Jan Kybic

Jan Kybic
Czech Technical University in Prague | ČVUT · Department of Cybernetics and Robotics

About

143
Publications
33,176
Reads
How we measure 'reads'
A 'read' is counted each time someone views a publication summary (such as the title, abstract, and list of authors), clicks on a figure, or views or downloads the full-text. Learn more
3,560
Citations

Publications

Publications (143)
Chapter
We address the task of detecting cancer in histological slide images based on training with weak, slide- and patch-level annotations, which are considerably easier to obtain than pixel-level annotations. we use CNN based patch-level descriptors and formulate the image classification task as a generalized multiple instance learning (MIL) problem. Th...
Article
Automatic Non-rigid Histological Image Registration (ANHIR) challenge was organized to compare the performance of image registration algorithms on several kinds of microscopy histology images in a fair and independent manner. We have assembled 8 datasets, containing 355 images with 18 different stains, resulting in 481 image pairs to be registered....
Presentation
Full-text available
In digital pathology, it is often useful to align spatially close but differently stained tissue sections in order to obtain the combined information. The images are large, in general, their appearance and their local structure are different, and they are related through a nonlinear transformation. The proposed challenge focuses on comparing the ac...
Poster
Full-text available
Image registration is a common task for many biomedical analysis applications. The present work focuses on the benchmarking of registration methods on differently stained histological slides. This is a challenging task due to the differences in the appearance model, the repetitive texture of the details and the large image size, between other issue...
Conference Paper
Full-text available
Image registration is a common task for many biomedical analysis applications. The present work focuses on the benchmarking of registration methods on differently stained histological slides. This is a challenging task due to the differences in the appearance model, the repetitive texture of the details and the large image size, between other issue...
Conference Paper
We address the problem of image registration when speed is more important than accuracy. We present a series of simplification and approximations applicable to almost any pixel-based image similarity criterion. We first sample the image at a set of sparse keypoints in a direction normal to image edges and then create a piecewise linear convex appro...
Article
Full-text available
The present paper deals with the problem of volume estimation of individual objects from a single 2D view. Our main application is volume estimation of pancreatic (Langerhans) islets and the single 2D view constraint comes from the time and equipment limitations of the standard clinical procedure. Two main approaches are followed in this paper. Fir...
Article
Image segmentation is widely used as an initial phase of many image analysis tasks. It is often advantageous to first group pixels into compact, edge-respecting superpixels, because these reduce the size of the segmentation problem and thus the segmentation time by an order of magnitudes. In addition, features calculated from superpixel regions are...
Conference Paper
Full-text available
Drosophila melanogaster is a well-known model organism that can be used for studying oogenesis (egg chamber development) including gene expression patterns. Standard analysis methods require manual segmentation of individual egg chambers, which is a difficult and time-consuming task. We present an image processing pipeline to detect and localize Dr...
Poster
Full-text available
Drosophila melanogaster is a well-known model organism that can be used for studying oogenesis (egg chamber development) including gene expression patterns. Standard analysis methods require manual segmentation of individual egg chambers, which is a difficult and time-consuming task. We present an image processing pipeline to detect and localize Dr...
Article
In recent years, computed tomography (CT) has become a standard technique in cardiac imaging because it provides detailed information that may facilitate the diagnosis of the conditions that interfere with correct heart function. However, CT-based cardiac diagnosis requires manual segmentation of heart cavities, which is a difficult and time-consum...
Conference Paper
This paper concerns the comparison of automatic volume estimation methods for isolated pancreatic islets. The estimated islet volumes are needed during the process of assessing the islet sample quality prior to the islet transplantation. We study several different methods for automatic volume estimation. For this purpose we acquired a set of projec...
Article
We present an efficient matching method for generalized geometric graphs. Such graphs consist of vertices in space connected by curves and can represent many real world structures such as road networks in remote sensing, or vessel networks in medical imaging. Graph matching can be used for very fast and possibly multimodal registration of images of...
