1,297 research outputs found
Segmentation of the Left Atrium and Pulmonary Veins from Contrast-Enhanced MR Images
No full textAtrial brillation is an important cardiovascular disease causing cardiac malfunction. The
left atrium and pulmonary veins are the structures most a ected. Radio-frequency catheter
ablation has now become a standard procedure for correcting atrial brillation. The procedure
is minimally invasive and pre-planning the procedure is essential. It is normally required to
image the atrium. Segmentation of the left atrium and pulmonary veins from medical images
is an important problem and a necessary step for further analysing the left atrium.
This dissertation describes techniques for segmenting the left atrium from MR angiography
images. It also describes methods for extracting sub-atrial structures of the atrium such as the
central atrial body and pulmonary veins. As pulmonary veins of the left atrium have complex
vessel networks, the centrelines of these vessels are extracted allowing for better visualisation
and compact representation. Furthermore, the dissertation describes a framework for analysing
the atrium. The pulmonary drainage trees are reconstructed using graph structures. Important
atrial characteristics relevant to catheter ablation procedures are quanti ed. These include
atrial anatomy and ostial diameters.
The methods described in the dissertation are evaluated on real patient datasets and compared
against manual approaches. A comparative study of the proposed left atrium segmentation
algorithm with an existing approach showed that the proposed approach yields better segmentations.
Furthermore, results show that the proposed techniques for pulmonary drainage
reconstruction correctly compute and classify atrial anatomy in the majority of cases. The
computation of ostial diameters also show close agreement with gold-standard measurements.
A series of studies performed to investigate the e ect of user parameters on the quality of
i
segmentation and measurements obtained show reproducibility of results. It is envisaged that
the methods proposed will improve the e cacy of catheter ablation by providing useful and
accurate atrial characteristics and information
4D Cardiac Volume Reconstruction from Free-Breathing 2D Real-Time Image Acquisitions using Iterative Motion Correction
No full textFor diagnosis, treatment and study of various cardiac diseases directly affecting the functionality and morphology of the heart, physicians rely more and more on MR imaging techniques. MRI has good tissue contrast and can achieve high spatial and temporal resolutions. However it requires a relatively long time to obtain enough data to reconstruct useful images. Additionally, when imaging the heart, the occurring motions - breathing and heart beat - have to be taken into account. While the cardiac motion still has to be correctly seen to asses functionality, the respiratory motion has to be removed to avoid serious motion artefacts. We present initial results for a reconstruction pipeline that takes multiple stacks of 2D slices, calculates the occurring deformations for both cardiac and respiratory motions and reconstructs a coherent 4D volume of the beating heart. The 2D slices are acquired during free-breathing over the whole respiratory cycle, using a fast real-time technique. For motion estimation two different transformation models were used. A cyclic 4D B-spline free-form deformation model for the cardiac motion and a 1D B-spline affine model for the respiratory motion. Both transformations and the common reference frame needed for the registration are optimized in an interleaved, iterative scheme
Daniel Rueckert's Quick Files
No full textThe Quick Files feature was discontinued and it’s files were migrated into this Project on March 11, 2022. The file URL’s will still resolve properly, and the Quick Files logs are available in the Project’s Recent Activity
Daniel Rueckert's Quick Files
No full textThe Quick Files feature was discontinued and it’s files were migrated into this Project on March 11, 2022. The file URL’s will still resolve properly, and the Quick Files logs are available in the Project’s Recent Activity
Daniel Rueckert's Quick Files
No full textThe Quick Files feature was discontinued and it’s files were migrated into this Project on March 11, 2022. The file URL’s will still resolve properly, and the Quick Files logs are available in the Project’s Recent Activity
Welcome
No full textThe 9th International Symposium on Biomedical Imaging (ISBI'12) was held Apr 30 - May 5, 2012, at the Centre Convencions International Barcelona (CCIB), in Barcelona, Spain. This is the third occasion that the meeting is held in Europe. The IEEE International Symposium on Biomedical Imaging (ISBI) is the premier forum for the presentation of technological advances in theoretical and applied biomedical imaging and image computing. ISBI is a joint initiative from the IEEE Signal Processing Society (SPS) and the IEEE Engineering in Medicine and Biology Society (EMBS). ISBI 2012 will be the 9th meeting in this series and its 10th anniversary since the first edition. Previous meetings have played an important role in facilitating interaction between medical and biological imaging researchers. The 2012 meeting will continue this tradition of fostering knowledge transfer between different imaging communities and contributing to an integrative approach to biomedical imaging across all scales of observation. The 2012 meeting will be preceded by two days of Satellite Open Source Workshops organized in conjunction with the EuroBioimaging consortium on Apr 30th and May 1st. These workshops will gather members from the biological and medical imaging communities to understand their needs and share new ideas for future developments of open source software tools. Two workshops have been organized: Bioimage Analysis Workshop and Medical Image Analysis Workshop. We received 701 submissions for the traditional full-paper track and 93 abstract submissions for the new abstractonly track; 48 full-paper submissions were solicited for inclusion in the special sessions. To ensure high quality of all accepted papers, each full-paper paper was sent out to three to four reviewers, of which at least one was a member of the Bio Imaging and Signal Processing (BISP, from the SPS) or the Biomedical Imaging and Image Processing (BIIP, from the EMBS) committees, the two expert IEEE Technical Committees involved with ISBI. Based on the reports from the reviewers, the Program Chairs together with help from the Technical Program Committee selected 135 (19%) papers for contributed oral sessions, 295 (42%) for full-paper poster sessions and 76 (82%) abstract-only poster sessions. The chart below provides an overview on how the various categories of papers have evolved over the 10 years of ISBI history. The total number of attendees for 2012 is based on the date of submission of this Welcome letter more than a month before the conference
