Marta Fidrich

University of Szeged · Department of Software Engineering

Background Heart rate variability (HRV) provides information about the activity of the autonomic nervous system. Because of the small amount of data collected, the importance of HRV has not yet been proven in clinical practice. To collect population-level data, smartphone applications leveraging photoplethysmography (PPG) and some medical knowledge...

Recording of fetal heart rate can be reassuring for the mother about the fetus’ wellbeing. Our smart phone application can detect, record and evaluate fetal heart rate at any time. This method is based on sound wave thus free from the effects of ultrasound, and can be used all day without harming the fetus. It does not require medical assistance an...

Our primary objective was to develop a mobile application for monitoring the changes of menstrual cycle for clinical treatment planning. Participating woman can use the application called “Infertility Handling”, which will be soon available from Google Play Store for general public. This Android-based application provides basic biological and physi...

In the field of telemedicine, one of the biggest challenge is to find the right solution corresponding to customers’ needs in terms of usability and business model. Though 259,000 mobile health apps are available worldwide, only a small portion accounts for the majority of the market. Half of the downloads come from less than 100 applications, 62%...

As a growing number of powerful devices join the Internet, a new world of smart devices is being formed. This new trend is due to the emergence of the Internet of Things (IoT) paradigm, which also has a significant impact on the global Internet traffic. There are also more and more cloud providers offering IoT-specific services, since cloud computi...

A method for segmenting organs on magnetic resonance (MR) images includes retrieving an MR image of a subject and generating a transformation matrix by segmenting bones on the MR image. An initial organ segmentation of the MR image is generated by registering a combined organ and bone atlas with the MR image using the transformation matrix. The MR...

A method for generating an image includes obtaining a first image and a second image of an object of interest, generating a joint histogram using the first and second images, transforming the information in the histogram from histogram space to image space using a look-up table, and generating a color image using the information output from the loo...

A method for segmenting bones on magnetic resonance (MR) images includes retrieving an MR image and performing an enhancement process on the MR image to generate a bone enhanced MR image. The bone enhanced MR image is then registered to a computer tomography (CT) based bone atlas. An MR image with bone segmentation is generated by segmenting the bo...

The goal of this study was to compare MR-based PET patient attenuation correction (AC) to CT-based AC in the head using clinical whole-body FDG-PET patient data obtained from a tri-modality PET/CT & MR setup. The MR-based AC utilizes an atlas-based approach, registering the patient's MR images to a CT-based atlas, producing `pseudoCT' images. Thirt...

The goal of this study was to compare MR-based PET patient attenuation correction (AC) to CT-based AC in the head using clinical whole-body FDG-PET patient data obtained from a tri-modality PET/CT & MR setup. The MR-based AC utilizes an atlas-based approach, registering the patient's MR images to a CT-based atlas, producing `pseudoCT' images. Thirt...

MR provides a more detailed image of soft tissues than CT, and is therefore more suitable for visualization of some tumors and critical organs. However, without well-established semi/fully automatic segmentation toolkits available to clinicians for pelvic region contouring, they typically manually contour several critical structures on a contiguous...

A system and process for analyzing multidimensional data characterizing a least a portion of a subject is described. An input module accepts at least one multidimensional dataset which is derived from any of several types of data sources. A registration module accepts the dataset from the input module and registers the dataset from the input module...

Purpose/Objective(s): Currently, nearly all radiation therapy plans for prostate cancer are constructed using CT images. While CT provides definitive density information for attenuation correction and positioning verification, there is considerable interest in planning with MRI due to its soft tissue contrast. Density information may be estimated f...

This paper presents a comparison study between 10 automatic and six interactive methods for liver segmentation from contrast-enhanced CT images. It is based on results from the "MICCAI 2007 Grand Challenge" workshop, where 16 teams evaluated their algorithms on a common database. A collection of 20 clinical images with reference segmentations was p...

Segmentation of contrast-enhanced abdominal CT images is required by many clinical applications of computer aided diagnosis and therapy planning. The research on automated methods involves different organs among which the liver is the most emphasized. In the current clinical practice more images (at different phases) are acquired from the region of...

