Extensive T1-weighted MRI preprocessing improves generalizability of deep brain age prediction models

Brain age is an estimate of chronological age obtained from T1-weighted magnetic resonance images (T1w MRI), representing a straightforward diagnostic biomarker of brain aging and associated diseases. While the current best accuracy of brain age predictions on T1w MRIs of healthy subjects ranges from two to three years, comparing results across studies is challenging due to differences in the datasets, T1w preprocessing pipelines, and evaluation protocols used. This paper investigates the impact of T1w image preprocessing on the performance of four deep learning brain age models from recent literature. Four preprocessing pipelines, which differed in terms of registration transform, grayscale correction, and software implementation, were evaluated. The results showed that the choice of software or preprocessing steps could significantly affect the prediction error, with a maximum increase of 0.75 years in mean absolute error (MAE) for the same model and dataset. While grayscale correction had no significant impact on MAE, using affine rather than rigid registration to brain atlas statistically significantly improved MAE. Models trained on 3D images with isotropic 1mm3 resolution exhibited less sensitivity to the T1w preprocessing variations compared to 2D models or those trained on downsampled 3D images. Our findings indicate that extensive T1w preprocessing improves MAE, especially when predicting on a new dataset. This runs counter to prevailing research literature, which suggests that models trained on minimally preprocessed T1w scans are better suited for age predictions on MRIs from unseen scanners. We demonstrate that, irrespective of the model or T1w preprocessing used during training, applying some form of offset correction is essential to enable the model's performance to generalize effectively on datasets from unseen sites, regardless of whether they have undergone the same or different T1w preprocessing as the training set.

Psychometric evaluation of the 5-item Medication Adherence Report Scale questionnaire in persons with multiple sclerosis

The 5-item Medication Adherence Report Scale (MARS-5) is a reliable and valid questionnaire for evaluating adherence in patients with asthma, hypertension, and diabetes. Validity has not been determined in multiple sclerosis (MS). We aimed to establish criterion validity and reliability of the MARS-5 in persons with MS (PwMS). Our prospective study included PwMS on dimethyl fumarate (DMF). PwMS self-completed the MARS-5 on the same day before baseline and follow-up brain magnetic resonance imaging (MRI) 3 and 9 months after treatment initiation and were graded as highly and medium adherent upon the 24-cut-off score, established by receiver operator curve analysis. Health outcomes were represented by relapse occurrence from the 1st DMF dispense till follow-up brain MRI and radiological progression (new T2 MRI lesions and quantitative analysis) between baseline and follow-up MRI. Criterion validity was established by association with the Proportion of Days Covered (PDC), new T2 MRI lesions, and Beliefs in Medicines questionnaire (BMQ). The reliability evaluation included internal consistency and the test-retest method. We included 40 PwMS (age 37.6 ± 9.9 years, 75% women), 34 were treatment-naive. No relapses were seen during the follow-up period but quantitative MRI analysis showed new T2 lesions in 6 PwMS. The mean (SD) MARS-5 score was 23.1 (2.5), with 24 PwMS graded as highly adherent. The higher MARS-5 score was associated with higher PDC (b = 0.027, P<0.001, 95% CI: (0.0134-0.0403)) and lower medication concerns (b = -1.25, P<0.001, 95% CI: (-1.93-(-0,579)). Lower adherence was associated with increased number (P = 0.00148) and total volume of new T2 MRI lesions (P = 0.00149). The questionnaire showed acceptable internal consistency (Cronbach α = 0.72) and moderate test-retest reliability (r = 0.62, P < 0.0001, 95% CI: 0.33-0.79). The MARS-5 was found to be valid and reliable for estimating medication adherence and predicting medication concerns in persons with MS.

