|
|
The relationship between substantia nigra echogenicity and speech and voice disorders
Adamkovičová, Lenka ; Novotný, Kryštof (referee) ; Mekyska, Jiří (advisor)
Transcranial sonography is a quick, simple and noninvasive examination method that allows to capture the loss of Substantia nigra in the brain. This loss is associated with the development of Lewy body disorders, and a confirmed correlation between Substantia nigra loss and development of dementia with Lewy bodies would allow for more accurate diagnosis of the disease. This thesis aims to investigate the accuracy of automated classification of individuals using a machine learning model, both according to their diagnosis of early DLB and also according to the size of Substantia nigra loss based on TCS examination. Automated acoustic analysis was applied to calculate speech and language parameters, those were statistically processed and then used to train a machine learning model. In a comparison of two binary classification problems it was found, that the model stratified by the size of Substantia nigra loss achieved lower accuracy than the model stratified by a diagnosis to healthy controls and persons with early-stage dementia with Lewy bodies. In addition, no correlation between SN hyperechogenicity and severity of DLB was confirmed.
|
|
|
Acoustic analysis of emotionally affected sentences in patients with Parkinson's disease
Gavlasová, Radka ; Kováč, Daniel (referee) ; Mekyska, Jiří (advisor)
This thesis focuses on Parkinson's disease and its effect on emotional expression in speech. The aim was to conduct a literature search on acoustic emotional analysis of PD patients and to implement acoustic parameters to distinguish between healthy and diseased individuals. The database used contained recordings of 100 patients with PD and 52 healthy controls for various speech tasks. For this analysis, 7 emotionally coloured sentences and 11 acoustic parameters were selected and implemented in Python. From the statistical analysis, it was found that the most significant parameters include pauses in speech and intensity variability. The XGBoost algorithm with 10-fold stratified cross-validation was used for classification. A total of 10 models were implemented to analyze all tasks together and each task separately. Optimization was performed using randomized search. For the combination of all tasks, the significant parameter was the variability in intensity or speech rate. For the individual speech tasks, variability in intonation and formant areas was highly significant. The best model achieved a 63% success rate (BACC) and 85% sensitivity. The results suggest that emotional prosody affects classification, confirming previous findings and pointing to the need for further investigation in this area.
|
|
|
Automated segmentation of the diadochokinetic task for remote monitoring of hypokinetic dysarthria
Svojanovský, Jan ; Mekyska, Jiří (referee) ; Kováč, Daniel (advisor)
The study describes health problems associated with Parkinson’s disease, especially hypokinetic dysarthria. It also points out the subjective and objective methods used to determine the severity of the disease. One of these methods is a diadochokinetic (DDK) task based on rapid syllable repetition to test the functionality of the articulatory apparatus (e.g., tongue, lips, or vocal cords). Correct speech production can also be examined by a speech therapist in the 3F test, which scores the severity of disorders in different areas of speech production. Next, the approaches of other authors, also dealing with the automated search of syllables in the speech signal, are described. The thesis also discusses some features of human speech that are needed for training a machine learning model. These features were computed for each of the 30 ms segments of a DDK task. The main goal is the automated detection and classification of [Pa]-[Ta]-[Ka] syllables in the recordings. For this purpose, an algorithm using a logistic regression was applied. The resulting average accuracy of syllable detection in the recordings was 89.4 %, average sensitivity 59.0 % and average specificity 93.79 %. The identification of individual syllable types was successful with an average accuracy of 90.78 %, an average sensitivity of 59.0 % and an average specificity of 95.39 %. Considering that the predicted onset was not located directly on the manually annotated onset, but in its close vicinity (up to ±3 segments), the average detection sensitivity and average syllable type classification sensitivity were 96.9 % and 85.1 % respectively, with an average difference between manually annotated and automatically segmented syllable onsets of 10.35 ms. The average accuracy of classification of speakers into healthy and PN patients using logistic regression (with speech parameters obtained after automated segmentation) was only 43.92 %, sensitivity 70.0 % and specificity 30.61 % (threshold 70 %). Using linear regression, the clinical scores of the 3F test were predicted. For faciokinesis, the root mean square error (RMSE) was 2.764 after manual syllable annotation and 3.271 after automated segmentation. The RMSE values for phonetics were 3.657 (manual) and 0.753 (automated). The developed algorithm can detect syllables in DDK tasks with relative success, and thus it is possible to determine parameters quantifying speech disorders with low differences with manual segmentation. If the recordings of DDK tasks meet the conditions for computing all these parameters, the algorithm could be used to classify speakers into healthy subjects and PN patients, for whom it could additionally assess the severity of dysarthria.