Segmentation of organs of sight such as the eyeballs, lenses, and optic nerves is a time consuming task for clinicians. The small size of the organs and the similar density of the surrounding tissues make the segmentation difficult. We developed a new algorithm to segment these organs with minimal user interaction. The algorithm needs only three se...

In radiation treatment (RT) planning, clinicians must trace the outline of a few critical structures on a large number of 2D images slices. Using automated or interactive image segmentation could save tremendous time and effort. Segmentation of the pelvic organs (e.g., prostate and bladder) from Computed Tomography (CT) images is an important and c...

Our objective is to provide a toolkit for 3D semi-automatic segmentation, which contains 3D shapebased interpolation, 3D edit and shape adaptation tools. 3D interpolation method is to speed up manual tracing of 3D image structures or objects. Fully automatic segmentation methods usually do not give perfect results. There are cases, when the segment...

The need for fast and precise segmentation has increased recently due to the spread of systems for computer aided diagnosis and therapy planning. The manual segmentation of the liver is very time con-suming, so it is desired to develop a method that can precisely segment the liver without any human interaction. In this paper we propose a fully auto...

The clinicians often need to segment the abdominal organs for radiotherapy planning. Manual segmentation of these organs is very time-consuming, therefore automated methods are desired. We developed a semi-automatic segmentation method to outline liver, spleen and kidneys. It works on CT images without contrast intake that are acquired with a routi...

We present two approaches for automatically segmenting the spinal cord/canal from native CT images of the thorax region contain-ing the spine. Different strategies are included to handle images where only part of the spinal column is visible. The algorithms require one seed point given on a slice located in the middle region of the spine, and the r...

Tomorrow’s competitive advantage of a technology-oriented company mainly comes from knowledge management and innovation. The focus shifts from problem solving to opportunity-identification. The key question is how the innovation process can be made to function for business success. We are not at loss for new ideas, but rather the organization and i...

During our tests to improve pre-raditotherapy planning we had to cope with several CT studies from all around the world. These CT scans made almost impossible to use one image quality evaluation scale, because of the so different imaging protocols used by the various institutes and doctors who sent us these examinations. An overview of these studie...

Prior to three dimensional radiotherapy the segmentation of the tumor volume and the organs which have to be avoided because of the risk of irradiation injury is required. This is done manually by the radiotherapists at our institution. The aim of our study was to find a way to ease their job. We used several pelvis CT studies from various institut...

The wired line network has been well studied and widely used for a long time. Most of its protocols are so successful that passed the test of time. There are many similar tasks in mobile and wired line environment, and we would like to achieve compatible, inter-working solutions. So it is a plausible idea to use the protocols of the wired line netw...

The aim of this paper is to present the design, specification, implementation and testing of a demonstration environment for examining a genuinely new communication technique. This technique ensures that 3G mobile networks can communicate with legacy Internet phones. More than one levels of the TCP/IP protocol family are necessary for the communica...

Accurate and robust correspondence calculations are very important in many medical and biological applications. Often, the correspondence calculation forms part of a rigid registration algorithm, but accurate correspondences are especially important for elastic registration algorithms and for quantifying changes over time. In this paper, a new corr...

The aim of this paper is to examine several transition mechanisms needed to change the Internet Protocol from version 4 to 6. First, methods of inter-operation between IPv4 and IPv6 hosts are summarized. The ones that will be compared -- configured tunneling, 6to4, SIIT -- are more detailed. After that, features chosen to be tested as well as thei...

The ability to accurately register images of patients taken at different times is very important in many medical applications. In most cases, the main reason for registration is to measure changes, and therefore any automatic registration algorithm employed for this task must be able to cope when there are significant differences in the images. In...

this paper we will compare two methods for analysing growth of faces. We will concentrate on on the shape and size of the profile of the face. The two methods differ in the way that the individual profiles are registered. In the first method Generalised Procrustes Analysis is used to register the profiles. This technique can cause some errors due t...

