Pub Date : 2017-04-18DOI: 10.1109/ISBI.2017.7950457
Dongwook Lee, J. Yoo, J. C. Ye
Compressed sensing (CS) enables significant reduction of MR acquisition time with performance guarantee. However, computational complexity of CS is usually expensive. To address this, here we propose a novel deep residual learning algorithm to reconstruct MR images from sparsely sampled k-space data. In particular, based on the observation that coherent aliasing artifacts from downsampled data has topologically simpler structure than the original image data, we formulate a CS problem as a residual regression problem and propose a deep convolutional neural network (CNN) to learn the aliasing artifacts. Experimental results using single channel and multi channel MR data demonstrate that the proposed deep residual learning outperforms the existing CS and parallel imaging algorithms. Moreover, the computational time is faster in several orders of magnitude.
{"title":"Deep residual learning for compressed sensing MRI","authors":"Dongwook Lee, J. Yoo, J. C. Ye","doi":"10.1109/ISBI.2017.7950457","DOIUrl":"https://doi.org/10.1109/ISBI.2017.7950457","url":null,"abstract":"Compressed sensing (CS) enables significant reduction of MR acquisition time with performance guarantee. However, computational complexity of CS is usually expensive. To address this, here we propose a novel deep residual learning algorithm to reconstruct MR images from sparsely sampled k-space data. In particular, based on the observation that coherent aliasing artifacts from downsampled data has topologically simpler structure than the original image data, we formulate a CS problem as a residual regression problem and propose a deep convolutional neural network (CNN) to learn the aliasing artifacts. Experimental results using single channel and multi channel MR data demonstrate that the proposed deep residual learning outperforms the existing CS and parallel imaging algorithms. Moreover, the computational time is faster in several orders of magnitude.","PeriodicalId":6547,"journal":{"name":"2017 IEEE 14th International Symposium on Biomedical Imaging (ISBI 2017)","volume":"79 1","pages":"15-18"},"PeriodicalIF":0.0,"publicationDate":"2017-04-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"78968196","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.2017.7950519
P. Looney, G. Stevenson, K. Nicolaides, W. Plasencia, Malid Molloholli, S. Natsis, S. Collins
Placental volume measured with 3D ultrasound in the first trimester has been shown to be correlated to adverse pregnancy outcomes. This could potentially be used as a screening test to predict the “at risk” pregnancy. However, manual segmentation whilst previously shown to be accurate and repeatable is very time consuming and semi-automated methods still require operator input. To generate a screening tool, fully automated placental segmentation is required. In this work, a deep convolutional neural network (cNN), DeepMedic, was trained using the output of the semi-automated Random Walker method as ground truth. 300 3D ultrasound scans of first trimester placentas were used to train, validate and test the cNN. Compared against the semi-automated segmentation, resultant median (1st Quartile, 3rd Quartile) Dice Similarity Coefficient was 0.73 (0.66, 0.76). The median (1st Quartile, 3rd Quartile) Hausdorff distance was 27 mm (18 mm, 36 mm). We present the first attempt at using a deep cNN for segmentation of 3D ultrasound of the placenta. This work shows that feasible results compared to ground truth were obtained that could form the basis of a fully automatic segmentation method.