Conference Paper
Full-text available
During the last decade leukemia and lymphomas have been a hot topic in the biomedical area. Their diagnosis is a time-consuming task that, in many cases, delays treatments. On the other hand, discrete orthogonal moments (DOMs) are a tool recently introduced in biomedical image analysis. Here, we propose a combination of DOMs to help in the diagnosi...
Conference Paper
Full-text available
We present an image processing pipeline which accepts a large number of images, containing spatial expression information for thousands of genes in Drosophila imaginal discs. We assume that the gene activations are binary and can be expressed as a union of a small set of non-overlapping spatial patterns, yielding a compact representation of the spa...
Article
Full-text available
Clinical islet transplantation programs rely on the capacities of individual centers to quantify isolated islets. Current computer-assisted methods require input from human operators. Here we describe two machine learning algorithms for islet quantification: the trainable islet algorithm (TIA) and the nontrainable purity algorithm (NPA). These algo...
Conference Paper
Periodic variations in patterns within a group of pixels provide important information about the surface of interest and can be used to identify objects or regions. Hence, a proper analysis can be applied to extract particular features according to some specific image properties. Recently, texture analysis using orthogonal polynomials has gained at...
Poster
Full-text available
Periodic variations in patterns within a group of pixels provide important information about the surface of interest and can be used to identify objects or regions. Hence, a proper analysis can be applied to extract particular features according to some specific image properties. Recently, texture analysis using orthogonal polynomials has gained at...
Conference Paper
In this contribution we study different methods of automatic volume estimation for pancreatic islets which can be used in the quality control step prior to the islet transplantation. The total islet volume is an important criterion in the quality control. Also, the individual islet volume distribution is interesting — it has been indicated that sma...
Conference Paper
This paper deals with separation of merged Langerhans islets in segmentations in order to evaluate correct histogram of islet diameters. A distribution of islet diameters is useful for determining the feasibility of islet transplantation in diabetes. First, the merged islets at training segmentations are manually separated by medical experts. Based...
Article
This paper presents a fully-automated method for the identification of bone marrow infiltration in femurs in low-dose CT of patients with multiple myeloma. We automatically find the femurs and the bone marrow within them. In the next step, we create a probabilistic, spatially-dependent density model of normal tissue. At test time, we detect unexpec...
Conference Paper
Full-text available
Chronic obstructive pulmonary disease is a non-reversible disorder characterized primarily by a dominant emphysema or bronchitis. Since early treatments can help to control the symptoms, the quantification of emphysema has become an important topic. Here, we introduce a novel procedure to quantify emphysematous lesions using an ensemble of features...
Conference Paper
Colorectal cancer is a major cause of mortality. As the disease progresses , adenomas and their surrounding tissue are modified. Therefore, a large number of samples from the epithelial cell layer and stroma must be collected and analyzed manually to estimate the potential evolution and stage of the disease. In this study, we propose a novel method...
Poster
Full-text available
Studies concerning gene expression patterns of Drosophila are of paramount importance in basic biological research because many genes are conserved across organisms providing information of fundamental activity. However, mapping a gene requires analyzing hundreds of objects that have been segmented previously. Hence, a reliable segmentation is a cr...
Conference Paper
This paper deals with color normalization of microscopy images of Langerhans islets in order to increase robustness of the islet segmentation to illumination changes. The main application is automatic quantitative evaluation of the islet parameters, useful for determining the feasibility of islet transplantation in diabetes. First, background illum...
Conference Paper
Full-text available
Studies concerning gene expression patterns of Drosophila are of paramount importance in basic biological research because many genes are conserved across organisms providing information of fundamental activity. However, mapping a gene requires analyzing hundreds of objects that have been segmented previously. Hence, a reliable segmentation is a cr...
