Robust thalamic nuclei segmentation from T1-weighted MRI using polynomial intensity transformation.

Accurate segmentation of thalamic nuclei, crucial for understanding their role in healthy cognition and in pathologies, is challenging to achieve on standard T1-weighted (T1w) magnetic resonance imaging (MRI) due to poor image contrast. White-matter-nulled (WMn) MRI sequences improve intrathalamic contrast but are not part of clinical protocols or extant databases. In this study, we introduce histogram-based polynomial synthesis (HIPS), a fast preprocessing transform step that synthesizes WMn-like image contrast from standard T1w MRI using a polynomial approximation for intensity transformation. HIPS was incorporated into THalamus Optimized Multi-Atlas Segmentation (THOMAS) pipeline, a method developed and optimized for WMn MRI. HIPS-THOMAS was compared to a convolutional neural network (CNN)-based segmentation method and THOMAS modified for T1w images (T1w-THOMAS). The robustness and accuracy of the three methods were tested across different image contrasts (MPRAGE, SPGR, and MP2RAGE), scanner manufacturers (PHILIPS, GE, and Siemens), and field strengths (3T and 7T). HIPS-transformed images improved intra-thalamic contrast and thalamic boundaries, and HIPS-THOMAS yielded significantly higher mean Dice coefficients and reduced volume errors compared to both the CNN method and T1w-THOMAS. Finally, all three methods were compared using the frequently travelling human phantom MRI dataset for inter- and intra-scanner variability, with HIPS displaying the least inter-scanner variability and performing comparably with T1w-THOMAS for intra-scanner variability. In conclusion, our findings highlight the efficacy and robustness of HIPS in enhancing thalamic nuclei segmentation from standard T1w MRI.

Deep learning microstructure estimation of developing brains from diffusion MRI: a newborn and fetal study.

Diffusion-weighted magnetic resonance imaging (dMRI) is widely used to assess the brain white matter. Fiber orientation distribution functions (FODs) are a common way of representing the orientation and density of white matter fibers. However, with standard FOD computation methods, accurate estimation of FODs requires a large number of measurements that usually cannot be acquired for newborns and fetuses. We propose to overcome this limitation by using a deep learning method to map as few as six diffusion-weighted measurements to the target FOD. To train the model, we use the FODs computed using multi-shell high angular resolution measurements as target. Extensive quantitative evaluations show that the new deep learning method, using significantly fewer measurements, achieves comparable or superior results to standard methods such as Constrained Spherical Deconvolution. We demonstrate the generalizability of the new deep learning method across scanners, acquisition protocols, and anatomy on two clinical datasets of newborns and fetuses. Additionally, we compute agreement metrics within the HARDI newborn dataset, and validate fetal FODs with post-mortem histological data. The results of this study show the advantage of deep learning in inferring the microstructure of the developing brain from in-vivo dMRI measurements that are often very limited due to subject motion and limited acquisition times, but also highlight the intrinsic limitations of dMRI in the analysis of the developing brain microstructure. These findings, therefore, advocate for the need for improved methods that are tailored to studying the early development of human brain.

A Multicenter Longitudinal MRI Study Assessing LeMan-PV Software Accuracy in the Detection of White Matter Lesions in Multiple Sclerosis Patients.

