Search

One of the fundamental elements of both traditional and certain deep learning medical image registration algorithms is measuring the similarity/dissimilarity between two images. In this work, we propose an analytical solution for measuring similarity between two different medical image modalities based on the Hessian of their intensities. First, assuming a functional dependence between the intensities of two perfectly corresponding patches, we investigate how their Hessians relate to each other. Secondly, we suggest a closed-form expression to quantify the deviation from this relationship, given arbitrary pairs of image patches. We propose a geometrical interpretation of the new similarity metric and an efficient implementation for registration. We demonstrate the robustness of the metric to intensity nonuniformities using synthetic bias fields. By integrating the new metric in an affine registration framework, we evaluate its performance for MRI and ultrasound registration in the context of image-guided neurosurgery using target registration error and computation time.

INTRODUCTION: Lateral ventricles are reliable and sensitive indicators of brain atrophy and disease progression in behavioral variant frontotemporal dementia (bvFTD). We aimed to investigate whether an automated tool using ventricular features could improve diagnostic accuracy in bvFTD across neurodegenerative diseases. METHODS: Using 678 subjects (2750 timepoints), differences in ventricular features were assessed between bvFTD, normal controls and other dementia cohorts. RESULTS: Ventricular antero-posterior ratio (APR) was the only feature that was significantly different and increased faster in bvFTD compared to all other cohorts. We achieved a 10-fold cross-validation accuracy of 80% (77% sensitivity, 82% specificity) in differentiating bvFTD from all other cohorts with ventricular features, and 76% accuracy using only the single APR feature. DISCUSSION: APR could be a useful and easy-to-implement feature to aid bvFTD diagnosis. We have made our ventricle feature estimation and bvFTD diagnostic tool publicly available, allowing application of our model in other studies.

INTRODUCTION: Heterogeneity in the progression of Alzheimer's disease makes it challenging to predict the rate of cognitive and functional decline for individual patients. Tools for short-term prediction could help enrich clinical trial designs and focus prevention strategies on the most at-risk patients. METHOD: We built a prognostic model using baseline cognitive scores and MRI-based features to determine which subjects with mild cognitive impairment remained stable and which functionally declined (measured by a two-point increase in CDR-SB) over 2 and 3-year follow-up periods, periods typical of the length of clinical trials. RESULTS: Combining both sets of features yields 77% accuracy (81% sensitivity and 75% specificity) to predict cognitive decline at 2 years (74% accuracy at 3 years with 75% sensitivity and 73% specificity). Using this tool to select trial participants yields a 3.8-fold decrease in the required sample size for a 2-year study (2.8-fold decrease for a 3-year study) for a hypothesized 25% treatment effect to reduce cognitive decline. DISCUSSION: This cohort enrichment tool could accelerate treatment development by increasing power in clinical trials.

Stroke is the second leading cause of disability worldwide. In order to minimize disability, the goal of stroke treatment is to preserve tissue in the area where blood supply is decreased but sufficient to stave off cell death. Thrombectomy has been shown to offer fast and efficient reperfusion with high recanalization rates. However, due to the inherent risks of thrombectomy, indications including evidence of good collateral circulation should be present. Currently, methods for evaluating collateral circulation are limited. In this work, we present an automated technique to compute a collateral circulation score based on differences seen in mean intensities between left and right cerebral hemispheres in 4D angiography images. In this preliminary study, we analyzed scans of 28 subjects: 4 with normal collateral circulation, 7 with good, 10 with intermediate, and 7 with poor collateral circulation, (based on radiologist score) and found a good correlation between the computed score and radiologist score (r2 = 0.71) and good separation between good and intermediate/poor groups. This work shows promise as the first step in building an automated collateral circulation score., Comment: 8 pages, 7 7 figures, MICCAI Computing and Visualization for Intravascular Imaging (CVII) Workshop

