Random Forest Classification for Automatic Delineation of Myocardium in Real-Time 3D Echocardiography

Comparative studies of deep learning segmentation models for left ventricle segmentation

One of the primary factors contributing to death across all age groups is cardiovascular disease. In the analysis of heart function, analyzing the left ventricle (LV) from 2D echocardiographic images is a common medical procedure for heart patients. Consistent and accurate segmentation of the LV exerts significant impact on the understanding of the normal anatomy of the heart, as well as the ability to distinguish the aberrant or diseased structure of the heart. Therefore, LV segmentation is an important and critical task in medical practice, and automated LV segmentation is a pressing need. The deep learning models have been utilized in research for automatic LV segmentation. In this work, three cutting-edge convolutional neural network architectures (SegNet, Fully Convolutional Network, and Mask R-CNN) are designed and implemented to segment the LV. In addition, an echocardiography image dataset is generated, and the amount of training data is gradually increased to measure segmentation performance using evaluation metrics. The pixel's accuracy, precision, recall, specificity, Jaccard index, and dice similarity coefficients are applied to evaluate the three models. The Mask R-CNN model outperformed the other two models in these evaluation metrics. As a result, the Mask R-CNN model is used in this study to examine the effect of training data. For 4,000 images, the network achieved 92.21% DSC value, 85.55% Jaccard index, 98.76% mean accuracy, 96.81% recall, 93.15% precision, and 96.58% specificity value. Relatively, the Mask R-CNN outperformed other architectures, and the performance achieves stability when the model is trained using more than 4,000 training images.

Cardiac Segmentation Method Based on Domain Knowledge

Echocardiography plays an important role in the clinical diagnosis of cardiovascular diseases. Cardiac function assessment by echocardiography is a crucial process in daily cardiology. However, cardiac segmentation in echocardiography is a challenging task due to shadows and speckle noise. The traditional manual segmentation method is a time-consuming process and limited by inter-observer variability. In this paper, we present a fast and accurate echocardiographic automatic segmentation framework based on Convolutional neural networks (CNN). We propose FAUet, a segmentation method serially integrated U-Net with coordinate attention mechanism and domain feature loss from VGG19 pre-trained on the ImageNet dataset. The coordinate attention mechanism can capture long-range dependencies along one spatial direction and meanwhile preserve precise positional information along the other spatial direction. And the domain feature loss is more concerned with the topology of cardiac structures by exploiting their higher-level features. In this research, we use a two-dimensional echocardiogram (2DE) of 88 patients from two devices, Philips Epiq 7C and Mindray Resona 7T, to segment the left ventricle (LV), interventricular septal (IVS), and posterior left ventricular wall (PLVW). We also draw the gradient weighted class activation mapping (Grad-CAM) to improve the interpretability of the segmentation results. Compared with the traditional U-Net, the proposed segmentation method shows better performance. The mean Dice Score Coefficient (Dice) of LV, IVS, and PLVW of FAUet can achieve 0.932, 0.848, and 0.868, and the average Dice of the three objects can achieve 0.883. Statistical analysis showed that there is no significant difference between the segmentation results of the two devices. The proposed method can realize fast and accurate segmentation of 2DE with a low time cost. Combining coordinate attention module and feature loss with the original U-Net framework can significantly increase the performance of the algorithm.

Artificial intelligence and machine learning for medical imaging: A technology review

Artificial intelligence (AI) has recently become a very popular buzzword, as a consequence of disruptive technical advances and impressive experimental results, notably in the field of image analysis and processing. In medicine, specialties where images are central, like radiology, pathology or oncology, have seized the opportunity and considerable efforts in research and development have been deployed to transfer the potential of AI to clinical applications. With AI becoming a more mainstream tool for typical medical imaging analysis tasks, such as diagnosis, segmentation, or classification, the key for a safe and efficient use of clinical AI applications relies, in part, on informed practitioners. The aim of this review is to present the basic technological pillars of AI, together with the state-of-the-art machine learning methods and their application to medical imaging. In addition, we discuss the new trends and future research directions. This will help the reader to understand how AI methods are now becoming an ubiquitous tool in any medical image analysis workflow and pave the way for the clinical implementation of AI-based solutions.

A new method for quantitative assessment of hand muscle volume and fat in magnetic resonance images

Background

Rheumatoid arthritis (RA) is characterized by systemic inflammation and bone and muscle loss. Recent research showed that obesity facilitates inflammation, but it is unknown if obesity also increases the risk or severity of RA. Further research requires an accurate quantification of muscle volume and fat content.

