We introduce a method for registration of brain images acquired in clinical settings. The algorithm relies on three-dimensional patches in a discrete registration framework to estimate correspondences. Clinical images present significant challenges for computational analysis. Fast acquisition often results in images with sparse slices, severe artifacts, and variable fields of view. Yet, large clinical datasets hold a wealth of clinically relevant information. Despite significant progress in image registration, most algorithms make strong assumptions about the continuity of image data, failing when presented with clinical images that violate these assumptions. In this paper, we demonstrate a non-rigid registration method for aligning such images. The method explicitly models the sparsely available image information to achieve robust registration. We demonstrate the algorithm on clinical images of stroke patients. The proposed method outperforms state of the art registration algorithms and avoids catastrophic failures often caused by these images. We provide a freely available open source implementation of the algorithm.
We offer a blazingly brief review of evolution of shape analysis methods in medical imaging. As the representations and the statistical models grew more sophisticated, the problem of shape analysis has been gradually redefined to accept images rather than binary segmentations as a starting point. This transformation enabled shape analysis to take its rightful place in the arsenal of tools for extracting and understanding patterns in large clinical image sets. We speculate on the future developments in shape analysis and potential applications that would bring this mathematically rich area to bear on clinical practice.
We present a robust method to correct for motion and deformations in in-utero volumetric MRI time series. Spatio-temporal analysis of dynamic MRI requires robust alignment across time in the presence of substantial and unpredictable motion. We make a Markov assumption on the nature of deformations to take advantage of the temporal structure in the image data. Forward message passing in the corresponding hidden Markov model (HMM) yields an estimation algorithm that only has to account for relatively small motion between consecutive frames. We demonstrate the utility of the temporal model by showing that its use improves the accuracy of the segmentation propagation through temporal registration. Our results suggest that the proposed model captures accurately the temporal dynamics of deformations in in-utero MRI time series.
Emphysema is one of the hallmarks of Chronic Obstructive Pulmonary Disorder (COPD), a devastating lung disease often caused by smoking. Emphysema appears on Computed Tomography (CT) scans as a variety of textures that correlate with disease subtypes. It has been shown that the disease subtypes and textures are linked to physiological indicators and prognosis, although neither is well characterized clinically. Most previous computational approaches to modeling emphysema imaging data have focused on supervised classification of lung textures in patches of CT scans. In this work, we describe a generative model that jointly captures heterogeneity of disease subtypes and of the patient population. We also describe a corresponding inference algorithm that simultaneously discovers disease subtypes and population structure in an unsupervised manner. This approach enables us to create image-based descriptors of emphysema beyond those that can be identified through manual labeling of currently defined phenotypes. By applying the resulting algorithm to a large data set, we identify groups of patients and disease subtypes that correlate with distinct physiological indicators.
PURPOSE: The aim of this study was to present a tractography algorithm using a two-tensor unscented Kalman filter (UKF) to improve the modeling of the corticospinal tract (CST) by tracking through regions of peritumoral edema and crossing fibers. METHODS: Ten patients with brain tumors in the vicinity of motor cortex and evidence of significant peritumoral edema were retrospectively selected for the study. All patients underwent 3-T magnetic resonance imaging (MRI) including functional MRI (fMRI) and a diffusion-weighted data set with 31 directions. Fiber tracking was performed using both single-tensor streamline and two-tensor UKF tractography methods. A two-region-of-interest approach was used to delineate the CST. Results from the two tractography methods were compared visually and quantitatively. fMRI was applied to identify the functional fiber tracts. RESULTS: Single-tensor streamline tractography underestimated the extent of tracts running through the edematous areas and could only track the medial projections of the CST. In contrast, two-tensor UKF tractography tracked fanning projections of the CST despite peritumoral edema and crossing fibers. Based on visual inspection, the two-tensor UKF tractography delineated tracts that were closer to motor fMRI activations, and it was apparently more sensitive than single-tensor streamline tractography to define the tracts directed to the motor sites. The volume of the CST was significantly larger on two-tensor UKF than on single-tensor streamline tractography ([Formula: see text]). CONCLUSION: Two-tensor UKF tractography tracks a larger volume CST than single-tensor streamline tractography in the setting of peritumoral edema and crossing fibers in brain tumor patients.