Conference Paper
Full-text available
It is known that image registration is mostly driven by image edges. We have taken this idea to the extreme. In segmented images, we ignore the interior of the components and focus on their boundaries only. Furthermore, by assuming spatial compactness of the components, the similarity criterion can be approximated by sampling only a small number of...
Article
Full-text available
We present a new approach for matching sets of branching curvilinear structures that form graphs embedded in ${mathbb {R}}^2$ or ${mathbb {R}}^3$ and may be subject to deformations. Unlike earlier methods, ours does not rely on local appearance similarity nor does require a good initial alignment. Furthermore, it can cope with non-linear deformatio...
Conference Paper
Graph and tree-like structures such as blood vessels and neuronal networks are abundant in medical imaging. We present a method to calculate path descriptors in geometrical graphs, so that the similarity between paths in the graphs can be determined efficiently. We show experimentally that our descriptors are more discriminative than existing alter...
Conference Paper
Full-text available
We propose an approach to reconstructing tree structures that evolve over time in 2D images and 3D image stacks such as neuronal axons or plant branches. Instead of reconstructing structures in each image independently, we do so for all images simultaneously to take advantage of temporal-consistency constraints. We show that this problem can be for...
Conference Paper
Full-text available
We describe an automatic method for fast registration of images with very different appearances. The images are jointly segmented into a small number of classes, the segmented images are registered, and the process is repeated. The segmentation calculates feature vectors on superpixels and then it finds a softmax classifier maximizing mu-tual infor...
Conference Paper
We register images based on their multiclass segmentations, for cases when correspondence of local features cannot be established. A discrete mutual information is used as a similarity criterion. It is evaluated at a sparse set of location on the interfaces between classes. A thin-plate spline regularization is approximated by pairwise interactions...
Conference Paper
Evaluation of images of Langerhans islets is a crucial procedure for planning an islet transplantation, which is a promising diabetes treatment. This paper deals with segmentation of microscopy images of Langerhans islets and evaluation of islet parameters such as area, diameter, or volume (IE). For all the available images, the ground truth and th...
Conference Paper
Full-text available
We present an algorithm to segment a set of parallel, intertwined and bifurcating fibers from 3D images, targeted for the identification of neuronal fibers in very large sets of 3D confocal microscopy images. The method consists of preprocessing, local calculation of fiber probabilities, seed detection, tracking by particle filtering, global superv...
Conference Paper
Full-text available
This paper presents the implementation and particular improvements on the superpixel clustering algorithm -SLIC (Simple Linear Iterative Clustering). The main contribution of the jSLIC is a significant speed-up of the original clustering method, transforming the compact-ness parameter such that the value is image independent, and a new post-process...
Poster
Full-text available
This paper presents the implementation and particular improvements on the superpixel clustering algorithm - SLIC (Simple Linear Iterative Clustering). The main contribution of the jSLIC is a significant speed-up of the original clustering method, transforming the compactness parameter such that the value is image independent, and a new post-process...
Article
Abstract We present a method for automatic surgical tool localization in 3D ultrasound images based on line filtering, voxel classification and model fitting. This could possibly provide assistance for biopsy needle or micro-electrode insertion, or a robotic system performing this insertion. The line-filtering method is first used to enhance the co...
Article
Accurate detection of liver lesions is of great importance in hepatic surgery planning. Recent studies have shown that the detection rate of liver lesions is significantly higher in gadoxetic acid-enhanced magnetic resonance imaging (Gd-EOB-DTPA-enhanced MRI) than in contrast-enhanced portal-phase computed tomography (CT); however, the latter remai...
Conference Paper
We present a general approach for solving the point-cloud matching problem for the case of mildly nonlinear transformations. Our method quickly finds a coarse approximation of the solution by exploring a reduced set of partial matches using an approach to which we refer to as Active Testing Search (ATS). We apply the method to registration of graph...
Conference Paper
Full-text available
The analysis of protein-level multigene expression signature maps computed from the fusion of differently stained immunohistochemistry images is an emerging tool in cancer management. Creating these maps requires registering sets of histological images, a challenging task due to their large size, the non-linear distortions existing between consecut...