Methods

The aim was to develop a reproducible (semi) automated method for hand muscle segmentation and quantification of hand muscle fat content and to reduce the time consuming efforts of manual segmentation. T1 weighted scans were used for muscle segmentation based on a random forest classifier. Optimal segmentation parameters were determined by cross validation with 30 manually segmented hand datasets (gold standard). An operator reviewed the automatically created segmentation and applied corrections if necessary. For fat quantification, the segmentation masks were automatically transferred to MRI Dixon sequences by rigid registration. In total 76 datasets from RA patients were analyzed. Accuracy was validated against the manual gold standard segmentations.

Results

Average analysis time per dataset was 10 min, more than 10 times faster compared to manual outlining. All 76 datasets could be analyzed and were accurate as judged by a clinical expert. 69 datasets needed minor manual segmentation corrections. Segmentation accuracy compared to the gold standard (Dice ratio 0.98 ± 0.04, average surface distance 0.04 ± 0.10 mm) and reanalysis precision were excellent. Intra- and inter-operator precision errors were below 0.3% (muscle) and 0.7% (fat). Average Hausdorff distances were higher (1.09 mm), but high values originated from a shift of the analysis VOI by one voxel in scan direction.

Conclusions

We presented a novel semi-automated method for quantitative assessment of hand muscles with excellent accuracy and operator precision, which highly reduced a traditional manual segmentation effort. This method may greatly facilitate further MRI image based muscle research of the hands.

Fully Automatic Myocardial Segmentation of Contrast Echocardiography Sequence Using Random Forests Guided by Shape Model

Myocardial contrast echocardiography (MCE) is an imaging technique that assesses left ventricle function and myocardial perfusion for the detection of coronary artery diseases. Automatic MCE perfusion quantification is challenging and requires accurate segmentation of the myocardium from noisy and time-varying images. Random forests (RF) have been successfully applied to many medical image segmentation tasks. However, the pixel-wise RF classifier ignores contextual relationships between label outputs of individual pixels. RF which only utilizes local appearance features is also susceptible to data suffering from large intensity variations. In this paper, we demonstrate how to overcome the above limitations of classic RF by presenting a fully automatic segmentation pipeline for myocardial segmentation in full-cycle 2-D MCE data. Specifically, a statistical shape model is used to provide shape prior information that guide the RF segmentation in two ways. First, a novel shape model (SM) feature is incorporated into the RF framework to generate a more accurate RF probability map. Second, the shape model is fitted to the RF probability map to refine and constrain the final segmentation to plausible myocardial shapes. We further improve the performance by introducing a bounding box detection algorithm as a preprocessing step in the segmentation pipeline. Our approach on 2-D image is further extended to 2-D+t sequences which ensures temporal consistency in the final sequence segmentations. When evaluated on clinical MCE data sets, our proposed method achieves notable improvement in segmentation accuracy and outperforms other state-of-the-art methods, including the classic RF and its variants, active shape model and image registration.

Manifold Embedding and Semantic Segmentation for Intraoperative Guidance With Hyperspectral Brain Imaging

Recent advances in hyperspectral imaging have made it a promising solution for intra-operative tissue characterization, with the advantages of being non-contact, non-ionizing, and non-invasive. Working with hyperspectral images in vivo, however, is not straightforward as the high dimensionality of the data makes real-time processing challenging. In this paper, a novel dimensionality reduction scheme and a new processing pipeline are introduced to obtain a detailed tumor classification map for intra-operative margin definition during brain surgery. However, existing approaches to dimensionality reduction based on manifold embedding can be time consuming and may not guarantee a consistent result, thus hindering final tissue classification. The proposed framework aims to overcome these problems through a process divided into two steps: dimensionality reduction based on an extension of the T-distributed stochastic neighbor approach is first performed and then a semantic segmentation technique is applied to the embedded results by using a Semantic Texton Forest for tissue classification. Detailed in vivo validation of the proposed method has been performed to demonstrate the potential clinical value of the system.

A novel myocardium segmentation approach based on neutrosophic active contour model

BACKGROUND AND OBJECTIVES

Automatic delineation of the myocardium in echocardiography can assist radiologists to diagnosis heart problems. However, it is still challenging to distinguish myocardium from other tissue due to a low signal-to-noise ratio, low contrast, vague boundary, and speckle noise. The purpose of this study is to automatically detect myocardium region in left ventricle myocardial contrast echocardiography (LVMCE) images to help radiologists' diagnosis and further measurement on infarction size.