BASE: Brain Age Standardized Evaluation

Brain age, most commonly inferred from T1-weighted magnetic resonance images (T1w MRI), is a robust biomarker of brain health and related diseases. Superior accuracy in brain age prediction, often falling within a 2-3 year range, is achieved predominantly through deep neural networks. However, comparing study results is difficult due to differences in datasets, evaluation methodologies and metrics. Addressing this, we introduce Brain Age Standardized Evaluation (BASE), which includes (i) a standardized T1w MRI dataset including multi-site, new unseen site, test-retest and longitudinal data, and an associated (ii) evaluation protocol, including repeated model training and upon based comprehensive set of performance metrics measuring accuracy, robustness, reproducibility and consistency aspects of brain age predictions, and (iii) statistical evaluation framework based on linear mixed-effects models for rigorous performance assessment and cross-comparison. To showcase BASE, we comprehensively evaluate four deep learning based brain age models, appraising their performance in scenarios that utilize multi-site, test-retest, unseen site, and longitudinal T1w brain MRI datasets. Ensuring full reproducibility and application in future studies, we have made all associated data information and code publicly accessible at https://github.com/AralRalud/BASE.git.

Extensive T1-weighted MRI Preprocessing Improves Generalizability of Deep Brain Age Prediction Models

Brain age is an estimate of chronological age obtained from T1-weighted magnetic resonance images (T1w MRI) and represents a simple diagnostic biomarker of brain ageing and associated diseases. While the current best accuracy of brain age predictions on T1w MRIs of healthy subjects ranges from two to three years, comparing results from different studies is challenging due to differences in the datasets, T1w preprocessing pipelines, and performance metrics used. This paper investigates the impact of T1w image preprocessing on the performance of four deep learning brain age models presented in recent literature. Four preprocessing pipelines were evaluated, differing in terms of registration, grayscale correction, and software implementation. The results showed that the choice of software or preprocessing steps can significantly affect the prediction error, with a maximum increase of 0.7 years in mean absolute error (MAE) for the same model and dataset. While grayscale correction had no significant impact on MAE, the affine registration, compared to the rigid registration of T1w images to brain atlas was shown to statistically significantly improve MAE. Models trained on 3D images with isotropic 1 mm3 resolution exhibited less sensitivity to the T1w preprocessing variations compared to 2D models or those trained on downsampled 3D images. Some proved invariant to the preprocessing pipeline, however only after offset correction. Our findings generally indicate that extensive T1w preprocessing enhances the MAE, especially when applied to a new dataset. This runs counter to prevailing research literature which suggests that models trained on minimally preprocessed T1w scans are better poised for age predictions on MRIs from unseen scanners. Regardless of model or T1w preprocessing used, we show that to enable generalization of model's performance on a new dataset with either the same or different T1w preprocessing than the one applied in model training, some form of offset correction should be applied.

A Systematic Review of Deep-Learning Methods for Intracranial Aneurysm Detection in CT Angiography

Background: Subarachnoid hemorrhage resulting from cerebral aneurysm rupture is a significant cause of morbidity and mortality. Early identification of aneurysms on Computed Tomography Angiography (CTA), a frequently used modality for this purpose, is crucial, and artificial intelligence (AI)-based algorithms can improve the detection rate and minimize the intra- and inter-rater variability. Thus, a systematic review and meta-analysis were conducted to assess the diagnostic accuracy of deep-learning-based AI algorithms in detecting cerebral aneurysms using CTA. Methods: PubMed (MEDLINE), Embase, and the Cochrane Library were searched from January 2015 to July 2023. Eligibility criteria involved studies using fully automated and semi-automatic deep-learning algorithms for detecting cerebral aneurysms on the CTA modality. Eligible studies were assessed using the Preferred Reporting Items for Systematic Reviews and Meta-Analysis (PRISMA) guidelines and the Quality Assessment of Diagnostic Accuracy Studies 2 (QUADAS-2) tool. A diagnostic accuracy meta-analysis was conducted to estimate pooled lesion-level sensitivity, size-dependent lesion-level sensitivity, patient-level specificity, and the number of false positives per image. An enhanced FROC curve was utilized to facilitate comparisons between the studies. Results: Fifteen eligible studies were assessed. The findings indicated that the methods exhibited high pooled sensitivity (0.87, 95% confidence interval: 0.835 to 0.91) in detecting intracranial aneurysms at the lesion level. Patient-level sensitivity was not reported due to the lack of a unified patient-level sensitivity definition. Only five studies involved a control group (healthy subjects), whereas two provided information on detection specificity. Moreover, the analysis of size-dependent sensitivity reported in eight studies revealed that the average sensitivity for small aneurysms (<3 mm) was rather low (0.56). Conclusions: The studies included in the analysis exhibited a high level of accuracy in detecting intracranial aneurysms larger than 3 mm in size. Nonetheless, there is a notable gap that necessitates increased attention and research focus on the detection of smaller aneurysms, the use of a common test dataset, and an evaluation of a consistent set of performance metrics.

