to-end for pixel-wise classification. Concurrently, we evaluate the performance for various configurations, depths and filter sizes within the network. In addition, we further propose a novel fusion of envelope and phase congruency data as an input to the network, as the latter provides an intensity-invariant data source to the network. We show that this data fusion and the proposed network structure yields higher segmentation performance than the state-of-the-art techniques.","PeriodicalId":6547,"journal":{"name":"2017 IEEE 14th International Symposium on Biomedical Imaging (ISBI 2017)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2017-04-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"89202546","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 : 2017-04-18DOI: 10.1109/ISBI.2017.7950614
Rashmi Panda, N. Puhan, A. Rao, Debananda Padhy, G. Panda
Retinal nerve fiber layer defect (RNFLD) is the earliest objective evidence of glaucoma in fundus images. Glaucoma is an optic neuropathy which causes irreversible vision impairment. Early glaucoma detection and its prevention are the only way to prevent further damage to human vision. In this paper, we propose a new automated method for RNFLD detection in fundus images through patch features driven recurrent neural network (RNN). A new dataset of fundus images is created for evaluation purpose which contains several challenging RNFLD boundaries. The true boundary pixels are classified using the RNN trained by novel cumulative zero count local binary pattern (CZC-LBP), directional differential energy (DDE) patch features. The experimental results demonstrate high RNFLD detection rate along with accurate boundary localization.
{"title":"Recurrent neural network based retinal nerve fiber layer defect detection in early glaucoma","authors":"Rashmi Panda, N. Puhan, A. Rao, Debananda Padhy, G. Panda","doi":"10.1109/ISBI.2017.7950614","DOIUrl":"https://doi.org/10.1109/ISBI.2017.7950614","url":null,"abstract":"Retinal nerve fiber layer defect (RNFLD) is the earliest objective evidence of glaucoma in fundus images. Glaucoma is an optic neuropathy which causes irreversible vision impairment. Early glaucoma detection and its prevention are the only way to prevent further damage to human vision. In this paper, we propose a new automated method for RNFLD detection in fundus images through patch features driven recurrent neural network (RNN). A new dataset of fundus images is created for evaluation purpose which contains several challenging RNFLD boundaries. The true boundary pixels are classified using the RNN trained by novel cumulative zero count local binary pattern (CZC-LBP), directional differential energy (DDE) patch features. The experimental results demonstrate high RNFLD detection rate along with accurate boundary localization.","PeriodicalId":6547,"journal":{"name":"2017 IEEE 14th International Symposium on Biomedical Imaging (ISBI 2017)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2017-04-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"91538296","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：