|
|
Atrial fibrillation localization for burden assessment
Martinásková, Klára ; Ředina, Richard (referee) ; Filipenská, Marina (advisor)
The diploma thesis deals with the problem of detection of atrial fibrillation from ECG recordings and localization of given fibrillation segments in signals with paroxysmal fibrillation. A research is done on atrial fibrillation, the origin of this pathology and methods of fibrillation detection from ECG recordings using deep learning. Subsequently, a convolutional neural network model with residual blocks is implemented in Python to classify short (3 s) segments of the ECG signal. Subsequently, the classification results are processed and the segments with paroxysmal fibrillation are localized in the signals with fibrillation. With the classification and localization, the burden assessment of fibrillation is further evaluated. The implemented classifier on the test set achieves an F1 score of 96,15 %. When the sections with fibrillation are localized by the algorithm, MAE of 0,95 s for detecting the beginnings and 1,29 s for detecting the ends with respect to the reference positions is achieved. The estimated patient's burden assessment is compared with the actual values and achieves MAE of 3 %
|
|
|
Registration of MR Images and Histological Sections
Martinásková, Klára ; Mézl, Martin (referee) ; Jiřík, Radovan (advisor)
This bachelor’s thesis deals with methods of multimodal image registration. The work is focused specifically on the registration of histological sections and MR images, which various studies examine because of improving oncological diagnostics. A substantial part of the work is devoted to theories of registration - types of registration, geometric transformations, criterial functions, interpolation and methods of optimization. There is also an overview of tools, which can be used for multimodal image registration. MR images and histological sections were provided from three different sources. The program for image registration was created in software MATLAB 2020a with a graphical user interface and it includes a converter for editing images before the registration began. In conclusion, the results of registration were analyzed.
|
|
|
Registration of MR Images and Histological Sections
Martinásková, Klára ; Mézl, Martin (referee) ; Jiřík, Radovan (advisor)
This bachelor’s thesis deals with methods of multimodal image registration. The work is focused specifically on the registration of histological sections and MR images, which various studies examine because of improving oncological diagnostics. A substantial part of the work is devoted to theories of registration - types of registration, geometric transformations, criterial functions, interpolation and methods of optimization. There is also an overview of tools, which can be used for multimodal image registration. MR images and histological sections were provided from three different sources. The program for image registration was created in software MATLAB 2020a with a graphical user interface and it includes a converter for editing images before the registration began. In conclusion, the results of registration were analyzed.
|
guest ::