Deep geometric learning for intracranial aneurysm detection: towards expert rater performance

BACKGROUND

Early detection of intracranial aneurysms (IAs) is crucial for patient outcomes. Typically identified on angiographic scans such as CT angiography (CTA) or MR angiography (MRA), the sensitivity of experts in studies on small IAs (diameter <3 mm) was moderate (64-74.1% for CTAs and 70-92.8% for MRAs), and these figures could be lower in a routine clinical setting. Recent research shows that the expert level of sensitivity might be achieved using deep learning approaches.

METHODS

A large multisite dataset including 1054 MRA and 2174 CTA scans with expert IA annotations was collected. A novel modality-agnostic two-step IA detection approach was proposed. The first step used nnU-Net for segmenting vascular structures, with model training performed separately for each modality. In the second step, segmentations were converted to vascular surface that was parcellated by sampling point clouds and, using a PointNet++ model, each point was labeled as an aneurysm or vessel class.

RESULTS

Quantitative validation of the test data from different sites than the training data showed that the proposed approach achieved pooled sensitivity of 85% and 90% on 157 MRA scans and 1338 CTA scans, respectively, while the sensitivity for small IAs was 72% and 83%, respectively. The corresponding number of false findings per image was low at 1.54 and 1.57, and 0.4 and 0.83 on healthy subject data.

CONCLUSIONS

The proposed approach achieved a state-of-the-art balance between the sensitivity and the number of false findings, matched the expert-level sensitivity to small (and other) IAs on external data, and therefore seems fit for computer-assisted detection of IAs in a clinical setting.

Automated intracranial vessel labeling with learning boosted by vessel connectivity, radii and spatial context

Cerebrovascular diseases are among the world's top causes of death and their screening and diagnosis rely on angiographic imaging. We focused on automated anatomical labeling of cerebral arteries that enables their cross-sectional quantification and inter-subject comparisons and thereby identification of geometric risk factors correlated to the cerebrovascular diseases. We used 152 cerebral TOF-MRA angiograms from three publicly available datasets and manually created reference labeling using Slicer3D. We extracted centerlines from nnU-net based segmentations using VesselVio and labeled them according to the reference labeling. Vessel centerline coordinates, in combination with additional vessel connectivity, radius and spatial context features were used for training seven distinct PointNet++ models. Model trained solely on the vessel centerline coordinates resulted in ACC of 0.93 and across-labels average TPR was 0.88. Including vessel radius significantly improved ACC to 0.95, and average TPR to 0.91. Finally, focusing spatial context to the Circle of Willis are resulted in best ACC of 0.96 and best average TPR of 0.93. Hence, using vessel radius and spatial context greatly improved vessel labeling, with the attained perfomance opening the avenue for clinical applications of intracranial vessel labeling.

Abstract WP10: Automated Methods Of Aneurysm Growth Detection Compared With Clinical Assessment And Follow-up

Introduction: In cases where the risk of intracranial aneurysms (IA) rupture is low or secondary to other patient health concerns, unruptured IA may be monitored through imaging. In this work, we applied different computational methods to detect IA growth and compared the results to clinical findings.

Hypothesis: We hypothesize that automated methods of IA growth detection are comparable to clinical assessment.

