In this paper we report the set-up and results of the Multimodal Brain Tumor Image Segmentation Benchmark (BRATS) organized in conjunction with the MICCAI 2012 and 2013 conferences Twenty state-of-the-art tumor segmentation algorithms were applied to a set of 65 multi-contrast MR scans of low- and high-grade glioma patients—manually annotated by up to four raters—and to 65 comparable scans generated using tumor image simulation software Quantitative evaluations revealed considerable disagreement between the human raters in segmenting various tumor sub-regions (Dice scores in the range 74%–85%), illustrating the difficulty of this task We found that different algorithms worked best for different sub-regions (reaching performance comparable to human inter-rater variability), but that no single algorithm ranked in the top for all sub-regions simultaneously Fusing several good algorithms using a hierarchical majority vote yielded segmentations that consistently ranked above all individual algorithms, indicating remaining opportunities for further methodological improvements The BRATS image data and manual annotations continue to be publicly available through an online evaluation system as an ongoing benchmarking resource

/pdf/the-multimodal-brain-tumor-image-segmentation-benchmark-2gfraj98dk.pdf

The Multimodal Brain Tumor Image Segmentation Benchmark (BRATS)

Medical image registration is an important task in medical image processing. It refers to the process of aligning data sets, possibly from different modalities (e.g., magnetic resonance and computed tomography), different time points (e.g., follow-up scans), and/or different subjects (in case of population studies). A large number of methods for image registration are described in the literature. Unfortunately, there is not one method that works for all applications. We have therefore developed elastix, a publicly available computer program for intensity-based medical image registration. The software consists of a collection of algorithms that are commonly used to solve medical image registration problems. The modular design of elastix allows the user to quickly configure, test, and compare different registration methods for a specific application. The command-line interface enables automated processing of large numbers of data sets, by means of scripting. The usage of elastix for comparing different registration methods is illustrated with three example experiments, in which individual components of the registration method are varied.

elastix : A Toolbox for Intensity-Based Medical Image Registration

Multi-atlas segmentation is an effective approach for automatically labeling objects of interest in biomedical images. In this approach, multiple expert-segmented example images, called atlases, are registered to a target image, and deformed atlas segmentations are combined using label fusion. Among the proposed label fusion strategies, weighted voting with spatially varying weight distributions derived from atlas-target intensity similarity have been particularly successful. However, one limitation of these strategies is that the weights are computed independently for each atlas, without taking into account the fact that different atlases may produce similar label errors. To address this limitation, we propose a new solution for the label fusion problem in which weighted voting is formulated in terms of minimizing the total expectation of labeling error and in which pairwise dependency between atlases is explicitly modeled as the joint probability of two atlases making a segmentation error at a voxel. This probability is approximated using intensity similarity between a pair of atlases and the target image in the neighborhood of each voxel. We validate our method in two medical image segmentation problems: hippocampus segmentation and hippocampus subfield segmentation in magnetic resonance (MR) images. For both problems, we show consistent and significant improvement over label fusion strategies that assign atlas weights independently.

/pdf/multi-atlas-segmentation-with-joint-label-fusion-4seweg68te.pdf

Multi-Atlas Segmentation with Joint Label Fusion

VoxResNet: Deep voxelwise residual networks for brain segmentation from 3D MR images

https://www.nmr.mgh.harvard.edu/~iglesias/pdf/Media2015surveyFusion.pdf

Multi-Atlas Segmentation of Biomedical Images: A Survey

It has been shown that employing multiple atlas images improves segmentation accuracy in atlas-based medical image segmentation. Each atlas image is registered to the target image independently and the calculated transformation is applied to the segmentation of the atlas image to obtain a segmented version of the target image. Several independent candidate segmentations result from the process, which must be somehow combined into a single final segmentation. Majority voting is the generally used rule to fuse the segmentations, but more sophisticated methods have also been proposed. In this paper, we show that the use of global weights to ponderate candidate segmentations has a major limitation. As a means to improve segmentation accuracy, we propose the generalized local weighting voting method. Namely, the fusion weights adapt voxel-by-voxel according to a local estimation of segmentation performance. Using digital phantoms and MR images of the human brain, we demonstrate that the performance of each combination technique depends on the gray level contrast characteristics of the segmented region, and that no fusion method yields better results than the others for all the regions. In particular, we show that local combination strategies outperform global methods in segmenting high-contrast structures, while global techniques are less sensitive to noise when contrast between neighboring structures is low. We conclude that, in order to achieve the highest overall segmentation accuracy, the best combination method for each particular structure must be selected.

