Author name cluster

Ender Konukoglu

Possible papers associated with this exact author name in Arrow. This page groups case-insensitive exact name matches and is not a full identity disambiguation profile.

19 papers

2 author rows

TMLR Journal 2026 Journal Article

Mixtures of Locally Bounded Langevin dynamics for Bayesian Model Averaging

Kilian Zepf
Tareen Dawood
Aasa Feragen
Ender Konukoglu

Properties of probability distributions change when going from low to high dimensions, to the extent that they exhibit counterintuitive behavior. Gaussian distributions intuitively illustrate a well-known effect of moving to higher dimensions, namely that the typical set almost surely does not contain the mean, which is the distribution's most probable point. This can be problematic in Bayesian Deep Learning, as the samples drawn from the high-dimensional posterior distribution are often used as Monte Carlo samples to estimate the integral of the predictive distribution. Here, the predictive distribution will reflect the behavior of the samples and, therefore, of the typical set. For instance, we cannot expect to sample networks close to the maximum a posteriori estimate after fitting a Gaussian approximation to the posterior using the Laplace method. In this paper, we introduce a method that aims to mitigate this typicality problem in high dimensions by sampling from the posterior with Langevin dynamics on a restricted support enforced by a reflective boundary condition. We demonstrate how this leads to improved posterior estimates by illustrating its capacity for fine-grained out-of-distribution (OOD) ranking on the Morpho-MNIST dataset.

PDF Details

NeurIPS Conference 2025 Conference Paper

CamSAM2: Segment Anything Accurately in Camouflaged Videos

Yuli Zhou
Yawei Li
Yuqian Fu
Luca Benini
Ender Konukoglu
Guolei Sun

Video camouflaged object segmentation (VCOS), aiming at segmenting camouflaged objects that seamlessly blend into their environment, is a fundamental vision task with various real-world applications. With the release of SAM2, video segmentation has witnessed significant progress. However, SAM2's capability of segmenting camouflaged videos is suboptimal, especially when given simple prompts such as point and box. To address the problem, we propose Camouflaged SAM2 (CamSAM2), which enhances SAM2's ability to handle camouflaged scenes without modifying SAM2's parameters. Specifically, we introduce a decamouflaged token to provide the flexibility of feature adjustment for VCOS. To make full use of fine-grained and high-resolution features from the current frame and previous frames, we propose implicit object-aware fusion (IOF) and explicit object-aware fusion (EOF) modules, respectively. Object prototype generation (OPG) is introduced to abstract and memorize object prototypes with informative details using high-quality features from previous frames. Extensive experiments are conducted to validate the effectiveness of our approach. While CamSAM2 only adds negligible learnable parameters to SAM2, it substantially outperforms SAM2 on three VCOS datasets, especially achieving 12. 2 mDice gains with click prompt on MoCA-Mask and 19. 6 mDice gains with mask prompt on SUN-SEG-Hard, with Hiera-T as the backbone. The code is available at https: //github. com/zhoustan/CamSAM2.

PDF Details

ICLR Conference 2025 Conference Paper

Multimodality Helps Few-shot 3D Point Cloud Semantic Segmentation

Zhaochong An
Guolei Sun
Yun Liu 0011
Runjia Li
Min Wu 0008
Ming-Ming Cheng
Ender Konukoglu
Serge J. Belongie

Few-shot 3D point cloud segmentation (FS-PCS) aims at generalizing models to segment novel categories with minimal annotated support samples. While existing FS-PCS methods have shown promise, they primarily focus on unimodal point cloud inputs, overlooking the potential benefits of leveraging multimodal information. In this paper, we address this gap by introducing a multimodal FS-PCS setup, utilizing textual labels and the potentially available 2D image modality. Under this easy-to-achieve setup, we present the MultiModal Few-Shot SegNet (MM-FSS), a model effectively harnessing complementary information from multiple modalities. MM-FSS employs a shared backbone with two heads to extract intermodal and unimodal visual features, and a pretrained text encoder to generate text embeddings. To fully exploit the multimodal information, we propose a Multimodal Correlation Fusion (MCF) module to generate multimodal correlations, and a Multimodal Semantic Fusion (MSF) module to refine the correlations using text-aware semantic guidance. Additionally, we propose a simple yet effective Test-time Adaptive Cross-modal Calibration (TACC) technique to mitigate training bias, further improving generalization. Experimental results on S3DIS and ScanNet datasets demonstrate significant performance improvements achieved by our method. The efficacy of our approach indicates the benefits of leveraging commonly-ignored free modalities for FS-PCS, providing valuable insights for future research. The code is available at github.com/ZhaochongAn/Multimodality-3D-Few-Shot.

