{"title":"One-shot learning of anatomical structure localization models","authors":"R. Donner, H. Bischof","doi":"10.1109/ISBI.2013.6556452","DOIUrl":"https://doi.org/10.1109/ISBI.2013.6556452","url":null,"abstract":"We propose an approach which allows to localize anatomical landmarks in radiological datasets given only a single manual annotation and set of un-annotated example images. Using top-down image patch regression to obtain potential landmark candidates in the set of training images, a model of the anatomical structure is incrementally enlarged, starting from the single, annotated image, until it encompasses the entire training set. The obtained model then allows to perform highly accurate anatomical structure localization on test data. We report preliminary results on a set of 2D radio-graphs, with a median/mean localization residual of 0.92 mm/1.30 mm. The approach yields very promising localization results, suggesting that is possible to eliminate the tedious manual annotation process still required by state of the art localization approaches.","PeriodicalId":178011,"journal":{"name":"2013 IEEE 10th International Symposium on Biomedical Imaging","volume":"139 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2013-04-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124419445","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}
Scott Kulp, Mingchen Gao, Shaoting Zhang, Z. Qian, S. Voros, Dimitris N. Metaxas, L. Axel
{"title":"Practical patient-specific cardiac blood flow simulations using SPH","authors":"Scott Kulp, Mingchen Gao, Shaoting Zhang, Z. Qian, S. Voros, Dimitris N. Metaxas, L. Axel","doi":"10.1109/ISBI.2013.6556604","DOIUrl":"https://doi.org/10.1109/ISBI.2013.6556604","url":null,"abstract":"While recent developments in the field of ventricular blood flow simulations have pushed modeling to increasingly high levels of accuracy, there has been a steep cost in computation time. Current state-of-the-art simulators take days to run, which is impractical for use in a clinical setting. In this paper, we describe novel adaptations of the SPH algorithm to this problem to achieve an order of magnitude faster performance, while maintaining accuracy in the flow. By constructing appropriate boundary particles and wall motion and adding a fast collision detection component to an existing SPH architecture, our system is able to simulate a cardiac cycle in as little as 30 minutes. This breakthrough will, in the near future, allow the useful simulation of blood flow and its related characterization for clinically useful applications.","PeriodicalId":178011,"journal":{"name":"2013 IEEE 10th International Symposium on Biomedical Imaging","volume":"24 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2013-04-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124883827","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}
{"title":"Cardiac localization in topograms using hierarchical models","authors":"Qi Song, V. Srikrishnan, Bipul Das, R. Bhagalia","doi":"10.1109/ISBI.2013.6556423","DOIUrl":"https://doi.org/10.1109/ISBI.2013.6556423","url":null,"abstract":"A vast number of medical imaging protocols identify anatomical regions of interest (ROI) from two dimensional (2D) localizer images to aid high resolution scan planning. These localizer scans are typically two dimensional projections of three dimensional data and as such have lower image detail due to overlapping tissue. The problem is further complicated by large variations in shape, size, appearance and the high occurrence of anomalies in the human anatomy. Manual ROI delineation is time consuming and error prone. To combat these issues we develop a hierarchical multi-object active appearance model (AAM) framework that is both robust to inaccuracies in model initialization yet sufficiently flexible to handle the large diversity of the human body. The method was successfully applied to automatically determine the extents of the human heart in 99 2D CT topograms yielding significant improvement in accuracy over a single global AAM approach.","PeriodicalId":178011,"journal":{"name":"2013 IEEE 10th International Symposium on Biomedical Imaging","volume":"69 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2013-04-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125098183","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}
Daniel Jimenez-Carretero, Andrés Santos, Sjoerd Kerkstra, R. D. Rudyanto, M. Ledesma-Carbayo
{"title":"3D Frangi-based lung vessel enhancement filter penalizing airways","authors":"Daniel Jimenez-Carretero, Andrés Santos, Sjoerd Kerkstra, R. D. Rudyanto, M. Ledesma-Carbayo","doi":"10.1109/ISBI.2013.6556627","DOIUrl":"https://doi.org/10.1109/ISBI.2013.6556627","url":null,"abstract":"This paper describes a fully automatic simultaneous lung vessel and airway enhancement filter. The approach consists of a Frangi-based multiscale vessel enhancement filtering specifically designed for lung vessel and airway detection, where arteries and veins have high contrast with respect to the lung parenchyma, and airway walls are hollow tubular structures with a non negative response using the classical Frangi's filter. The features extracted from the Hessian matrix are used to detect centerlines and approximate walls of airways, decreasing the filter response in those areas by applying a penalty function to the vesselness measure. We validate the segmentation method in 20 CT scans with different pathological states within the VESSEL12 challenge framework. Results indicate that our approach obtains good results, decreasing the number of false positives in airway walls.","PeriodicalId":178011,"journal":{"name":"2013 IEEE 10th International Symposium on Biomedical Imaging","volume":"363 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2013-04-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"134234200","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}
