Improved segmentation of white matter tracts with adaptive Riemannian metrics

Fibre orientation atlas guided rapid segmentation of white matter tracts

Fibre tract delineation from diffusion magnetic resonance imaging (MRI) is a valuable clinical tool for neurosurgical planning and navigation, as well as in research neuroimaging pipelines. Several popular methods are used for this task, each with different strengths and weaknesses making them more or less suited to different contexts. For neurosurgical imaging, priorities include ease of use, computational efficiency, robustness to pathology and ability to generalise to new tracts of interest. Many existing methods use streamline tractography, which may require expert neuroimaging operators for setting parameters and delineating anatomical regions of interest, or suffer from as a lack of generalisability to clinical scans involving deforming tumours and other pathologies. More recently, data-driven approaches including deep-learning segmentation models and streamline clustering methods have improved reproducibility and automation, although they can require large amounts of training data and/or computationally intensive image processing at the point of application. We describe an atlas-based direct tract mapping technique called 'tractfinder', utilising tract-specific location and orientation priors. Our aim was to develop a clinically practical method avoiding streamline tractography at the point of application while utilising prior anatomical knowledge derived from only 10-20 training samples. Requiring few training samples allows emphasis to be placed on producing high quality, neuro-anatomically accurate training data, and enables rapid adaptation to new tracts of interest. Avoiding streamline tractography at the point of application reduces computational time, false positives and vulnerabilities to pathology such as tumour deformations or oedema. Carefully filtered training streamlines and track orientation distribution mapping are used to construct tract specific orientation and spatial probability atlases in standard space. Atlases are then transformed to target subject space using affine registration and compared with the subject's voxel-wise fibre orientation distribution data using a mathematical measure of distribution overlap, resulting in a map of the tract's likely spatial distribution. This work includes extensive performance evaluation and comparison with benchmark techniques, including streamline tractography and the deep-learning method TractSeg, in two publicly available healthy diffusion MRI datasets (from TractoInferno and the Human Connectome Project) in addition to a clinical dataset comprising paediatric and adult brain tumour scans. Tract segmentation results display high agreement with established techniques while requiring less than 3 min on average when applied to a new subject. Results also display higher robustness than compared methods when faced with clinical scans featuring brain tumours and resections. As well as describing and evaluating a novel proposed tract delineation technique, this work continues the discussion on the challenges surrounding the white matter segmentation task, including issues of anatomical definitions and the use of quantitative segmentation comparison metrics.

Geodesic fiber tracking in white matter using activation function

BACKGROUND AND OBJECTIVE

The geodesic ray-tracing method has shown its effectiveness for the reconstruction of fibers in white matter structure. Based on reasonable metrics on the spaces of the diffusion tensors, it can provide multiple solutions and get robust to noise and curvatures of fibers. The choice of the metric on the spaces of diffusion tensors has a significant impact on the outcome of this method. Our objective is to suggest metrics and modifications of the algorithms leading to more satisfactory results in the construction of white matter tracts as geodesics.

METHODS

Starting with the DTI modality, we propose to rescale the initially chosen metric on the space of diffusion tensors to increase the geodetic cost in the isotropic regions. This change should be conformal in order to preserve the angles between crossing fibers. We also suggest to enhance the methods to be more robust to noise and to employ the fourth order tensor data in order to handle the fiber crossings properly.

RESULTS

We propose a way to choose the appropriate conformal class of metrics where the metric gets scaled according to tensor anisotropy. We use the logistic functions, which are commonly used in statistics as cumulative distribution functions. To prevent deviation of geodesics from the actual paths, we propose a hybrid ray-tracing approach. Furthermore, we suggest how to employ diagonal projections of 4th order tensors to perform fiber tracking in crossing regions.

CONCLUSIONS

The algorithms based on the newly suggested methods were succesfuly implemented, their performance was tested on both synthetic and real data, and compared to some of the previously known approaches.