Methods: The study cohort consisted of 20 female patients with saccular IA diagnosed between 2005-2011 in UCLA Medical Center. 6 were located at the PcoA, 10 at the superior hypophyseal artery, and 4 at the ophthalmic artery. 8 IA were determined to be growing. Baseline IA size was 3.85±4.30 mm. For each case, initial and first follow-up CTA image studies (interval 2.50±2.75 yrs) were analyzed. Cohort follow-up continued for an average of 8.5±5.75 yrs. Automated methods to detect IA growth included maximum diameter (HMAX), surface area (SA), volume (V), and a novel 2-stage morphing approach which deforms the baseline IA surface mesh to that of the subsequent scan and yields a set of characteristics that describe the changes: dMPL, dSA, dV, and dICDD. Statistical methods used included the Mann-Whitney U test and Chi-Square Test with significance set at p <0.01, and ROC AUC analysis.

Results: The stable and growth groups did not significantly differ with respect to case details and medical history, including IA size, location, imaging interval, age, family history, stroke, hypertension, thyroid disease, cancer, and atherosclerosis. Clinically determined change in IA diameter (p=0.007, AUC=0.927), computed HMAX (p=0.0002, AUC=0.958), SA (p=0.001, AUC=0.917), V (p=0.001, AUC=0.927), and dSA (p=0.005, AUC=0.865) were significantly different between the groups. The duration of follow-up significantly differed between the groups (p<0.01), largely due to treatment of growing IA. During follow-up only one IA changing from stable to growing, and 5 of 6 subsequently treated IA were from within the initial growth group.

Conclusion: Several automated measures provided comparable performance to clinical size when assessing IA growth. HMAX in particular may be useful to assist clinical evaluation, as it was slightly more effective than recorded clinical size alone.

Computer-Assisted Aneurysm Growth Evaluation and Detection (AGED): Comparison with Clinical Aneurysm Follow-Up

Background and Purpose

Since growing intracranial aneurysms (IA) are more likely to rupture, detecting growth is an important part of unruptured IA follow-up. Recent studies have consistently shown that detecting IA growth can be challenging, especially in smaller aneurysms. In this study, we present an automated computational method to assist detecting aneurysm growth.

Materials and Methods

An analysis program, Aneurysm Growth Evaluation & Detection (AGED) based on IA images was developed. To verify the program can satisfactorily detect clinical aneurysm growth, we performed this comparative study using clinical determinations of growth during IA follow-up as a gold standard. Patients with unruptured, saccular IA followed by diagnostic brain CTA to monitor IA progression were reviewed. 48 IA image series from twenty longitudinally-followed ICA IA were analyzed using AGED. A set of IA morphologic features were calculated. Nonparametric statistical tests and ROC analysis were performed to evaluate the performance of each feature for growth detection.

Results

The set of automatically calculated morphologic features demonstrated comparable results to standard, manual clinical IA growth evaluation. Specifically, automatically calculated HMAX was superior (AUC = 0.958) at distinguishing growing and stable IA, followed by V, and SA (AUC = 0.927 and 0.917, respectively).

Conclusion

Our findings support automatic methods of detecting IA growth from sequential imaging studies as a useful adjunct to standard clinical assessment. AGED-generated growth detection shows promise for characterization and detection of IA growth and time-saving comparing with manual measurements.

Deep Shape Features for Predicting Future Intracranial Aneurysm Growth

Introduction: Intracranial aneurysms (IAs) are a common vascular pathology and are associated with a risk of rupture, which is often fatal. Aneurysm growth is considered a surrogate of rupture risk; therefore, the study aimed to develop and evaluate prediction models of future artificial intelligence (AI) growth based on baseline aneurysm morphology as a computer-aided treatment decision support.

Materials and methods: Follow-up CT angiography (CTA) and magnetic resonance angiography (MRA) angiograms of 39 patients with 44 IAs were classified by an expert as growing and stable (25/19). From the angiograms vascular surface meshes were extracted and the aneurysm shape was characterized by established morphologic features and novel deep shape features. The features corresponding to the baseline aneurysms were used to predict future aneurysm growth using univariate thresholding, multivariate random forest and multi-layer perceptron (MLP) learning, and deep shape learning based on the PointNet++ model.

