Deep-learning based fully automatic segmentation of the globus pallidus interna and externa using ultra-high 7 Tesla MRI

Quantitative susceptibility mapping based basal ganglia segmentation via AGSeg: leveraging active gradient guiding mechanism in deep learning

Background

With better visual contrast and the ability for magnetic susceptibility quantification analysis, quantitative susceptibility mapping (QSM) has emerged as an important magnetic resonance imaging (MRI) method for basal ganglia studies. Precise segmentation of basal ganglia is a prerequisite for quantification analysis of tissue magnetic susceptibility, which is crucial for subsequent disease diagnosis and surgical planning. The conventional method of localizing and segmenting basal ganglia heavily relies on layer-by-layer manual annotation by experts, resulting in a tedious amount of workload. Although several morphology registration and deep learning based methods have been developed to automate segmentation, the voxels around the nuclei boundary remain a challenge to distinguish due to insufficient tissue contrast. This paper proposes AGSeg, an active gradient guidance-based susceptibility and magnitude information complete (MIC) network for real-time and accurate basal ganglia segmentation.

Methods

Various datasets, including clinical scans and data from healthy volunteers, were collected across multiple centers with different magnetic field strengths (3T/5T/7T), with a total of 210 three-dimensional (3D) susceptibility measurements. Manual segmentations following fixed rules for anatomical borders annotated by experts were used as ground truth labels. The proposed network took QSM maps and Magnitude images as two individual inputs, of which the features are selectively enhanced in the proposed magnitude information complete (MIC) module. AGSeg utilized a dual-branch architecture, with Seg-branch aiming to generate a proper segmentation map and Grad-branch to reconstruct the gradient map of regions of interest (ROIs). With the support of the newly designed active gradient module (AGM) and gradient guiding module (GGM), the Grad-branch provided attention guidance for the Seg-branch, facilitating it to focus on the boundary of target nuclei.

Results

Ablation studies were conducted to assess the functionality of the proposed modules. Significant performance decrement was observed after ablating relative modules. AGSeg was evaluated against several existing methods on both healthy and clinical data, achieving an average Dice similarity coefficient (DSC) =0.874 and average 95% Hausdorff distance (HD95) =2.009. Comparison experiments indicated that our model had superior performance on basal ganglia segmentation and better generalization ability over existing methods. The AGSeg outperformed all implemented comparison deep learning algorithms with average DSC enhancement ranging from 0.036 to 0.074.

Conclusions

The current work integrates a deep learning-based method into automated basal ganglia segmentation. The high processing speed and segmentation robustness of AGSeg contribute to the feasibility of future surgery planning and intraoperative navigation. Experiments show that leveraging active gradient guidance mechanisms and magnitude information completion can facilitate the segmentation process. Moreover, this approach also offers a portable solution for other multi-modality medical image segmentation tasks.

Structural and functional correlates of disability, motor and cognitive performances in multiple sclerosis: Focus on the globus pallidus

OBJECTIVES

To explore structural and functional alterations of external (GPe) and internal (GPi) globus pallidus in people with multiple sclerosis (pwMS) compared to healthy controls (HC) and analyze their relationship with measures of clinical disability, motor and cognitive impairment.

METHODS

Sixty pwMS and 30 HC comparable for age and sex underwent 3.0T MRI, including conventional, diffusion tensor MRI and resting state (RS) functional MRI. Expanded Disability Status Scale (EDSS) scores were rated and timed 25-foot walk (T25FW) test, nine-hole peg test (9HPT), and paced auditory serial addition test (PASAT) were administered. Two operators segmented the GP into GPe and GPi. Volumes, T1/T2 ratio, diffusivity indices and seed-based RS functional connectivity (FC) of the GP and its components were assessed.