BACKGROUND: Detecting new and enlarged lesions in multiple sclerosis (MS) patients is needed to determine their disease activity. LeMan-PV is a software embedded in the scanner reconstruction system of one vendor, which automatically assesses new and enlarged white matter lesions (NELs) in the follow-up of MS patients; however, multicenter validation studies are lacking. PURPOSE: To assess the accuracy of LeMan-PV for the longitudinal detection NEL white-matter MS lesions in a multicenter clinical setting. STUDY TYPE: Retrospective, longitudinal. SUBJECTS: A total of 206 patients with a definitive MS diagnosis and at least two follow-up MRI studies from five centers participating in the Swiss Multiple Sclerosis Cohort study. Mean age at first follow-up = 45.2 years (range: 36.9-52.8 years); 70 males. FIELD STRENGTH/SEQUENCE: Fluid attenuated inversion recovery (FLAIR) and T1-weighted magnetization prepared rapid gradient echo (T1-MPRAGE) sequences at 1.5 T and 3 T. ASSESSMENT: The study included 313 MRI pairs of datasets. Data were analyzed with LeMan-PV and compared with a manual "reference standard" provided by a neuroradiologist. A second rater (neurologist) performed the same analysis in a subset of MRI pairs to evaluate the rating-accuracy. The Sensitivity (Se), Specificity (Sp), Accuracy (Acc), F1-score, lesion-wise False-Positive-Rate (aFPR), and other measures were used to assess LeMan-PV performance for the detection of NEL at 1.5 T and 3 T. The performance was also evaluated in the subgroup of 123 MRI pairs at 3 T. STATISTICAL TESTS: Intraclass correlation coefficient (ICC) and Cohen's kappa (CK) were used to evaluate the agreement between readers. RESULTS: The interreader agreement was high for detecting new lesions (ICC = 0.97, Pvalue < 10-20 , CK = 0.82, P value = 0) and good (ICC = 0.75, P value < 10-12 , CK = 0.68, P value = 0) for detecting enlarged lesions. Across all centers, scanner field strengths (1.5 T, 3 T), and for NEL, LeMan-PV achieved: Acc = 61%, Se = 65%, Sp = 60%, F1-score = 0.44, aFPR = 1.31. When both follow-ups were acquired at 3 T, LeMan-PV accuracy was higher (Acc = 66%, Se = 66%, Sp = 66%, F1-score = 0.28, aFPR = 3.03). DATA CONCLUSION: In this multicenter study using clinical data settings acquired at 1.5 T and 3 T, and variations in MRI protocols, LeMan-PV showed similar sensitivity in detecting NEL with respect to other recent 3 T multicentric studies based on neural networks. While LeMan-PV performance is not optimal, its main advantage is that it provides automated clinical decision support integrated into the radiological-routine flow. EVIDENCE LEVEL: 4 TECHNICAL EFFICACY: Stage 2.

Towards Automated Brain Aneurysm Detection in TOF-MRA: Open Data, Weak Labels, and Anatomical Knowledge.

Brain aneurysm detection in Time-Of-Flight Magnetic Resonance Angiography (TOF-MRA) has undergone drastic improvements with the advent of Deep Learning (DL). However, performances of supervised DL models heavily rely on the quantity of labeled samples, which are extremely costly to obtain. Here, we present a DL model for aneurysm detection that overcomes the issue with "weak" labels: oversized annotations which are considerably faster to create. Our weak labels resulted to be four times faster to generate than their voxel-wise counterparts. In addition, our model leverages prior anatomical knowledge by focusing only on plausible locations for aneurysm occurrence. We first train and evaluate our model through cross-validation on an in-house TOF-MRA dataset comprising 284 subjects (170 females / 127 healthy controls / 157 patients with 198 aneurysms). On this dataset, our best model achieved a sensitivity of 83%, with False Positive (FP) rate of 0.8 per patient. To assess model generalizability, we then participated in a challenge for aneurysm detection with TOF-MRA data (93 patients, 20 controls, 125 aneurysms). On the public challenge, sensitivity was 68% (FP rate = 2.5), ranking 4th/18 on the open leaderboard. We found no significant difference in sensitivity between aneurysm risk-of-rupture groups (p = 0.75), locations (p = 0.72), or sizes (p = 0.15). Data, code and model weights are released under permissive licenses. We demonstrate that weak labels and anatomical knowledge can alleviate the necessity for prohibitively expensive voxel-wise annotations.

CROSS-AGE AND CROSS-SITE DOMAIN SHIFT IMPACTS ON DEEP LEARNING-BASED WHITE MATTER FIBER ESTIMATION IN NEWBORN AND BABY BRAINS.

Deep learning models have shown great promise in estimating tissue microstructure from limited diffusion magnetic resonance imaging data. However, these models face domain shift challenges when test and train data are from different scanners and protocols, or when the models are applied to data with inherent variations such as the developing brains of infants and children scanned at various ages. Several techniques have been proposed to address some of these challenges, such as data harmonization or domain adaptation in the adult brain. However, those techniques remain unexplored for the estimation of fiber orientation distribution functions in the rapidly developing brains of infants. In this work, we extensively investigate the age effect and domain shift within and across two different cohorts of 201 newborns and 165 babies using the Method of Moments and fine-tuning strategies. Our results show that reduced variations in the microstructural development of babies in comparison to newborns directly impact the deep learning models' cross-age performance. We also demonstrate that a small number of target domain samples can significantly mitigate domain shift problems.

