Ender Konukoglu

The Multimodal Brain Tumor Image Segmentation Benchmark (BRATS)

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.

Decision Forests: A Unified Framework for Classification, Regression, Density Estimation, Manifold Learning and Semi-Supervised Learning

This review presents a unified, efficient model of random decision forests which can be applied to a number of machine learning, computer vision, and medical image analysis tasks. Our model extends existing forest-based techniques as it unifies classification, regression, density estimation, manifold learning, semi-supervised learning, and active learning under the same decision forest framework. This gives us the opportunity to write and optimize the core implementation only once, with application to many diverse tasks. The proposed model may be used both in a discriminative or generative way and may be applied to discrete or continuous, labeled or unlabeled data. The main contributions of this review are: (1) Proposing a unified, probabilistic and efficient model for a variety of learning tasks; (2) Demonstrating margin-maximizing properties of classification forests; (3) Discussing probabilistic regression forests in comparison with other nonlinear regression algorithms; (4) Introducing density forests for estimating probability density functions; (5) Proposing an efficient algorithm for sampling from a density forest; (6) Introducing manifold forests for nonlinear dimensionality reduction; (7) Proposing new algorithms for transductive learning and active learning. Finally, we discuss how alternatives such as random ferns and extremely randomized trees stem from our more general forest model. This document is directed at both students who wish to learn the basics of decision forests, as well as researchers interested in the new contributions. It presents both fundamental and novel concepts in a structured way, with many illustrative examples and real-world applications. Thorough comparisons with state-of-the-art algorithms such as support vector machines, boosting and Gaussian processes are presented and relative advantages and disadvantages discussed. The many synthetic examples and existing commercial applications demonstrate the validity of the proposed model and its flexibility.

Regression forests for efficient anatomy detection and localization in computed tomography scans

This paper proposes a new algorithm for the efficient, automatic detection and localization of multiple anatomical structures within three-dimensional computed tomography (CT) scans. Applications include selective retrieval of patients images from PACS systems, semantic visual navigation and tracking radiation dose over time. The main contribution of this work is a new, continuous parametrization of the anatomy localization problem, which allows it to be addressed effectively by multi-class random regression forests. Regression forests are similar to the more popular classification forests, but trained to predict continuous, multi-variate outputs, where the training focuses on maximizing the confidence of output predictions. A single pass of our probabilistic algorithm enables the direct mapping from voxels to organ location and size. Quantitative validation is performed on a database of 400 highly variable CT scans. We show that the proposed method is more accurate and robust than techniques based on efficient multi-atlas registration and template-based nearest-neighbor detection. Due to the simplicity of the regressors context-rich visual features and the algorithms parallelism, these results are achieved in typical run-times of only ∼4 s on a conventional single-core machine.

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

A new algorithm is presented for the automatic segmentation of Multiple Sclerosis (MS) lesions in 3D Magnetic Resonance (MR) images. It builds on a discriminative random decision forest framework to provide a voxel-wise probabilistic classification of the volume. The method uses multi-channel MR intensities (T1, T2, and FLAIR), knowledge on tissue classes and long-range spatial context to discriminate lesions from background. A symmetry feature is introduced accounting for the fact that some MS lesions tend to develop in an asymmetric way. Quantitative evaluation of the proposed methods is carried out on publicly available labeled cases from the MICCAI MS Lesion Segmentation Challenge 2008 dataset. When tested on the same data, the presented method compares favorably to all earlier methods. In an a posteriori analysis, we show how selected features during classification can be ranked according to their discriminative power and reveal the most important ones.

