Deep white matter analysis (DeepWMA): Fast and consistent tractography segmentation

Anat-SFSeg: Anatomically-guided superficial fiber segmentation with point-cloud deep learning

Diffusion magnetic resonance imaging (dMRI) tractography is a critical technique to map the brain's structural connectivity. Accurate segmentation of white matter, particularly the superficial white matter (SWM), is essential for neuroscience and clinical research. However, it is challenging to segment SWM due to the short adjacent gyri connection in a U-shaped pattern. In this work, we propose an Anatomically-guided Superficial Fiber Segmentation (Anat-SFSeg) framework to improve the performance on SWM segmentation. The framework consists of a unique fiber anatomical descriptor (named FiberAnatMap) and a deep learning network based on point-cloud data. The spatial coordinates of fibers represented as point clouds, as well as the anatomical features at both the individual and group levels, are fed into a neural network. The network is trained on Human Connectome Project (HCP) datasets and tested on the subjects with a range of cognitive impairment levels. One new metric named fiber anatomical region proportion (FARP), quantifies the ratio of fibers in the defined brain regions and enables the comparison with other methods. Another metric named anatomical region fiber count (ARFC), represents the average fiber number in each cluster for the assessment of inter-subject differences. The experimental results demonstrate that Anat-SFSeg achieves the highest accuracy on HCP datasets and exhibits great generalization on clinical datasets. Diffusion tensor metrics and ARFC show disorder severity associated alterations in patients with Alzheimer's disease (AD) and mild cognitive impairments (MCI). Correlations with cognitive grades show that these metrics are potential neuroimaging biomarkers for AD. Furthermore, Anat-SFSeg could be utilized to explore other neurodegenerative, neurodevelopmental or psychiatric disorders.

Individual differences of white matter characteristic along the anterior insula-based fiber tract circuit for pain empathy in healthy women and women with primary dysmenorrhea

Pain empathy, defined as the ability of one person to understand another person's pain, shows large individual variations. The anterior insula is the core region of the pain empathy network. However, the relationship between white matter (WM) properties of the fiber tracts connecting the anterior insula with other cortical regions and an individual's ability to modulate pain empathy remains largely unclear. In this study, we outline an automatic seed-based fiber streamline (sFS) analysis method and multivariate pattern analysis (MVPA) to predict the levels of pain empathy in healthy women and women with primary dysmenorrhoea (PDM). Using the sFS method, the anterior insula-based fiber tract network was divided into five fiber cluster groups. In healthy women, interindividual differences in pain empathy were predicted only by the WM properties of the five fiber cluster groups, suggesting that interindividual differences in pain empathy may rely on the connectivity of the anterior insula-based fiber tract network. In women with PDM, pain empathy could be predicted by a single cluster group. The mean WM properties along the anterior insular-rostroventral area of the inferior parietal lobule further mediated the effect of pain on empathy in patients with PDM. Our results suggest that chronic periodic pain may lead to maladaptive plastic changes, which could further impair empathy by making women with PDM feel more pain when they see other people experiencing pain. Our study also addresses an important gap in the analysis of the microstructural characteristics of seed-based fiber tract network.

Blurred streamlines: A novel representation to reduce redundancy in tractography

Tractography is a powerful tool to study brain connectivity in vivo, but it is well known to suffer from an intrinsic trade-off between sensitivity and specificity. A critical - but usually underrated - parameter to choose that can heavily impact the quality of the estimates is the number of streamlines to be reconstructed for a given data set. In fact, sensitivity can be improved by generating more and more streamlines, as all real anatomical connections are likely reconstructed, but lots of false positives are inevitably introduced, too. Consequently, so-called tractography filtering techniques have become increasingly popular to get rid of these false positives and improve specificity. However, increasing number of streamlines introduces redundancy in tractography reconstructions, which may negatively impact the performance of filtering algorithms, especially those based on linear formulations. To address this problem, we introduce a novel streamlines representation, called "blurred streamlines", which drastically reduces the redundancy among streamlines by (i) clustering similar trajectories and (ii) spatially blurring the corresponding signal contributions. We tested the effectiveness of the blurred streamlines both on synthetic and in vivo data. Our results clearly show that this new representation is as accurate as state-of-the-art methods despite using only 5% of the input streamlines, thus significantly decreasing the computational complexity of filtering algorithms as well as storage requirements of the resulting reconstructions.

A systematic review of automated methods to perform white matter tract segmentation

White matter tract segmentation is a pivotal research area that leverages diffusion-weighted magnetic resonance imaging (dMRI) for the identification and mapping of individual white matter tracts and their trajectories. This study aims to provide a comprehensive systematic literature review on automated methods for white matter tract segmentation in brain dMRI scans. Articles on PubMed, ScienceDirect [NeuroImage, NeuroImage (Clinical), Medical Image Analysis], Scopus and IEEEXplore databases and Conference proceedings of Medical Imaging Computing and Computer Assisted Intervention Society (MICCAI) and International Symposium on Biomedical Imaging (ISBI), were searched in the range from January 2013 until September 2023. This systematic search and review identified 619 articles. Adhering to the specified search criteria using the query, "white matter tract segmentation OR fiber tract identification OR fiber bundle segmentation OR tractography dissection OR white matter parcellation OR tract segmentation," 59 published studies were selected. Among these, 27% employed direct voxel-based methods, 25% applied streamline-based clustering methods, 20% used streamline-based classification methods, 14% implemented atlas-based methods, and 14% utilized hybrid approaches. The paper delves into the research gaps and challenges associated with each of these categories. Additionally, this review paper illuminates the most frequently utilized public datasets for tract segmentation along with their specific characteristics. Furthermore, it presents evaluation strategies and their key attributes. The review concludes with a detailed discussion of the challenges and future directions in this field.