A multi-scale probabilistic atlas of the human connectome.

The human brain is a complex system that can be efficiently represented as a network of structural connectivity. Many imaging studies would benefit from such network information, which is not always available. In this work, we present a whole-brain multi-scale structural connectome atlas. This tool has been derived from a cohort of 66 healthy subjects imaged with optimal technology in the setting of the Human Connectome Project. From these data we created, using extensively validated diffusion-data processing, tractography and gray-matter parcellation tools, a multi-scale probabilistic atlas of the human connectome. In addition, we provide user-friendly and accessible code to match this atlas to individual brain imaging data to extract connection-specific quantitative information. This can be used to associate individual imaging findings, such as focal white-matter lesions or regional alterations, to specific connections and brain circuits. Accordingly, network-level consequences of regional changes can be analyzed even in absence of diffusion and tractography data. This method is expected to broaden the accessibility and lower the yield for connectome research.

CVSnet: A machine learning approach for automated central vein sign assessment in multiple sclerosis.

The central vein sign (CVS) is an efficient imaging biomarker for multiple sclerosis (MS) diagnosis, but its application in clinical routine is limited by inter-rater variability and the expenditure of time associated with manual assessment. We describe a deep learning-based prototype for automated assessment of the CVS in white matter MS lesions using data from three different imaging centers. We retrospectively analyzed data from 3 T magnetic resonance images acquired on four scanners from two different vendors, including adults with MS (n = 42), MS mimics (n = 33, encompassing 12 distinct neurological diseases mimicking MS) and uncertain diagnosis (n = 5). Brain white matter lesions were manually segmented on FLAIR* images. Perivenular assessment was performed according to consensus guidelines and used as ground truth, yielding 539 CVS-positive (CVS+ ) and 448 CVS-negative (CVS- ) lesions. A 3D convolutional neural network ("CVSnet") was designed and trained on 47 datasets, keeping 33 for testing. FLAIR* lesion patches of CVS+ /CVS- lesions were used for training and validation (n = 375/298) and for testing (n = 164/150). Performance was evaluated lesion-wise and subject-wise and compared with a state-of-the-art vesselness filtering approach through McNemar's test. The proposed CVSnet approached human performance, with lesion-wise median balanced accuracy of 81%, and subject-wise balanced accuracy of 89% on the validation set, and 91% on the test set. The process of CVS assessment, in previously manually segmented lesions, was ~ 600-fold faster using the proposed CVSnet compared with human visual assessment (test set: 4 seconds vs. 40 minutes). On the validation and test sets, the lesion-wise performance outperformed the vesselness filter method (P < 0.001). The proposed deep learning prototype shows promising performance in differentiating MS from its mimics. Our approach was evaluated using data from different hospitals, enabling larger multicenter trials to evaluate the benefit of introducing the CVS marker into MS diagnostic criteria.

Episodic memory decline in Parkinson' s disease: relation with white matter hyperintense lesions and influence of quantification method.

The relation of white matter hyperintense lesions to episodic memory impairment in patients with Parkinson's disease (PD) is still controversial. We aimed at evaluating the relation between white matter hyperintense lesions and episodic memory decline in patients with PD. In this multicentric prospective study, twenty-one normal controls, 15 PD patients without mild cognitive impairment (MCI) and 13 PD patients with MCI were selected to conduct a clinico-radiological correlation analysis. Performance during episodic memory testing, age-related white matter changes score, total manual and automated white matter hyperintense lesions volume and lobar white matter hyperintense lesions volumes were compared between groups using the Kruskal-Wallis and Wilcoxon signed-rank tests, and correlations were assessed using the Spearman test. MCI PD patients had impaired free recall. They also had higher total, left prefrontal and left temporal white matter hyperintense lesions volumes than normal controls. Free recall performance was negatively correlated with the total white matter hyperintense lesions volume, either manually or automatically delineated, but not with the age-related white matter changes score. Using automated segmentation, both the left prefrontal and temporal white matter hyperintense lesions volumes were negatively correlated with the free recall performance. Early episodic memory impairment in MCI PD patients may be related to white matter hyperintense lesions, mainly in the prefrontal and temporal lobes. This relation is influenced by the method used for white matter hyperintense lesions quantification. Automated volumetry allows for detecting those changes.