Details

NeurIPS Conference 2025 Conference Paper

SceneSplat++: A Large Dataset and Comprehensive Benchmark for Language Gaussian Splatting

Mengjiao Ma
Qi Ma
Yue Li
Jiahuan Cheng
Runyi Yang
Bin Ren
Nikola Popovic
Mingqiang Wei

3D Gaussian Splatting (3DGS) serves as a highly performant and efficient encoding of scene geometry, appearance, and semantics. Moreover, grounding language in 3D scenes has proven to be an effective strategy for 3D scene understanding. Current Language Gaussian Splatting line of work fall into three main groups: (i) per-scene optimization-based, (ii) per-scene optimization-free, and (iii) generalizable approach. However, most of them are evaluated only on rendered 2D views of a handful of scenes and viewpoints close to the training views, limiting ability and insight into holistic 3D understanding. To address this gap, we propose the first large-scale benchmark that systematically assesses these three groups of methods directly in 3D space, evaluating on 1060 scenes across three indoor datasets and one outdoor dataset. Benchmark results demonstrate a clear advantage of the generalizable paradigm, particularly in relaxing the scene-specific limitation, enabling fast feed-forward inference on novel scenes, and achieving superior segmentation performance. We further introduce SceneSplat-49K -- a carefully curated 3DGS dataset comprising of around 49K diverse indoor and outdoor scenes trained from multiple sources, with which we demonstrate generalizable approach could harness strong data priors. Our codes, benchmark, and datasets are available.

PDF Details

ICLR Conference 2025 Conference Paper

Uncertainty modeling for fine-tuned implicit functions

Anna Susmelj
Mael Macuglia
Natasa Tagasovska
Reto Sutter
Sebastiano Caprara
Jean-Philippe Thiran
Ender Konukoglu

Implicit functions such as Neural Radiance Fields (NeRFs), occupancy networks, and signed distance functions (SDFs) have become pivotal in computer vision for reconstructing detailed object shapes from sparse views. Achieving optimal performance with these models can be challenging due to the extreme sparsity of inputs and distribution shifts induced by data corruptions. To this end, large, noise-free synthetic datasets can serve as shape priors to help models fill in gaps, but the resulting reconstructions must be approached with caution. Uncertainty estimation is crucial for assessing the quality of these reconstructions, particularly in identifying areas where the model is uncertain about the parts it has inferred from the prior. In this paper, we introduce Dropsembles, a novel method for uncertainty estimation in tuned implicit functions. We demonstrate the efficacy of our approach through a series of experiments, starting with toy examples and progressing to a real-world scenario. Specifically, we train a Convolutional Occupancy Network on synthetic anatomical data and test it on low-resolution MRI segmentations of the lumbar spine. Our results show that Dropsembles achieve the accuracy and calibration levels of deep ensembles but with significantly less computational cost.

Details

NeurIPS Conference 2024 Conference Paper

Implicit Zoo: A Large-Scale Dataset of Neural Implicit Functions for 2D Images and 3D Scenes

Qi Ma
Danda P. Paudel
Ender Konukoglu
Luc Van Gool

Neural implicit functions have demonstrated significant importance in various areas such as computer vision, graphics. Their advantages include the ability to represent complex shapes and scenes with high fidelity, smooth interpolation capabilities, and continuous representations. Despite these benefits, the development and analysis of implicit functions have been limited by the lack of comprehensive datasets and the substantial computational resources required for their implementation and evaluation. To address these challenges, we introduce "Implicit-Zoo": a large-scale dataset requiring thousands of GPU training days designed to facilitate research and development in this field. Our dataset includes diverse 2D and 3D scenes, such as CIFAR-10, ImageNet-1K, and Cityscapes for 2D image tasks, and the OmniObject3D dataset for 3D vision tasks. We ensure high quality through strict checks, refining or filtering out low-quality data. Using Implicit-Zoo, we showcase two immediate benefits as it enables to: (1) learn token locations for transformer models; (2) Directly regress 3D cameras poses of 2D images with respect to NeRF models. This in turn leads to an \emph{improved performance} in all three task of image classification, semantic segmentation, and 3D pose regression -- thereby unlocking new avenues for research.

