A5007576681- Medical Imaging and Analysis
- Medical Imaging Techniques and Applications
- Medical Image Segmentation Techniques
- Radiomics and Machine Learning in Medical Imaging
- Intracerebral and Subarachnoid Hemorrhage Research
- Brain Tumor Detection and Classification
- Image Processing Techniques and Applications
- Machine Learning in Healthcare
- Advanced X-ray and CT Imaging
- Digital Holography and Microscopy
- Dental Radiography and Imaging
- Spinal Fractures and Fixation Techniques
- Retinal Imaging and Analysis
- Advanced MRI Techniques and Applications
- Glaucoma and retinal disorders
- Anatomy and Medical Technology
- Advanced Neural Network Applications
- Genomics and Phylogenetic Studies
- Advanced Neuroimaging Techniques and Applications
- Management of metastatic bone disease
- AI in cancer detection
- Cell Image Analysis Techniques
- Optical measurement and interference techniques
- Pregnancy and preeclampsia studies
- Nanopore and Nanochannel Transport Studies
Brno University of Technology
2016-2025
Technical museum in Brno
2023
Zdravstveni centar
2023
Healthcare Technology Innovation Centre
2021
Indian Institute of Technology Madras
2021
Martin Jurka, Iva Macova, Monika Wagnerova, Otakar Capoun, Roman Jakubicek, Petr Ourednicek, Lukas Lambert, Andrea Burgetova
ABSTRACT This paper describes a compact video‐ophthalmoscope (VO) designed for capturing retinal video sequences of the optic nerve head (ONH) under flicker light stimulation. The device uses an OLED display and fiber optic‐coupled LED source, enabling high‐frame‐rate at low illumination intensity (12 μW/cm 2 ). Retinal responses were recorded in 10 healthy subjects during exposure with pupil irradiance . Following 20 s stimulation, all displayed changes reflectance pulsation attenuation,...
Intracranial hemorrhage is a life-threatening disease, which requires fast medical intervention.Owing to the duration of data annotation, head CT images are usually available only with slice-level labeling.However, information about exact position could be beneficial for radiologist.This paper presents fully automated weakly supervised method precise localization in axial slices using position-free labels.An algorithm based on multiple instance learning introduced that generates likelihood...
In this contribution, we present a fully automatic approach, that is based on two convolution neural networks (CNN) together with spine tracing algorithm utilizing population optimization algorithm. Based the evaluation of 130 CT scans including heavily distorted and complicated cases, it turned out new combination enables fast robust detection almost 90% correctly determined spinal centerlines computing time fewer than 20 seconds.
In this paper, a novel U-Net-based method for robust adherent cell segmentation quantitative phase microscopy image is designed and optimised. We evaluated four specific post-processing pipelines. To increase the transferability to different types, non-deep learning transfer with adjustable parameters used in step. Additionally, we proposed self-supervised pretraining technique using nonlabelled data, which trained reconstruct multiple distortions improved performance from 0.67 0.70 of...
The optimal rotational alignment of brain Computed Tomography (CT) images to a required standard position has crucial importance for both automatic and manual diagnostic analysis. In this contribution, we present novel two-step iterative approach the 3D CT data. angles axial coronal rotations are determined by an unsupervised localisation Midsagittal Plane (MSP) method. This includes detection pairing medially symmetrical feature points. sagittal rotation angle is subsequently estimated...
Two novel statistically based methods for bone lesion detection and classification are presented. Together with the previously published MRF method [15], they form a triad of mutually complementary that promise, when fused, to enable higher reliability assessment.
Recently, nanopore sequencing has come to the fore as library preparation is rapid and simple, can be done almost anywhere, longer reads are obtained than with next-generation sequencing. The main bottleneck still lies in data postprocessing which consists of basecalling, genome assembly, localizing significant sequences, time consuming computationally demanding, thus prolonging delivery crucial results for clinical practice. Here, we present a neural network-based method capable detecting...
Hintergrund Die nicht-invasive Messung von Netzhautgefäßen erlaubt die frühzeitige Detektion Veränderungen der Mikrovaskulatur, was wiederum als prädiktiver Biomarker für spätere Herz-Kreislauf-Erkrankungen (CVD) verwendet werden kann. Mittels Adaptiver Optik (AO, rtx1e, Imagine Eyes, Orsay, Frankreich) lassen sich nicht-invasive, hochauflösende in-vivo-Messung Mikrovaskulatur durchführen. Derzeit liegen keine Daten zur Veränderung im physiologischen Schwangerschaftsverlauf vor.
Hintergrund Die nicht-invasive Messung von Netzhautgefäßen erlaubt die frühzeitige Detektion Veränderungen der Mikrovaskulatur, was wiederum als prädiktiver Biomarker für spätere Herz-Kreislauf-Erkrankungen (CVD) verwendet werden kann. Mittels Adaptiver Optik (AO) (rtx1e, Imagine Eyes, Orsay, Frankreich) lassen sich nicht-invasive, hochauflösende in-vivo-Messung Mikrovaskulatur durchführen. Derzeit liegen keine Daten zur Veränderung im physiologischen Schwangerschaftsverlauf vor.
The high amount of data obtained from a single 3D whole heart multiparametric scan (up to ~40 slices per parametric map) increases considerably the time required segment and analyse quantitative maps. Thus, an automated segmentation tool for these maps is desirable perform this otherwise prohibitively laborious task. In work, we leverage potential nnU-Net fast, whole-heart simultaneous T1 T2 show its feasibility predict masks with comparable quality while shortening analysis by ~100x.