METHODS

The LVMCE image is firstly mapped into neutrosophic similarity (NS) domain using the intensity and homogeneity features. Then, a neutrosophic active contour model (NACM) is proposed and the energy function is defined by the NS values. Finally, the ventricle is detected using the curve evolving results. The ventricle's boundary is identified as the endocardium. To speed up the evolution procedure and increase the detection accuracy, a clustering algorithm is employed to obtain the initial ventricle region. The curve evolution procedure in NACM is utilized again to obtain the epicardium, where the initial contour uses the detected endocardium and the anatomy knowledge on the thickness of the myocardium.

RESULTS

Echocardiographic studies are performed on 10 male Sprague-Dawley rats using a Vivid 7 system including 5 normal cases and 5 rats with myocardial infarction. The myocardium boundaries manually outlined by an experienced radiologist are used as the reference standard for the performance evaluation. Two metrics, Hdist and AvgDist, are employed to evaluate the detection results. The NACM method was compared with those from the eliminated particle swarm optimization (EPSO) and active contour model without edges (ACMWE) methods. The mean and standard deviation of the Hdist and AvgDist on endocardium are 6.83 ± 1.12mm and 0.79 ± 0.28mm using EPSO method, 7.12 ± 0.98mm and 0.82 ± 0.32mm using ACMWE method, and 4.55 ± 0.9mm and 0.58 ± 0.18mm using NACM method, respectively. The improvement on epicardium is much more significant, and two metrics are decreased from 7.45 ± 1.24mm, and 1.47 ± 0.34mm using EPSO method, and 8.21±0.43mm, and 1.73±0.47mm using ACMWE method, to 4.94 ± 0.82mm, and 0.84 ± 0.22mm using NACM method, respectively.

CONCLUSIONS

The proposed method can automatically detect myocardium accurately, and is helpful for clinical therapeutics to measure myocardial perfusion and infarct size.

Left Ventricular Myocardial Segmentation in 3-D Ultrasound Recordings: Effect of Different Endocardial and Epicardial Coupling Strategies

Cardiac volume/function assessment remains a critical step in daily cardiology, and 3-D ultrasound plays an increasingly important role. Though development of automatic endocardial segmentation methods has received much attention, the same cannot be said about epicardial segmentation, in spite of the importance of full myocardial segmentation. In this paper, different ways of coupling the endocardial and epicardial segmentations are contrasted and compared with uncoupled segmentation. For this purpose, the B-spline explicit active surfaces framework was used; 27 3-D echocardiographic images were used to validate the different coupling strategies, which were compared with manual contouring of the endocardial and epicardial borders performed by an expert. It is shown that an independent segmentation of the endocardium followed by an epicardial segmentation coupled to the endocardium is the most advantageous. In this way, a framework for fully automatic 3-D myocardial segmentation is proposed using a novel coupling strategy.

Training echo state networks for rotation-invariant bone marrow cell classification

The main principle of diagnostic pathology is the reliable interpretation of individual cells in context of the tissue architecture. Especially a confident examination of bone marrow specimen is dependent on a valid classification of myeloid cells. In this work, we propose a novel rotation-invariant learning scheme for multi-class echo state networks (ESNs), which achieves very high performance in automated bone marrow cell classification. Based on representing static images as temporal sequence of rotations, we show how ESNs robustly recognize cells of arbitrary rotations by taking advantage of their short-term memory capacity. The performance of our approach is compared to a classification random forest that learns rotation-invariance in a conventional way by exhaustively training on multiple rotations of individual samples. The methods were evaluated on a human bone marrow image database consisting of granulopoietic and erythropoietic cells in different maturation stages. Our ESN approach to cell classification does not rely on segmentation of cells or manual feature extraction and can therefore directly be applied to image data.

Segmentation of the metacarpus and phalange in musculoskeletal ultrasound images using local active contours

This work presents a method for the automatic segmentation of metacarpus and phalange bones in ultrasound images of the second metacarpophalangeal joint (MCPJ) using Active Contours. The MCPJ is known to be the one of the first structures to be affected by rheumatic diseases like rheumatoid arthritis. The early detection and follow-up of this disease is important to prevent irreversible damage of the joints, which occurs continuously and faster if no treatment is used. To our knowledge, there is no automatic system to quantify the extension of the lesions resulting from rheumatic activity. The objective of this work is to identify the metacarpus and the phalange bones using local active contours. To our knowledge, there is no well established method for this problem and this technique has not been used yet in these structures. Results proved that the automatic segmentation is possible with an error of 3 pixels for a confidence of 80%.