M. Koch, Andreas Kleinoeder, F. Bourier, J. Hornegger, Norbert Strobel
{"title":"Novel method for comparison of pre-planned ablation lines for treatment of atrial fibrillation using a common reference model","authors":"M. Koch, Andreas Kleinoeder, F. Bourier, J. Hornegger, Norbert Strobel","doi":"10.1109/ISBI.2013.6556405","DOIUrl":"https://doi.org/10.1109/ISBI.2013.6556405","url":null,"abstract":"The standard approach in interventional treatment of atrial fibrillation (AFib) is pulmonary vein isolation (PVI). PVI can be achieved by placing radio-frequency (RF) lesions contiguously around the pulmonary veins attached to the left atrium. Since accurate lesion placement may be difficult, pre-planned ablation lines can be used for better navigation both when using mapping systems or also when relying on fluoro overlay techniques. By working with physicians in this field, we learned that clinically acceptable ablation lines are not necessarily limited to a unique line, but there appears to be some flexibility when defining regions within which ablation should be performed. We present a novel method to investigate the dimensions of such a region based on comparing pre-planned ablation lines set up for different left atria. A common reference model is proposed as a means to combine and compare different pre-planned ablation lines. Based on our data, we found an average deviation of individually pre-planned ablation lines from their respective mean of 2.9±1.9 mm and 1.8±1.5 mm for right and left sided ipsilateral planning lines, respectively. Beyond ablation line assessment, this work also introduces a framework which can be extended to automatic pre-planning of ablation lines for PVI procedures.","PeriodicalId":178011,"journal":{"name":"2013 IEEE 10th International Symposium on Biomedical Imaging","volume":"49 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2013-04-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132517144","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}
T. Dietenbeck, D. Barbosa, M. Alessandrini, R. Jasaityte, Valérie Robesyn, J. D’hooge, D. Friboulet, O. Bernard
{"title":"Multiview myocardial tracking in echocardiographic 2D sequences using shape and motion constrained level-set","authors":"T. Dietenbeck, D. Barbosa, M. Alessandrini, R. Jasaityte, Valérie Robesyn, J. D’hooge, D. Friboulet, O. Bernard","doi":"10.1109/ISBI.2013.6556651","DOIUrl":"https://doi.org/10.1109/ISBI.2013.6556651","url":null,"abstract":"Segmentation of the myocardium in echocardiographic images is an important task for the diagnosis of heart disease. This task is difficult due to the inherent problems of echographic images (i.e. low contrast, speckle noise, signal dropout, presence of shadows). In this article, we extend a level-set method recently proposed in [1] in order to track the whole myocardium in echocardiographic sequences. To this end, we formulate a new motion prior energy that constrains the zero-level of the implicit function to satisfy the optical flow hypothesis. The algorithm is then compared to experts references and to another method on a dataset of 12 sequences (more than 700 images) acquired in the four main echocardiographic views.","PeriodicalId":178011,"journal":{"name":"2013 IEEE 10th International Symposium on Biomedical Imaging","volume":"21 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2013-04-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133168439","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}
{"title":"Computer-guided ultrasound probe realignment by optical tracking","authors":"Shih-Yu Sun, Matthew W. Gilbertson, B. Anthony","doi":"10.1109/ISBI.2013.6556402","DOIUrl":"https://doi.org/10.1109/ISBI.2013.6556402","url":null,"abstract":"In longitudinal studies and localized therapies, tissue changes are commonly tracked by repeated ultrasound scans at a fixed location marked on the patient body. However, the accuracy of this probe realignment approach is sometimes inadequate, especially when maintaining the insonification angle is essential. This paper describes a system that provides real-time visual guidance for accurate realignment of the ultrasound probe in six degrees of freedom (6 DoF). This system uses a small camera rigidly mounted on the probe to track artificial skin features, from which the current probe pose relative to the target pose is estimated. A virtual pyramid is created in the skin map and shown in the camera frame to intuitively indicate the probe movement required to achieve the target pose. Performance of this system was examined in vivo, and it was shown that this system significantly improves alignment of tissue structures in repeated ultrasound scans.","PeriodicalId":178011,"journal":{"name":"2013 IEEE 10th International Symposium on Biomedical Imaging","volume":"39 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2013-04-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115887656","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}