Dense multi-frame optic flow for non-rigid objects using subspace constraints
No full textIn this paper we describe a variational approach to computing dense optic flow in the case of non-rigid motion. We optimise a global energy to compute the optic flow between each image in a sequence and a reference frame simultaneously. Our approach is based on subspace constraints which allow to express the optic flow at each pixel in a compact way as a linear combination of a 2D motion basis that can be pre-estimated from a set of reliable 2D tracks. We reformulate the multi-frame optic flow problem as the estimation of the coefficients that multiplied with the known basis will give the displacement vectors for each pixel. We adopt a variational framework in which we optimise a non-linearised global brightness constancy to cope with large displacements and impose homogeneous regularization on the multi-frame motion basis coefficients. Our approach has two strengths. First, the dramatic reduction in the number of variables to be computed (typically one order of magnitude) which has obvious computational advantages and second, the ability to deal with large displacements due to strong deformations. We conduct experiments on various sequences of non-rigid objects which show that our approach provides results comparable to state of the art variational multi-frame optic flow methods.Ravi Garg, Luis Pizarro, Daniel Rueckert, and Lourdes Agapit
PhaKIR Dataset - Surgical Procedure Phase, Keypoint, and Instrument Recognition [Data set]
No full textNote: A script for extracting the individual frames from the video files while preserving the challenge-compliant directory structure and frame-to-mask naming conventions is available on GitHub and can be accessed here: https://github.com/remic-othr/PhaKIR_Dataset.
The dataset is described in the following publications:
Rueckert, Tobias et al.: Comparative validation of surgical phase recognition, instrument keypoint estimation, and instrument instance segmentation in endoscopy: Results of the PhaKIR 2024 challenge. arXiv preprint, https://arxiv.org/abs/2507.16559. 2025.
Rueckert, Tobias et al.: Video Dataset for Surgical Phase, Keypoint, and Instrument Recognition in Laparoscopic Surgery (PhaKIR). arXiv preprint, https://arxiv.org/abs/2511.06549. 2025.
The proposed dataset was used as the training dataset in the PhaKIR challenge (https://phakir.re-mic.de/) as part of EndoVis-2024 at MICCAI 2024 and consists of eight real-world videos of human cholecystectomies ranging from 23 to 60 minutes in duration. The procedures were performed by experienced physicians, and the videos were recorded in three hospitals. In addition to existing datasets, our annotations provide pixel-wise instance segmentation masks of surgical instruments for a total of 19 categories, coordinates of relevant instrument keypoints (instrument tip(s), shaft-tip transition, shaft), both at an interval of one frame per second, and specifications regarding the intervention phases for a total of eight different phase categories for each individual frame in one dataset and thus comprehensively cover instrument localization and the context of the operation. Furthermore, the provision of the complete video sequences offers the opportunity to include the temporal information regarding the respective tasks and thus further optimize the resulting methods and outcomes
Tensor-based analysis of genetic influences on brain integrity using DTI in 100 twins
No full textInformation from the full diffusion tensor (DT) was used to compute voxel-wise genetic contributions to brain fiber microstructure. First, we designed a new multivariate intraclass correlation formula in the log-Euclidean framework [1]. We then analyzed used the full multivariate structure of the tensor in a multivariate version of a voxel-wise maximum-likelihood structural equation model (SEM) that computes the variance contributions in the DTs from genetic (A), common environmental (C) and unique environmental (E) factors. Our algorithm was tested on DT images from 25 identical and 25 fraternal twin pairs. After linear and fluid registration to a mean template, we computed the intraclass correlation and Falconer’s heritability statistic for several scalar DT-derived measures and for the full multivariate tensors. Covariance matrices were found from the DTs, and inputted into SEM. Analyzing the full DT enhanced the detection of A and C effects. This approach should empower imaging genetics studies that use DTI
Genetics of anisotropy asymmetry: Registration and sample size effects
No full textBrain asymmetry has been a topic of interest for neuroscientists for many years. The advent of diffusion tensor imaging (DTI) allows researchers to extend the study of asymmetry to a microscopic scale by examining fiber integrity differences across hemispheres rather than the macroscopic differences in shape or structure volumes. Even so, the power to detect these microarchitectural differences depends on the sample size and how the brain images are registered and how many subjects are studied. We fluidly registered 4 Tesla DTI scans from 180 healthy adult twins (45 identical and fraternal pairs) to a geometrically-centered population mean template. We computed voxelwise maps of significant asymmetries (left/right hemisphere differences) for common fiber anisotropy indices (FA, GA). Quantitative genetic models revealed that 47-62% of the variance in asymmetry was due to genetic differences in the population. We studied how these heritability estimates varied with the type of registration target (T1- or T2-weighted) and with sample size. All methods consistently found that genetic factors strongly determined the lateralization of fiber anisotropy, facilitating the quest for specific genes that might influence brain asymmetry and fiber integrity
- …