Results: The proposed deep shape feature learning method achieved an accuracy of 0.82 (sensitivity = 0.96, specificity = 0.63), while the multivariate learning and univariate thresholding methods were inferior with an accuracy of up to 0.68 and 0.63, respectively.

Conclusion: High-performing classification of future growing IAs renders the proposed deep shape features learning approach as the key enabling tool to manage rupture risk in the “no treatment” paradigm of patient follow-up imaging.

Impact of aerobic exercise on clinical and magnetic resonance imaging biomarkers in persons with multiple sclerosis: An exploratory randomized controlled trial

BACKGROUND

There is insufficient knowledge about how aerobic exercise impacts the disease process of multiple sclerosis, which is characterized by accumulation of white matter lesions and accelerated brain atrophy.

OBJECTIVE

To examine the effect of aerobic exercise on neuroinflammation and neurodegeneration by magnetic resonance imaging and clinical measures of disease activity and progression in persons with multiple sclerosis.

PATIENTS AND METHODS

An exploratory 12-week randomized control trial including an intervention group (n = 14, 12 weeks of aerobic exercise twice weekly) and a control group (n = 14, continuation of usual lifestyle). Primary outcomes were magnetic resonance imaging measures (lesion load, brain structure volume change), while secondary outcomes included disability measures, blood cytokine levels, cognitive tests and patient-reported outcomes.

RESULTS

The effects of aerobic exercise on whole brain and grey matter atrophy were minor. Surprisingly, the observed effect on volume (atrophy) in selected brain substructures was heterogeneous. Putaminal and posterior cingulate volumes decreased, parahippocampal gyrus volume increased, thalamus and amygdala volume remained the same, and active lesion load and count decreased. However, apart from weak improvements in walking speed and brain-derived neurotrophic factor levels, there was no effect of aerobic exercise on other clinical, cognitive or patient-reported outcomes.

CONCLUSION

These results suggest that aerobic exercise in persons with multiple sclerosis has a positive effect on the volume of some of the substructures of the brain, possibly indicating a slowing of the neurodegenerative process in these regions, but a negative impact on the volume of some other substructures, with unclear implications. Further research is needed to determine whether the slight decrease in active lesion volume and count implies an anti-inflammatory effect of aerobic exercise, and the exact significance of the heterogeneous results of volumetric assessments.

An Image Registration-Based Method for EPI Distortion Correction Based on Opposite Phase Encoding (COPE)

Surprisingly, estimated voxel displacement maps (VDMs), based on image registration, seem to work just as well to correct geometrical distortion in functional MRI data (EPI) as VDMs based on actual information about the magnetic field. In this article, we compare our new image registration-based distortion correction method ‘COPE’ to an implementation of the pixelshift method. Our approach builds on existing image registration-based techniques using opposite phase encoding, extending these by local cost aggregation. Comparison of these methods with 3T and 7T spin-echo (SE) and gradient-echo (GE) data show that the image registration-based method is a good alternative to the fieldmap-based EPI distortion correction method.

An Unsupervised Learning Approach to Discontinuity-Preserving Image Registration

Most traditional image registration algorithms aimed at aligning a pair of images impose well-established regularizers to guarantee smoothness of unknown deformation fields. Since these methods assume global smoothness within the image domain, they pose issues for scenarios where local discontinuities are expected, such as the sliding motion between the lungs and the chest wall during the respiratory cycle. Furthermore, an objective function must be optimized for each given pair of images, thus registering multiple sets of images become very time-consuming and scale poorly to higher resolution image volumes.

Using recent advances in deep learning, we propose an unsupervised learning-based image registration model. The model is trained over a loss function with a custom regularizer that preserves local discontinuities, while simultaneously respecting the smoothness assumption in homogeneous regions of image volumes. Qualitative and quantitative validations on 3D pairs of lung CT datasets will be presented.