Pretherapeutic Motor Thalamus Resting-State Functional Connectivity with Visual Areas Predicts Tremor Arrest After Thalamotomy for Essential Tremor: Tracing the Cerebello-thalamo-visuo-motor Network.

BACKGROUND: Essential tremor (ET) is a common movement disorder. Resting-state functional magnetic resonance imaging is a noninvasive neuroimaging method acquired in absence of task. OBJECTIVE: Our study aimed to correlate pretherapeutic ventrolateral thalamus functional connectivity (FC) with clinical results 1 year after stereotactic radiosurgical thalamotomy (SRS-T) for drug-resistant ET. Data from 12 healthy control individuals were additionally included. METHODS: Resting state was acquired for 17 consecutive (right-handed) patients, before and 1 year after left unilateral SRS-T. Standard tremor scores were evaluated pretherapeutically and 1 year after SRS-T. Tremor network was investigated using region of interest, left ventrolateral ventral (VLV) cluster, obtained from pretherapeutic diffusion magnetic resonance imaging. Seed-based FC was obtained as correlations between the time courses of the VLV and that of every other voxel. The seed-connectivity maps were obtained pretherapeutically and correlated across all patients with clinical outcome 1 year after SRS-T. One-year magnetic resonance signature volume was always located inside VLV and did not correlate with reported seed-FC measures (P > 0.05). RESULTS: We report statistically significant correlations between pretherapeutic VLV FC with clinical outcome for 1) right visual association area (Brodmann area, BA19) predicting 1 year activities of daily living decrease (Punc = 0.02); 2) left fusiform gyrus (BA37) predicting 1 year head tremor score improvement (Punc = 0.04); and 3) posterior cingulate (left BA23, Puncor = 0.009), lateral temporal cortex (right BA21, Punc = 0.02) predicting time to tremor arrest. CONCLUSIONS: Our results suggest that pretherapeutic resting-state seed-FC of left VLV predicts tremor arrest after SRS-T for ET. Visual areas are identified as the main regions in this correlation.

Ventrolateral Motor Thalamus Abnormal Connectivity in Essential Tremor Before and After Thalamotomy: A Resting-State Functional Magnetic Resonance Imaging Study.

OBJECTIVE: To evaluate functional connectivity (FC) of the ventrolateral thalamus, a common target for drug-resistant essential tremor (ET), resting-state data were analyzed before and 1 year after stereotactic radiosurgical thalamotomy and compared against healthy controls (HCs). METHODS: In total, 17 consecutive patients with ET and 10 HCs were enrolled. Tremor network was investigated using the ventrolateral ventral (VLV) thalamic nucleus as the region of interest, extracted with automated segmentation from pretherapeutic diffusion magnetic resonance imaging. Temporal correlations of VLV at whole brain level were evaluated by comparing drug-naïve patients with ET with HCs, and longitudinally, 1 year after stereotactic radiosurgical thalamotomy. 1 year thalamotomy MR signature was always located inside VLV and did not correlate with any of FC measures (P > 0.05). This suggested presence of longitudinal changes in VLV FC independently of the MR signature volume. RESULTS: Pretherapeutic ET displayed altered VLV FC with left primary sensory-motor cortex, pedunculopontine nucleus, dorsal anterior cingulate, left visual association, and left superior parietal areas. Pretherapeutic negative FC with primary somatosensory cortex and pedunculopontine nucleus correlated with poorer baseline tremor scores (Spearman = 0.04 and 0.01). Longitudinal study displayed changes within right dorsal attention (frontal eye-fields and posterior parietal) and salience (anterior insula) networks, as well as areas involved in hand movement planning or language production. CONCLUSIONS: Our results demonstrated that patients with ET and HCs differ in their left VLV FC to primary somatosensory and supplementary motor, visual association, or brainstem areas (pedunculopontine nucleus). Longitudinal changes display reorganization of dorsal attention and salience networks after thalamotomy. Beside attentional gateway, they are also known for their major role in facilitating a rapid access to the motor system.