Combination Strategies in Multi-Atlas Image Segmentation: Application to Brain MR Data

To define the sensitivity of microcomputed tomography- (micro-CT-) derived descriptors for the quantification of lung damage caused by elastase instillation. Materials and Methods. The lungs of 30 elastase treated and 30 control A/J mice were analyzed 1, 6, 12, and 24 hours and 7 and 17 days after elastase instillation using (i) breath-hold-gated micro-CT, (ii) pulmonary function tests (PFTs), (iii) RT-PCR for RNA cytokine expression, and (iv) histomorphometry. For the latter, an automatic, parallel software toolset was implemented that computes the airspace enlargement descriptors: mean linear intercept (Lm) and weighted means of airspace diameters (D0, D1, and D2). A Support Vector Classifier was trained and tested based on three nonhistological descriptors using D2 as ground truth. Results. D2 detected statistically significant differences (P < 0.01) between the groups at all time points. Furthermore, D2 at 1 hour (24 hours) was significantly lower (P < 0.01) than D2 at 24 hours (7 days). The classifier trained on the micro-CT-derived descriptors achieves an area under the curve (AUC) of 0.95 well above the others (PFTS AUC = 0.71; cytokine AUC = 0.88). Conclusion. Micro-CT-derived descriptors are more sensitive than the other methods compared, to detect in vivo early signs of the disease.

/pdf/quantification-of-lung-damage-in-an-elastase-induced-mouse-2t6cih9ezz.pdf

Quantification of lung damage in an elastase-induced mouse model of emphysema

Objectives
To define the potential, limitations and synergies of micro-CT and other non-radiological techniques for the quantification of emphysema and related processes in mice, by performing a complete characterization of the elastase-induced emphysema model.

Evaluation of micro-CT for emphysema assessment in mice: comparison with non-radiological techniques

Atlas-based segmentation has proven effective in multiple applications. Usually, several reference images are combined
to create a representative average atlas image. Alternatively, a number of independent atlas images can be used, from which multiple segmentations of the image of interest are derived and later combined. One of the major drawbacks of this approach is its large computational burden caused by the high number of required registrations. To address this problem, we introduce One Registration, Multiple Segmentations (ORMS), a procedure to obtain multiple segmentations with a single online registration. This can be achieved by pre-computing intermediate transformations from the initial atlas images to an average image. We show that, compared to the usual approach, our method reduces time considerably
with little or no loss in accuracy. On the other hand, optimum combination of these segmentations remains an unresolved problem. Different approaches have been adopted, but they are all far from the upper bound of any combination strategy. This is given by the
Combination Oracle, which classifies a voxel correctly if any individual segmentation coincides with the ground truth.
We present here a novel combination approach, based on weighting the different segmentations according to the mutual information between the test image and the atlas image after registration. We compare this method with other existing combination strategies using microscopic MR images of mouse brains, achieving statistically significant improvement in segmentation accuracy.

Efficient classifier generation and weighted voting for atlas-based segmentation: two small steps faster and closer to the combination oracle

Animal models of lung disease are gaining importance in understanding the underlying mechanisms of diseases such as emphysema and lung cancer. Micro-CT allows in vivo imaging of these models, thus permitting the study of the progression of the disease or the effect of therapeutic drugs in longitudinal studies. Automated analysis of micro-CT images can be helpful to understand the physiology of diseased lungs, especially when combined with measurements of respiratory system input impedance. In this work, we present a fast and robust murine airway segmentation and reconstruction algorithm. The algorithm is based on a propagating fast marching wavefront that, as it grows, divides the tree into segments. We devised a number of specific rules to guarantee that the front propagates only inside the airways and to avoid leaking into the parenchyma. The algorithm was tested on normal mice, a mouse model of chronic inflammation and a mouse model of emphysema. A comparison with manual segmentations of two independent observers shows that the specificity and sensitivity values of our method are comparable to the inter-observer variability, and radius measurements of the mainstem bronchi reveal significant differences between healthy and diseased mice. Combining measurements of the automatically segmented airways with the parameters of the constant phase model provides extra information on how disease affects lung function.

/pdf/airway-segmentation-and-analysis-for-the-study-of-mouse-1a7r96mv9t.pdf

Xabier Artaechevarria

Papers

Combination Strategies in Multi-Atlas Image Segmentation: Application to Brain MR Data

Quantification of lung damage in an elastase-induced mouse model of emphysema

Evaluation of micro-CT for emphysema assessment in mice: comparison with non-radiological techniques

Efficient classifier generation and weighted voting for atlas-based segmentation: two small steps faster and closer to the combination oracle

Airway segmentation and analysis for the study of mouse models of lung disease using micro-CT.