Learning-Based Affine Registration of Histological Images

The use of different stains for histological sample preparation reveals distinct tissue properties and may result in a more accurate diagnosis. However, as a result of the staining process, the tissue slides are being deformed and registration is required before further processing. The importance of this problem led to organizing an open challenge named Automatic Non-rigid Histological Image Registration Challenge (ANHIR), organized jointly with the IEEE ISBI 2019 conference. The challenge organizers provided several hundred image pairs and a server-side evaluation platform. One of the most difficult sub-problems for the challenge participants was to find an initial, global transform, before attempting to calculate the final, non-rigid deformation field. This article solves the problem by proposing a deep network trained in an unsupervised way with a good generalization. We propose a method that works well for images with different resolutions, aspect ratios, without the necessity to perform image padding, while maintaining a low number of network parameters and fast forward pass time. The proposed method is orders of magnitude faster than the classical approach based on the iterative similarity metric optimization or computer vision descriptors. The success rate is above 98% for both the training set and the evaluation set. We make both the training and inference code freely available.

Enabling Manual Intervention for Otherwise Automated Registration of Large Image Series

Aligning thousands of images from serial imaging techniques can be a cumbersome task. Methods ([2, 11, 21]) and programs for automation exist (e.g. [1, 4, 10]) but often need case-specific tuning of many meta-parameters (e.g. mask, pyramid-scales, denoise, transform-type, method/metric, optimizer and its parameters). Other programs, that apparently only depend on a few parameter often just hide many of the remaining ones (initialized with default values), often cannot handle challenging cases satisfactorily.

Instead of spending much time on the search for suitable meta-parameters that yield a usable result for the complete image series, the described approach allows to intervene by manually aligning problematic image pairs. The manually found transform is then used by the automatic alignment as an initial transformation that is then optimized as in the pure automatic case. Therefore the manual alignment does not have to be very precise. This way the worst case time consumption is limited and can be estimated (manual alignment of the whole series) in contrast to tuning of meta-parameters of pure auto-alignment of complete series which can hardly be guessed.

An Image Registration Framework for Discontinuous Mappings Along Cracks

A novel crack capable image registration framework is proposed. The approach is designed for registration problems suffering from cracks, gaps, or holes. The approach enables discontinuous transformation fields and also features an automatically computed crack indicator function and therefore does not require a pre-segmentation. The new approach is a generalization of the commonly used variational image registration approach. New contributions are an additional dissipation term in the overall energy, a proper balancing of different ingredients, and a joint optimization for both, the crack indicator function and the transformation. Results for histological serial sectioning of marmoset brain images demonstrate the potential of the approach and its superiority as compared to a standard registration.

Nonlinear Alignment of Whole Tractograms with the Linear Assignment Problem

After registration of the imaging data of two brains, homologous anatomical structures are expected to overlap better than before registration. Diffusion magnetic resonance imaging (dMRI) techniques and tractography techniques provide a representation of the anatomical connections in the white matter, as hundreds of thousands of streamlines, forming the tractogram. The literature on methods for aligning tractograms is in active development and provides methods that operate either from voxel information, e.g. fractional anisotropy, orientation distribution function, T1-weighted MRI, or directly from streamline information. In this work, we align streamlines using the linear assignment problem (LAP) and propose a method to reduce the high computational cost of aligning whole brain tractograms. As further contribution, we present a comparison among some of the freely-available linear and nonlinear tractogram alignment methods, where we show that our LAP-based method outperforms all others. In discussing the results, we show that a main limitation of all streamline-based nonlinear registration methods is the computational cost and that addressing such problem may lead to further improvement in the quality of registration.