PDF Details DOI

NeurIPS Conference 2023 Conference Paper

Canonical normalizing flows for manifold learning

Kyriakos Flouris
Ender Konukoglu

Manifold learning flows are a class of generative modelling techniques that assume a low-dimensional manifold description of the data. The embedding of such a manifold into the high-dimensional space of the data is achieved via learnable invertible transformations. Therefore, once the manifold is properly aligned via a reconstruction loss, the probability density is tractable on the manifold and maximum likelihood can be used to optimize the network parameters. Naturally, the lower-dimensional representation of the data requires an injective-mapping. Recent approaches were able to enforce that the density aligns with the modelled manifold, while efficiently calculating the density volume-change term when embedding to the higher-dimensional space. However, unless the injective-mapping is analytically predefined, the learned manifold is not necessarily an \emph{efficient representation} of the data. Namely, the latent dimensions of such models frequently learn an entangled intrinsic basis, with degenerate information being stored in each dimension. Alternatively, if a locally orthogonal and/or sparse basis is to be learned, here coined canonical intrinsic basis, it can serve in learning a more compact latent space representation. Toward this end, we propose a canonical manifold learning flow method, where a novel optimization objective enforces the transformation matrix to have few prominent and non-degenerate basis functions. We demonstrate that by minimizing the off-diagonal manifold metric elements $\ell_1$-norm, we can achieve such a basis, which is simultaneously sparse and/or orthogonal. Canonical manifold flow yields a more efficient use of the latent space, automatically generating fewer prominent and distinct dimensions to represent data, and consequently a better approximation of target distributions than other manifold flow methods in most experiments we conducted, resulting in lower FID scores.

PDF Details

NeurIPS Conference 2023 Conference Paper

Expert load matters: operating networks at high accuracy and low manual effort

Sara Sangalli
Ertunc Erdil
Ender Konukoglu

In human-AI collaboration systems for critical applications, in order to ensure minimal error, users should set an operating point based on model confidence to determine when the decision should be delegated to human experts. Samples for which model confidence is lower than the operating point would be manually analysed by experts to avoid mistakes. Such systems can become truly useful only if they consider two aspects: models should be confident only for samples for which they are accurate, and the number of samples delegated to experts should be minimized. The latter aspect is especially crucial for applications where available expert time is limited and expensive, such as healthcare. The trade-off between the model accuracy and the number of samples delegated to experts can be represented by a curve that is similar to an ROC curve, which we refer to as confidence operating characteristic (COC) curve. In this paper, we argue that deep neural networks should be trained by taking into account both accuracy and expert load and, to that end, propose a new complementary loss function for classification that maximizes the area under this COC curve. This promotes simultaneously the increase in network accuracy and the reduction in number of samples delegated to humans. We perform experiments on multiple computer vision and medical image datasets for classification. Our results demonstrate that the proposed loss improves classification accuracy and delegates less number of decisions to experts, achieves better out-of-distribution samples detection and on par calibration performance compared to existing loss functions.

PDF Details

ICLR Conference 2023 Conference Paper

Explicitly Minimizing the Blur Error of Variational Autoencoders

Gustav Bredell
Kyriakos Flouris
Krishna Chaitanya
Ertunc Erdil
Ender Konukoglu

Variational autoencoders (VAEs) are powerful generative modelling methods, however they suffer from blurry generated samples and reconstructions compared to the images they have been trained on. Significant research effort has been spent to increase the generative capabilities by creating more flexible models but often flexibility comes at the cost of higher complexity and computational cost. Several works have focused on altering the reconstruction term of the evidence lower bound (ELBO), however, often at the expense of losing the mathematical link to maximizing the likelihood of the samples under the modeled distribution. Here we propose a new formulation of the reconstruction term for the VAE that specifically penalizes the generation of blurry images while at the same time still maximizing the ELBO under the modeled distribution. We show the potential of the proposed loss on three different data sets, where it outperforms several recently proposed reconstruction losses for VAEs.