TractLearn: A geodesic learning framework for quantitative analysis of brain bundles

Deep learning-based convolutional neural networks have recently proved their efficiency in providing fast segmentation of major brain fascicles structures, based on diffusion-weighted imaging. The quantitative analysis of brain fascicles then relies on metrics either coming from the tractography process itself or from each voxel along the bundle. Statistical detection of abnormal voxels in the context of disease usually relies on univariate and multivariate statistics models, such as the General Linear Model (GLM). Yet in the case of high-dimensional low sample size data, the GLM often implies high standard deviation range in controls due to anatomical variability, despite the commonly used smoothing process. This can lead to difficulties to detect subtle quantitative alterations from a brain bundle at the voxel scale. Here we introduce TractLearn, a unified framework for brain fascicles quantitative analyses by using geodesic learning as a data-driven learning task. TractLearn allows a mapping between the image high-dimensional domain and the reduced latent space of brain fascicles using a Riemannian approach. We illustrate the robustness of this method on a healthy population with test-retest acquisition of multi-shell diffusion MRI data, demonstrating that it is possible to separately study the global effect due to different MRI sessions from the effect of local bundle alterations. We have then tested the efficiency of our algorithm on a sample of 5 age-matched subjects referred with mild traumatic brain injury. Our contributions are to propose: 1/ A manifold approach to capture controls variability as standard reference instead of an atlas approach based on a Euclidean mean. 2/ A tool to detect global variation of voxels' quantitative values, which accounts for voxels' interactions in a structure rather than analyzing voxels independently. 3/ A ready-to-plug algorithm to highlight nonlinear variation of diffusion MRI metrics. With this regard, TractLearn is a ready-to-use algorithm for precision medicine.

Fully automatic catheter segmentation in MRI with 3D convolutional neural networks: application to MRI-guided gynecologic brachytherapy

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.

White Matter Segmentation Algorithm for DTI Images Based on Super-Pixel Full Convolutional Network

Diffusion tensor imaging (DTI) is a new imaging method that can be used to non-invasively measure the diffusion coefficient of water molecules in biological tissue structures in recent years. Since the DTI data is a tensor space, its segmentation is different from ordinary MRI images. Based on the existing deep learning model, an improved image semantic segmentation method based on super-pixels and conditional random field is proposed. Firstly, this paper uses the existing feature extraction model based on deep learning to obtain rough semantic segmentation results, including high-level semantic information of the image but lacking details of the image. In addition, the super-pixel segmentation algorithm is implemented to obtain super-pixels that carries more low-level information. Secondly, due to the lack of image details in rough segmentation results, the segmentation of the edge of the image is inaccurate. In this paper, a boundary optimization algorithm is proposed to optimize the edge segmentation accuracy of the rough results. Finally, the use of super-pixels for local boundary optimization can improve the segmentation accuracy. Experiments results show that this segment is a practical and effective method.

Automatic Needle Segmentation and Localization in MRI With 3-D Convolutional Neural Networks: Application to MRI-Targeted Prostate Biopsy

Image guidance improves tissue sampling during biopsy by allowing the physician to visualize the tip and trajectory of the biopsy needle relative to the target in MRI, CT, ultrasound, or other relevant imagery. This paper reports a system for fast automatic needle tip and trajectory localization and visualization in MRI that has been developed and tested in the context of an active clinical research program in prostate biopsy. To the best of our knowledge, this is the first reported system for this clinical application and also the first reported system that leverages deep neural networks for segmentation and localization of needles in MRI across biomedical applications. Needle tip and trajectory were annotated on 583 T2-weighted intra-procedural MRI scans acquired after needle insertion for 71 patients who underwent transperineal MRI-targeted biopsy procedure at our institution. The images were divided into two independent training-validation and test sets at the patient level. A deep 3-D fully convolutional neural network model was developed, trained, and deployed on these samples. The accuracy of the proposed method, as tested on previously unseen data, was 2.80-mm average in needle tip detection and 0.98° in needle trajectory angle. An observer study was designed in which independent annotations by a second observer, blinded to the original observer, were compared with the output of the proposed method. The resultant error was comparable to the measured inter-observer concordance, reinforcing the clinical acceptability of the proposed method. The proposed system has the potential for deployment in clinical routine.