Mediastinal lymph node detection and station mapping on chest CT using spatial priors and random forest

PURPOSE

To develop an automated system for mediastinal lymph node detection and station mapping for chest CT.

METHODS

The contextual organs, trachea, lungs, and spine are first automatically identified to locate the region of interest (ROI) (mediastinum). The authors employ shape features derived from Hessian analysis, local object scale, and circular transformation that are computed per voxel in the ROI. Eight more anatomical structures are simultaneously segmented by multiatlas label fusion. Spatial priors are defined as the relative multidimensional distance vectors corresponding to each structure. Intensity, shape, and spatial prior features are integrated and parsed by a random forest classifier for lymph node detection. The detected candidates are then segmented by the following curve evolution process. Texture features are computed on the segmented lymph nodes and a support vector machine committee is used for final classification. For lymph node station labeling, based on the segmentation results of the above anatomical structures, the textual definitions of mediastinal lymph node map according to the International Association for the Study of Lung Cancer are converted into patient-specific color-coded CT image, where the lymph node station can be automatically assigned for each detected node.

RESULTS

The chest CT volumes from 70 patients with 316 enlarged mediastinal lymph nodes are used for validation. For lymph node detection, their system achieves 88% sensitivity at eight false positives per patient. For lymph node station labeling, 84.5% of lymph nodes are correctly assigned to their stations.

CONCLUSIONS

Multiple-channel shape, intensity, and spatial prior features aggregated by a random forest classifier improve mediastinal lymph node detection on chest CT. Using the location information of segmented anatomic structures from the multiatlas formulation enables accurate identification of lymph node stations.

3D Fast Automatic Segmentation of Kidney Based on Modified AAM and Random Forest

In this paper, a fully automatic method is proposed to segment the kidney into multiple components: renal cortex, renal column, renal medulla and renal pelvis, in clinical 3D CT abdominal images. The proposed fast automatic segmentation method of kidney consists of two main parts: localization of renal cortex and segmentation of kidney components. In the localization of renal cortex phase, a method which fully combines 3D Generalized Hough Transform (GHT) and 3D Active Appearance Models (AAM) is applied to localize the renal cortex. In the segmentation of kidney components phase, a modified Random Forests (RF) method is proposed to segment the kidney into four components based on the result from localization phase. During the implementation, a multithreading technology is applied to speed up the segmentation process. The proposed method was evaluated on a clinical abdomen CT data set, including 37 contrast-enhanced volume data using leave-one-out strategy. The overall true-positive volume fraction and false-positive volume fraction were 93.15%, 0.37% for renal cortex segmentation; 83.09%, 0.97% for renal column segmentation; 81.92%, 0.55% for renal medulla segmentation; and 80.28%, 0.30% for renal pelvis segmentation, respectively. The average computational time of segmenting kidney into four components took 20 seconds.

Standardized Evaluation System for Left Ventricular Segmentation Algorithms in 3D Echocardiography

Real-time 3D Echocardiography (RT3DE) has been proven to be an accurate tool for left ventricular (LV) volume assessment. However, identification of the LV endocardium remains a challenging task, mainly because of the low tissue/blood contrast of the images combined with typical artifacts. Several semi and fully automatic algorithms have been proposed for segmenting the endocardium in RT3DE data in order to extract relevant clinical indices, but a systematic and fair comparison between such methods has so far been impossible due to the lack of a publicly available common database. Here, we introduce a standardized evaluation framework to reliably evaluate and compare the performance of the algorithms developed to segment the LV border in RT3DE. A database consisting of 45 multivendor cardiac ultrasound recordings acquired at different centers with corresponding reference measurements from three experts are made available. The algorithms from nine research groups were quantitatively evaluated and compared using the proposed online platform. The results showed that the best methods produce promising results with respect to the experts' measurements for the extraction of clinical indices, and that they offer good segmentation precision in terms of mean distance error in the context of the experts' variability range. The platform remains open for new submissions.