在妊娠早期用三维超声测量胎盘体积已被证明与不良妊娠结局相关。这可能被用作预测“有风险”怀孕的筛查试验。然而，人工分割虽然以前被证明是准确和可重复的，但非常耗时，半自动方法仍然需要操作员的输入。为了生成筛选工具，需要完全自动化的胎盘分割。在这项工作中，深度卷积神经网络(cNN) DeepMedic使用半自动Random Walker方法的输出作为ground truth进行训练。使用300个早期妊娠胎盘的3D超声扫描来训练、验证和测试cNN。与半自动分割相比，得到的中位数(第1四分位，第3四分位)骰子相似系数为0.73(0.66,0.76)。Hausdorff距离中位数(第一、第三四分位数)为27 mm (18 mm、36 mm)。我们提出了使用深度cNN分割胎盘三维超声的第一次尝试。本文的工作表明，与地面真实情况相比，得到了可行的结果，可以构成全自动分割方法的基础。
{"title":"Automatic 3D ultrasound segmentation of the first trimester placenta using deep learning","authors":"P. Looney, G. Stevenson, K. Nicolaides, W. Plasencia, Malid Molloholli, S. Natsis, S. Collins","doi":"10.1109/ISBI.2017.7950519","DOIUrl":"https://doi.org/10.1109/ISBI.2017.7950519","url":null,"abstract":"Placental volume measured with 3D ultrasound in the first trimester has been shown to be correlated to adverse pregnancy outcomes. This could potentially be used as a screening test to predict the “at risk” pregnancy. However, manual segmentation whilst previously shown to be accurate and repeatable is very time consuming and semi-automated methods still require operator input. To generate a screening tool, fully automated placental segmentation is required. In this work, a deep convolutional neural network (cNN), DeepMedic, was trained using the output of the semi-automated Random Walker method as ground truth. 300 3D ultrasound scans of first trimester placentas were used to train, validate and test the cNN. Compared against the semi-automated segmentation, resultant median (1st Quartile, 3rd Quartile) Dice Similarity Coefficient was 0.73 (0.66, 0.76). The median (1st Quartile, 3rd Quartile) Hausdorff distance was 27 mm (18 mm, 36 mm). We present the first attempt at using a deep cNN for segmentation of 3D ultrasound of the placenta. This work shows that feasible results compared to ground truth were obtained that could form the basis of a fully automatic segmentation method.","PeriodicalId":6547,"journal":{"name":"2017 IEEE 14th International Symposium on Biomedical Imaging (ISBI 2017)","volume":"412 1","pages":"279-282"},"PeriodicalIF":0.0,"publicationDate":"2017-04-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"75005918","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.2017.7950581
Rami Ben-Ari, A. Akselrod-Ballin, Leonid Karlinsky, Sharbell Y. Hashoul
Detection of Architectural distortion (AD) is important for ruling out possible pre-malignant lesions in breast, but due to its subtlety, it is often missed on the screening mammograms. In this work we suggest a novel AD detection method based on region proposal convolution neural nets (R-CNN). When the data is scarce, as typically the case in medical domain, R-CNN yields poor results. In this study, we suggest a new R-CNN method addressing this shortcoming by using a pretrained network on a candidate region guided by clinical observations. We test our method on the publicly available DDSM data set, with comparison to the latest faster R-CNN and previous works. Our detection accuracy allows binary image classification (normal vs. containing AD) with over 80% sensitivity and specificity, and yields 0.46 false-positives per image at 83% true-positive rate, for localization accuracy. These measures significantly improve the best results in the literature.
{"title":"Domain specific convolutional neural nets for detection of architectural distortion in mammograms","authors":"Rami Ben-Ari, A. Akselrod-Ballin, Leonid Karlinsky, Sharbell Y. Hashoul","doi":"10.1109/ISBI.2017.7950581","DOIUrl":"https://doi.org/10.1109/ISBI.2017.7950581","url":null,"abstract":"Detection of Architectural distortion (AD) is important for ruling out possible pre-malignant lesions in breast, but due to its subtlety, it is often missed on the screening mammograms. In this work we suggest a novel AD detection method based on region proposal convolution neural nets (R-CNN). When the data is scarce, as typically the case in medical domain, R-CNN yields poor results. In this study, we suggest a new R-CNN method addressing this shortcoming by using a pretrained network on a candidate region guided by clinical observations. We test our method on the publicly available DDSM data set, with comparison to the latest faster R-CNN and previous works. Our detection accuracy allows binary image classification (normal vs. containing AD) with over 80% sensitivity and specificity, and yields 0.46 false-positives per image at 83% true-positive rate, for localization accuracy. These measures significantly improve the best results in the literature.","PeriodicalId":6547,"journal":{"name":"2017 IEEE 14th International Symposium on Biomedical Imaging (ISBI 2017)","volume":"99 1","pages":"552-556"},"PeriodicalIF":0.0,"publicationDate":"2017-04-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"80561752","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.2017.7950498
Chunjuan Bo, Xin Liang, Peng Chu, Jonathan Xu, D. Wang, Jie Yang, V. Megalooikonomou, H. Ling
A panoramic radiography image provides not only details of teeth but also rich information about trabecular bone. Recent studies have addressed the correlation between trabecular bone structure and osteoporosis. In this paper, we collect a dataset containing 40 images from 40 different subjects, and construct a new methodology based on a two-stage classification framework that combines multiple trabecular bone regions of interest (ROIs) for osteoporosis prescreening. In the first stage, different support vector machines (SVMs) are adopted to describe different information of different ROIs. In the second stage, the output probabilities of the first stage are effectively combined by using an additional linear SVM model to make a final prediction. Based on our two stage model, we test the performance of different image features by using leave-one-out cross-valuation and analysis of variance rules. The results suggest that the proposed method with the HOG (histogram of oriented gradients) feature achieves the best overall accuracy.