Hengameh Mirzaalian, Lipeng Ning, Peter Savadjiev, Ofer Pasternak, Sylvain Bouix, Oleg Michailovich, G Grant, CE Marx, RA Morey, LA Flashman, MS George, TW McAllister, N Andaluz, L Shutter, R Coimbra, Ross Zafonte, Michael J Coleman, Marek Kubicki, Carl-Fredrik Westin, M.B. Stein, Martha E Shenton, and Yogesh Rathi. 7/2016. “Inter-site and Inter-scanner Diffusion MRI Data Harmonization.” Neuroimage, 135, Pp. 311-23.Abstract
We propose a novel method to harmonize diffusion MRI data acquired from multiple sites and scanners, which is imperative for joint analysis of the data to significantly increase sample size and statistical power of neuroimaging studies. Our method incorporates the following main novelties: i) we take into account the scanner-dependent spatial variability of the diffusion signal in different parts of the brain; ii) our method is independent of compartmental modeling of diffusion (e.g., tensor, and intra/extra cellular compartments) and the acquired signal itself is corrected for scanner related differences; and iii) inter-subject variability as measured by the coefficient of variation is maintained at each site. We represent the signal in a basis of spherical harmonics and compute several rotation invariant spherical harmonic features to estimate a region and tissue specific linear mapping between the signal from different sites (and scanners). We validate our method on diffusion data acquired from seven different sites (including two GE, three Philips, and two Siemens scanners) on a group of age-matched healthy subjects. Since the extracted rotation invariant spherical harmonic features depend on the accuracy of the brain parcellation provided by Freesurfer, we propose a feature based refinement of the original parcellation such that it better characterizes the anatomy and provides robust linear mappings to harmonize the dMRI data. We demonstrate the efficacy of our method by statistically comparing diffusion measures such as fractional anisotropy, mean diffusivity and generalized fractional anisotropy across multiple sites before and after data harmonization. We also show results using tract-based spatial statistics before and after harmonization for independent validation of the proposed methodology. Our experimental results demonstrate that, for nearly identical acquisition protocol across sites, scanner-specific differences can be accurately removed using the proposed method.
We propose a unified Bayesian framework for detecting genetic variants associated with disease by exploiting image-based features as an intermediate phenotype. The use of imaging data for examining genetic associations promises new directions of analysis, but currently the most widely used methods make sub-optimal use of the richness that these data types can offer. Currently, image features are most commonly selected based on their relevance to the disease phenotype. Then, in a separate step, a set of genetic variants is identified to explain the selected features. In contrast, our method performs these tasks simultaneously in order to jointly exploit information in both data types. The analysis yields probabilistic measures of clinical relevance for both imaging and genetic markers. We derive an efficient approximate inference algorithm that handles the high dimensionality of image and genetic data. We evaluate the algorithm on synthetic data and demonstrate that it outperforms traditional models. We also illustrate our method on Alzheimer's Disease Neuroimaging Initiative data.
This work describes a new diffusion MR framework for imaging and modeling of microstructure that we call q-space trajectory imaging (QTI). The QTI framework consists of two parts: encoding and modeling. First we propose q-space trajectory encoding, which uses time-varying gradients to probe a trajectory in q-space, in contrast to traditional pulsed field gradient sequences that attempt to probe a point in q-space. Then we propose a microstructure model, the diffusion tensor distribution (DTD) model, which takes advantage of additional information provided by QTI to estimate a distributional model over diffusion tensors. We show that the QTI framework enables microstructure modeling that is not possible with the traditional pulsed gradient encoding as introduced by Stejskal and Tanner. In our analysis of QTI, we find that the well-known scalar b-value naturally extends to a tensor-valued entity, i.e., a diffusion measurement tensor, which we call the b-tensor. We show that b-tensors of rank 2 or 3 enable estimation of the mean and covariance of the DTD model in terms of a second order tensor (the diffusion tensor) and a fourth order tensor. The QTI framework has been designed to improve discrimination of the sizes, shapes, and orientations of diffusion microenvironments within tissue. We derive rotationally invariant scalar quantities describing intuitive microstructural features including size, shape, and orientation coherence measures. To demonstrate the feasibility of QTI on a clinical scanner, we performed a small pilot study comparing a group of five healthy controls with five patients with schizophrenia. The parameter maps derived from QTI were compared between the groups, and 9 out of the 14 parameters investigated showed differences between groups. The ability to measure and model the distribution of diffusion tensors, rather than a quantity that has already been averaged within a voxel, has the potential to provide a powerful paradigm for the study of complex tissue architecture.
