1,082 Hits in 1.4 sec

Gradient Boosted Trees for Corrective Learning [chapter]

Baris U. Oguz, Russell T. Shinohara, Paul A. Yushkevich, Ipek Oguz
2017 Lecture Notes in Computer Science  
Random forests (RF) have long been a widely popular method in medical image analysis. Meanwhile, the closely related gradient boosted trees (GBT) have not become a mainstream tool in medical imaging despite their attractive performance, perhaps due to their computational cost. In this paper, we leverage the recent availability of an efficient open-source GBT implementation to illustrate the GBT method in a corrective learning framework, in application to the segmentation of the caudate nucleus,
more » ... putamen and hippocampus. The size and shape of these structures are used to derive important biomarkers in many neurological and psychiatric conditions. However, the large variability in deep gray matter appearance makes their automated segmentation from MRI scans a challenging task. We propose using GBT to improve existing segmentation methods. We begin with an existing 'host' segmentation method to create an estimate surface. Based on this estimate, a surface-based sampling scheme is used to construct a set of candidate locations. GBT models are trained on features derived from the candidate locations, including spatial coordinates, image intensity, texture, and gradient magnitude. The classification probabilities from the GBT models are used to calculate a final surface estimate. The method is evaluated on a public dataset, with a 2-fold cross-validation. We use a multi-atlas approach and FreeSurfer as host segmentation methods. The mean reduction in surface distance error metric for FreeSurfer was 0.2 -0.3 mm, whereas for multi-atlas segmentation, it was 0.1mm for each of caudate, putamen and hippocampus. Importantly, our approach outperformed an RF model trained on the same features (p < 0.05 on all measures). Our method is readily generalizable and can be applied to a wide range of medical image segmentation problems and allows any segmentation method to be used as input.
doi:10.1007/978-3-319-67389-9_24 pmid:30327797 pmcid:PMC6186453 fatcat:yifznhicorhmplj6b3hhrpnrgm

Serotonin Noradrenaline Reuptake Inhibitors (SNRIs) [chapter]

Ipek Komsuoglu, Oguz Mutlu, Guner Ulak
2012 Effects of Antidepressants  
How to reference In order to correctly reference this scholarly work, feel free to copy and paste the following: Ipek Komsuoglu Celikyurt, Oguz Mutlu and Guner Ulak (2012) .  ... 
doi:10.5772/37999 fatcat:r44e2avrxndlxi2mfyxp62y4n4

Efficient optimization for Hierarchically-structured Interacting Segments (HINTS) [article]

Hossam Isack, Olga Veksler, Ipek Oguz, Milan Sonka, Yuri Boykov
2017 arXiv   pre-print
We propose an effective optimization algorithm for a general hierarchical segmentation model with geometric interactions between segments. Any given tree can specify a partial order over object labels defining a hierarchy. It is well-established that segment interactions, such as inclusion/exclusion and margin constraints, make the model significantly more discriminant. However, existing optimization methods do not allow full use of such models. Generic -expansion results in weak local minima,
more » ... hile common binary multi-layered formulations lead to non-submodularity, complex high-order potentials, or polar domain unwrapping and shape biases. In practice, applying these methods to arbitrary trees does not work except for simple cases. Our main contribution is an optimization method for the Hierarchically-structured Interacting Segments (HINTS) model with arbitrary trees. Our Path-Moves algorithm is based on multi-label MRF formulation and can be seen as a combination of well-known a-expansion and Ishikawa techniques. We show state-of-the-art biomedical segmentation for many diverse examples of complex trees.
arXiv:1703.10530v1 fatcat:resycmrjobbxvcg6mupy3e4bja

Synthetic Atrophy for Longitudinal Cortical Surface Analyses

Kathleen E. Larson, Ipek Oguz
2022 Frontiers in Neuroimaging  
., 2004; Oguz and Sonka, 2014a,b; Oguz et al., 2015) , determining the accuracy of observed measurements still remains challenging due to the difficulty of obtaining ground truth for experimental validation  ...  recently, both longitudinal and cross-sectional studies often achieve validation of CT measurements by comparing thicknesses observed by a new pipeline to those from previously existing algorithms (Oguz  ...  ACKNOWLEDGMENTS A preliminary version of this work was previously published in the SPIE Medical Imaging: Image Processing conference proceedings (Larson and Oguz, 2021) .  ... 
doi:10.3389/fnimg.2022.861687 fatcat:tgtt5cat6zhi3dbqa5xoqschlm

Particle-Guided Image Registration [chapter]