Image Guided Personalization of Reaction-Diffusion Type Tumor Growth Models Using Modified Anisotropic Eikonal Equations

Reaction-diffusion based tumor growth models have been widely used in the literature for modeling the growth of brain gliomas. Lately, recent models have started integrating medical images in their formulation. Including different tissue types, geometry of the brain and the directions of white matter fiber tracts improved the spatial accuracy of reaction-diffusion models. The adaptation of the general model to the specific patient cases on the other hand has not been studied thoroughly yet. In this paper, we address this adaptation. We propose a parameter estimation method for reaction-diffusion tumor growth models using time series of medical images. This method estimates the patient specific parameters of the model using the images of the patient taken at successive time instances. The proposed method formulates the evolution of the tumor delineation visible in the images based on the reaction-diffusion dynamics; therefore, it remains consistent with the information available. We perform thorough analysis of the method using synthetic tumors and show important couplings between parameters of the reaction-diffusion model. We show that several parameters can be uniquely identified in the case of fixing one parameter, namely the proliferation rate of tumor cells. Moreover, regardless of the value the proliferation rate is fixed to, the speed of growth of the tumor can be estimated in terms of the model parameters with accuracy. We also show that using the model-based speed, we can simulate the evolution of the tumor for the specific patient case. Finally, we apply our method to two real cases and show promising preliminary results.

Decision forests for tissue-specific segmentation of high-grade gliomas in multi-channel MR.

We present a method for automatic segmentation of high-grade gliomas and their subregions from multi-channel MR images. Besides segmenting the gross tumor, we also differentiate between active cells, necrotic core, and edema. Our discriminative approach is based on decision forests using context-aware spatial features, and integrates a generative model of tissue appearance, by using the probabilities obtained by tissue-specific Gaussian mixture models as additional input for the forest. Our method classifies the individual tissue types simultaneously, which has the potential to simplify the classification task. The approach is computationally efficient and of low model complexity. The validation is performed on a labeled database of 40 multi-channel MR images, including DTI. We assess the effects of using DTI, and varying the amount of training data. Our segmentation results are highly accurate, and compare favorably to the state of the art.

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.

Computational modeling of the WHO grade II glioma dynamics: principles and applications to management paradigm

The advent of magnetic resonance imaging (MRI) has allowed the follow-up of tumor growth by precise volumetric measurements. Such information about tumor dynamics is, however, usually not fully integrated in the therapeutic management, and the assessment of tumor evolution is still limited to qualitative description. In parallel, computational models have been developed to simulate in silico tumor growth and treatment efficacy. Nevertheless, direct clinical interest of these models remains questionable, and there is a gap between scientific advances and clinical practice. In this paper, WHO grade II glioma will serve as a paradigmatic example to illustrate that computational models allow characterizing tumor dynamics from serial MRIs. The role of these dynamics for both therapeutic management and biological research will be discussed.

Glioma Dynamics and Computational Models: A Review of Segmentation, Registration, and In Silico Growth Algorithms and their Clinical Applications

Tracking gliomas dynamics on MRI has became more and more important for therapeutic management. Powerful computational tools have been recently developed in this context enabling in silico growth on a virtual brain that can be matched with real 3D segmented evolution through registration between atlases and patient brain MRI data. In this paper, we provide an extensive review of existing algorithms for the three computational tasks involved in patient-specific tumor modeling: image segmentation, image registration, and in silico growth modelling (with special emphasis on the proliferation-diffusion model). Accuracy and limits of the reviewed algorithms are systematically discussed. Finally applications of these methods for both clinical practice and fundamental research are also discussed.

Automatic Localization and Identification of Vertebrae in Arbitrary Field-of-View CT Scans

This paper presents a new method for automatic localization and identification of vertebrae in arbitrary field-of-view CT scans. No assumptions are made about which section of the spine is visible or to which extent. Thus, our approach is more general than previous work while being computationally efficient. Our algorithm is based on regression forests and probabilistic graphical models. The discriminative, regression part aims at roughly detecting the visible part of the spine. Accurate localization and identification of individual vertebrae is achieved through a generative model capturing spinal shape and appearance. The system is evaluated quantitatively on 200 CT scans, the largest dataset reported for this purpose. We obtain an overall median localization error of less than 6mm, with an identification rate of 81%.