全景x线摄影图像不仅提供牙齿的细节，而且提供有关小梁骨的丰富信息。近年来的研究已经探讨了骨小梁结构与骨质疏松症的关系。在本文中，我们收集了一个包含40个不同受试者的40张图像的数据集，并构建了一种基于两阶段分类框架的新方法，该框架结合了多个感兴趣的骨小梁区域(roi)，用于骨质疏松症的预筛查。第一阶段采用不同的支持向量机(svm)来描述不同roi的不同信息。在第二阶段，通过使用附加的线性支持向量机模型有效地组合第一阶段的输出概率，进行最终预测。在两阶段模型的基础上，利用留一交叉评价和方差规则分析对不同图像特征的性能进行了测试。结果表明，采用HOG (histogram of oriented gradients)特征的方法获得了最好的整体精度。
{"title":"Osteoporosis prescreening using dental panoramic radiographs feature analysis","authors":"Chunjuan Bo, Xin Liang, Peng Chu, Jonathan Xu, D. Wang, Jie Yang, V. Megalooikonomou, H. Ling","doi":"10.1109/ISBI.2017.7950498","DOIUrl":"https://doi.org/10.1109/ISBI.2017.7950498","url":null,"abstract":"A panoramic radiography image provides not only details of teeth but also rich information about trabecular bone. Recent studies have addressed the correlation between trabecular bone structure and osteoporosis. In this paper, we collect a dataset containing 40 images from 40 different subjects, and construct a new methodology based on a two-stage classification framework that combines multiple trabecular bone regions of interest (ROIs) for osteoporosis prescreening. In the first stage, different support vector machines (SVMs) are adopted to describe different information of different ROIs. In the second stage, the output probabilities of the first stage are effectively combined by using an additional linear SVM model to make a final prediction. Based on our two stage model, we test the performance of different image features by using leave-one-out cross-valuation and analysis of variance rules. The results suggest that the proposed method with the HOG (histogram of oriented gradients) feature achieves the best overall accuracy.","PeriodicalId":6547,"journal":{"name":"2017 IEEE 14th International Symposium on Biomedical Imaging (ISBI 2017)","volume":"29 8 1","pages":"188-191"},"PeriodicalIF":0.0,"publicationDate":"2017-04-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"84721757","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.2017.7950554
G. Malandain, G. Michelin
In developmental imaging, 3D+t series of microscopic images allow to follow the organism development at the cell level and have now became the standard way of imaging the development of living organs. Dedicated tools for cell segmentation in 3D images as well as cell lineage calculation from 3D+t sequences have been proposed to analyze these data. For some applications, it may be desirable to interpolate label images at intermediary time-points. However, the known methods do not allow to locally handle the topological changes (ie cell. division). In the present work, we propose an extrapolation method that coherently deformed the label images to be interpolated.