Superficial white matter microstructural imaging method based on time-space fractional-order diffusion

Objective. Microstructure imaging based on diffusion magnetic resonance signal is an advanced imaging technique that enablesin vivomapping of the brain's microstructure. Superficial white matter (SWM) plays an important role in brain development, maturation, and aging, while fewer microstructure imaging methods address the SWM due to its complexity. Therefore, this study aims to develop a diffusion propagation model to investigate the microstructural characteristics of the SWM region.Approach. In this paper, we hypothesize that the effect of cell membrane permeability and the water exchange between soma and dendrites cannot be neglected for typical clinical diffusion times (20 ms Collapse

Key Words

• anomalous diffusion
• diffusion magnetic resonance imaging
• fractional diffusion equation
• microstructure imaging
• superficial white matter

Collapse

MESH Headings Collapse

Grants Collapse

Affiliation(s)

Jianglin He School of Health Science and Engineering, University of Shanghai for Science and Technology, Shanghai 200093, People's Republic of China
Yuanjun Wang School of Health Science and Engineering, University of Shanghai for Science and Technology, Shanghai 200093, People's Republic of China

Collapse

A, Hernandez Larzabal H, Román C, Poupon C, Mangin JF, Hernández C, Guevara P. Phybers: a package for brain tractography analysis

We present a Python library (Phybers) for analyzing brain tractography data. Tractography datasets contain streamlines (also called fibers) composed of 3D points representing the main white matter pathways. Several algorithms have been proposed to analyze this data, including clustering, segmentation, and visualization methods. The manipulation of tractography data is not straightforward due to the geometrical complexity of the streamlines, the file format, and the size of the datasets, which may contain millions of fibers. Hence, we collected and structured state-of-the-art methods for the analysis of tractography and packed them into a Python library, to integrate and share tools for tractography analysis. Due to the high computational requirements, the most demanding modules were implemented in C/C++. Available functions include brain Bundle Segmentation (FiberSeg), Hierarchical Fiber Clustering (HClust), Fast Fiber Clustering (FFClust), normalization to a reference coordinate system, fiber sampling, calculation of intersection between sets of brain fibers, tools for cluster filtering, calculation of measures from clusters, and fiber visualization. The library tools were structured into four principal modules: Segmentation, Clustering, Utils, and Visualization (Fibervis). Phybers is freely available on a GitHub repository under the GNU public license for non-commercial use and open-source development, which provides sample data and extensive documentation. In addition, the library can be easily installed on both Windows and Ubuntu operating systems through the pip library.

DDParcel: Deep Learning Anatomical Brain Parcellation From Diffusion MRI

Parcellation of anatomically segregated cortical and subcortical brain regions is required in diffusion MRI (dMRI) analysis for region-specific quantification and better anatomical specificity of tractography. Most current dMRI parcellation approaches compute the parcellation from anatomical MRI (T1- or T2-weighted) data, using tools such as FreeSurfer or CAT12, and then register it to the diffusion space. However, the registration is challenging due to image distortions and low resolution of dMRI data, often resulting in mislabeling in the derived brain parcellation. Furthermore, these approaches are not applicable when anatomical MRI data is unavailable. As an alternative we developed the Deep Diffusion Parcellation (DDParcel), a deep learning method for fast and accurate parcellation of brain anatomical regions directly from dMRI data. The input to DDParcel are dMRI parameter maps and the output are labels for 101 anatomical regions corresponding to the FreeSurfer Desikan-Killiany (DK) parcellation. A multi-level fusion network leverages complementary information in the different input maps, at three network levels: input, intermediate layer, and output. DDParcel learns the registration of diffusion features to anatomical MRI from the high-quality Human Connectome Project data. Then, to predict brain parcellation for a new subject, the DDParcel network no longer requires anatomical MRI data but only the dMRI data. Comparing DDParcel's parcellation with T1w-based parcellation shows higher test-retest reproducibility and a higher regional homogeneity, while requiring much less computational time. Generalizability is demonstrated on a range of populations and dMRI acquisition protocols. Utility of DDParcel's parcellation is demonstrated on tractography analysis for fiber tract identification.

Harmonized diffusion MRI data and white matter measures from the Adolescent Brain Cognitive Development Study

The Adolescent Brain Cognitive Development (ABCD) Study® has collected data from over 10,000 children across 21 sites, providing insights into adolescent brain development. However, site-specific scanner variability has made it challenging to use diffusion MRI (dMRI) data from this study. To address this, a dataset of harmonized and processed ABCD dMRI data (from release 3) has been created, comprising quality-controlled imaging data from 9,345 subjects, focusing exclusively on the baseline session, i.e., the first time point of the study. This resource required substantial computational time (approx. 50,000 CPU hours) for harmonization, whole-brain tractography, and white matter parcellation. The dataset includes harmonized dMRI data, 800 white matter clusters, 73 anatomically labeled white matter tracts in full and low resolution, and 804 different dMRI-derived measures per subject (72.3 TB total size). Accessible via the NIMH Data Archive, it offers a large-scale dMRI dataset for studying structural connectivity in child and adolescent neurodevelopment. Additionally, several post-harmonization experiments were conducted to demonstrate the success of the harmonization process on the ABCD dataset.

Tractography-based automated identification of the retinogeniculate visual pathway with novel microstructure-informed supervised contrastive learning

The retinogeniculate visual pathway (RGVP) is responsible for carrying visual information from the retina to the lateral geniculate nucleus. Identification and visualization of the RGVP are important in studying the anatomy of the visual system and can inform the treatment of related brain diseases. Diffusion MRI (dMRI) tractography is an advanced imaging method that uniquely enables in vivo mapping of the 3D trajectory of the RGVP. Currently, identification of the RGVP from tractography data relies on expert (manual) selection of tractography streamlines, which is time-consuming, has high clinical and expert labor costs, and is affected by inter-observer variability. In this paper, we present a novel deep learning framework, DeepRGVP , to enable fast and accurate identification of the RGVP from dMRI tractography data. We design a novel microstructure-informed supervised contrastive learning method that leverages both streamline label and tissue microstructure information to determine positive and negative pairs. We propose a simple and successful streamline-level data augmentation method to address highly imbalanced training data, where the number of RGVP streamlines is much lower than that of non-RGVP streamlines. We perform comparisons with several state-of-the-art deep learning methods that were designed for tractography parcellation, and we show superior RGVP identification results using DeepRGVP. In addition, we demonstrate a good generalizability of DeepRGVP to dMRI tractography data from neurosurgical patients with pituitary tumors and we show DeepRGVP can successfully identify RGVPs despite the effect of lesions affecting the RGVPs. Overall, our study shows the high potential of using deep learning to automatically identify the RGVP.