Details

ICLR Conference 2023 Conference Paper

FedFA: Federated Feature Augmentation

Tianfei Zhou
Ender Konukoglu

Federated learning is a distributed paradigm that allows multiple parties to collaboratively train deep models without exchanging the raw data. However, the data distribution among clients is naturally non-i.i.d., which leads to severe degradation of the learnt model. The primary goal of this paper is to develop a robust federated learning algorithm to address feature shift in clients’ samples, which can be caused by various factors, e.g., acquisition differences in medical imaging. To reach this goal, we propose FedFA to tackle federated learning from a dis- tinct perspective of federated feature augmentation. FedFA is based on a major insight that each client’s data distribution can be characterized by statistics (i.e., mean and standard deviation) of latent features; and it is likely to manipulate these local statistics globally, i.e., based on information in the entire federation, to let clients have a better sense of the underlying distribution and therefore alleviate local data bias. Based on this insight, we propose to augment each local feature statistic probabilistically based on a normal distribution, whose mean is the original statistic and variance quantifies the augmentation scope. Key to our approach is the determination of a meaningful Gaussian variance, which is accomplished by taking into account not only biased data of each individual client, but also underlying feature statistics characterized by all participating clients. We offer both theoretical and empirical justifications to verify the effectiveness of FedFA. Our code is available at https://github.com/tfzhou/FedFA.

Details

ICLR Conference 2022 Conference Paper

Zero Pixel Directional Boundary by Vector Transform

Edoardo Mello Rella
Ajad Chhatkuli
Yun Liu 0011
Ender Konukoglu
Luc Van Gool

Boundaries or contours are among the primary visual cues used by human and computer vision systems. One of the key problems in boundary detection is the loss formulation, which typically leads to class imbalance and, as a consequence, to thick boundaries which require non-differential post-processing steps to be thinned. In this paper, we re-interpret boundaries as 1-D surfaces and formulate a one-to-one vector transform function that allows for training of boundary prediction completely avoiding the class imbalance issue. Specifically, we define the boundary representation at any point as the unit vector pointing to the closest boundary surface. Our problem formulation leads to the estimation of direction as well as richer contextual information of the boundary, and, if desired, the availability of zero-pixel thin boundaries also at training time. Our method uses no hyper-parameter in the training loss and a fixed stable hyper-parameter at inference. We provide theoretical justification/discussions of the vector transform representation. We evaluate the proposed loss method using a standard architecture and show the excellent performance over other losses and representations on several datasets.

Details

NeurIPS Conference 2021 Conference Paper

Constrained Optimization to Train Neural Networks on Critical and Under-Represented Classes

Sara Sangalli
Ertunc Erdil
Andeas Hötker
Olivio Donati
Ender Konukoglu

Deep neural networks (DNNs) are notorious for making more mistakes for the classes that have substantially fewer samples than the others during training. Such class imbalance is ubiquitous in clinical applications and very crucial to handle because the classes with fewer samples most often correspond to critical cases (e. g. , cancer) where misclassifications can have severe consequences. Not to miss such cases, binary classifiers need to be operated at high True Positive Rates (TPRs) by setting a higher threshold, but this comes at the cost of very high False Positive Rates (FPRs) for problems with class imbalance. Existing methods for learning under class imbalance most often do not take this into account. We argue that prediction accuracy should be improved by emphasizing the reduction of FPRs at high TPRs for problems where misclassification of the positive, i. e. critical, class samples are associated with higher cost. To this end, we pose the training of a DNN for binary classification as a constrained optimization problem and introduce a novel constraint that can be used with existing loss functions to enforce maximal area under the ROC curve (AUC) through prioritizing FPR reduction at high TPR. We solve the resulting constrained optimization problem using an Augmented Lagrangian method (ALM). Going beyond binary, we also propose two possible extensions of the proposed constraint for multi-class classification problems. We present experimental results for image-based binary and multi-class classification applications using an in-house medical imaging dataset, CIFAR10, and CIFAR100. Our results demonstrate that the proposed method improves the baselines in majority of the cases by attaining higher accuracy on critical classes while reducing the misclassification rate for the non-critical class samples.

PDF Details

NeurIPS Conference 2020 Conference Paper

Contrastive learning of global and local features for medical image segmentation with limited annotations

Krishna Chaitanya
Ertunc Erdil
Neerav Karani
Ender Konukoglu

A key requirement for the success of supervised deep learning is a large labeled dataset - a condition that is difficult to meet in medical image analysis. Self-supervised learning (SSL) can help in this regard by providing a strategy to pre-train a neural network with unlabeled data, followed by fine-tuning for a downstream task with limited annotations. Contrastive learning, a particular variant of SSL, is a powerful technique for learning image-level representations. In this work, we propose strategies for extending the contrastive learning framework for segmentation of volumetric medical images in the semi-supervised setting with limited annotations, by leveraging domain-specific and problem-specific cues. Specifically, we propose (1) novel contrasting strategies that leverage structural similarity across volumetric medical images (domain-specific cue) and (2) a local version of the contrastive loss to learn distinctive representations of local regions that are useful for per-pixel segmentation (problem-specific cue). We carry out an extensive evaluation on three Magnetic Resonance Imaging (MRI) datasets. In the limited annotation setting, the proposed method yields substantial improvements compared to other self-supervision and semi-supervised learning techniques. When combined with a simple data augmentation technique, the proposed method reaches within 8\% of benchmark performance using only two labeled MRI volumes for training. The code is made public at https: //github. com/krishnabits001/domain_specific_cl.