Conference Paper
We present a new approach to matching graphs embedded in ℝ2 or ℝ3. Unlike earlier methods, our approach does not rely on the similarity of local appearance features, does not require an initial alignment, can handle partial matches, and can cope with non-linear deformations and topological differences. To handle arbitrary non-linear deformations, w...
Article
Information theoretic criteria such as mutual information are often used as similarity measures for inter-modality image registration. For better performance, it is useful to consider vector-valued pixel features. However, this leads to the task of estimating entropy in medium to high dimensional spaces, for which standard histogram entropy estimat...
Article
Full-text available
Deformable registration generally relies on the assumption that the sought spatial transformation is smooth. Yet, breathing motion involves sliding of the lung with respect to the chest wall, causing a discontinuity in the motion field, and the smoothness assumption can lead to poor matching accuracy. In response, alternative registration methods h...
Article
Full-text available
We present an algorithm for geometric matching of graphs embedded in 2D or 3D space. It is applicable for registering any graph-like structures appearing in biomedical images, such as blood vessels, pulmonary bronchi, nerve fibers, or dendritic arbors. Our approach does not rely on the similarity of local appearance features, so it is suitable for...
Conference Paper
Full-text available
In ultrasound (US), a natural competition exists between the resolution of the image and the depth-of-field (DOF) into the medium, competition which is difficult to overcome with current US probe. Using large bandwidth transducer, such as cMUT, and the possibility to transmit several frequencies in one single transmission, we propose a multi-freque...
Article
We address the problem of estimating the uncertainty of optical flow algorithm results. Our method estimates the error magnitude at all points in the image. It can be used as a confidence measure. It is based on bootstrap resampling, which is a computational statistical inference technique based on repeating the optical flow calculation several tim...
Article
Full-text available
Colposcopy is a well-established method to detect and diagnose intraepithelial lesions and uterine cervical cancer in early stages. During the exam color and texture changes are induced by the application of a contrast agent (e.g.3-5% acetic acid solution or iodine). Our aim is to densely quantify the change in the acetowhite decay level for a sequ...
Article
Full-text available
Four-dimensional computed tomography (4D CT) can provide patient-specific motion information for radiotherapy planning and delivery. Motion estimation in 4D CT is challenging due to the reduced image quality and the presence of artifacts. We aim to improve the robustness of deformable registration applied to respiratory-correlated imaging of the lu...
Conference Paper
Full-text available
To assist surgeons during their surgical operations, which involve a tool insertion, a real-time application which is able to localise the surgical tool during its movement is proposed. The position of the needle is estimated with a method based on model fitting using a Random Sample Consensus (RANSAC). Our proposed application has been implemented...
Article
Full-text available
Ultrasound guidance is used for many surgical interventions such as biopsy and electrode insertion. We present a method to localize a thin surgical tool such as a biopsy needle or a microelectrode in a 3-D ultrasound image. The proposed method starts with thresholding and model fitting using random sample consensus for robust localization of the ax...
Article
Full-text available
We present a novel algorithm for the registration of 2D image sequences that combines the principles of multiresolution B-spline-based elastic registration and those of bidirectional consistent registration. In our method, consecutive triples of images are iteratively registered to gradually extend the information through the set of images of the e...
Article
Full-text available
We describe an approximate algorithm to find all nearest neighbors (NN) for a set of points in moderate to high-dimensional spaces. Although the method is generally applicable, it is tailored to our main application, which is a NN-based entropy estimation for an image similarity criterion for image registration. Our algorithm is unique for having s...
Article
Full-text available
We address the problem of estimating the uncertainty of pixel based image registration algorithms, given just the two images to be registered, for cases when no ground truth data is available. Our novel method uses bootstrap resampling. It is very general, applicable to almost any registration method based on minimizing a pixel-based similarity cri...