Joohwi Lee, Ilwoo Lyu, İpek Oğuz, Martin A. Styner
2013 Lecture Notes in Computer Science  
We present a novel image registration method based on B-spline free-form deformation that simultaneously optimizes particle correspondence and image similarity metrics. Different from previous Bspline based registration methods optimized w.r.t. the control points, the deformation in our method is estimated from a set of dense unstructured pair of points, which we refer as corresponding particles. As intensity values are matched on the corresponding location, the registration performance is
more » ... tively improved. Moreover, the use of corresponding particles naturally extends our method to a group-wise registration by computing a mean of particles. Motivated by a surface-based groupwise particle correspondence method, we developed a novel system that takes such particles to the image domain, while keeping the spirit of the method similar. The core algorithm both minimizes an entropy based group-wise correspondence metric as well as maximizes the space sampling of the particles. We demonstrate the results of our method in an application of rodent brain structure segmentation and show that our method provides better accuracy in two structures compared to other registration methods.
doi:10.1007/978-3-642-40760-4_26 fatcat:3cglbw4bxjbhnaeaiuxgyxnati

Retinal OCT Denoising with Pseudo-Multimodal Fusion Network [article]

Dewei Hu, Joseph D. Malone, Yigit Atay, Yuankai K. Tao, Ipek Oguz
2021 arXiv   pre-print
In a recent study, Oguz et al. [11] proposed the self-fusion method for retinal OCT denoising.  ... 
arXiv:2107.04288v1 fatcat:w26tkfoo5nhbdikkumdkylhfli

Finite volume flow simulations on arbitrary domains

Jeremy D. Wendt, William Baxter, Ipek Oguz, Ming C. Lin
2007 Graphical Models  
We present a novel method for solving the incompressible Navier-Stokes equations that more accurately handles arbitrary boundary conditions and sharp geometric features in the fluid domain. It uses a space filling tetrahedral mesh, which can be created using many well known methods, to represent the fluid domain. Examples of the method's strengths are illustrated by free surface fluid simulations and smoke simulations of flows around objects with complex geometry.
doi:10.1016/j.gmod.2006.05.004 fatcat:wpw52vaqlvgjbgiv5liy36uufa

New Approaches for the Therapy of Treatment Refractory Depression [chapter]

Oguz Mutlu, Gner Ulak, Ipek Komsuoglu, Fruzan Yldz, Faruk Erde
2012 Psychology - Selected Papers  
How to reference In order to correctly reference this scholarly work, feel free to copy and paste the following: Oguz Mutlu, Güner Ulak, Ipek Komsuoglu Celikyurt, Füruzan Yıldız Akar and Faruk Erden (  ... 
doi:10.5772/37974 fatcat:ghcagsn4v5azzczhf6psqvjqke

Assessment of The Prevalence of Methicillin Resistant Staphylococcus aureus (MRSA) with Different Methods

2001 Flora Infeksiyon Hastalıkları ve Klinik Mikrobiyoloji Dergisi  
Agar dilüsyona göre disk difüzyonun özgüllük ve duyarlılığı Metisilin Dirençli Staphylococcus aureus (MRSA) Prevalansının Farklı Yöntemlerle Araştırılması Avkan Oğuz V, Dodanlı S, Yıldırım İ, Öztürk O,  ...  aureus suşları, 12 marker (Hae III). 12 2 1 mec A (1.1 kb) Flora 2001;6(3):178-183 181 Metisilin Dirençli Staphylococcus aureus (MRSA) Prevalansının Farklı Yöntemlerle Araştırılması Avkan Oğuz  ... 
doaj:ad6cbce47be2449aa456d98e6c103f6a fatcat:hbckj3a335cclnhzciswl3y2cq

LIFE: A Generalizable Autodidactic Pipeline for 3D OCT-A Vessel Segmentation [article]

Dewei Hu, Can Cui, Hao Li, Kathleen E. Larson, Yuankai K. Tao, Ipek Oguz
2021 arXiv   pre-print
Optical coherence tomography (OCT) is a non-invasive imaging technique widely used for ophthalmology. It can be extended to OCT angiography (OCT-A), which reveals the retinal vasculature with improved contrast. Recent deep learning algorithms produced promising vascular segmentation results; however, 3D retinal vessel segmentation remains difficult due to the lack of manually annotated training data. We propose a learning-based method that is only supervised by a self-synthesized modality named
more » ... local intensity fusion (LIF). LIF is a capillary-enhanced volume computed directly from the input OCT-A. We then construct the local intensity fusion encoder (LIFE) to map a given OCT-A volume and its LIF counterpart to a shared latent space. The latent space of LIFE has the same dimensions as the input data and it contains features common to both modalities. By binarizing this latent space, we obtain a volumetric vessel segmentation. Our method is evaluated in a human fovea OCT-A and three zebrafish OCT-A volumes with manual labels. It yields a Dice score of 0.7736 on human data and 0.8594 +/- 0.0275 on zebrafish data, a dramatic improvement over existing unsupervised algorithms.
arXiv:2107.04282v1 fatcat:w7ejavhgord3nkuugsp4fbi774