{"title":"Data-driven MRSI spectral localization using non-cartesian sampling trajectories","authors":"Jeffrey Kasten, F. Lazeyras, D. Ville","doi":"10.1109/ISBI.2013.6556635","DOIUrl":"https://doi.org/10.1109/ISBI.2013.6556635","url":null,"abstract":"The ability to non-invasively visualize spatially-localized maps of metabolite concentrations in vivo as afforded by Magnetic Resonance Spectroscopic Imaging (MRSI) is an attractive prospect in clinically-focused biomedical imaging. However, the current gold standard implementation, known as Chemical Shift Imaging (CSI), is plagued by various artifacts, due primarily to the limitations dictated through use of the Fourier transform. To counter these impediments, numerous “constrained” reconstruction methods have been suggested, which typically inject some type of a priori information, usually with the aid of structural MR images, into the signal model. While this may be desirable for some applications, it introduces an assumption which posits a general equivalency between the spatial and spectral distributions, which may not always be appropriate. This work examines an alternative formulation in which, with the aid of statistical techniques and spatial regularization, constituent high-resolution spatial and spectral components are estimated from the raw MRSI data. We demonstrate the efficacy of this technique, and the robustness of the estimated components to alternative sampling strategies, thereby broadening the applicability of the method and offering the prospect of reduced acquisition times in more pressed clinical settings.","PeriodicalId":178011,"journal":{"name":"2013 IEEE 10th International Symposium on Biomedical Imaging","volume":"20 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2013-04-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116331825","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}
{"title":"Using bilateral symmetry to improve non-local means denoising of MR brain images","authors":"S. Prima, O. Commowick","doi":"10.1109/ISBI.2013.6556703","DOIUrl":"https://doi.org/10.1109/ISBI.2013.6556703","url":null,"abstract":"The popular NL-means denoising algorithm proposes to modify the intensity of each voxel of an image by a weighted sum of the intensities of similar voxels. The success of the NL-means rests on the fact that there are typically enough such similar voxels in natural, and even medical images; in other words, that there is some self-similarity/redundancy in such images. However, similarity between voxels (or rather, between patches around them) is usually only assessed in a spatial neighbourhood of the voxel under study. As the human brain exhibits approximate bilateral symmetry, one could wonder whether a voxel in a brain image could be more accurately denoised using information from both ipsi- and contralateral hemispheres. This is the idea we investigate in this paper. We define and compute a mid-sagittal plane which best superposes the brain with itself when mirrored about the plane. Then we use this plane to double the size of the neighbourhoods and hopefully find additional interesting voxels to be included in the weighted sum. We evaluate this strategy using an extensive set of experiments on both simulated and real datasets.","PeriodicalId":178011,"journal":{"name":"2013 IEEE 10th International Symposium on Biomedical Imaging","volume":"120 1 Suppl 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2013-04-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116375035","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}
M. Maška, Xabier Morales, A. Muñoz-Barrutia, A. Rouzaut, C. Ortíz-de-Solórzano
{"title":"Automatic quantification of filopodia-based cell migration","authors":"M. Maška, Xabier Morales, A. Muñoz-Barrutia, A. Rouzaut, C. Ortíz-de-Solórzano","doi":"10.1109/ISBI.2013.6556563","DOIUrl":"https://doi.org/10.1109/ISBI.2013.6556563","url":null,"abstract":"We present a fully automatic approach to quantitatively analyze filopodia-based migration of fluorescent cells in 3D time-lapse series. The proposed method involves three steps. First, each frame of the time-lapse series is preprocessed using a steerable filter and binarized to obtain a coarse segmentation of the cell shape. Second, a sequence of morphological filters is applied on the coarse binary mask to separate the cell body from individual filopodia. Finally, their length is estimated using a geodesic distance transform. The proposed approach is validated on 3D time-lapse series of lung adenocarcinoma cells. We show that the number of filopodia and their average length can be used as a descriptor to discriminate between different phenotypes of migrating cells.","PeriodicalId":178011,"journal":{"name":"2013 IEEE 10th International Symposium on Biomedical Imaging","volume":"10 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2013-04-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115432388","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}