Pretherapeutic Functional Imaging Allows Prediction of Head Tremor Arrest After Thalamotomy for Essential Tremor: The Role of Altered Interconnectivity Between Thalamolimbic and Supplementary Motor Circuits.

OBJECTIVE: To correlate pretherapeutic resting-state functional magnetic resonance imaging (rs-fMRI) measures with pretherapeutic head tremor presence and/or further improvement 1 year after stereotactic radiosurgical thalamotomy (SRS-T) for essential tremor (ET). METHODS: We prospectively collected head tremor scores (range, 0-3) and rs-fMRI data for a cohort of 17 consecutive ET patients in pretherapeutic and 1 year after SRS-T states. We additionally acquired rs-fMRI data for a healthy control (HC) group (n = 12). Group-level independent component analysis (n = 17 for pretherapeutic rs-fMRI) was applied to decompose neuroimaging data into 20 large-scale brain networks using a standard approach. Through spatial regression, we projected 1 year after SRS-T and HC rs-fMRI time points, on the same 20 brain networks. RESULTS: Pretherapeutic interconnectivity (IC) strength between the network including bilateral thalamus and limbic system with left supplementary motor area predicted head tremor improvement at 1 year after SRS-T (family-wise corrected P < 0.001, cluster size Kc = 146). For the statistically significant cluster, IC strength was strongest in HCs (mean, 4.6; median, 3.8) compared with pre- (mean, 0.1; median, 0.2) or posttherapeutic (mean, -0.2; median, 0.09) states. CONCLUSIONS: Baseline measures of IC between bilateral thalamus and limbic system with left supplementary motor area may predict head tremor arrest after thalamotomy. However, procedures such as SRS-T, for this particular clinical feature, do not align patients to HCs in terms of functional brain connectivity. We postulate that supplementary motor area is modulating head tremor appearance, by abnormal connectivity with the thalamolimbic system.

Clinical response to Vim's thalamic stereotactic radiosurgery for essential tremor is associated with distinctive functional connectivity patterns.

INTRODUCTION: Essential tremor (ET) is the most common movement disorder. Drug-resistant ET can benefit from standard surgical stereotactic procedures (deep brain stimulation, thalamotomy) or minimally invasive high-intensity focused ultrasound (HIFU) or stereotactic radiosurgical thalamotomy (SRS-T). Resting-state fMRI (rs-fMRI) is a non-invasive imaging method acquired in absence of a task. We examined whether rs-fMRI correlates with tremor score on the treated hand (TSTH) improvement 1 year after SRS-T. METHODS: We included 17 consecutive patients treated with left unilateral SRS-T in Marseille, France. Tremor score evaluation and rs-fMRI were acquired at baseline and 1 year after SRS-T. Resting-state data (34 scans) were analyzed without a priori hypothesis, in Lausanne, Switzerland. Based on degree of improvement in TSTH, to consider SRS-T at least as effective as medication, we separated two groups: 1, ≤ 50% (n = 6, 35.3%); 2, > 50% (n = 11, 64.7%). They did not differ statistically by age (p = 0.86), duration of symptoms (p = 0.41), or lesion volume at 1 year (p = 0.06). RESULTS: We report TSTH improvement correlated with interconnectivity strength between salience network with the left claustrum and putamen, as well as between bilateral motor cortices, frontal eye fields and left cerebellum lobule VI with right visual association area (the former also with lesion volume). Longitudinal changes showed additional associations in interconnectivity strength between right dorsal attention network with ventro-lateral prefrontal cortex and a reminiscent salience network with fusiform gyrus. CONCLUSIONS: Brain connectivity measured by resting-state fMRI relates to clinical response after SRS-T. Relevant networks are visual, motor, and attention. Interconnectivity between visual and motor areas is a novel finding, revealing implication in movement sensory guidance.

Right Brodmann area 18 predicts tremor arrest after Vim radiosurgery: a voxel-based morphometry study.