{"title":"Coherent temporal extrapolation of labeled images","authors":"G. Malandain, G. Michelin","doi":"10.1109/ISBI.2017.7950554","DOIUrl":"https://doi.org/10.1109/ISBI.2017.7950554","url":null,"abstract":"In developmental imaging, 3D+t series of microscopic images allow to follow the organism development at the cell level and have now became the standard way of imaging the development of living organs. Dedicated tools for cell segmentation in 3D images as well as cell lineage calculation from 3D+t sequences have been proposed to analyze these data. For some applications, it may be desirable to interpolate label images at intermediary time-points. However, the known methods do not allow to locally handle the topological changes (ie cell. division). In the present work, we propose an extrapolation method that coherently deformed the label images to be interpolated.","PeriodicalId":6547,"journal":{"name":"2017 IEEE 14th International Symposium on Biomedical Imaging (ISBI 2017)","volume":"55 1","pages":"433-436"},"PeriodicalIF":0.0,"publicationDate":"2017-04-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"87823695","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.2017.7950459
Laurène Donati, M. Nilchian, M. Unser, S. Trépout, C. Messaoudi, S. Marcoy
We designed a complete acquisition-reconstruction framework to reduce the radiation dosage in 3D scanning transmission electron microscopy (STEM). Projection measurements are acquired by randomly scanning a subset of pixels at every tilt-view (i.e., random-beam STEM or “RB-STEM”). High-quality images are then recovered from the randomly downsampled measurements through a regularized tomographic reconstruction framework. By fulfilling the compressed sensing requirements, the proposed approach improves the reconstruction of heavily-downsampled RB-STEM measurements over the current state-of-the-art technique. This development opens new perspectives in the search for methods permitting lower-dose 3D STEM imaging of electron-sensitive samples without degrading the quality of the reconstructed volume. A Matlab code implementing the proposed reconstruction algorithm has been made available online.
{"title":"Compressed sensing for dose reduction in STEM tomography","authors":"Laurène Donati, M. Nilchian, M. Unser, S. Trépout, C. Messaoudi, S. Marcoy","doi":"10.1109/ISBI.2017.7950459","DOIUrl":"https://doi.org/10.1109/ISBI.2017.7950459","url":null,"abstract":"We designed a complete acquisition-reconstruction framework to reduce the radiation dosage in 3D scanning transmission electron microscopy (STEM). Projection measurements are acquired by randomly scanning a subset of pixels at every tilt-view (i.e., random-beam STEM or “RB-STEM”). High-quality images are then recovered from the randomly downsampled measurements through a regularized tomographic reconstruction framework. By fulfilling the compressed sensing requirements, the proposed approach improves the reconstruction of heavily-downsampled RB-STEM measurements over the current state-of-the-art technique. This development opens new perspectives in the search for methods permitting lower-dose 3D STEM imaging of electron-sensitive samples without degrading the quality of the reconstructed volume. A Matlab code implementing the proposed reconstruction algorithm has been made available online.","PeriodicalId":6547,"journal":{"name":"2017 IEEE 14th International Symposium on Biomedical Imaging (ISBI 2017)","volume":"7 2","pages":"23-27"},"PeriodicalIF":0.0,"publicationDate":"2017-04-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"91436345","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.2017.7950518
E. J. Chang, Yuexin Guo, Wei-Ning Lee
Ultrasound shear wave elastography (SWE) is an emerging technique for characterizing local arterial stiffness - a known indicator for vascular health. However, the implications due to vascular anatomy and tissue environment are still relatively under-examined. Using polyvinyl alcohol (PVA) based tissue mimicking phantoms, this study assessed the current signal processing framework in demonstrating the challenges due to the wave dispersion (at the medium thicknesses smaller than the shear wavelength) and wave interference at the interface of different media which cause biased stiffness estimations. Hence, 5% PVA and 10% PVA phantoms of varying thicknesses (from 1 to 10 mm) were imaged when placed in water and in 5% PVA and 10% PVA phantoms. Our results confirmed that shear wave propagation was thickness dependent (315% underestimation in 10% PVA). The shear wave velocity was shown to be influenced by the surrounding media with a 150% overestimation in 5% PVA surrounded by 10% PVA. It also demonstrated a key limitation of arterial SWE in that the current phase velocity estimation does not provide accurate SWV estimation, requiring optimization for addressing wave interference.