Quantification of cerebral white matter hyperintensities (WMH) of presumed vascular origin is of key importance in many neurological research studies. Currently, measurements are often still obtained from manual segmentations on brain MR images, which is a laborious procedure. Automatic WMH segmentation methods exist, but a standardized comparison of the performance of such methods is lacking. We organized a scientific challenge, in which developers could evaluate their method on a standardized multi-center/-scanner image dataset, giving an objective comparison: the WMH Segmentation Challenge (https://wmh.isi.uu.nl/). Sixty T1+FLAIR images from three MR scanners were released with manual WMH segmentations for training. A test set of 110 images from five MR scanners was used for evaluation. Segmentation methods had to be containerized and submitted to the challenge organizers. Five evaluation metrics were used to rank the methods: (1) Dice similarity coefficient, (2) modified Hausdorff distance (95th percentile), (3) absolute log-transformed volume difference, (4) sensitivity for detecting individual lesions, and (5) F1-score for individual lesions. Additionally, methods were ranked on their inter-scanner robustness. Twenty participants submitted their method for evaluation. This paper provides a detailed analysis of the results. In brief, there is a cluster of four methods that rank significantly better than the other methods, with one clear winner. The inter-scanner robustness ranking shows that not all methods generalize to unseen scanners. The challenge remains open for future submissions and provides a public platform for method evaluation., Comment: Accepted for publication in IEEE Transactions on Medical Imaging

Automatic segmentation methods are important tools for quantitative analysis of Magnetic Resonance Images (MRI). Recently, patch-based label fusion approaches have demonstrated state-of-the-art segmentation accuracy. In this paper, we introduce a new patch-based label fusion framework to perform segmentation of anatomical structures. The proposed approach uses an Optimized PAtchMatch Label fusion (OPAL) strategy that drastically reduces the computation time required for the search of similar patches. The reduced computation time of OPAL opens the way for new strategies and facilitates processing on large databases. In this paper, we investigate new perspectives offered by OPAL, by introducing a new multi-scale and multi-feature framework. During our validation on hippocampus segmentation we use two datasets: young adults in the ICBM cohort and elderly adults in the EADC-ADNI dataset. For both, OPAL is compared to state-of-the-art methods. Results show that OPAL obtained the highest median Dice coefficient (89.9% for ICBM and 90.1% for EADC-ADNI). Moreover, in both cases, OPAL produced a segmentation accuracy similar to inter-expert variability. On the EADC-ADNI dataset, we compare the hippocampal volumes obtained by manual and automatic segmentation. The volumes appear to be highly correlated that enables to perform more accurate separation of pathological populations., Comment: Neuroimage 2016

Neuroanatomical segmentation in magnetic resonance imaging (MRI) of the brain is a prerequisite for volume, thickness and shape measurements. This work introduces a new highly accurate and versatile method based on 3D convolutional neural networks for the automatic segmentation of neuroanatomy in T1-weighted MRI. In combination with a deep 3D fully convolutional architecture, efficient linear registration-derived spatial priors are used to incorporate additional spatial context into the network. An aggressive data augmentation scheme using random elastic deformations is also used to regularize the networks, allowing for excellent performance even in cases where only limited labelled training data are available. Applied to hippocampus segmentation in an elderly population (mean Dice coefficient = 92.1%) and sub-cortical segmentation in a healthy adult population (mean Dice coefficient = 89.5%), we demonstrate new state-of-the-art accuracies and a high robustness to outliers with the same architecture. Further validation on a multi-structure segmentation task in a scan-rescan dataset demonstrates accuracy (mean Dice coefficient = 86.6%) similar to the scan-rescan reliability of expert manual segmentations (mean Dice coefficient = 86.9%), and improved reliability compared to both expert manual segmentations and automated segmentations using FIRST. Furthermore, our method maintains a highly competitive runtime performance (e.g. requiring only 10 seconds for left/right hippocampal segmentation in 1x1x1 MNI stereotaxic space), orders of magnitude faster than conventional multi-atlas segmentation methods.