|
|
Object Detection Networks For Localization And Classification Of Intracranial Hemorrhages
Nemcek, Jakub
Intracranial hemorrhages represent life-threatening brain injuries. This paper presents twostate-of-the-art object detection systems (Faster R-CNN and YOLO v2) which are trained to localizeand classify hemorrhages in axial head CT slices by providing labelled rectangular bounding boxes.Publicly available datasets of head CT data and ground truth bounding boxes are used to evaluate andcompare the performance of both detectors. The Faster R-CNN shows better results by achieving anaverage Jaccard coefficient of 58.7 %.
|
|
|
Detection Of Intracranial Haemorrhages In Head Ct Data Based On Deep Learning
Nemček, Jakub
In this paper, we present a method for detection of intracranial haemorrhages in the head CT data using convolutional neural networks. We introduce three 2D image classifiers that perform in three perpendicular anatomical planes and classify the CT slices into healthy or pathological, whereby they provide the information about the position of the haemorrhage in the 3D CT image. The accuracies of the three models are 90.19%, 88.15%, and 80.90% for the axial, sagittal and coronal plane.
|
|
|
Image segmentation of spinal disc in medical imaging
Meloun, Jan ; Nemček, Jakub (referee) ; Mézl, Martin (advisor)
The thesis is focused on the segmentation of the intervertebral disc in the image data.The introduction deals with the issue of the spine, the herniation of the intervertebraldisc. It also deals with imaging modalities, especially computed tomography and mag-netic resonance imaging. The practical part describes the image data segmentation andthe implementation of three of the published segmentation methods.
|
|
|
Detection of intracranial hemorrhages in head CT data
Nemček, Jakub ; Jan, Jiří (referee) ; Jakubíček, Roman (advisor)
This thesis deals with the detection of intracranial haemorrhages and their type classification in head CT images. The method of haemorrhages detection is based on a series of classifiers of the presence and type of haemorrhages in 2D CT slices in axial, sagittal and coronal plane, that may localise the bleedings and determine their types. The classifiers are based on the convolutional neural network architecture Inception-ResNet-v2. The head CT dataset CQ500 which is made available for public access, is used for the experiments. The thesis describes an additional manual annotation of the data, as the available annotations are insufficient for the purposes of the experiments. This thesis includes a theoretical basis of the essential medical knowledge, machine learning based classification and detection methods, and the detection algorithm proposal, realisation and testing. The algorithm performance is evaluated and discussed together with the potential implementation of the algorithm in computer-aided diagnosis systems.
|
|
|
Detection and segmentation of lumbar vertebrae in 3D CT data
Nemček, Jakub ; Kolář, Radim (referee) ; Jakubíček, Roman (advisor)
This thesis deals with the detection and the segmentation of lumbar vertebrae in CT image datas. The described detection method is based on the use of a trained SVM classificator and histograms of oriented gradients as the image features. The detection method is applied on two-dimensional sagital slices of the CT image. The segmentation method is implemented as triangular mesh model deformation of models, that are obtained from averaged vertebrae in real CT datas. The first part of the thesis describes essential theoretical knowledge about the anatomy of the axial skeleton, computer tomography, image processing methods and about the detection and segmentation issues. The second part contains the algorithms realisation description, the evaluation and the discussion of the results. Applications of the algorithms in CAD systems is described at the end. The application of all of the points is done in the programming software Matlab.
|
|
|
Designing an automated workplace for charge and high-impedance measurement
Nemček, Jakub ; Bartušek, Karel (referee) ; Gescheidtová, Eva (advisor)
This barchelor thesis is about Desig an automated workplace forchargeable and high-impedant measurements. This automated workplace is realized by tubular aspiration capacitor, which is connected via differential converter U/I to data acquisition switch unit HP 34970A. The data acquisition switch unit HP 34970A is also connected by serial line RS-232 to Computer (PC), on which the directed program Agilent VEE Pro 7.0 is installed. To the right connection data acquisition switch unit HP 34970A and PC is necessary to set the same parameters on data acquisition switch unit HP 34970A, such in I/O config and also in Instrument manager too. In Instrument manager is requisite to set Plug und Play driver for data acquisition switch unit HP 34970A. The programing in Agilent VEE Pro 7.0 is based on object oriented programming. To start the program press the button “START“ and automatic measuring of concentration air ionts, will start the process (the trend is marked to the graph). The program is indicated if the ventilator blows an air in the aspiration capacitor and draws the trend of voltage on this ventilator to the graph. To stop the program press the buton “STOP“. Measured data are exported to program Excel. For the export Excel has to be running before the process. The function is verifing by measuring of background negativ a positiv ionts, by influence of position the source of ionts behind the aspiration capacitor and by influence of materials (metal plate, paper carton, wood, conductive paint) to the concentration of negativ ionts.
|
guest ::
RSS feed.