A combined deep-learning and deformable-model approach to fully automatic segmentation of the left ventricle in cardiac MRI

Segmentation of the left ventricle (LV) from cardiac magnetic resonance imaging (MRI) datasets is an essential step for calculation of clinical indices such as ventricular volume and ejection fraction. In this work, we employ deep learning algorithms combined with deformable models to develop and evaluate a fully automatic LV segmentation tool from short-axis cardiac MRI datasets. The method employs deep learning algorithms to learn the segmentation task from the ground true data. Convolutional networks are employed to automatically detect the LV chamber in MRI dataset. Stacked autoencoders are used to infer the LV shape. The inferred shape is incorporated into deformable models to improve the accuracy and robustness of the segmentation. We validated our method using 45 cardiac MR datasets from the MICCAI 2009 LV segmentation challenge and showed that it outperforms the state-of-the art methods. Excellent agreement with the ground truth was achieved. Validation metrics, percentage of good contours, Dice metric, average perpendicular distance and conformity, were computed as 96.69%, 0.94, 1.81 mm and 0.86, versus those of 79.2-95.62%, 0.87-0.9, 1.76-2.97 mm and 0.67-0.78, obtained by other methods, respectively.

MR volumetric assessment of endolymphatic hydrops

OBJECTIVES

We aimed to volumetrically quantify endolymph and perilymph spaces of the inner ear in order to establish a methodological basis for further investigations into the pathophysiology and therapeutic monitoring of Menière's disease.

METHODS

Sixteen patients (eight females, aged 38-71 years) with definite unilateral Menière's disease were included in this study. Magnetic resonance (MR) cisternography with a T2-SPACE sequence was combined with a Real reconstruction inversion recovery (Real-IR) sequence for delineation of inner ear fluid spaces. Machine learning and automated local thresholding segmentation algorithms were applied for three-dimensional (3D) reconstruction and volumetric quantification of endolymphatic hydrops. Test-retest reliability was assessed by the intra-class coefficient; correlation of cochlear endolymph volume ratio with hearing function was assessed by the Pearson correlation coefficient.

RESULTS

Endolymph volume ratios could be reliably measured in all patients, with a mean (range) value of 15% (2-25) for the cochlea and 28% (12-40) for the vestibulum. Test-retest reliability was excellent, with an intra-class coefficient of 0.99. Cochlear endolymphatic hydrops was significantly correlated with hearing loss (r = 0.747, p = 0.001).

CONCLUSIONS

MR imaging after local contrast application and image processing, including machine learning and automated local thresholding, enable the volumetric quantification of endolymphatic hydrops. This allows for a quantitative assessment of the effect of therapeutic interventions on endolymphatic hydrops.

KEY POINTS

• Endolymphatic hydrops is the pathological hallmark of Menière's disease. • Endolymphatic hydrops can be visualized by locally enhanced ultra-high-resolution MR imaging. • Computer-aided image processing enables quantification of endolymphatic hydrops. • Endolymphatic hydrops correlates with hearing loss in patients with Menière's disease. • Therapeutic trials in Menière's disease can be monitored with this quantitative approach.

A complete system for automatic extraction of left ventricular myocardium from CT images using shape segmentation and contour evolution

The left ventricular myocardium plays a key role in the entire circulation system and an automatic delineation of the myocardium is a prerequisite for most of the subsequent functional analysis. In this paper, we present a complete system for an automatic segmentation of the left ventricular myocardium from cardiac computed tomography (CT) images using the shape information from images to be segmented. The system follows a coarse-to-fine strategy by first localizing the left ventricle and then deforming the myocardial surfaces of the left ventricle to refine the segmentation. In particular, the blood pool of a CT image is extracted and represented as a triangulated surface. Then, the left ventricle is localized as a salient component on this surface using geometric and anatomical characteristics. After that, the myocardial surfaces are initialized from the localization result and evolved by applying forces from the image intensities with a constraint based on the initial myocardial surface locations. The proposed framework has been validated on 34-human and 12-pig CT images, and the robustness and accuracy are demonstrated.

Laplacian forests: semantic image segmentation by guided bagging

This paper presents a new, efficient and accurate technique for the semantic segmentation of medical images. The paper builds upon the successful random decision forests model and improves on it by modifying the way in which randomness is injected into the tree training process. The contribution of this paper is two-fold. First, we replace the conventional bagging procedure (the uniform sampling of training images) with a guided bagging approach, which exploits the inherent structure and organization of the training image set. This allows the creation of decision trees that are specialized to a specific sub-type of images in the training set. Second, the segmentation of a previously unseen image happens via selection and application of only the trees that are relevant to the given test image. Tree selection is done automatically, via the learned image embedding, with more precisely a Laplacian eigenmap. We, therefore, call the proposed approach Laplacian Forests. We validate Laplacian Forests on a dataset of 256, manually segmented 3D CT scans of patients showing high variability in scanning protocols, resolution, body shape and anomalies. Compared with conventional decision forests, Laplacian Forests yield both higher training efficiency, due to the local analysis of the training image space, as well as higher segmentation accuracy, due to the specialization of the forest to image sub-types.