One-shot segmentation of novel white matter tracts via extensive data augmentation and adaptive knowledge transfer

The use of convolutional neural networks (CNNs) has allowed accurate white matter (WM) tract segmentation on diffusion magnetic resonance imaging (dMRI). To train the CNN-based segmentation models, a large number of scans on which WM tracts are annotated need to be collected, and these annotated scans can be accumulated over a long period of time. However, when novel WM tracts that are different from existing annotated WM tracts are of interest, additional annotations are required for their segmentation. Due to the cost of manual annotations, methods have been developed for few-shot segmentation of novel WM tracts, where the segmentation knowledge is transferred from existing WM tracts to novel WM tracts and the amount of annotated data for novel WM tracts is reduced. Despite these developments, it is desirable to further reduce the amount of annotated data to the one-shot setting with a single annotated image. To address this problem, we develop an approach to one-shot segmentation of novel WM tracts. Our method follows the existing pretraining/fine-tuning framework that transfers segmentation knowledge from existing to novel WM tracts. First, as there is extremely scarce annotated data in the one-shot setting, we design several different data augmentation strategies so that extensive data augmentation can be performed to obtain extra synthetic training data. The data augmentation strategies are based on image masking and thus applicable to the one-shot setting. Second, to address overfitting and knowledge forgetting in the fine-tuning stage that can be more severe given limited training data, we propose an adaptive knowledge transfer strategy that selects the network weights to be updated. The data augmentation and adaptive knowledge transfer strategies are combined to train the segmentation model. Considering that the different data augmentation strategies can generate synthetic data that contain potentially conflicting information, we apply the data augmentation strategies separately, each leading to a different segmentation model. The results predicted by the different models are fused to produce the final segmentation. We validated our method on two brain dMRI datasets, including a public dataset and an in-house dataset. Different settings were considered for the validation, and the results show that the proposed method improves the one-shot segmentation of novel WM tracts.

Supervised tractogram filtering using Geometric Deep Learning

A tractogram is a virtual representation of the brain white matter. It is composed of millions of virtual fibers, encoded as 3D polylines, which approximate the white matter axonal pathways. To date, tractograms are the most accurate white matter representation and thus are used for tasks like presurgical planning and investigations of neuroplasticity, brain disorders, or brain networks. However, it is a well-known issue that a large portion of tractogram fibers is not anatomically plausible and can be considered artifacts of the tracking procedure. With Verifyber, we tackle the problem of filtering out such non-plausible fibers using a novel fully-supervised learning approach. Differently from other approaches based on signal reconstruction and/or brain topology regularization, we guide our method with the existing anatomical knowledge of the white matter. Using tractograms annotated according to anatomical principles, we train our model, Verifyber, to classify fibers as either anatomically plausible or non-plausible. The proposed Verifyber model is an original Geometric Deep Learning method that can deal with variable size fibers, while being invariant to fiber orientation. Our model considers each fiber as a graph of points, and by learning features of the edges between consecutive points via the proposed sequence Edge Convolution, it can capture the underlying anatomical properties. The output filtering results highly accurate and robust across an extensive set of experiments, and fast; with a 12GB GPU, filtering a tractogram of 1M fibers requires less than a minute.

Reconstructing the somatotopic organization of the corticospinal tract remains a challenge for modern tractography methods

The corticospinal tract (CST) is a critically important white matter fiber tract in the human brain that enables control of voluntary movements of the body. The CST exhibits a somatotopic organization, which means that the motor neurons that control specific body parts are arranged in order within the CST. Diffusion magnetic resonance imaging (MRI) tractography is increasingly used to study the anatomy of the CST. However, despite many advances in tractography algorithms over the past decade, modern, state-of-the-art methods still face challenges. In this study, we compare the performance of six widely used tractography methods for reconstructing the CST and its somatotopic organization. These methods include constrained spherical deconvolution (CSD) based probabilistic (iFOD1) and deterministic (SD-Stream) methods, unscented Kalman filter (UKF) tractography methods including multi-fiber (UKF2T) and single-fiber (UKF1T) models, the generalized q-sampling imaging (GQI) based deterministic tractography method, and the TractSeg method. We investigate CST somatotopy by dividing the CST into four subdivisions per hemisphere that originate in the leg, trunk, hand, and face areas of the primary motor cortex. A quantitative and visual comparison is performed using diffusion MRI data (N = 100 subjects) from the Human Connectome Project. Quantitative evaluations include the reconstruction rate of the eight anatomical subdivisions, the percentage of streamlines in each subdivision, and the coverage of the white matter-gray matter (WM-GM) interface. CST somatotopy is further evaluated by comparing the percentage of streamlines in each subdivision to the cortical volumes for the leg, trunk, hand, and face areas. Overall, UKF2T has the highest reconstruction rate and cortical coverage. It is the only method with a significant positive correlation between the percentage of streamlines in each subdivision and the volume of the corresponding motor cortex. However, our experimental results show that all compared tractography methods are biased toward generating many trunk streamlines (ranging from 35.10% to 71.66% of total streamlines across methods). Furthermore, the coverage of the WM-GM interface in the largest motor area (face) is generally low (under 40%) for all compared tractography methods. Different tractography methods give conflicting results regarding the percentage of streamlines in each subdivision and the volume of the corresponding motor cortex, indicating that there is generally no clear relationship, and that reconstruction of CST somatotopy is still a large challenge. Overall, we conclude that while current tractography methods have made progress toward the well-known challenge of improving the reconstruction of the lateral projections of the CST, the overall problem of performing a comprehensive CST reconstruction, including clinically important projections in the lateral (hand and face areas) and medial portions (leg area), remains an important challenge for diffusion MRI tractography.

FASSt : Filtering via Symmetric Autoencoder for Spherical Superficial White Matter Tractography

Superficial white matter (SWM) plays an important role in functioning of the human brain, and it contains a large amount of cortico-cortical connections. However, the difficulties of generating complete and reliable U-fibers make SWM-related analysis lag behind relatively matured Deep white matter (DWM) analysis. With the aid of some newly proposed surface-based SWM tractography algorithms, we have developed a specialized SWM filtering method based on a symmetric variational autoencoder (VAE). In this work, we first demonstrate the advantage of the spherical representation and generate these spherical tracts using the triangular mesh and the registered spherical surface. We then introduce the Filtering via symmetric Autoencoder for Spherical Superficial White Matter tractography (FASSt) framework with a novel symmetric weights module to perform the filtering task in a latent space. We evaluate and compare our method with the state-of-the-art clustering-based method on diffusion MRI data from Human Connectome Project (HCP). The results show that our proposed method outperform these clustering methods and achieves excellent performance in groupwise consistency and topographic regularity.

Assessing informative tract segmentation and nTMS for pre-operative planning

BACKGROUND

Deep learning-based (DL) methods are the best-performing methods for white matter tract segmentation in anatomically healthy subjects. However, tract annotations are variable or absent in clinical data and manual annotations are especially difficult in patients with tumors where normal anatomy may be distorted. Direct cortical and subcortical stimulation is the gold standard ground truth to determine the cortical and sub-cortical lo- cation of motor-eloquent areas intra-operatively. Nonetheless, this technique is invasive, prolongs the surgical procedure, and may cause patient fatigue. Navigated Transcranial Magnetic Stimulation (nTMS) has a well-established correlation to direct cortical stimulation for motor mapping and the added advantage of being able to be acquired pre-operatively.