Conference Paper
Full-text available
Fast level set methods replace continuous PDEs by a discrete formulation, improving the execution times. The regularization in fast level set methods was so far handled indirectly via level set function smoothing. We propose to incorporate standard curvature based regularization into fast level set methods and address the problem of efficiently est...
Conference Paper
Full-text available
We propose a robust method for localization of elongated surgical tools in 3D ultrasound data based on shape analysis. The tubular structures in input data are enhanced by a line filter in the pre-processing phase. A new model of a surgical tool appearance in 3D ultrasound image is proposed which exploits its tubular shape. The tool axis is estimat...
Conference Paper
Full-text available
Respiratory motion introduces uncertainties when planning and delivering radiotherapy for lung cancer patients. Cone-beam projections acquired in the treatment room could provide valuable information for building motion models, useful for gated treatment delivery or motion compensated reconstruction. We propose a method for estimating 3D+T respirat...
Article
Full-text available
The Lung Test Images from Motol Environment (Lung TIME) is a new publicly available dataset of thoracic CT scans with manually annotated pulmonary nodules. It is larger than other publicly available datasets. Pulmonary nodules are lesions in the lungs, which may indicate lung cancer. Their early detection significantly improves survival rate of pat...
Article
Full-text available
In surgical practice, small metallic instruments are frequently used to perform various tasks inside the human body. We address the problem of their accurate localization in the tissue. Recent experiments using medical ultrasound have shown that this modality is suitable for real-time visualization of anatomical structures as well as the position o...
Conference Paper
Full-text available
Mutual information is one of the most widespread similarity criteria for multi-modal image registration but is limited to low dimensional feature spaces when calculated using histogram and kernel based entropy estimators. In the present article we propose the use of the Kozachenko-Leonenko entropy estimator (KLE) to calculate higher order regional...
Conference Paper
Full-text available
We are developing a complex computer aided diagnosis (CAD) system to detect small pulmonary nodules from helical CT scans. Here we present a classifier to reduce the number of false positive responses of the primary detector. Our approach is based on an asymmetric Adaboost which enables us to give different weights to missed nodules (false negative...
Conference Paper
Full-text available
Image registration algorithms provide a displacement field between two images. We consider the problem of estimating accuracy of the calculated displacement field from the input images only and without assuming any specific model for the deformation. We compare two algorithms: the first is based on bootstrap resampling, the second, new method, uses...
Conference Paper
Full-text available
We address the problem of fast and accurate localization of miniature surgical instruments like needles or electrodes using 3D ultrasound (US). An algorithm based on maximizing a parallel integral transform (PIP) can automatically localize line-shaped objects in 3D US images with accuracy on the order of hundreds of micrometers. Here we propose to...
Article
Full-text available
Our task is to segment bones from 3D CT and MRI images. The main application is creation of 3D mesh models for finite element modeling. These surface and volume vector models can be used for further biomechanical processing and analysis. We selected a novel fast level set method [1] because of its high computational efficiency, while preserving all...
Article
Full-text available
In this paper, a 2-D locally regularized strain estimation method for imaging deformation of soft biological tissues from radio-frequency (RF) ultrasound (US) data is introduced. Contrary to most 2-D techniques that model the compression-induced local displacement as a 2-D shift, our algorithm also considers a local scaling factor in the axial dire...
Article
Full-text available
The Laplace-Cauchy problem of propagating Dirichlet and Neumann data from a portion to the rest of the boundary is an ill-posed inverse problem. Many regularizing algorithms have been recently proposed, in order to stabilize the solution with respect to noisy or incomplete data. Our main application is in electro-encephalography (EEG) where potenti...
Article
A new reconstruction method for parallel MRI called PROBER is proposed. The method PROBER works in an image domain similar to methods based on Sensitivity Encoding (SENSE). However, unlike SENSE, which first estimates the spatial sensitivity maps, PROBER approximates the reconstruction coefficients directly by B-splines. Also, B-spline coefficients...