PDF Details

JMLR Journal 2019 Journal Article

Morpho-MNIST: Quantitative Assessment and Diagnostics for Representation Learning

Daniel C. Castro
Jeremy Tan
Bernhard Kainz
Ender Konukoglu
Ben Glocker

Revealing latent structure in data is an active field of research, having introduced exciting technologies such as variational autoencoders and adversarial networks, and is essential to push machine learning towards unsupervised knowledge discovery. However, a major challenge is the lack of suitable benchmarks for an objective and quantitative evaluation of learned representations. To address this issue we introduce Morpho-MNIST, a framework that aims to answer: “to what extent has my model learned to represent specific factors of variation in the data? We extend the popular MNIST dataset by adding a morphometric analysis enabling quantitative comparison of trained models, identification of the roles of latent variables, and characterisation of sample diversity. We further propose a set of quantifiable perturbations to assess the performance of unsupervised and supervised methods on challenging tasks such as outlier detection and domain adaptation. Data and code are available at https://github.com/dccastro/Morpho-MNIST. [abs] [ pdf ][ bib ] &copy JMLR 2019. ( edit, beta )

PDF Details

YNIMG Journal 2018 Journal Article

as-PSOCT: Volumetric microscopic imaging of human brain architecture and connectivity

Hui Wang
Caroline Magnain
Ruopeng Wang
Jay Dubb
Ani Varjabedian
Lee S. Tirrell
Allison Stevens
Jean C. Augustinack

Polarization sensitive optical coherence tomography (PSOCT) with serial sectioning has enabled the investigation of 3D structures in mouse and human brain tissue samples. By using intrinsic optical properties of back-scattering and birefringence, PSOCT reliably images cytoarchitecture, myeloarchitecture and fiber orientations. In this study, we developed a fully automatic serial sectioning polarization sensitive optical coherence tomography (as-PSOCT) system to enable volumetric reconstruction of human brain samples with unprecedented sample size and resolution. The 3. 5 μm in-plane resolution and 50 μm through-plane voxel size allow inspection of cortical layers that are a single-cell in width, as well as small crossing fibers. We show the abilities of as-PSOCT in quantifying layer thicknesses of the cerebellar cortex and creating microscopic tractography of intricate fiber networks in the subcortical nuclei and internal capsule regions, all based on volumetric reconstructions. as-PSOCT provides a viable tool for studying quantitative cytoarchitecture and myeloarchitecture and mapping connectivity with microscopic resolution in the human brain.

Details DOI

YNIMG Journal 2018 Journal Article

Reconstructing subject-specific effect maps

Ender Konukoglu
Ben Glocker

Predictive models allow subject-specific inference when analyzing disease related alterations in neuroimaging data. Given a subject's data, inference can be made at two levels: global, i. e. identifiying condition presence for the subject, and local, i. e. detecting condition effect on each individual measurement extracted from the subject's data. While global inference is widely used, local inference, which can be used to form subject-specific effect maps, is rarely used because existing models often yield noisy detections composed of dispersed isolated islands. In this article, we propose a reconstruction method, named RSM, to improve subject-specific detections of predictive modeling approaches and in particular, binary classifiers. RSM specifically aims to reduce noise due to sampling error associated with using a finite sample of examples to train classifiers. The proposed method is a wrapper-type algorithm that can be used with different binary classifiers in a diagnostic manner, i. e. without information on condition presence. Reconstruction is posed as a Maximum-A-Posteriori problem with a prior model whose parameters are estimated from training data in a classifier-specific fashion. Experimental evaluation is performed on synthetically generated data and data from the Alzheimer's Disease Neuroimaging Initiative (ADNI) database. Results on synthetic data demonstrate that using RSM yields higher detection accuracy compared to using models directly or with bootstrap averaging. Analyses on the ADNI dataset show that RSM can also improve correlation between subject-specific detections in cortical thickness data and non-imaging markers of Alzheimer's Disease (AD), such as the Mini Mental State Examination Score and Cerebrospinal Fluid amyloid-β levels. Further reliability studies on the longitudinal ADNI dataset show improvement on detection reliability when RSM is used.