NEW METHOD

In this work, we evaluate the feasibility of using nTMS motor responses as a method to assess corticospinal tract (CST) binary masks and estimated uncertainty generated by a DL-based tract segmentation in patients with diffuse gliomas.

RESULTS

Our results show CST binary masks have a high overlap coefficient (OC) with nTMS response masks. A strong negative correlation is found between estimated uncertainty and nTMS response mask distance to the CST binary mask.

COMPARISON WITH EXISTING METHODS

We compare our approach (UncSeg) with the state-of-the-art TractSeg in terms of OC between the CST binary masks and nTMS response masks.

CONCLUSIONS

In this study, we demonstrate that estimated uncertainty from UncSeg is a good measure of the agreement between the CST binary masks and nTMS response masks distance to the CST binary mask boundary.

Deep Learning Methods for Identification of White Matter Fiber Tracts: Review of State-of-the-Art and Future Prospective

Quantitative analysis of white matter fiber tracts from diffusion Magnetic Resonance Imaging (dMRI) data is of great significance in health and disease. For example, analysis of fiber tracts related to anatomically meaningful fiber bundles is highly demanded in pre-surgical and treatment planning, and the surgery outcome depends on accurate segmentation of the desired tracts. Currently, this process is mainly done through time-consuming manual identification performed by neuro-anatomical experts. However, there is a broad interest in automating the pipeline such that it is fast, accurate, and easy to apply in clinical settings and also eliminates the intra-reader variabilities. Following the advancements in medical image analysis using deep learning techniques, there has been a growing interest in using these techniques for the task of tract identification as well. Recent reports on this application show that deep learning-based tract identification approaches outperform existing state-of-the-art methods. This paper presents a review of current tract identification approaches based on deep neural networks. First, we review the recent deep learning methods for tract identification. Next, we compare them with respect to their performance, training process, and network properties. Finally, we end with a critical discussion of open challenges and possible directions for future works.

Deep fiber clustering: Anatomically informed fiber clustering with self-supervised deep learning for fast and effective tractography parcellation

White matter fiber clustering is an important strategy for white matter parcellation, which enables quantitative analysis of brain connections in health and disease. In combination with expert neuroanatomical labeling, data-driven white matter fiber clustering is a powerful tool for creating atlases that can model white matter anatomy across individuals. While widely used fiber clustering approaches have shown good performance using classical unsupervised machine learning techniques, recent advances in deep learning reveal a promising direction toward fast and effective fiber clustering. In this work, we propose a novel deep learning framework for white matter fiber clustering, Deep Fiber Clustering (DFC), which solves the unsupervised clustering problem as a self-supervised learning task with a domain-specific pretext task to predict pairwise fiber distances. This process learns a high-dimensional embedding feature representation for each fiber, regardless of the order of fiber points reconstructed during tractography. We design a novel network architecture that represents input fibers as point clouds and allows the incorporation of additional sources of input information from gray matter parcellation. Thus, DFC makes use of combined information about white matter fiber geometry and gray matter anatomy to improve the anatomical coherence of fiber clusters. In addition, DFC conducts outlier removal naturally by rejecting fibers with low cluster assignment probability. We evaluate DFC on three independently acquired cohorts, including data from 220 individuals across genders, ages (young and elderly adults), and different health conditions (healthy control and multiple neuropsychiatric disorders). We compare DFC to several state-of-the-art white matter fiber clustering algorithms. Experimental results demonstrate superior performance of DFC in terms of cluster compactness, generalization ability, anatomical coherence, and computational efficiency.

Computational approaches for the reconstruction of optic nerve fibers along the visual pathway from medical images: a comprehensive review

Optic never fibers in the visual pathway play significant roles in vision formation. Damages of optic nerve fibers are biomarkers for the diagnosis of various ophthalmological and neurological diseases; also, there is a need to prevent the optic nerve fibers from getting damaged in neurosurgery and radiation therapy. Reconstruction of optic nerve fibers from medical images can facilitate all these clinical applications. Although many computational methods are developed for the reconstruction of optic nerve fibers, a comprehensive review of these methods is still lacking. This paper described both the two strategies for optic nerve fiber reconstruction applied in existing studies, i.e., image segmentation and fiber tracking. In comparison to image segmentation, fiber tracking can delineate more detailed structures of optic nerve fibers. For each strategy, both conventional and AI-based approaches were introduced, and the latter usually demonstrates better performance than the former. From the review, we concluded that AI-based methods are the trend for optic nerve fiber reconstruction and some new techniques like generative AI can help address the current challenges in optic nerve fiber reconstruction.

Directionally encoded color track density imaging in brain tumor patients: A potential application to neuro-oncology surgical planning

BACKGROUND

Diffusion magnetic resonance imaging white matter tractography, an increasingly popular preoperative planning modality used for pre-surgical planning in brain tumor patients, is employed with the goal of maximizing tumor resection while sparing postoperative neurological function. Clinical translation of white matter tractography has been limited by several shortcomings of standard diffusion tensor imaging (DTI), including poor modeling of fibers crossing through regions of peritumoral edema and low spatial resolution for typical clinical diffusion MRI (dMRI) sequences. Track density imaging (TDI) is a post-tractography technique that uses the number of tractography streamlines and their long-range continuity to map the white matter connections of the brain with enhanced image resolution relative to the acquired dMRI data, potentially offering improved white matter visualization in patients with brain tumors. The aim of this study was to assess the utility of TDI-based white matter maps in a neurosurgical planning context compared to the current clinical standard of DTI-based white matter maps.

METHODS

Fourteen consecutive brain tumor patients from a single institution were retrospectively selected for the study. Each patient underwent 3-Tesla dMRI scanning with 30 gradient directions and a b-value of 1000 s/mm2. For each patient, two directionally encoded color (DEC) maps were produced as follows. DTI-based DEC-fractional anisotropy maps (DEC-FA) were generated on the scanner, while DEC-track density images (DEC-TDI) were generated using constrained spherical deconvolution based tractography. The potential clinical utility of each map was assessed by five practicing neurosurgeons, who rated the maps according to four clinical utility statements regarding different clinical aspects of pre-surgical planning. The neurosurgeons rated each map according to their agreement with four clinical utility statements regarding if the map 1 identified clinically relevant tracts, (2) helped establish a goal resection margin, (3) influenced a planned surgical route, and (4) was useful overall. Cumulative link mixed effect modeling and analysis of variance were performed to test the primary effect of map type (DEC-TDI vs. DEC-FA) on rater score. Pairwise comparisons using estimated marginal means were then calculated to determine the magnitude and directionality of differences in rater scores by map type.