INTRODUCTION: Drug-resistant essential tremor (ET) can benefit from open standard stereotactic procedures, such as deep-brain stimulation or radiofrequency thalamotomy. Non-surgical candidates can be offered either high-focused ultrasound (HIFU) or radiosurgery (RS). All procedures aim to target the same thalamic site, the ventro-intermediate nucleus (e.g., Vim). The mechanisms by which tremor stops after Vim RS or HIFU remain unknown. We used voxel-based morphometry (VBM) on pretherapeutic neuroimaging data and assessed which anatomical site would best correlate with tremor arrest 1 year after Vim RS. METHODS: Fifty-two patients (30 male, 22 female; mean age 71.6 years, range 49-82) with right-sided ET benefited from left unilateral Vim RS in Marseille, France. Targeting was performed in a uniform manner, using 130 Gy and a single 4-mm collimator. Neurological (pretherapeutic and 1 year after) and neuroimaging (baseline) assessments were completed. Tremor score on the treated hand (TSTH) at 1 year after Vim RS was included in a statistical parametric mapping analysis of variance (ANOVA) model as a continuous variable with pretherapeutic neuroimaging data. Pretherapeutic gray matter density (GMD) was further correlated with TSTH improvement. No a priori hypothesis was used in the statistical model. RESULTS: The only statistically significant region was right Brodmann area (BA) 18 (visual association area V2, p = 0.05, cluster size Kc = 71). Higher baseline GMD correlated with better TSTH improvement at 1 year after Vim RS (Spearman's rank correlation coefficient = 0.002). CONCLUSIONS: Routine baseline structural neuroimaging predicts TSTH improvement 1 year after Vim RS. The relevant anatomical area is the right visual association cortex (BA 18, V2). The question whether visual areas should be included in the targeting remains open.

Assessing the clinical outcome of Vim radiosurgery with voxel-based morphometry: visual areas are linked with tremor arrest!

INTRODUCTION: Radiosurgery (RS) is an alternative to open standard stereotactic procedures (deep-brain stimulation or radiofrequency thalamotomy) for drug-resistant essential tremor (ET), aiming at the same target (ventro-intermediate nucleus, Vim). We investigated the Vim RS outcome using voxel-based morphometry by evaluating the interaction between clinical response and time. METHODS: Thirty-eight patients with right-sided ET benefited from left unilateral Vim RS. Targeting was performed using 130 Gy and a single 4-mm collimator. Neurological and neuroimaging assessment was completed at baseline and 1 year. Clinical responders were considered those with at least 50% improvement in tremor score on the treated hand (TSTH). RESULTS: Interaction between clinical response and time showed the left temporal pole and occipital cortex (Brodmann area 19, including V4, V5 and the parahippocampal place area) as statistically significant. A decrease in gray matter density (GMD) 1 year after Vim RS correlated with higher TSTH improvement (Spearman = 0.01) for both anatomical areas. Higher baseline GMD within the left temporal pole correlated with better TSTH improvement (Spearman = 0.004). CONCLUSIONS: Statistically significant structural changes in the relationship to clinical response after Vim RS are present in remote areas, advocating a distant neurobiological effect. The former regions are mainly involved in locomotor monitoring toward the local and distant environment, suggesting the recruiting requirement in targeting of the specific visuomotor networks.

An efficient total variation algorithm for super-resolution in fetal brain MRI with adaptive regularization.

Although fetal anatomy can be adequately viewed in new multi-slice MR images, many critical limitations remain for quantitative data analysis. To this end, several research groups have recently developed advanced image processing methods, often denoted by super-resolution (SR) techniques, to reconstruct from a set of clinical low-resolution (LR) images, a high-resolution (HR) motion-free volume. It is usually modeled as an inverse problem where the regularization term plays a central role in the reconstruction quality. Literature has been quite attracted by Total Variation energies because of their ability in edge preserving but only standard explicit steepest gradient techniques have been applied for optimization. In a preliminary work, it has been shown that novel fast convex optimization techniques could be successfully applied to design an efficient Total Variation optimization algorithm for the super-resolution problem. In this work, two major contributions are presented. Firstly, we will briefly review the Bayesian and Variational dual formulations of current state-of-the-art methods dedicated to fetal MRI reconstruction. Secondly, we present an extensive quantitative evaluation of our SR algorithm previously introduced on both simulated fetal and real clinical data (with both normal and pathological subjects). Specifically, we study the robustness of regularization terms in front of residual registration errors and we also present a novel strategy for automatically select the weight of the regularization as regards the data fidelity term. Our results show that our TV implementation is highly robust in front of motion artifacts and that it offers the best trade-off between speed and accuracy for fetal MRI recovery as in comparison with state-of-the art methods.