The Surgical Planning Laboratory at Brigham and Women's Hospital, Harvard Medical School, developed the SPL Ear Atlas. The atlas was derived from a high-resolution flat-panel computed tomography (CT) scan (aprox 140 µm high contrast resultion), using semi-automated image segmentation and three-dimensional reconstruction techniques [Gupta, Bartling, et al. AJNR Am J Neuroradiol. 2004.]. The current version consists of: 1. the original CT scan; 2. a set of detailed label maps; 3. a set of three-dimensional models of the labeled anatomical structures; 4. mrb (Medical Reality Bundle) file archive that contains the mrml scene file and all data for loading into Slicer 4 for displaying the volumes in 3D Slicer version 4.0 or greater; 5. several pre-defined 3D-views (“anatomy teaching files”). The SPL Ear Atlas provides important reference information for surgical planning, anatomy teaching, and template driven segmentation. Visualization of the data requires 3D Slicer. This software package can be downloaded from here. We are pleased to make this atlas available to our colleagues for free download. Please note that the data is being distributed under the Slicer license. By downloading these data, you agree to acknowledge our contribution in any of your publications that result form the use of this atlas. This work is funded as part of the Neuroimaging Analysis Center, grant number P41 RR013218, by the NIH's National Center for Research Resources (NCRR) and grant number P41 EB015902, by the NIH's National Institute of Biomedical Imaging and Bioengineering (NIBIB) and the Google Faculty Research Award.
Background. Imaging biomarkers hold tremendous promise for precision medicine clinical applications. Development of such biomarkers relies heavily on image post-processing tools for automated image quantitation. Their deployment in the context of clinical research necessitates interoperability with the clinical systems. Comparison with the established outcomes and evaluation tasks motivate integration of the clinical and imaging data, and the use of standardized approaches to support annotation and sharing of the analysis results and semantics. We developed the methodology and tools to support these tasks in Positron Emission Tomography and Computed Tomography (PET/CT) quantitative imaging (QI) biomarker development applied to head and neck cancer (HNC) treatment response assessment, using the Digital Imaging and Communications in Medicine (DICOM(®)) international standard and free open-source software. Methods. Quantitative analysis of PET/CT imaging data collected on patients undergoing treatment for HNC was conducted. Processing steps included Standardized Uptake Value (SUV) normalization of the images, segmentation of the tumor using manual and semi-automatic approaches, automatic segmentation of the reference regions, and extraction of the volumetric segmentation-based measurements. Suitable components of the DICOM standard were identified to model the various types of data produced by the analysis. A developer toolkit of conversion routines and an Application Programming Interface (API) were contributed and applied to create a standards-based representation of the data. Results. DICOM Real World Value Mapping, Segmentation and Structured Reporting objects were utilized for standards-compliant representation of the PET/CT QI analysis results and relevant clinical data. A number of correction proposals to the standard were developed. The open-source DICOM toolkit (DCMTK) was improved to simplify the task of DICOM encoding by introducing new API abstractions. Conversion and visualization tools utilizing this toolkit were developed. The encoded objects were validated for consistency and interoperability. The resulting dataset was deposited in the QIN-HEADNECK collection of The Cancer Imaging Archive (TCIA). Supporting tools for data analysis and DICOM conversion were made available as free open-source software. Discussion. We presented a detailed investigation of the development and application of the DICOM model, as well as the supporting open-source tools and toolkits, to accommodate representation of the research data in QI biomarker development. We demonstrated that the DICOM standard can be used to represent the types of data relevant in HNC QI biomarker development, and encode their complex relationships. The resulting annotated objects are amenable to data mining applications, and are interoperable with a variety of systems that support the DICOM standard.
The ability to detect neuronal currents with high spatiotemporal resolution using magnetic resonance imaging (MRI) is important for studying human brain function in both health and disease. While significant progress has been made, we still lack evidence showing that it is possible to measure an MR signal time-locked to neuronal currents with a temporal waveform matching concurrently recorded local field potentials (LFPs). Also lacking is evidence that such MR data can be used to image current distribution in active tissue. Since these two results are lacking even in vitro, we obtained these data in an intact isolated whole cerebellum of turtle during slow neuronal activity mediated by metabotropic glutamate receptors using a gradient-echo EPI sequence (TR=100ms) at 4.7T. Our results show that it is possible (1) to reliably detect an MR phase shift time course matching that of the concurrently measured LFP evoked by stimulation of a cerebellar peduncle, (2) to detect the signal in single voxels of 0.1mm3, (3) to determine the spatial phase map matching the magnetic field distribution predicted by the LFP map, (4) to estimate the distribution of neuronal current in the active tissue from a group-average phase map, and (5) to provide a quantitatively accurate theoretical account of the measured phase shifts. The peak values of the detected MR phase shifts were 0.27-0.37°, corresponding to local magnetic field changes of 0.67-0.93nT (for TE=26ms). Our work provides an empirical basis for future extensions to in vivo imaging of neuronal currents.