RESULTS

A majority of rater responses agreed with the four clinical utility statements, indicating that neurosurgeons found both DEC maps to be useful. Across all four investigated clinical utility statements, the DEC map type significantly influenced rater score. Rater scores were significantly higher for DEC-TDI maps compared to DEC-FA maps. The largest effect size in rater scores in favor of DEC-TDI maps was observed for clinical utility statement 2, which assessed establishing a goal resection margin.

CONCLUSION

We observed a significant neurosurgeon preference for DEC-TDI maps, indicating their potential utility for neurosurgical planning.

Accurate corresponding fiber tract segmentation via FiberGeoMap learner with application to autism

Fiber tract segmentation is a prerequisite for tract-based statistical analysis. Brain fiber streamlines obtained by diffusion magnetic resonance imaging and tractography technology are usually difficult to be leveraged directly, thus need to be segmented into fiber tracts. Previous research mainly consists of two steps: defining and computing the similarity features of fiber streamlines, then adopting machine learning algorithms for fiber clustering or classification. Defining the similarity feature is the basic premise and determines its potential reliability and application. In this study, we adopt geometric features for fiber tract segmentation and develop a novel descriptor (FiberGeoMap) for the corresponding representation, which can effectively depict fiber streamlines' shapes and positions. FiberGeoMap can differentiate fiber tracts within the same subject, meanwhile preserving the shape and position consistency across subjects, thus can identify common fiber tracts across brains. We also proposed a Transformer-based encoder network called FiberGeoMap Learner, to perform segmentation based on the geometric features. Experimental results showed that the proposed method can differentiate the 103 various fiber tracts, which outperformed the existing methods in both the number of categories and segmentation accuracy. Furthermore, the proposed method identified some fiber tracts that were statistically different on fractional anisotropy (FA), mean diffusion (MD), and fiber number ration in autism.

Superficial white matter analysis: An efficient point-cloud-based deep learning framework with supervised contrastive learning for consistent tractography parcellation across populations and dMRI acquisitions

Diffusion MRI tractography is an advanced imaging technique that enables in vivo mapping of the brain's white matter connections. White matter parcellation classifies tractography streamlines into clusters or anatomically meaningful tracts. It enables quantification and visualization of whole-brain tractography. Currently, most parcellation methods focus on the deep white matter (DWM), whereas fewer methods address the superficial white matter (SWM) due to its complexity. We propose a novel two-stage deep-learning-based framework, Superficial White Matter Analysis (SupWMA), that performs an efficient and consistent parcellation of 198 SWM clusters from whole-brain tractography. A point-cloud-based network is adapted to our SWM parcellation task, and supervised contrastive learning enables more discriminative representations between plausible streamlines and outliers for SWM. We train our model on a large-scale tractography dataset including streamline samples from labeled long- and medium-range (over 40 mm) SWM clusters and anatomically implausible streamline samples, and we perform testing on six independently acquired datasets of different ages and health conditions (including neonates and patients with space-occupying brain tumors). Compared to several state-of-the-art methods, SupWMA obtains highly consistent and accurate SWM parcellation results on all datasets, showing good generalization across the lifespan in health and disease. In addition, the computational speed of SupWMA is much faster than other methods.

Sleep Quality Disturbances Are Associated with White Matter Alterations in Veterans with Post-Traumatic Stress Disorder and Mild Traumatic Brain Injury

Sleep disturbances are strongly associated with mild traumatic brain injury (mTBI) and post-traumatic stress disorder (PTSD). PTSD and mTBI have been linked to alterations in white matter (WM) microstructure, but whether poor sleep quality has a compounding effect on WM remains largely unknown. We evaluated sleep and diffusion magnetic resonance imaging (dMRI) data from 180 male post-9/11 veterans diagnosed with (1) PTSD (n = 38), (2) mTBI (n = 25), (3) comorbid PTSD+mTBI (n = 94), and (4) a control group with neither PTSD nor mTBI (n = 23). We compared sleep quality (Pittsburgh Sleep Quality Index, PSQI) between groups using ANCOVAs and calculated regression and mediation models to assess associations between PTSD, mTBI, sleep quality, and WM. Veterans with PTSD and comorbid PTSD+mTBI reported poorer sleep quality than those with mTBI or no history of PTSD or mTBI (p = 0.012 to <0.001). Poor sleep quality was associated with abnormal WM microstructure in veterans with comorbid PTSD+mTBI (p < 0.001). Most importantly, poor sleep quality fully mediated the association between greater PTSD symptom severity and impaired WM microstructure (p < 0.001). Our findings highlight the significant impact of sleep disturbances on brain health in veterans with PTSD+mTBI, calling for sleep-targeted interventions.

TrGANet: Transforming 3T to 7T dMRI using Trapezoidal Rule and Graph based Attention Modules

Diffusion MRI (dMRI) is a non-invasive tool for assessing the white matter region of the brain by approximating the fiber streamlines, structural connectivity, and estimation of microstructure. This modality can yield useful information for diagnosing several mental diseases as well as for surgical planning. The higher angular resolution diffusion imaging (HARDI) technique is helpful in obtaining more robust fiber tracts by getting a good approximation of regions where fibers cross. Moreover, HARDI is more sensitive to tissue changes and can accurately represent anatomical details in the human brain at higher magnetic strengths. In other words, magnetic strengths affect the quality of the image, and hence high magnetic strength has good tissue contrast with better spatial resolution. However, a higher magnetic strength scanner (like 7T) is costly and unaffordable to most hospitals. Hence, in this work, we have proposed a novel CNN architecture for the transformation of 3T to 7T dMRI. Additionally, we have also reconstructed the multi-shell multi-tissue fiber orientation distribution function (MSMT fODF) at 7T from single-shell 3T. The proposed architecture consists of a CNN-based ODE solver utilizing the Trapezoidal rule and graph-based attention layer alongwith L₁ and total variation loss. Finally, the model has been validated on the HCP data set quantitatively and qualitatively.

Posttraumatic Stress and Traumatic Brain Injury: Cognition, Behavior, and Neuroimaging Markers in Vietnam Veterans

BACKGROUND

Posttraumatic stress disorder (PTSD) and traumatic brain injury (TBI) are common in Veterans and linked to behavioral disturbances, increased risk of cognitive decline, and Alzheimer's disease.

OBJECTIVE

We studied the synergistic effects of PTSD and TBI on behavioral, cognitive, and neuroimaging measures in Vietnam war Veterans.

METHODS

Data were acquired at baseline and after about one-year from male Veterans categorized into: PTSD, TBI, PTSD+TBI, and Veteran controls without PTSD or TBI. We applied manual tractography to examine white matter microstructure of three fiber tracts: uncinate fasciculus (N = 91), cingulum (N = 87), and inferior longitudinal fasciculus (N = 95). ANCOVAs were used to compare Veterans' baseline behavioral and cognitive functioning (N = 285), white matter microstructure, amyloid-β (N = 230), and tau PET (N = 120). Additional ANCOVAs examined scores' differences from baseline to follow-up.