Reference-free error estimation for multiple measurement methods

We present a computational framework to select the most accurate and precise method of measurement of a certain quantity, when there is no access to the true value of the measurand. A typical use case is when several image analysis methods are applied to measure the value of a particular quantitative imaging biomarker from the same images. The accuracy of each measurement method is characterized by systematic error (bias), which is modeled as a polynomial in true values of measurand, and the precision as random error modeled with a Gaussian random variable. In contrast to previous works, the random errors are modeled jointly across all methods, thereby enabling the framework to analyze measurement methods based on similar principles, which may have correlated random errors. Furthermore, the posterior distribution of the error model parameters is estimated from samples obtained by Markov chain Monte-Carlo and analyzed to estimate the parameter values and the unknown true values of the measurand. The framework was validated on six synthetic and one clinical dataset containing measurements of total lesion load, a biomarker of neurodegenerative diseases, which was obtained with four automatic methods by analyzing brain magnetic resonance images. The estimates of bias and random error were in a good agreement with the corresponding least squares regression estimates against a reference.

Locally adaptive magnetic resonance intensity models for unsupervised segmentation of multiple sclerosis lesions

Multiple sclerosis (MS) is a neurological disease characterized by focal lesions and morphological changes in the brain captured on magnetic resonance (MR) images. However, extraction of the corresponding imaging markers requires accurate segmentation of normal-appearing brain structures (NABS) and the lesions in MR images. On MR images of healthy brains, the NABS can be accurately captured by MR intensity mixture models, which, in combination with regularization techniques, such as in Markov random field (MRF) models, are known to give reliable NABS segmentation. However, on MR images that also contain abnormalities such as MS lesions, obtaining an accurate and reliable estimate of NABS intensity models is a challenge. We propose a method for automated segmentation of normal-appearing and abnormal structures in brain MR images that is based on a locally adaptive NABS model, a robust model parameters estimation method, and an MRF-based segmentation framework. Experiments on multisequence brain MR images of 30 MS patients show that, compared to whole-brain MR intensity model and compared to four popular unsupervised lesion segmentation methods, the proposed method increases the accuracy of MS lesion segmentation.

3D-2D registration in endovascular image-guided surgery: evaluation of state-of-the-art methods on cerebral angiograms

PURPOSE

Image guidance for minimally invasive surgery is based on spatial co-registration and fusion of 3D pre-interventional images and treatment plans with the 2D live intra-interventional images. The spatial co-registration or 3D-2D registration is the key enabling technology; however, the performance of state-of-the-art automated methods is rather unclear as they have not been assessed under the same test conditions. Herein we perform a quantitative and comparative evaluation of ten state-of-the-art methods for 3D-2D registration on a public dataset of clinical angiograms.

METHODS

Image database consisted of 3D and 2D angiograms of 25 patients undergoing treatment for cerebral aneurysms or arteriovenous malformations. On each of the datasets, highly accurate "gold-standard" registrations of 3D and 2D images were established based on patient-attached fiducial markers. The database was used to rigorously evaluate ten state-of-the-art 3D-2D registration methods, namely two intensity-, two gradient-, three feature-based and three hybrid methods, both for registration of 3D pre-interventional image to monoplane or biplane 2D images.

RESULTS

Intensity-based methods were most accurate in all tests (0.3 mm). One of the hybrid methods was most robust with 98.75% of successful registrations (SR) and capture range of 18 mm for registrations of 3D to biplane 2D angiograms. In general, registration accuracy was similar whether registration of 3D image was performed onto mono- or biplanar 2D images; however, the SR was substantially lower in case of 3D to monoplane 2D registration. Two feature-based and two hybrid methods had clinically feasible execution times in the order of a second.

CONCLUSIONS

Performance of methods seems to fall below expectations in terms of robustness in case of registration of 3D to monoplane 2D images, while translation into clinical image guidance systems seems readily feasible for methods that perform registration of the 3D pre-interventional image onto biplanar intra-interventional 2D images.