Retrieving medical images that present similar diseases is an active research area for diagnostics and therapy. However, it can be problematic given the visual variations between anatomical structures. In this paper, we propose a new feature extraction method for similarity computation in medical imaging. Instead of the low-level visual appearance, we design a CCA-PairLDA feature representation method to capture the similarity between images with high-level semantics. First, we extract the PairLDA topics to represent an image as a mixture of latent semantic topics in an image pair context. Second, we generate a CCA-correlation model to represent the semantic association between an image pair for similarity computation. While PairLDA adjusts the latent topics for all image pairs, CCA-correlation helps to associate an individual image pair. In this way, the semantic descriptions of an image pair are closely correlated, and naturally correspond to similarity computation between images. We evaluated our method on two public medical imaging datasets for image retrieval and showed improved performance.
Quantifying the systemic risk and fragility of financial systems is of vital importance in analyzing market efficiency, deciding on portfolio allocation, and containing financial contagions. At a high level, financial systems may be represented as weighted graphs that characterize the complex web of interacting agents and information flow (for example, debt, stock returns, and shareholder ownership). Such a representation often turns out to provide keen insights. We show that fragility is a system-level characteristic of "business-as-usual" market behavior and that financial crashes are invariably preceded by system-level changes in robustness. This was done by leveraging previous work, which suggests that Ricci curvature, a key geometric feature of a given network, is negatively correlated to increases in network fragility. To illustrate this insight, we examine daily returns from a set of stocks comprising the Standard and Poor's 500 (S&P 500) over a 15-year span to highlight the fact that corresponding changes in Ricci curvature constitute a financial "crash hallmark." This work lays the foundation of understanding how to design (banking) systems and policy regulations in a manner that can combat financial instabilities exposed during the 2007-2008 crisis.
We introduce a generative probabilistic model for segmentation of brain lesions in multi-dimensional images that generalizes the EM segmenter, a common approach for modelling brain images using Gaussian mixtures and a probabilistic tissue atlas that employs expectation-maximization (EM), to estimate the label map for a new image. Our model augments the probabilistic atlas of the healthy tissues with a latent atlas of the lesion. We derive an estimation algorithm with closed-form EM update equations. The method extracts a latent atlas prior distribution and the lesion posterior distributions jointly from the image data. It delineates lesion areas individually in each channel, allowing for differences in lesion appearance across modalities, an important feature of many brain tumor imaging sequences. We also propose discriminative model extensions to map the output of the generative model to arbitrary labels with semantic and biological meaning, such as "tumor core" or "fluid-filled structure", but without a one-to-one correspondence to the hypo- or hyper-intense lesion areas identified by the generative model. We test the approach in two image sets: the publicly available BRATS set of glioma patient scans, and multimodal brain images of patients with acute and subacute ischemic stroke. We find the generative model that has been designed for tumor lesions to generalize well to stroke images, and the extended discriminative-discriminative model to be one of the top ranking methods in the BRATS evaluation.
Disentangling the tissue microstructural information from the diffusion magnetic resonance imaging (dMRI) measurements is quite important for extracting brain tissue specific measures. The autocorrelation function of diffusing spins is key for understanding the relation between dMRI signals and the acquisition gradient sequences. In this paper, we demonstrate that the autocorrelation of diffusion in restricted or bounded spaces can be well approximated by exponential functions. To this end, we propose to use the multivariate Ornstein-Uhlenbeck (OU) process to model the matrix-valued exponential autocorrelation function of three-dimensional diffusion processes with bounded trajectories. We present detailed analysis on the relation between the model parameters and the time-dependent apparent axon radius and provide a general model for dMRI signals from the frequency domain perspective. For our experimental setup, we model the diffusion signal as a mixture of two compartments that correspond to diffusing spins with bounded and unbounded trajectories, and analyze the corpus-callosum in an ex-vivo data set of a monkey brain.