Automatic delineation of the myocardial wall from CT images via shape segmentation and variational region growing

Prognosis and diagnosis of cardiac diseases frequently require quantitative evaluation of the ventricle volume, mass, and ejection fraction. The delineation of the myocardial wall is involved in all of these evaluations, which is a challenging task due to large variations in myocardial shapes and image quality. In this paper, we present an automatic method for extracting the myocardial wall of the left and right ventricles from cardiac CT images. In the method, the left and right ventricles are located sequentially, in which each ventricle is detected by first identifying the endocardium and then segmenting the epicardium. To this end, the endocardium is localized by utilizing its geometric features obtained on-line from a CT image. After that, a variational region-growing model is employed to extract the epicardium of the ventricles. In particular, the location of the endocardium of the left ventricle is determined via using an active contour model on the blood-pool surface. To localize the right ventricle, the active contour model is applied on a heart surface extracted based on the left ventricle segmentation result. The robustness and accuracy of the proposed approach is demonstrated by experimental results from 33 human and 12 pig CT images.

Delineating anatomical boundaries using the boundary fragment model

In this paper we present a method to automatically isolate relevant anatomical boundary positions in an image using only the structure of edges. The purpose of this method is to facilitate model-based segmentation algorithms which rely on accurate initialisation and assume that the correct anatomical boundary positions are close to the current model surface. The method is built around a weak parts-based shape model - the Boundary Fragment Model (BFM) - which represents an object by sections of its boundary. Following previous literature, we use the BFM in a boosted classifier framework to first automatically detect the object of interest. Extending previous work, we use the BFM to drive a classifier which isolates boundary candidates from spurious and irrelevant edge responses. The application of our algorithm leads to a labelled edge map which encodes the positions of (multiple) object boundaries. By way of illustrating what is a general solution, the task of identifying the endocardium and epicardium in three-dimensional ultrasound images is completely examined, including a detailed analysis of the parameters which impact on the model construction, the structure of the learned edge response classifier, and implementation concerns. For completeness, we also demonstrate how the output boundary positions can be used in a full model-based segmentation framework.

Entangled decision forests and their application for semantic segmentation of CT images

This work addresses the challenging problem of simultaneously segmenting multiple anatomical structures in highly varied CT scans. We propose the entangled decision forest (EDF) as a new discriminative classifier which augments the state of the art decision forest, resulting in higher prediction accuracy and shortened decision time. Our main contribution is two-fold. First, we propose entangling the binary tests applied at each tree node in the forest, such that the test result can depend on the result of tests applied earlier in the same tree and at image points offset from the voxel to be classified. This is demonstrated to improve accuracy and capture long-range semantic context. Second, during training, we propose injecting randomness in a guided way, in which node feature types and parameters are randomly drawn from a learned (nonuniform) distribution. This further improves classification accuracy. We assess our probabilistic anatomy segmentation technique using a labeled database of CT image volumes of 250 different patients from various scan protocols and scanner vendors. In each volume, 12 anatomical structures have been manually segmented. The database comprises highly varied body shapes and sizes, a wide array of pathologies, scan resolutions, and diverse contrast agents. Quantitative comparisons with state of the art algorithms demonstrate both superior test accuracy and computational efficiency.

Spatial decision forests for MS lesion segmentation in multi-channel MR images

A new algorithm is presented for the automatic segmentation of Multiple Sclerosis (MS) lesions in 3D MR images. It builds on the discriminative random decision forest framework to provide a voxel-wise probabilistic classification of the volume. Our method uses multi-channel MIR intensities (T1, T2, Flair), spatial prior and long-range comparisons with 3D regions to discriminate lesions. A symmetry feature is introduced accounting for the fact that some MS lesions tend to develop in an asymmetric way. Quantitative evaluation of the data is carried out on publicly available labeled cases from the MS Lesion Segmentation Challenge 2008 dataset and demonstrates improved results over the state of the art.