RATS: Rapid Automatic Tissue Segmentation in rodent brain MRI

Ipek Oguz, Honghai Zhang, Ashley Rumple, Milan Sonka
2014 Journal of Neuroscience Methods  
., 2009; Oguz et al., 2011) and the pulse-coupled neural network approach (PCNN) (Chou et al., 2011) .  ... 
doi:10.1016/j.jneumeth.2013.09.021 pmid:24140478 pmcid:PMC3914765 fatcat:v6aec26ib5hotinectynsegn7e

Cortical Correspondence with Probabilistic Fiber Connectivity [chapter]

Ipek Oguz, Marc Niethammer, Josh Cates, Ross Whitaker, Thomas Fletcher, Clement Vachet, Martin Styner
2009 Lecture Notes in Computer Science  
This paper presents a novel method of optimizing pointbased correspondence among populations of human cortical surfaces by combining structural cues with probabilistic connectivity maps. The proposed method establishes a tradeoff between an even sampling of the cortical surfaces (a low surface entropy) and the similarity of corresponding points across the population (a low ensemble entropy). The similarity metric, however, isn't constrained to be just spatial proximity, but uses local sulcal
more » ... th measurements as well as probabilistic connectivity maps, computed from DWI scans via a stochastic tractography algorithm, to enhance the correspondence definition. We propose a novel method for projecting this fiber connectivity information on the cortical surface, using a surface evolution technique. Our cortical correspondence method does not require a spherical parameterization. Experimental results are presented, showing improved correspondence quality demonstrated by a cortical thickness analysis, as compared to correspondence methods using spatial metrics as the sole correspondence criterion.
doi:10.1007/978-3-642-02498-6_54 fatcat:r6gtumncp5gtjmsqhd5byqn4ne

Multiple Sclerosis Lesion Segmentation Using Joint Label Fusion [chapter]

Mengjin Dong, Ipek Oguz, Nagesh Subbana, Peter Calabresi, Russell T. Shinohara, Paul Yushkevich
2017 Lecture Notes in Computer Science  
This paper adapts the joint label fusion (JLF) multi-atlas image segmentation algorithm to the problem of multiple sclerosis (MS) lesion segmentation in multi-modal MRI. Conventionally, JLF requires a set of atlas images to be co-registered to the target image using deformable registration. However, given the variable spatial distribution of lesions in the brain, whole-brain deformable registration is unlikely to line up lesions between atlases and the target image. As a solution, we propose to
more » ... first pre-segment the target image using an intensity regression based technique, yielding a set of "candidate" lesions. Each "candidate" lesion is then matched to a set of similar lesions in the atlas based on location and size; and deformable registration and JLF are applied at the level of the "candidate" lesion. The approach is evaluated on a dataset of 74 subjects with MS and shown to improve Dice similarity coefficient with reference manual segmentation by 12% over intensity regression technique.
doi:10.1007/978-3-319-67434-6_16 pmid:29707700 pmcid:PMC5918408 fatcat:zzgtvhx4rbg7xnd6x4r3hpgifa

Gabapentin, A GABA analogue, enhances cognitive performance in mice

Ipek Komsuoglu Celikyurt, Oguz Mutlu, Guner Ulak, Furuzan Yildiz Akar, Faruk Erden
2011 Neuroscience Letters  
doi:10.1016/j.neulet.2011.01.072 pmid:21296127 fatcat:ydy5bqo2hzar7oquazw34foyuu

DTIPrep: quality control of diffusion-weighted images

Ipek Oguz, Mahshid Farzinfar, Joy Matsui, Francois Budin, Zhexing Liu, Guido Gerig, Hans J. Johnson, Martin Styner
2014 Frontiers in Neuroinformatics  
Oguz et al.DTIPrep  ...  Connectivity studies (Boucharin et al. [2011] , Oguz et al. [2012a] , Hagmann et al. [2008] ) can further elucidate pathologies by analyzing the strength of connections between distant regions of the  ... 
doi:10.3389/fninf.2014.00004 pmid:24523693 pmcid:PMC3906573 fatcat:dlw2ombdsna77epabss2jhn5g4
« Previous Showing results 1 — 15 out of 1,082 results