We examine the changes in the profile of the human face with age. First the medial plane running down the middle of the face is found using a variant of the Iterative Closest Point Algorithm, optimising over the set of reflections. The boundary of the silhouette as viewed from the side is extracted. Landmarks are found using bitangent lines and ext...

To provide a good basis for the registration of medical images we search for reliable feature points using a scale-space approach. Our main concern is with 2D images: we analyze corner points, defined by differential invariants, at increasing scales. The number and position of corner points change in the scale-extended space, which define moving pa...

A method is presented to extract space curves, defined by differential invariants, at increasing scales. The curves are considered as the intersection of two iso-surfaces in 3D, so their moving paths or orbits can be explicitly obtained in scale space as the intersection of two iso-surfaces in 4D. This method is based on a novel algorithm to search...

We present an algorithm to extract space curves, defined by differential invariants, at increasing scales. The algorithm uses an extension of the 3D Marching Lines that allows us to search for iso-surfaces and their intersections in spaces of arbitrary dimension. Specifically, we have implemented a 4D extension that we apply to track lines efficien...

A method is presented to extract space curves, defined by differential invariants, at increasing scales. The curves are considered as the intersection of two iso-surfaces in 3D, so their moving paths or orbits can be explicitly obtained in scale space as the intersection of two isosurface in 4D. This method is based on a novel algorithm to search f...

Two facial models corresponding to two deceased subjects have been manually created and the two corresponding skulls have been dissected and skeletonized. These pairs of skull/ facial data have been scanned with a CT scanner, and the computed geometric three-dimensional models of both skulls and facial tissue have been built. One set of skull/facia...

We present an algorithm to extract space curves, defined by differential invariants, at increasing scales. The algorithm uses an extension of the 3D Marching Lines that allows us to search for iso-surfaces and their intersections in spaces of arbitrary dimension. Specifically, we have implemented a 4D extension that we apply to track lines efficien...

To provide a basis for the registration of medical images we search for reliable feature points using a scale-space approach. The features are defined by differential invariants at increasing scales and their extraction is based on iso-surface techniques. We investigate some topological changes of orbits which can be observed as a result of image t...

We address here the problem of multiscale extraction and representation of characteristic points based on iso-surface techniques. Our main concern is with 2D images: we analyze corner points at increasing scales using the Marching Lines algorithm. Since we can exploit the intrinsic nature of intensity of medical images, segmentation of components o...

We present a fast and reliable algorithm, based on iso-surface techniques, to extract differential invariant features at increasing scales. We show that it automatically finds the connection order of singularities, hence it is easy to follow features across scales. As an example, we visualize the orbits of corner points, and compare some criterions...

To provide a good basis for the registration of medical images we search for reliablefeature points using a scale-space approach. Our main concern is with 2D images:we analyze corner points, defined by differential invariants, at increasing scales. Thenumber and position of corner points change in the scale-extended space, which definemoving paths...

We present a method for extracting iso-surfaces and their intersections in 4D. Our work is a significant extension of the 3D Marching Lines algorithm with new orientation and implementation considerations. As a practical tool, it can be applied to track efficiently space curves, defined by differential invariants, across increasing scale.

We present a fast and reliable algorithm, based on iso-surface techniques, to extract differential invariant features at increasing scales. We show that it automatically finds the connection order of singularities, hence it is easy to follow features across scales. As an example, we visualize the orbits of corner points, and compare some criterions...

We address here the problem of multiscale extraction and representation of characteristic points based on iso-surface techniques. Our main concern is with 2D images: we analyze corner points at increasing scales using the Marching Lines algorithm. Since we can exploit the intrinsic nature of intensity of medical images, segmentation of components o...

For automatic registration of medical images, we must search for geometric features that are invariant both with respect to rigid transformations and to smooth changes of resolution. Beginning with Witkin's seminal paper, scale space theory provides an elegant framework for studying the multiscale behavior of these characteristics. However, a natur...