Extracting nuclei is one of the most actively studied topic in the digital pathology researches. Most of the studies directly search the nuclei (or seeds for the nuclei) from the finest resolution available. While the richest information has been utilized by such approaches, it is sometimes difficult to address the heterogeneity of nuclei in different tissues. In this work, we propose a hierarchical approach which starts from the lower resolution level and adaptively adjusts the parameters while progressing into finer and finer resolution. The algorithm is tested on brain and lung cancers images from The Cancer Genome Atlas data set.
Digital histopathological images provide detailed spatial information of the tissue at micrometer resolution. Among the available contents in the pathology images, meso-scale information, such as the gland morphology, texture, and distribution, are useful diagnostic features. In this work, focusing on the colon-rectal cancer tissue samples, we propose a multi-scale learning based segmentation scheme for the glands in the colon-rectal digital pathology slides. The algorithm learns the gland and non-gland textures from a set of training images in various scales through a sparse dictionary representation. After the learning step, the dictionaries are used collectively to perform the classification and segmentation for the new image.
Registration of multiple 3D ultrasound sectors in order to provide an extended field of view is important for the appreciation of larger anatomical structures at high spatial and temporal resolution. In this paper, we present a method for fully automatic spatio-temporal registration between two partially overlapping 3D ultrasound sequences. The temporal alignment is solved by aligning the normalized cross correlation-over-time curves of the sequences. For the spatial alignment, corresponding 3D Scale Invariant Feature Transform (SIFT) features are extracted from all frames of both sequences independently of the temporal alignment. A rigid transform is then calculated by least squares minimization in combination with random sample consensus. The method is applied to 16 echocardiographic sequences of the left and right ventricles and evaluated against manually annotated temporal events and spatial anatomical landmarks. The mean distances between manually identified landmarks in the left and right ventricles after automatic registration were (mean ± SD) 4.3 ± 1.2 mm compared to a reference error of 2.8 ± 0.6 mm with manual registration. For the temporal alignment, the absolute errors in valvular event times were 14.4 ± 11.6 ms for Aortic Valve (AV) opening, 18.6 ± 16.0 ms for AV closing, and 34.6 ± 26.4 ms for mitral valve opening, compared to a mean inter-frame time of 29 ms.
PURPOSE: Diffusion encoding with asymmetric gradient waveforms is appealing because the asymmetry provides superior efficiency. However, concomitant gradients may cause a residual gradient moment at the end of the waveform, which can cause significant signal error and image artifacts. The purpose of this study was to develop an asymmetric waveform designs for tensor-valued diffusion encoding that is not sensitive to concomitant gradients. METHODS: The "Maxwell index" was proposed as a scalar invariant to capture the effect of concomitant gradients. Optimization of "Maxwell-compensated" waveforms was performed in which this index was constrained. Resulting waveforms were compared to waveforms from literature, in terms of the measured and predicted impact of concomitant gradients, by numerical analysis as well as experiments in a phantom and in a healthy human brain. RESULTS: Maxwell-compensated waveforms with Maxwell indices below 100 (mT/m) ms showed negligible signal bias in both numerical analysis and experiments. By contrast, several waveforms from literature showed gross signal bias under the same conditions, leading to a signal bias that was large enough to markedly affect parameter maps. Experimental results were accurately predicted by theory. CONCLUSION: Constraining the Maxwell index in the optimization of asymmetric gradient waveforms yields efficient diffusion encoding that negates the effects of concomitant fields while enabling arbitrary shapes of the b-tensor. This waveform design is especially useful in combination with strong gradients, long encoding times, thick slices, simultaneous multi-slice acquisition, and large FOVs.
Although brain functionality is often remarkably robust to lesions and other insults, it may be fragile when these take place in specific locations. Previous attempts to quantify robustness and fragility sought to understand how the functional connectivity of brain networks is affected by structural changes, using either model-based predictions or empirical studies of the effects of lesions. We advance a geometric viewpoint relying on a notion of network curvature, the so-called Ollivier-Ricci curvature. This approach has been proposed to assess financial market robustness and to differentiate biological networks of cancer cells from healthy ones. Here, we apply curvature-based measures to brain structural networks to identify robust and fragile brain regions in healthy subjects. We show that curvature can also be used to track changes in brain connectivity related to age and autism spectrum disorder (ASD), and we obtain results that are in agreement with previous MRI studies.