{"title":"Shear wave elastography for the characterization of arterial wall stiffness: A thin-plate phantom and ex vivo aorta study","authors":"E. J. Chang, Yuexin Guo, Wei-Ning Lee","doi":"10.1109/ISBI.2017.7950518","DOIUrl":"https://doi.org/10.1109/ISBI.2017.7950518","url":null,"abstract":"Ultrasound shear wave elastography (SWE) is an emerging technique for characterizing local arterial stiffness - a known indicator for vascular health. However, the implications due to vascular anatomy and tissue environment are still relatively under-examined. Using polyvinyl alcohol (PVA) based tissue mimicking phantoms, this study assessed the current signal processing framework in demonstrating the challenges due to the wave dispersion (at the medium thicknesses smaller than the shear wavelength) and wave interference at the interface of different media which cause biased stiffness estimations. Hence, 5% PVA and 10% PVA phantoms of varying thicknesses (from 1 to 10 mm) were imaged when placed in water and in 5% PVA and 10% PVA phantoms. Our results confirmed that shear wave propagation was thickness dependent (315% underestimation in 10% PVA). The shear wave velocity was shown to be influenced by the surrounding media with a 150% overestimation in 5% PVA surrounded by 10% PVA. It also demonstrated a key limitation of arterial SWE in that the current phase velocity estimation does not provide accurate SWV estimation, requiring optimization for addressing wave interference.","PeriodicalId":6547,"journal":{"name":"2017 IEEE 14th International Symposium on Biomedical Imaging (ISBI 2017)","volume":"5 1","pages":"275-278"},"PeriodicalIF":0.0,"publicationDate":"2017-04-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"88505491","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.2017.7950602
Yohannes K. Tsehay, Nathan S. Lay, Xiaosong Wang, J. T. Kwak, B. Turkbey, P. Choyke, P. Pinto, B. Wood, R. Summers
Prostate Cancer (PCa) is highly prevalent and is the second most common cause of cancer-related deaths in men. Multiparametric MRI (mpMRI) is robust in detecting PCa. We developed a weakly supervised computer-aided detection (CAD) system that uses biopsy points to learn to identify PCa on mpMRI. Our CAD system, which is based on a deep convolutional neural network architecture, yielded an area under the curve (AUC) of 0.903±0.009 on a receiver operation characteristic (ROC) curve computed on 10 different models in a 10 fold cross-validation. 9 of the 10 ROCs were statistically significantly different from a competing support vector machine based CAD, which yielded a 0.86 AUC when tested on the same dataset (α = 0.05). Furthermore, our CAD system proved to be more robust in detecting high-grade transition zone lesions.
{"title":"Biopsy-guided learning with deep convolutional neural networks for Prostate Cancer detection on multiparametric MRI","authors":"Yohannes K. Tsehay, Nathan S. Lay, Xiaosong Wang, J. T. Kwak, B. Turkbey, P. Choyke, P. Pinto, B. Wood, R. Summers","doi":"10.1109/ISBI.2017.7950602","DOIUrl":"https://doi.org/10.1109/ISBI.2017.7950602","url":null,"abstract":"Prostate Cancer (PCa) is highly prevalent and is the second most common cause of cancer-related deaths in men. Multiparametric MRI (mpMRI) is robust in detecting PCa. We developed a weakly supervised computer-aided detection (CAD) system that uses biopsy points to learn to identify PCa on mpMRI. Our CAD system, which is based on a deep convolutional neural network architecture, yielded an area under the curve (AUC) of 0.903±0.009 on a receiver operation characteristic (ROC) curve computed on 10 different models in a 10 fold cross-validation. 9 of the 10 ROCs were statistically significantly different from a competing support vector machine based CAD, which yielded a 0.86 AUC when tested on the same dataset (α = 0.05). Furthermore, our CAD system proved to be more robust in detecting high-grade transition zone lesions.","PeriodicalId":6547,"journal":{"name":"2017 IEEE 14th International Symposium on Biomedical Imaging (ISBI 2017)","volume":"6 1","pages":"642-645"},"PeriodicalIF":0.0,"publicationDate":"2017-04-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"79228033","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.2017.7950625
B. Haeffele, Sophie Roth, Lin Zhou, R. Vidal
Mitigating the effects of the twin image artifact is one of the key challenges in holographic lens-free microscopy. This artifact arises due to the fact that imaging detectors can only record the magnitude of the hologram wavefront but not the phase. Prior work addresses this problem by attempting to simultaneously estimate the missing phase and reconstruct an image of the object specimen. Here we explore a fundamentally different approach based on post-processing the reconstructed image using sparse dictionary learning and coding techniques originally developed for processing conventional images. First, a dictionary of atoms representing characteristics from either the true image of the specimen or the twin image are learned from a collection of patches of the observed images. Then, by expressing each patch of the observed image as a sparse linear combination of the dictionary atoms, the observed image is decomposed into a component that corresponds to the true image and another one that corresponds to the twin image artifact. Experiments on counting red blood cells demonstrate the effectiveness of the proposed approach.