Accurate model-based segmentation of gynecologic brachytherapy catheter collections in MRI-images

The gynecological cancer mortality rate, including cervical, ovarian, vaginal and vulvar cancers, is more than 20,000 annually in the US alone. In many countries, including the US, external-beam radiotherapy followed by high dose rate brachytherapy is the standard-of-care. The superior ability of MR to visualize soft tissue has led to an increase in its usage in planning and delivering brachytherapy treatment. A technical challenge associated with the use of MRI imaging for brachytherapy, in contrast to that of CT imaging, is the visualization of catheters that are used to place radiation sources into cancerous tissue. We describe here a precise, accurate method for achieving catheter segmentation and visualization. The algorithm, with the assistance of manually provided tip locations, performs segmentation using image-features, and is guided by a catheter-specific, estimated mechanical model. A final quality control step removes outliers or conflicting catheter trajectories. The mean Hausdorff error on a 54 patient, 760 catheter reference database was 1.49  mm; 51 of the outliers deviated more than two catheter widths (3.4  mm) from the gold standard, corresponding to catheter identification accuracy of 93% in a Syed-Neblett template. In a multi-user simulation experiment for evaluating RMS precision by simulating varying manually-provided superior tip positions, 3σ maximum errors were 2.44  mm. The average segmentation time for a single catheter was 3 s on a standard PC. The segmentation time, accuracy and precision, are promising indicators of the value of this method for clinical translation of MR-guidance in gynecologic brachytherapy and other catheter-based interventional procedures.

Bayesian Tractography Using Geometric Shape Priors

The problem of estimating neuronal fiber tracts connecting different brain regions is important for various types of brain studies, including understanding brain functionality and diagnosing cognitive impairments. The popular techniques for tractography are mostly sequential—tracts are grown sequentially following principal directions of local water diffusion profiles. Despite several advancements on this basic idea, the solutions easily get stuck in local solutions, and can't incorporate global shape information. We present a global approach where fiber tracts between regions of interest are initialized and updated via deformations based on gradients of a posterior energy. This energy has contributions from diffusion data, global shape models, and roughness penalty. The resulting tracts are relatively immune to issues such as tensor noise and fiber crossings, and achieve more interpretable tractography results. We demonstrate this framework using both simulated and real dMRI and HARDI data.

Surface-based vertexwise analysis of morphometry and microstructural integrity for white matter tracts in diffusion tensor imaging: With application to the corpus callosum in Alzheimer's disease

In this article, we present a unified statistical pipeline for analyzing the white matter (WM) tracts morphometry and microstructural integrity, both globally and locally within the same WM tract, from diffusion tensor imaging. Morphometry is quantified globally by the volumetric measurement and locally by the vertexwise surface areas. Meanwhile, microstructural integrity is quantified globally by the mean fractional anisotropy (FA) and trace values within the specific WM tract and locally by the FA and trace values defined at each vertex of its bounding surface. The proposed pipeline consists of four steps: (1) fully automated segmentation of WM tracts in a multi-contrast multi-atlas framework; (2) generation of the smooth surface representations for the WM tracts of interest; (3) common template surface generation on which the localized morphometric and microstructural statistics are defined and a variety of statistical analyses can be conducted; (4) multiple comparison correction to determine the significance of the statistical analysis results. Detailed herein, this pipeline has been applied to the corpus callosum in Alzheimer's disease (AD) with significantly decreased FA values and increased trace values, both globally and locally, being detected in patients with AD when compared to normal aging populations. A subdivision of the corpus callosum in both hemispheres revealed that the AD pathology primarily affects the body and splenium of the corpus callosum. Validation analyses and two multiple comparison correction strategies are provided. Hum Brain Mapp 38:1875-1893, 2017. © 2017 Wiley Periodicals, Inc.