Simultaneous 3D-2D image registration and C-arm calibration: Application to endovascular image-guided interventions

PURPOSE

Three-dimensional to two-dimensional (3D-2D) image registration is a key to fusion and simultaneous visualization of valuable information contained in 3D pre-interventional and 2D intra-interventional images with the final goal of image guidance of a procedure. In this paper, the authors focus on 3D-2D image registration within the context of intracranial endovascular image-guided interventions (EIGIs), where the 3D and 2D images are generally acquired with the same C-arm system. The accuracy and robustness of any 3D-2D registration method, to be used in a clinical setting, is influenced by (1) the method itself, (2) uncertainty of initial pose of the 3D image from which registration starts, (3) uncertainty of C-arm's geometry and pose, and (4) the number of 2D intra-interventional images used for registration, which is generally one and at most two. The study of these influences requires rigorous and objective validation of any 3D-2D registration method against a highly accurate reference or "gold standard" registration, performed on clinical image datasets acquired in the context of the intervention.

METHODS

The registration process is split into two sequential, i.e., initial and final, registration stages. The initial stage is either machine-based or template matching. The latter aims to reduce possibly large in-plane translation errors by matching a projection of the 3D vessel model and 2D image. In the final registration stage, four state-of-the-art intrinsic image-based 3D-2D registration methods, which involve simultaneous refinement of rigid-body and C-arm parameters, are evaluated. For objective validation, the authors acquired an image database of 15 patients undergoing cerebral EIGI, for which accurate gold standard registrations were established by fiducial marker coregistration.

RESULTS

Based on target registration error, the obtained success rates of 3D to a single 2D image registration after initial machine-based and template matching and final registration involving C-arm calibration were 36%, 73%, and 93%, respectively, while registration accuracy of 0.59 mm was the best after final registration. By compensating in-plane translation errors by initial template matching, the success rates achieved after the final stage improved consistently for all methods, especially if C-arm calibration was performed simultaneously with the 3D-2D image registration.

CONCLUSIONS

Because the tested methods perform simultaneous C-arm calibration and 3D-2D registration based solely on anatomical information, they have a high potential for automation and thus for an immediate integration into current interventional workflow. One of the authors' main contributions is also comprehensive and representative validation performed under realistic conditions as encountered during cerebral EIGI.

Robust estimation of unbalanced mixture models on samples with outliers

Mixture models are often used to compactly represent samples from heterogeneous sources. However, in real world, the samples generally contain an unknown fraction of outliers and the sources generate different or unbalanced numbers of observations. Such unbalanced and contaminated samples may, for instance, be obtained by high density data sensors such as imaging devices. Estimation of unbalanced mixture models from samples with outliers requires robust estimation methods. In this paper, we propose a novel robust mixture estimator incorporating trimming of the outliers based on component-wise confidence level ordering of observations. The proposed method is validated and compared to the state-of-the-art FAST-TLE method on two data sets, one consisting of synthetic samples with a varying fraction of outliers and a varying balance between mixture weights, while the other data set contained structural magnetic resonance images of the brain with tumors of varying volumes. The results on both data sets clearly indicate that the proposed method is capable to robustly estimate unbalanced mixtures over a broad range of outlier fractions. As such, it is applicable to real-world samples, in which the outlier fraction cannot be estimated in advance.

3D-2D registration of cerebral angiograms: a method and evaluation on clinical images

Endovascular image-guided interventions (EIGI) involve navigation of a catheter through the vasculature followed by application of treatment at the site of anomaly using live 2D projection images for guidance. 3D images acquired prior to EIGI are used to quantify the vascular anomaly and plan the intervention. If fused with the information of live 2D images they can also facilitate navigation and treatment. For this purpose 3D-2D image registration is required. Although several 3D-2D registration methods for EIGI achieve registration accuracy below 1 mm, their clinical application is still limited by insufficient robustness or reliability. In this paper, we propose a 3D-2D registration method based on matching a 3D vasculature model to intensity gradients of live 2D images. To objectively validate 3D-2D registration methods, we acquired a clinical image database of 10 patients undergoing cerebral EIGI and established "gold standard" registrations by aligning fiducial markers in 3D and 2D images. The proposed method had mean registration accuracy below 0.65 mm, which was comparable to tested state-of-the-art methods, and execution time below 1 s. With the highest rate of successful registrations and the highest capture range the proposed method was the most robust and thus a good candidate for application in EIGI.