RESULTS

PwMS had no atrophy or altered diffusivity measures of the GP. Compared to HC, pwMS had higher T1/T2 ratio in both GP regions, which correlated with EDSS score (r = 0.26-0.39, p = 0.01-0.05). RS FC analysis highlighted component-specific functional alterations in pwMS: the GPe had decreased RS FC with fronto-parietal cortices, whereas the GPi had decreased intra-GP RS FC and increased RS FC with the thalamus. Worse EDSS, 9HPT, T25FW and PASAT scores were associated with GP RS FC modifications (r=-0.51‒0.51, p < 0.001).

CONCLUSIONS

Structural GP involvement in MS was homogeneous across its portions. Increased T1/T2 ratio values, possibly representing iron accumulation, were related to more severe disability. RS FC alterations of the GPe and GPi were consistent with their roles within the basal ganglia network and correlated with worse functional status, suggesting less efficient communication between structures.

Use of a Commercial 7-T MRI Scanner for Clinical Brain Imaging: Indications, Protocols, Challenges, and Solutions-A Single-Center Experience

The first commercially available 7-T MRI scanner (Magnetom Terra) was approved by the FDA in 2017 for clinical imaging of the brain and knee. After initial protocol development and sequence optimization efforts in volunteers, the 7-T system, in combination with an FDA-approved 1-channel transmit/32-channel receive array head coil, can now be routinely used for clinical brain MRI examinations. The ultrahigh field strength of 7-T MRI has the advantages of improved spatial resolution, increased SNR, and increased CNR but also introduces an array of new technical challenges. The purpose of this article is to describe an institutional experience with the use of the commercially available 7-T MRI scanner for routine clinical brain imaging. Specific clinical indications for which 7-T MRI may be useful for brain imaging include brain tumor evaluation with possible perfusion imaging and/or spectroscopy, radiotherapy planning; evaluation of multiple sclerosis and other demyelinating diseases, evaluation of Parkinson disease and guidance of deep brain stimulator placement, high-detail intracranial MRA and vessel wall imaging, evaluation of pituitary pathology, and evaluation of epilepsy. Detailed protocols, including sequence parameters, for these various indications are presented, and implementation challenges (including artifacts, safety, and side effects) and potential solutions are explored.

Automatic Localization of Key Structures for Subthalamic Nucleus-Deep Brain Stimulation Surgery via Prior-Enhanced Multi-Object Magnetic Resonance Imaging Segmentation

BACKGROUND

Deep brain stimulation (DBS) of the subthalamic nucleus (STN) is an established and effective neurosurgical treatment for relieving motor symptoms in Parkinson disease. The localization of key brain structures is critical to the success of DBS surgery. However, in clinical practice, this process is heavily dependent on the radiologist's experience.

METHODS

In this study, we propose an automatic localization method of key structures for STN-DBS surgery via prior-enhanced multi-object magnetic resonance imaging segmentation. We use the U-Net architecture for the multi-object segmentation, including STN, red nucleus, brain sulci, gyri, and ventricles. To address the challenge that only half of the brain sulci and gyri locate in the upper area, potentially causing interference in the lower area, we perform region of interest detection and ensemble joint processing to enhance the segmentation performance of brain sulci and gyri.

RESULTS

We evaluate the segmentation accuracy by comparing our method with other state-of-the-art machine learning segmentation methods. The experimental results show that our approach outperforms state-of-the-art methods in terms of segmentation performance. Moreover, our method provides effective visualization of key brain structures from a clinical application perspective and can reduce the segmentation time compared with manual delineation.

CONCLUSIONS

Our proposed method uses deep learning to achieve accurate segmentation of the key structures more quickly than and with comparable accuracy to human manual segmentation. Our method has the potential to improve the efficiency of surgical planning for STN-DBS.