Automatic Segmentation of the Eye in 3D Magnetic Resonance Imaging: A Novel Statistical Shape Model for Treatment Planning of Retinoblastoma.

PURPOSE: Proper delineation of ocular anatomy in 3-dimensional (3D) imaging is a big challenge, particularly when developing treatment plans for ocular diseases. Magnetic resonance imaging (MRI) is presently used in clinical practice for diagnosis confirmation and treatment planning for treatment of retinoblastoma in infants, where it serves as a source of information, complementary to the fundus or ultrasonographic imaging. Here we present a framework to fully automatically segment the eye anatomy for MRI based on 3D active shape models (ASM), and we validate the results and present a proof of concept to automatically segment pathological eyes. METHODS AND MATERIALS: Manual and automatic segmentation were performed in 24 images of healthy children's eyes (3.29 ± 2.15 years of age). Imaging was performed using a 3-T MRI scanner. The ASM consists of the lens, the vitreous humor, the sclera, and the cornea. The model was fitted by first automatically detecting the position of the eye center, the lens, and the optic nerve, and then aligning the model and fitting it to the patient. We validated our segmentation method by using a leave-one-out cross-validation. The segmentation results were evaluated by measuring the overlap, using the Dice similarity coefficient (DSC) and the mean distance error. RESULTS: We obtained a DSC of 94.90 ± 2.12% for the sclera and the cornea, 94.72 ± 1.89% for the vitreous humor, and 85.16 ± 4.91% for the lens. The mean distance error was 0.26 ± 0.09 mm. The entire process took 14 seconds on average per eye. CONCLUSION: We provide a reliable and accurate tool that enables clinicians to automatically segment the sclera, the cornea, the vitreous humor, and the lens, using MRI. We additionally present a proof of concept for fully automatically segmenting eye pathology. This tool reduces the time needed for eye shape delineation and thus can help clinicians when planning eye treatment and confirming the extent of the tumor.

Landmark detection for fusion of fundus and MRI toward a patient-specific multimodal eye model.

Ophthalmologists typically acquire different image modalities to diagnose eye pathologies. They comprise, e.g., Fundus photography, optical coherence tomography, computed tomography, and magnetic resonance imaging (MRI). Yet, these images are often complementary and do express the same pathologies in a different way. Some pathologies are only visible in a particular modality. Thus, it is beneficial for the ophthalmologist to have these modalities fused into a single patient-specific model. The goal of this paper is a fusion of Fundus photography with segmented MRI volumes. This adds information to MRI that was not visible before like vessels and the macula. This paper contributions include automatic detection of the optic disc, the fovea, the optic axis, and an automatic segmentation of the vitreous humor of the eye.

Efficient total variation algorithm for fetal brain MRI reconstruction.

Fetal MRI reconstruction aims at finding a high-resolution image given a small set of low-resolution images. It is usually modeled as an inverse problem where the regularization term plays a central role in the reconstruction quality. Literature has considered several regularization terms s.a. Dirichlet/Laplacian energy, Total Variation (TV)- based energies and more recently non-local means. Although TV energies are quite attractive because of their ability in edge preservation, standard explicit steepest gradient techniques have been applied to optimize fetal-based TV energies. The main contribution of this work lies in the introduction of a well-posed TV algorithm from the point of view of convex optimization. Specifically, our proposed TV optimization algorithm or fetal reconstruction is optimal w.r.t. the asymptotic and iterative convergence speeds O(1/n2) and O(1/√ε), while existing techniques are in O(1/n2) and O(1/√ε). We apply our algorithm to (1) clinical newborn data, considered as ground truth, and (2) clinical fetal acquisitions. Our algorithm compares favorably with the literature in terms of speed and accuracy.