Quality Assurance using Outlier Detection on an Automatic Segmentation Method for the Cerebellar Peduncles

Cerebellar peduncles (CPs) are white matter tracts connecting the cerebellum to other brain regions. Automatic segmentation methods of the CPs have been proposed for studying their structure and function. Usually the performance of these methods is evaluated by comparing segmentation results with manual delineations (ground truth). However, when a segmentation method is run on new data (for which no ground truth exists) it is highly desirable to efficiently detect and assess algorithm failures so that these cases can be excluded from scientific analysis. In this work, two outlier detection methods aimed to assess the performance of an automatic CP segmentation algorithm are presented. The first one is a univariate non-parametric method using a box-whisker plot. We first categorize automatic segmentation results of a dataset of diffusion tensor imaging (DTI) scans from 48 subjects as either a success or a failure. We then design three groups of features from the image data of nine categorized failures for failure detection. Results show that most of these features can efficiently detect the true failures. The second method-supervised classification-was employed on a larger DTI dataset of 249 manually categorized subjects. Four classifiers-linear discriminant analysis (LDA), logistic regression (LR), support vector machine (SVM), and random forest classification (RFC)-were trained using the designed features and evaluated using a leave-one-out cross validation. Results show that the LR performs worst among the four classifiers and the other three perform comparably, which demonstrates the feasibility of automatically detecting segmentation failures using classification methods.

Segmentation of the Cerebellar Peduncles Using a Random Forest Classifier and a Multi-object Geometric Deformable Model: Application to Spinocerebellar Ataxia Type 6

The cerebellar peduncles, comprising the superior cerebellar peduncles (SCPs), the middle cerebellar peduncle (MCP), and the inferior cerebellar peduncles (ICPs), are white matter tracts that connect the cerebellum to other parts of the central nervous system. Methods for automatic segmentation and quantification of the cerebellar peduncles are needed for objectively and efficiently studying their structure and function. Diffusion tensor imaging (DTI) provides key information to support this goal, but it remains challenging because the tensors change dramatically in the decussation of the SCPs (dSCP), the region where the SCPs cross. This paper presents an automatic method for segmenting the cerebellar peduncles, including the dSCP. The method uses volumetric segmentation concepts based on extracted DTI features. The dSCP and noncrossing portions of the peduncles are modeled as separate objects, and are initially classified using a random forest classifier together with the DTI features. To obtain geometrically correct results, a multi-object geometric deformable model is used to refine the random forest classification. The method was evaluated using a leave-one-out cross-validation on five control subjects and four patients with spinocerebellar ataxia type 6 (SCA6). It was then used to evaluate group differences in the peduncles in a population of 32 controls and 11 SCA6 patients. In the SCA6 group, we have observed significant decreases in the volumes of the dSCP and the ICPs and significant increases in the mean diffusivity in the noncrossing SCPs, the MCP, and the ICPs. These results are consistent with a degeneration of the cerebellar peduncles in SCA6 patients.

Adaptive distance metric learning for diffusion tensor image segmentation

High quality segmentation of diffusion tensor images (DTI) is of key interest in biomedical research and clinical application. In previous studies, most efforts have been made to construct predefined metrics for different DTI segmentation tasks. These methods require adequate prior knowledge and tuning parameters. To overcome these disadvantages, we proposed to automatically learn an adaptive distance metric by a graph based semi-supervised learning model for DTI segmentation. An original discriminative distance vector was first formulated by combining both geometry and orientation distances derived from diffusion tensors. The kernel metric over the original distance and labels of all voxels were then simultaneously optimized in a graph based semi-supervised learning approach. Finally, the optimization task was efficiently solved with an iterative gradient descent method to achieve the optimal solution. With our approach, an adaptive distance metric could be available for each specific segmentation task. Experiments on synthetic and real brain DTI datasets were performed to demonstrate the effectiveness and robustness of the proposed distance metric learning approach. The performance of our approach was compared with three classical metrics in the graph based semi-supervised learning framework.