The Human Placenta Project has focused attention on the need for noninvasive magnetic resonance imaging (MRI)-based techniques to diagnose and monitor placental function throughout pregnancy. The hope is that the management of placenta-related pathologies would be improved if physicians had more direct, real-time measures of placental health to guide clinical decision making. As oxygen alters signal intensity on MRI and oxygen transport is a key function of the placenta, many of the MRI methods under development are focused on quantifying oxygen transport or oxygen content of the placenta. For example, measurements from blood oxygen level-dependent imaging of the placenta during maternal hyperoxia correspond to outcomes in twin pregnancies, suggesting that some aspects of placental oxygen transport can be monitored by MRI. Additional methods are being developed to accurately quantify baseline placental oxygenation by MRI relaxometry. However, direct validation of placental MRI methods is challenging and therefore animal studies and ex vivo studies of human placentas are needed. Here we provide an overview of the current state of the art of oxygen transport and quantification with MRI. We suggest that as these techniques are being developed, increased focus be placed on ensuring they are robust and reliable across individuals and standardized to enable predictive diagnostic models to be generated from the data. The field is still several years away from establishing the clinical benefit of monitoring placental function in real time with MRI, but the promise of individual personalized diagnosis and monitoring of placental disease in real time continues to motivate this effort.
Jie Luo, Alireza Sedghi, Karteek Popuri, Dana Cobzas, Miaomiao Zhang, Frank Preiswerk, Matthew Toews, Alexandra Golby, Masashi Sugiyama, William III M Wells, and Sarah Frisken. 10/2019. “On the Applicability of Registration Uncertainty.” In MICCAI 2019, LNCS 11765: Pp. 410-9. Shenzhen, China: Springer.Abstract
Estimating the uncertainty in (probabilistic) image registration enables, e.g., surgeons to assess the operative risk based on the trustworthiness of the registered image data. If surgeons receive inaccurately calculated registration uncertainty and misplace unwarranted confidence in the alignment solutions, severe consequences may result. For probabilistic image registration (PIR), the predominant way to quantify the registration uncertainty is using summary statistics of the distribution of transformation parameters. The majority of existing research focuses on trying out different summary statistics as well as means to exploit them. Distinctively, in this paper, we study two rarely examined topics: (1) whether those summary statistics of the transformation distribution most informatively represent the registration uncertainty; (2) Does utilizing the registration uncertainty always be beneficial. We show that there are two types of uncertainties: the transformation uncertainty, Ut, and label uncertainty Ul. The conventional way of using Ut to quantify Ul is inappropriate and can be misleading. By a real data experiment, we also share a potentially critical finding that making use of the registration uncertainty may not always be an improvement.
External-beam radiotherapy followed by high dose rate (HDR) brachytherapy is the standard-of-care for treating gynecologic cancers. The enhanced soft-tissue contrast provided by magnetic resonance imaging (MRI) makes it a valuable imaging modality for diagnosing and treating these cancers. However, in contrast to computed tomography (CT) imaging, the appearance of the brachytherapy catheters, through which radiation sources are inserted to reach the cancerous tissue later on, is often variable across images. This paper reports, for the first time, a new deep-learning-based method for fully automatic segmentation of multiple closely spaced brachytherapy catheters in intraoperative MRI. Represented in the data are 50 gynecologic cancer patients treated by MRI-guided HDR brachytherapy. For each patient, a single intraoperative MRI was used. 826 catheters in the images were manually segmented by an expert radiation physicist who is also a trained radiation oncologist. The number of catheters in a patient ranged between 10 and 35. A deep 3D convolutional neural network (CNN) model was developed and trained. In order to make the learning process more robust, the network was trained 5 times, each time using a different combination of shown patients. Finally, each test case was processed by the five networks and the final segmentation was generated by voting on the obtained five candidate segmentations. 4-fold validation was executed and all the patients were segmented. An average distance error of 2.0 ± 3.4 mm was achieved. False positive and false negative catheters were 6.7% and 1.5% respectively. Average Dice score was equal to 0.60 ± 0.17. The algorithm is available for use in the open source software platform 3D Slicer allowing for wide scale testing and research discussion. In conclusion, to the best of our knowledge, fully automatic segmentation of multiple closely spaced catheters from intraoperative MR images was achieved for the first time in gynecological brachytherapy.