{"title":"Removal of the twin image artifact in holographic lens-free imaging by sparse dictionary learning and coding","authors":"B. Haeffele, Sophie Roth, Lin Zhou, R. Vidal","doi":"10.1109/ISBI.2017.7950625","DOIUrl":"https://doi.org/10.1109/ISBI.2017.7950625","url":null,"abstract":"Mitigating the effects of the twin image artifact is one of the key challenges in holographic lens-free microscopy. This artifact arises due to the fact that imaging detectors can only record the magnitude of the hologram wavefront but not the phase. Prior work addresses this problem by attempting to simultaneously estimate the missing phase and reconstruct an image of the object specimen. Here we explore a fundamentally different approach based on post-processing the reconstructed image using sparse dictionary learning and coding techniques originally developed for processing conventional images. First, a dictionary of atoms representing characteristics from either the true image of the specimen or the twin image are learned from a collection of patches of the observed images. Then, by expressing each patch of the observed image as a sparse linear combination of the dictionary atoms, the observed image is decomposed into a component that corresponds to the true image and another one that corresponds to the twin image artifact. Experiments on counting red blood cells demonstrate the effectiveness of the proposed approach.","PeriodicalId":6547,"journal":{"name":"2017 IEEE 14th International Symposium on Biomedical Imaging (ISBI 2017)","volume":"42 1","pages":"741-744"},"PeriodicalIF":0.0,"publicationDate":"2017-04-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"87561574","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.2017.7950670
N. Brieu, G. Schmidt
The detection of cells and nuclei is a crucial step for the automatic analysis of digital pathology slides and as such for the quantification of the phenotypic information contained in tissue sections. This task is however challenging because of high variability in size, shape and textural appearance of the objects to be detected and of the high variability of tissue appearance. In this work, we propose an approach to specifically tackle the variability in size. Modeling the detection problem as a local maxima detection problem on a center probabilistic map, we introduce a nuclear surface area map to guide the selection of local maxima while releasing apriori knowledge on the size or structure of the objects to be detected. The good performance of our approach is quantitatively shown against state-of-the-art nuclei detection methods.
{"title":"Learning size adaptive local maxima selection for robust nuclei detection in histopathology images","authors":"N. Brieu, G. Schmidt","doi":"10.1109/ISBI.2017.7950670","DOIUrl":"https://doi.org/10.1109/ISBI.2017.7950670","url":null,"abstract":"The detection of cells and nuclei is a crucial step for the automatic analysis of digital pathology slides and as such for the quantification of the phenotypic information contained in tissue sections. This task is however challenging because of high variability in size, shape and textural appearance of the objects to be detected and of the high variability of tissue appearance. In this work, we propose an approach to specifically tackle the variability in size. Modeling the detection problem as a local maxima detection problem on a center probabilistic map, we introduce a nuclear surface area map to guide the selection of local maxima while releasing apriori knowledge on the size or structure of the objects to be detected. The good performance of our approach is quantitatively shown against state-of-the-art nuclei detection methods.","PeriodicalId":6547,"journal":{"name":"2017 IEEE 14th International Symposium on Biomedical Imaging (ISBI 2017)","volume":"1 1","pages":"937-941"},"PeriodicalIF":0.0,"publicationDate":"2017-04-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"79869129","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：