RESULTS

Veterans with PTSD and PTSD+TBI, but not Veterans with TBI only, exhibited poorer behavioral and cognitive functioning at baseline than controls. The groups did not differ in baseline white matter, amyloid-β, or tau, nor in behavioral and cognitive functioning, and tau accumulation change. Progression of white matter abnormalities of the uncinate fasciculus in Veterans with PTSD compared to controls was observed; analyses in TBI and PTSD+TBI were not run due to insufficient sample size.

CONCLUSIONS

PTSD and PTSD+TBI negatively affect behavioral and cognitive functioning, while TBI does not contribute independently. Whether progressive decline in uncinate fasciculus microstructure in Veterans with PTSD might account for cognitive decline should be further studied. Findings did not support an association between PTSD, TBI, and Alzheimer's disease pathology based on amyloid and tau PET.

Diffusion tensor estimation with transformer neural networks

Diffusion tensor imaging (DTI) is a widely used method for studying brain white matter development and degeneration. However, standard DTI estimation methods depend on a large number of high-quality measurements. This would require long scan times and can be particularly difficult to achieve with certain patient populations such as neonates. Here, we propose a method that can accurately estimate the diffusion tensor from only six diffusion-weighted measurements. Our method achieves this by learning to exploit the relationships between the diffusion signals and tensors in neighboring voxels. Our model is based on transformer networks, which represent the state of the art in modeling the relationship between signals in a sequence. In particular, our model consists of two such networks. The first network estimates the diffusion tensor based on the diffusion signals in a neighborhood of voxels. The second network provides more accurate tensor estimations by learning the relationships between the diffusion signals as well as the tensors estimated by the first network in neighboring voxels. Our experiments with three datasets show that our proposed method achieves highly accurate estimations of the diffusion tensor and is significantly superior to three competing methods. Estimations produced by our method with six diffusion-weighted measurements are comparable with those of standard estimation methods with 30-88 diffusion-weighted measurements. Hence, our method promises shorter scan times and more reliable assessment of brain white matter, particularly in non-cooperative patients such as neonates and infants.

Informative and Reliable Tract Segmentation for Preoperative Planning

Identifying white matter (WM) tracts to locate eloquent areas for preoperative surgical planning is a challenging task. Manual WM tract annotations are often used but they are time-consuming, suffer from inter- and intra-rater variability, and noise intrinsic to diffusion MRI may make manual interpretation difficult. As a result, in clinical practice direct electrical stimulation is necessary to precisely locate WM tracts during surgery. A measure of WM tract segmentation unreliability could be important to guide surgical planning and operations. In this study, we use deep learning to perform reliable tract segmentation in combination with uncertainty quantification to measure segmentation unreliability. We use a 3D U-Net to segment white matter tracts. We then estimate model and data uncertainty using test time dropout and test time augmentation, respectively. We use a volume-based calibration approach to compute representative predicted probabilities from the estimated uncertainties. In our findings, we obtain a Dice of ≈0.82 which is comparable to the state-of-the-art for multi-label segmentation and Hausdorff distance <10mm. We demonstrate a high positive correlation between volume variance and segmentation errors, which indicates a good measure of reliability for tract segmentation ad uncertainty estimation. Finally, we show that calibrated predicted volumes are more likely to encompass the ground truth segmentation volume than uncalibrated predicted volumes. This study is a step toward more informed and reliable WM tract segmentation for clinical decision-making.

Intellectual Structure and Emerging Trends of White Matter Hyperintensity Studies: A Bibliometric Analysis From 2012 to 2021

White matter hyperintensities (WMHs), which have a significant effect on human health, have received increasing attention since their number of publications has increased in the past 10 years. We aimed to explore the intellectual structure, hotspots, and emerging trends of publications on WMHs using bibliometric analysis from 2012 to 2021. Publications on WMHs from 2012 to 2021 were retrieved from the Web of Science Core Collection. CiteSpace 5.8.R3, VOSviewer 1.6.17, and an online bibliometric analysis platform (Bibliometric. com) were used to quantitatively analyze the trends of publications from multiple perspectives. A total of 29,707 publications on WMHs were obtained, and the number of annual publications generally increased from 2012 to 2021. Neurology had the most publications on WMHs. The top country and institution were the United States and Harvard University, respectively. Massimo Filippi and Stephen M. Smith were the most productive and co-cited authors, respectively. Thematic concentrations primarily included cerebral small vessel disease, diffusion magnetic resonance imaging (dMRI), schizophrenia, Alzheimer’s disease, multiple sclerosis, microglia, and oligodendrocyte. The hotspots were clustered into five groups: white matter and diffusion tensor imaging, inflammation and demyelination, small vessel disease and cognitive impairment, MRI and multiple sclerosis, and Alzheimer’s disease. Emerging trends mainly include deep learning, machine learning, perivascular space, convolutional neural network, neurovascular unit, and neurite orientation dispersion and density imaging. This study presents an overview of publications on WMHs and provides insights into the intellectual structure of WMH studies. Our study provides information to help researchers and clinicians quickly and comprehensively understand the hotspots and emerging trends within WMH studies as well as providing direction for future basic and clinical studies on WMHs.

Quantitative mapping of the brain's structural connectivity using diffusion MRI tractography: A review

Diffusion magnetic resonance imaging (dMRI) tractography is an advanced imaging technique that enables in vivo reconstruction of the brain's white matter connections at macro scale. It provides an important tool for quantitative mapping of the brain's structural connectivity using measures of connectivity or tissue microstructure. Over the last two decades, the study of brain connectivity using dMRI tractography has played a prominent role in the neuroimaging research landscape. In this paper, we provide a high-level overview of how tractography is used to enable quantitative analysis of the brain's structural connectivity in health and disease. We focus on two types of quantitative analyses of tractography, including: 1) tract-specific analysis that refers to research that is typically hypothesis-driven and studies particular anatomical fiber tracts, and 2) connectome-based analysis that refers to research that is more data-driven and generally studies the structural connectivity of the entire brain. We first provide a review of methodology involved in three main processing steps that are common across most approaches for quantitative analysis of tractography, including methods for tractography correction, segmentation and quantification. For each step, we aim to describe methodological choices, their popularity, and potential pros and cons. We then review studies that have used quantitative tractography approaches to study the brain's white matter, focusing on applications in neurodevelopment, aging, neurological disorders, mental disorders, and neurosurgery. We conclude that, while there have been considerable advancements in methodological technologies and breadth of applications, there nevertheless remains no consensus about the "best" methodology in quantitative analysis of tractography, and researchers should remain cautious when interpreting results in research and clinical applications.