Motion robust magnetic resonance imaging via efficient Fourier aggregation

We present a method for suppressing motion artifacts in anatomical magnetic resonance acquisitions. Our proposed technique, termed MOTOR-MRI, can recover and salvage images which are otherwise heavily corrupted by motion induced artifacts and blur which renders them unusable. Contrary to other techniques, MOTOR-MRI operates on the reconstructed images and not on k-space data. It relies on breaking the standard acquisition protocol into several shorter ones (while maintaining the same total acquisition time) and subsequent efficient aggregation in Fourier space of locally sharp and consistent information among them, producing a sharp and motion mitigated image. We demonstrate the efficacy of the technique on T₂-weighted turbo spin echo magnetic resonance brain scans with severe motion corruption from both 3 T and 7 T scanners and show significant qualitative and quantitative improvement in image quality. MOTOR-MRI can operate independently, or in conjunction with additional motion correction methods.

Lead location as a determinant of motor benefit in subthalamic nucleus deep brain stimulation for Parkinson’s disease

Background

Subthalamic nucleus (STN) deep brain stimulation (DBS) is regarded as an effective treatment for patients with advanced Parkinson’s disease (PD). Clinical benefit, however, varies significantly across patients. Lead location has been hypothesized to play a critical role in determining motor outcome and may account for much of the observed variability reported among patients.

Objective

To retrospectively evaluate the relationship of lead location to motor outcomes in patients who had been implanted previously at another center by employing a novel visualization technology that more precisely determines the location of the DBS lead and its contacts with respect to each patient’s individually defined STN.

Methods

Anatomical models were generated using novel imaging in 40 PD patients who had undergone bilateral STN DBS (80 electrodes) at another center. Patient-specific models of each STN were evaluated to determine DBS electrode contact locations with respect to anterior to posterior and medial to lateral regions of the individualized STNs and compared to the change in the contralateral hemi-body Unified Parkinson’s Disease Rating Scale Part III (UPDRS-III) motor score.

Results

The greatest improvement in hemi-body motor function was found when active contacts were located within the posterolateral portion of the STN (71.5%). Motor benefit was 52 and 36% for central and anterior segments, respectively. Active contacts within the posterolateral portion also demonstrated the greatest reduction in levodopa dosage (77%).

Conclusion

The degree of motor benefit was dependent on the location of the stimulating contact within the STN. Although other factors may play a role, we provide further evidence in support of the hypothesis that lead location is a critical factor in determining clinical outcomes in STN DBS.

High-resolution atlasing and segmentation of the subcortex: Review and perspective on challenges and opportunities created by machine learning

This paper reviews almost three decades of work on atlasing and segmentation methods for subcortical structures in human brain MRI. In writing this survey, we have three distinct aims. First, to document the evolution of digital subcortical atlases of the human brain, from the early MRI templates published in the nineties, to the complex multi-modal atlases at the subregion level that are available today. Second, to provide a detailed record of related efforts in the automated segmentation front, from earlier atlas-based methods to modern machine learning approaches. And third, to present a perspective on the future of high-resolution atlasing and segmentation of subcortical structures in in vivo human brain MRI, including open challenges and opportunities created by recent developments in machine learning.

Advances in DBS Technology and Novel Applications: Focus on Movement Disorders

PURPOSE OF REVIEW

Deep brain stimulation (DBS) is an established treatment in several movement disorders, including Parkinson's disease, dystonia, tremor, and Tourette syndrome. In this review, we will review and discuss the most recent findings including but not limited to clinical evidence.

RECENT FINDINGS

New DBS technologies include novel hardware design (electrodes, cables, implanted pulse generators) enabling new stimulation patterns and adaptive DBS which delivers potential stimulation tailored to moment-to-moment changes in the patient's condition. Better understanding of movement disorders pathophysiology and functional anatomy has been pivotal for studying the effects of DBS on the mesencephalic locomotor region, the nucleus basalis of Meynert, the substantia nigra, and the spinal cord. Eventually, neurosurgical practice has improved with more accurate target visualization or combined targeting. A rising research domain emphasizes bridging neuromodulation and neuroprotection. Recent advances in DBS therapy bring more possibilities to effectively treat people with movement disorders. Future research would focus on improving adaptive DBS, leading more clinical trials on novel targets, and exploring neuromodulation effects on neuroprotection.