Details DOI

YNIMG Journal 2016 Journal Article

Multivariate statistical analysis of diffusion imaging parameters using partial least squares: Application to white matter variations in Alzheimer's disease

Ender Konukoglu
Jean-Philippe Coutu
David H. Salat
Bruce Fischl

Diffusion magnetic resonance imaging (dMRI) is a unique technology that allows the noninvasive quantification of microstructural tissue properties of the human brain in healthy subjects as well as the probing of disease-induced variations. Population studies of dMRI data have been essential in identifying pathological structural changes in various conditions, such as Alzheimer's and Huntington's diseases (Salat et al. , 2010; Rosas et al. , 2006). The most common form of dMRI involves fitting a tensor to the underlying imaging data (known as diffusion tensor imaging, or DTI), then deriving parametric maps, each quantifying a different aspect of the underlying microstructure, e. g. fractional anisotropy and mean diffusivity. To date, the statistical methods utilized in most DTI population studies either analyzed only one such map or analyzed several of them, each in isolation. However, it is most likely that variations in the microstructure due to pathology or normal variability would affect several parameters simultaneously, with differing variations modulating the various parameters to differing degrees. Therefore, joint analysis of the available diffusion maps can be more powerful in characterizing histopathology and distinguishing between conditions than the widely used univariate analysis. In this article, we propose a multivariate approach for statistical analysis of diffusion parameters that uses partial least squares correlation (PLSC) analysis and permutation testing as building blocks in a voxel-wise fashion. Stemming from the common formulation, we present three different multivariate procedures for group analysis, regressing-out nuisance parameters and comparing effects of different conditions. We used the proposed procedures to study the effects of non-demented aging, Alzheimer's disease and mild cognitive impairment on the white matter. Here, we present results demonstrating that the proposed PLSC-based approach can differentiate between effects of different conditions in the same region as well as uncover spatial variations of effects across the white matter. The proposed procedures were able to answer questions on structural variations such as: “are there regions in the white matter where Alzheimer's disease has a different effect than aging or similar effect as aging? ” and “are there regions in the white matter that are affected by both mild cognitive impairment and Alzheimer's disease but with differing multivariate effects? ”

Details DOI

YNIMG Journal 2015 Journal Article

Relevant feature set estimation with a knock-out strategy and random forests

Melanie Ganz
Douglas N. Greve
Bruce Fischl
Ender Konukoglu

Group analysis of neuroimaging data is a vital tool for identifying anatomical and functional variations related to diseases as well as normal biological processes. The analyses are often performed on a large number of highly correlated measurements using a relatively smaller number of samples. Despite the correlation structure, the most widely used approach is to analyze the data using univariate methods followed by post-hoc corrections that try to account for the data's multivariate nature. Although widely used, this approach may fail to recover from the adverse effects of the initial analysis when local effects are not strong. Multivariate pattern analysis (MVPA) is a powerful alternative to the univariate approach for identifying relevant variations. Jointly analyzing all the measures, MVPA techniques can detect global effects even when individual local effects are too weak to detect with univariate analysis. Current approaches are successful in identifying variations that yield highly predictive and compact models. However, they suffer from lessened sensitivity and instabilities in identification of relevant variations. Furthermore, current methods' user-defined parameters are often unintuitive and difficult to determine. In this article, we propose a novel MVPA method for group analysis of high-dimensional data that overcomes the drawbacks of the current techniques. Our approach explicitly aims to identify all relevant variations using a “knock-out” strategy and the Random Forest algorithm. In evaluations with synthetic datasets the proposed method achieved substantially higher sensitivity and accuracy than the state-of-the-art MVPA methods, and outperformed the univariate approach when the effect size is low. In experiments with real datasets the proposed method identified regions beyond the univariate approach, while other MVPA methods failed to replicate the univariate results. More importantly, in a reproducibility study with the well-known ADNI dataset the proposed method yielded higher stability and power than the univariate approach.

Details DOI

YNIMG Journal 2011 Journal Article

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

Ezequiel Geremia
Olivier Clatz
Bjoern H. Menze
Ender Konukoglu
Antonio Criminisi
Nicholas Ayache

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.

Details DOI