CONTINUITY: CONnectivity Tool with INtegration of sUbcortical regions, regIstration and visualization of TractographY

In this work, we present CONTINUITY, a novel, open-source interactive computation and visualization tool for brain connectome data. The connectome processing pipeline performs surface based processing as the main mode of operation. The automated processing includes structural-to-diffusion image co-registration, surface reconstruction for subcortical structures, as well as fiber tractography. The tool supports 3 different probabilistic methods of tractography offered by the tractography frameworks in FSL, MRtrix and DIPY. All methods employ brain and subcortical surfaces as seeds to initialize the tractography algorithms. CONTINUITY implements a friendly Graphical User Interface (GUI) to make the workflow accessible for nontechnical users. Additionally, it offers the possibility to visualize the results of the brain connectome in several interactive plot types such as a hierarchical edge bundling circle plot and over 2D/3D brain templates. This visualization tool can also be applied to connectome matrices computed with other tools and pipelines.

Volumetric Segmentation of White Matter Tracts with Label Embedding

Convolutional neural networks have achieved state-of-the-art performance for white matter (WM) tract segmentation based on diffusion magnetic resonance imaging (dMRI). However, the segmentation can still be difficult for challenging WM tracts with thin bodies or complicated shapes; the segmentation is even more problematic in challenging scenarios with reduced data quality or domain shift between training and test data, which can be easily encountered in clinical settings. In this work, we seek to improve the segmentation of WM tracts, especially for challenging WM tracts in challenging scenarios. In particular, our method is based on volumetric WM tract segmentation, where voxels are directly labeled without performing tractography. To improve the segmentation, we exploit the characteristics of WM tracts that different tracts can cross or overlap and revise the network design accordingly. Specifically, because multiple tracts can co-exist in a voxel, we hypothesize that the different tract labels can be correlated. The tract labels at a single voxel are concatenated as a label vector, the length of which is the number of tract labels. Due to the tract correlation, this label vector can be projected into a lower-dimensional space-referred to as the embedded space-for each voxel, which allows the segmentation network to solve a simpler problem. By predicting the coordinate in the embedded space for the tracts at each voxel and subsequently mapping the coordinate to the label vector with a reconstruction module, the segmentation result can be achieved. To facilitate the learning of the embedded space, an auxiliary label reconstruction loss is integrated with the segmentation accuracy loss during network training, and network training and inference are end-to-end. Our method was validated on two dMRI datasets under various settings. The results show that the proposed method improves the accuracy of WM tract segmentation, and the improvement is more prominent for challenging tracts in challenging scenarios.

Auto-encoded Latent Representations of White Matter Streamlines for Quantitative Distance Analysis

Parcellation of whole brain tractograms is a critical step to study brain white matter structures and connectivity patterns. The existing methods based on supervised classification of streamlines into predefined streamline bundle types are not designed to explore sub-bundle structures, and methods with manually designed features are expensive to compute streamline-wise similarities. To resolve these issues, we propose a novel atlas-free method that learns a latent space using a deep recurrent auto-encoder trained in an unsupervised manner. The method efficiently embeds any length of streamlines to fixed-size feature vectors, named streamline embedding, for tractogram parcellation using non-parametric clustering in the latent space. The method was evaluated on the ISMRM 2015 tractography challenge dataset with discrimination of major bundles using clustering algorithms and streamline querying based on similarity, as well as real tractograms of 102 subjects Human Connectome Project. The learnt latent streamline and bundle representations open the possibility of quantitative studies of arbitrary granularity of sub-bundle structures using generic data mining techniques.

TractEM: Evaluation of protocols for deterministic tractography white matter atlas

Reproducible identification of white matter pathways across subjects is essential for the study of structural connectivity of the human brain. One of the key challenges is anatomical differences between subjects and human rater subjectivity in labeling. Labeling white matter regions of interest presents many challenges due to the need to integrate both local and global information. Clearly communicating the manual processes to capture this information is cumbersome, yet essential to lay a solid foundation for comprehensive atlases. Segmentation protocols must be designed so the interpretation of the requested tasks as well as locating structural landmarks is anatomically accurate, intuitive and reproducible. In this work, we quantified the reproducibility of a first iteration of an open/public multi-bundle segmentation protocol. This allowed us to establish a baseline for its reproducibility as well as to identify the limitations for future iterations. The protocol was tested/evaluated on both typical 3 T research acquisition Baltimore Longitudinal Study of Aging (BLSA) and high-acquisition quality Human Connectome Project (HCP) datasets. The results show that a rudimentary protocol can produce acceptable intra-rater and inter-rater reproducibility. However, this work highlights the difficulty in generalizing reproducible results and the importance of reaching consensus on anatomical description of white matter pathways. The protocol has been made available in open source to improve generalizability and reliability in collaboration. The goal is to improve upon the first iteration and initiate a discussion on the anatomical validity (or lack thereof) of some bundle definitions and the importance of reproducibility of tractography segmentation.

Fiber tractography bundle segmentation depends on scanner effects, vendor effects, acquisition resolution, diffusion sampling scheme, diffusion sensitization, and bundle segmentation workflow

When investigating connectivity and microstructure of white matter pathways of the brain using diffusion tractography bundle segmentation, it is important to understand potential confounds and sources of variation in the process. While cross-scanner and cross-protocol effects on diffusion microstructure measures are well described (in particular fractional anisotropy and mean diffusivity), it is unknown how potential sources of variation effect bundle segmentation results, which features of the bundle are most affected, where variability occurs, nor how these sources of variation depend upon the method used to reconstruct and segment bundles. In this study, we investigate six potential sources of variation, or confounds, for bundle segmentation: variation (1) across scan repeats, (2) across scanners, (3) across vendors (4) across acquisition resolution, (5) across diffusion schemes, and (6) across diffusion sensitization. We employ four different bundle segmentation workflows on two benchmark multi-subject cross-scanner and cross-protocol databases, and investigate reproducibility and biases in volume overlap, shape geometry features of fiber pathways, and microstructure features within the pathways. We find that the effects of acquisition protocol, in particular acquisition resolution, result in the lowest reproducibility of tractography and largest variation of features, followed by vendor-effects, scanner-effects, and finally diffusion scheme and b-value effects which had similar reproducibility as scan-rescan variation. However, confounds varied both across pathways and across segmentation workflows, with some bundle segmentation workflows more (or less) robust to sources of variation. Despite variability, bundle dissection is consistently able to recover the same location of pathways in the deep white matter, with variation at the gray matter/ white matter interface. Next, we show that differences due to the choice of bundle segmentation workflows are larger than any other studied confound, with low-to-moderate overlap of the same intended pathway when segmented using different methods. Finally, quantifying microstructure features within a pathway, we show that tractography adds variability over-and-above that which exists due to noise, scanner effects, and acquisition effects. Overall, these confounds need to be considered when harmonizing diffusion datasets, interpreting or combining data across sites, and when attempting to understand the successes and limitations of different methodologies in the design and development of new tractography or bundle segmentation methods.