Neuroimaging at 7 Tesla: a pictorial narrative review

Neuroimaging using the 7-Tesla (7T) human magnetic resonance (MR) system is rapidly gaining popularity after being approved for clinical use in the European Union and the USA. This trend is the same for functional MR imaging (MRI). The primary advantages of 7T over lower magnetic fields are its higher signal-to-noise and contrast-to-noise ratios, which provide high-resolution acquisitions and better contrast, making it easier to detect lesions and structural changes in brain disorders. Another advantage is the capability to measure a greater number of neurochemicals by virtue of the increased spectral resolution. Many structural and functional studies using 7T have been conducted to visualize details in the white matter and layers of the cortex and hippocampus, the subnucleus or regions of the putamen, the globus pallidus, thalamus and substantia nigra, and in small structures, such as the subthalamic nucleus, habenula, perforating arteries, and the perivascular space, that are difficult to observe at lower magnetic field strengths. The target disorders for 7T neuroimaging range from tumoral diseases to vascular, neurodegenerative, and psychiatric disorders, including Alzheimer's disease, Parkinson's disease, multiple sclerosis, epilepsy, major depressive disorder, and schizophrenia. MR spectroscopy has also been used for research because of its increased chemical shift that separates overlapping peaks and resolves neurochemicals more effectively at 7T than a lower magnetic field. This paper presents a narrative review of these topics and an illustrative presentation of images obtained at 7T. We expect 7T neuroimaging to provide a new imaging biomarker of various brain disorders.

Essential Tremor-Do We Have Better Therapeutics? A Review of Recent Advances and Future Directions

PURPOSE OF REVIEW

Essential tremor (ET) is a very common condition that significantly impacts quality of life. Current medical treatments are quite limited, and while surgical treatments like deep brain stimulation (DBS) can be very effective, they come with their own limitations as well as procedural risks. This article reviews updates on recent advances and future directions in the treatment of ET.

RECENT FINDINGS

A new generation of pharmacologic agents specifically designed for ET is in clinical trials. Advances in DBS technology continue to improve this therapy. MRI-guided focused ultrasound (MRgFUS) is now an approved noninvasive ablative treatment for ET that is effective and shows potential for continuing improvement. The first peripheral stimulation device for ET has also now been approved. This article reviews updates on the treatment of ET, encompassing pharmacologic agents in clinical trials, DBS, MRgFUS, and noninvasive stimulation therapies. Recent treatment advances and future directions of development show a great deal of promise for ET therapeutics.

Clinical applications of magnetic resonance imaging based functional and structural connectivity

Advances in computational neuroimaging techniques have expanded the armamentarium of imaging tools available for clinical applications in clinical neuroscience. Non-invasive, in vivo brain MRI structural and functional network mapping has been used to identify therapeutic targets, define eloquent brain regions to preserve, and gain insight into pathological processes and treatments as well as prognostic biomarkers. These tools have the real potential to inform patient-specific treatment strategies. Nevertheless, a realistic appraisal of clinical utility is needed that balances the growing excitement and interest in the field with important limitations associated with these techniques. Quality of the raw data, minutiae of the processing methodology, and the statistical models applied can all impact on the results and their interpretation. A lack of standardization in data acquisition and processing has also resulted in issues with reproducibility. This limitation has had a direct impact on the reliability of these tools and ultimately, confidence in their clinical use. Advances in MRI technology and computational power as well as automation and standardization of processing methods, including machine learning approaches, may help address some of these issues and make these tools more reliable in clinical use. In this review, we will highlight the current clinical uses of MRI connectomics in the diagnosis and treatment of neurological disorders; balancing emerging applications and technologies with limitations of connectivity analytic approaches to present an encompassing and appropriate perspective.