The Organization of Frontostriatal Brain Wiring in Healthy Subjects Using a Novel Diffusion Imaging Fiber Cluster Analysis

To assess normal organization of frontostriatal brain wiring, we analyzed diffusion magnetic resonance imaging (dMRI) scans in 100 young adult healthy subjects (HSs). We identified fiber clusters intersecting the frontal cortex and caudate, a core component of associative striatum, and quantified their degree of deviation from a strictly topographic pattern. Using whole brain dMRI tractography and an automated tract parcellation clustering method, we extracted 17 white matter fiber clusters per hemisphere connecting the frontal cortex and caudate. In a novel approach to quantify the geometric relationship among clusters, we measured intercluster endpoint distances between corresponding cluster pairs in the frontal cortex and caudate. We show first, the overall frontal cortex wiring pattern of the caudate deviates from a strictly topographic organization due to significantly greater convergence in regionally specific clusters; second, these significantly convergent clusters originate in subregions of ventrolateral, dorsolateral, and orbitofrontal prefrontal cortex (PFC); and, third, a similar organization in both hemispheres. Using a novel tractography method, we find PFC-caudate brain wiring in HSs deviates from a strictly topographic organization due to a regionally specific pattern of cluster convergence. We conjecture cortical subregions projecting to the caudate with greater convergence subserve functions that benefit from greater circuit integration.

Comparison of multiple tractography methods for reconstruction of the retinogeniculate visual pathway using diffusion MRI

The retinogeniculate visual pathway (RGVP) conveys visual information from the retina to the lateral geniculate nucleus. The RGVP has four subdivisions, including two decussating and two nondecussating pathways that cannot be identified on conventional structural magnetic resonance imaging (MRI). Diffusion MRI tractography has the potential to trace these subdivisions and is increasingly used to study the RGVP. However, it is not yet known which fiber tracking strategy is most suitable for RGVP reconstruction. In this study, four tractography methods are compared, including constrained spherical deconvolution (CSD) based probabilistic (iFOD1) and deterministic (SD-Stream) methods, and multi-fiber (UKF-2T) and single-fiber (UKF-1T) unscented Kalman filter (UKF) methods. Experiments use diffusion MRI data from 57 subjects in the Human Connectome Project. The RGVP is identified using regions of interest created by two clinical experts. Quantitative anatomical measurements and expert anatomical judgment are used to assess the advantages and limitations of the four tractography methods. Overall, we conclude that UKF-2T and iFOD1 produce the best RGVP reconstruction results. The iFOD1 method can better quantitatively estimate the percentage of decussating fibers, while the UKF-2T method produces reconstructed RGVPs that are judged to better correspond to the known anatomy and have the highest spatial overlap across subjects. Overall, we find that it is challenging for current tractography methods to both accurately track RGVP fibers that correspond to known anatomy and produce an approximately correct percentage of decussating fibers. We suggest that future algorithm development for RGVP tractography should take consideration of both of these two points.

Filtering in tractography using autoencoders (FINTA)

Current brain white matter fiber tracking techniques show a number of problems, including: generating large proportions of streamlines that do not accurately describe the underlying anatomy; extracting streamlines that are not supported by the underlying diffusion signal; and under-representing some fiber populations, among others. In this paper, we describe a novel autoencoder-based learning method to filter streamlines from diffusion MRI tractography, and hence, to obtain more reliable tractograms. Our method, dubbed FINTA (Filtering in Tractography using Autoencoders) uses raw, unlabeled tractograms to train the autoencoder, and to learn a robust representation of brain streamlines. Such an embedding is then used to filter undesired streamline samples using a nearest neighbor algorithm. Our experiments on both synthetic and in vivo human brain diffusion MRI tractography data obtain accuracy scores exceeding the 90% threshold on the test set. Results reveal that FINTA has a superior filtering performance compared to conventional, anatomy-based methods, and the RecoBundles state-of-the-art method. Additionally, we demonstrate that FINTA can be applied to partial tractograms without requiring changes to the framework. We also show that the proposed method generalizes well across different tracking methods and datasets, and shortens significantly the computation time for large (>1 M streamlines) tractograms. Together, this work brings forward a new deep learning framework in tractography based on autoencoders, which offers a flexible and powerful method for white matter filtering and bundling that could enhance tractometry and connectivity analyses.

Volumetric white matter tract segmentation with nested self-supervised learning using sequential pretext tasks

White matter (WM) tract segmentation based on diffusion magnetic resonance imaging (dMRI) provides an important tool for the analysis of brain development, function, and disease. Deep learning based methods of WM tract segmentation have been proposed, which greatly improve the accuracy of the segmentation. However, the training of the deep networks usually requires a large number of manual delineations of WM tracts, which can be especially difficult to obtain and unavailable in many scenarios. Therefore, in this work, we explore how to perform deep learning based WM tract segmentation when annotated training data is scarce. To this end, we seek to exploit the abundant unannotated dMRI data in the self-supervised learning framework. From the unannotated data, knowledge about image context can be learned with pretext tasks that do not require manual annotations. Specifically, a deep network can be pretrained for the pretext task, and the knowledge learned from the pretext task is then transferred to the subsequent WM tract segmentation task with only a small number of annotated scans via fine-tuning. We explore two designs of pretext tasks that are related to WM tracts. The first pretext task predicts the density map of fiber streamlines, which are representations of generic WM pathways, and the training data can be obtained automatically with tractography. The second pretext task learns to mimic the results of registration-based WM tract segmentation, which, although inaccurate, is more relevant to WM tract segmentation and provides a good target for learning context knowledge. Then, we combine the two pretext tasks and develop a nested self-supervised learning strategy. In the nested self-supervised learning strategy, the first pretext task provides initial knowledge for the second pretext task, and the knowledge learned from the second pretext task with the initial knowledge is transferred to the target WM tract segmentation task via fine-tuning. To evaluate the proposed method, experiments were performed on brain dMRI scans from the Human Connectome Project dataset with various experimental settings. The results show that the proposed method improves the performance of WM tract segmentation when tract annotations are scarce.