Machine learning in deep brain stimulation: A systematic review

Deep Brain Stimulation (DBS) is an increasingly common therapy for a large range of neurological disorders, such as abnormal movement disorders. The effectiveness of DBS in terms of controlling patient symptomatology has made this procedure increasingly used over the past few decades. Concurrently, the popularity of Machine Learning (ML), a subfield of artificial intelligence, has skyrocketed and its influence has more recently extended to medical domains such as neurosurgery. Despite its growing research interest, there has yet to be a literature review specifically on the use of ML in DBS. We have followed a fully systematic methodology to obtain a corpus of 73 papers. In each paper, we identified the clinical application, the type/amount of data used, the method employed, and the validation strategy, further decomposed into 12 different sub-categories. The papers overall illustrated some existing trends in how ML is used in the context of DBS, including the breath of the problem domain and evolving techniques, as well as common frameworks and limitations. This systematic review analyzes at a broad level how ML have been recently used to address clinical problems on DBS, giving insight into how these new computational methods are helping to push the state-of-the-art of functional neurosurgery. DBS clinical workflow is complex, involves many specialists, and raises several clinical issues which have partly been addressed with artificial intelligence. However, several areas remain and those that have been recently addressed with ML are by no means considered "solved" by the community nor are they closed to new and evolving methods.

New Frontiers for Deep Brain Stimulation: Directionality, Sensing Technologies, Remote Programming, Robotic Stereotactic Assistance, Asleep Procedures, and Connectomics

Over the last few years, while expanding its clinical indications from movement disorders to epilepsy and psychiatry, the field of deep brain stimulation (DBS) has seen significant innovations. Hardware developments have introduced directional leads to stimulate specific brain targets and sensing electrodes to determine optimal settings via feedback from local field potentials. In addition, variable-frequency stimulation and asynchronous high-frequency pulse trains have introduced new programming paradigms to efficiently desynchronize pathological neural circuitry and regulate dysfunctional brain networks not responsive to conventional settings. Overall, these innovations have provided clinicians with more anatomically accurate programming and closed-looped feedback to identify optimal strategies for neuromodulation. Simultaneously, software developments have simplified programming algorithms, introduced platforms for DBS remote management via telemedicine, and tools for estimating the volume of tissue activated within and outside the DBS targets. Finally, the surgical accuracy has improved thanks to intraoperative magnetic resonance or computerized tomography guidance, network-based imaging for DBS planning and targeting, and robotic-assisted surgery for ultra-accurate, millimetric lead placement. These technological and imaging advances have collectively optimized DBS outcomes and allowed “asleep” DBS procedures. Still, the short- and long-term outcomes of different implantable devices, surgical techniques, and asleep vs. awake procedures remain to be clarified. This expert review summarizes and critically discusses these recent innovations and their potential impact on the DBS field.

Deep-learning based fully automatic segmentation of the globus pallidus interna and externa using ultra-high 7 Tesla MRI

Deep brain stimulation (DBS) surgery has been shown to dramatically improve the quality of life for patients with various motor dysfunctions, such as those afflicted with Parkinson's disease (PD), dystonia, and essential tremor (ET), by relieving motor symptoms associated with such pathologies. The success of DBS procedures is directly related to the proper placement of the electrodes, which requires the ability to accurately detect and identify relevant target structures within the subcortical basal ganglia region. In particular, accurate and reliable segmentation of the globus pallidus (GP) interna is of great interest for DBS surgery for PD and dystonia. In this study, we present a deep-learning based neural network, which we term GP-net, for the automatic segmentation of both the external and internal segments of the globus pallidus. High resolution 7 Tesla images from 101 subjects were used in this study; GP-net is trained on a cohort of 58 subjects, containing patients with movement disorders as well as healthy control subjects. GP-net performs 3D inference in a patient-specific manner, alleviating the need for atlas-based segmentation. GP-net was extensively validated, both quantitatively and qualitatively over 43 test subjects including patients with movement disorders and healthy control and is shown to consistently produce improved segmentation results compared with state-of-the-art atlas-based segmentations. We also demonstrate a postoperative lead location assessment with respect to a segmented globus pallidus obtained by GP-net.