|
|
|
Monitoring of long-term effects of repetitive transcranial magnetic stimulation on speech and voice in patients with Parkinson's disease
Kaplan, Václav ; Novotný, Kryštof (referee) ; Mekyska, Jiří (advisor)
An individual's response to dopaminergic therapy for Parkinson's Disease (PD), which often presents with hypokinetic dysarthria, varies in its effect on speech disorders. This study examines the long-term effects of alternative treatment using repetitive transcranial magnetic stimulation (rTMS) in PD patients. The aim is to conduct research into acoustic and statistical analyses employed in similar studies in the past, quantify treatment-induced changes using a set of parameters, and statistically evaluate the outcomes. Acoustic parameters describing phonation, articulation, and prosody (areas of speech production) are selected. A database of recordings from patients with mild PD is utilized, from which 18 patients are chosen, participating in one pre-treatment measurement and four post-treatment measurements. Patients are divided into active and sham (placebo) groups. Observable changes in several parameters, particularly in phonation, are noted after rTMS treatment. However, the statistical analysis of acoustic parameters also highlights a significant placebo effect, as good, and often comparable results are observed in the sham group as well.
|
|
|
Assessment of Parkinson’s Disease Based on Acoustic Analysis of Hypokinetic Dysarthria
Galáž, Zoltán ; Brezany, Peter (referee) ; Sklenář, Jaroslav (referee) ; Mekyska, Jiří (advisor)
Hypokinetická dysartrie (HD) je častým symptomem vyskytujícím se až u 90% pacientů trpících idiopatickou Parkinsonovou nemocí (PN), která výrazně přispívá k nepřirozenosti a nesrozumitelnosti řeči těchto pacientů. Hlavním cílem této disertační práce je prozkoumat možnosti použití kvantitativní paraklinické analýzy HD, s použitím parametrizace řeči, statistického zpracování a strojového učení, za účelem diagnózy a objektivního hodnocení PN. Tato práce dokazuje, že počítačová akustická analýza je schopná dostatečně popsat HD, speciálně tzv. dysprozodii, která se projevuje nedokonalou intonací a nepřirozeným tempem řeči. Navíc také dokazuje, že použití klinicky interpretovatelných akustických parametrů kvantifikujících různé aspekty HD, jako jsou fonace, artikulace a prozodie, může být použito k objektivnímu posouzení závažnosti motorických a nemotorických symptomů vyskytujících se u pacientů s PN. Dále tato práce prezentuje výzkum společných patofyziologických mechanizmů stojících za HD a zárazy v chůzi při PN. Nakonec tato práce dokazuje, že akustická analýza HD může být použita pro odhad progrese zárazů v chůzi v horizontu dvou let.
|
|
|
Detection of face parts in the thermographic spectrum
Šujan, Miroslav ; Smékal, Zdeněk (referee) ; Mekyska, Jiří (advisor)
Master´s thesis deals with current problems of face detection and its parts in the infrared thermographic spectrum. Most previously published literature deals with the detection in the visible spectrum, making the thermographic detection range an interesting alternative. The work deals with the processing of image signals, images and faces in thermographic spectrum, selected methods of face detection and its parts and also deals with practical system design for detecting facial parts in this spectrum and its subsequent testing.
|
|
|
Making OpenType fonts with free software
Bednár, Peter ; Mekyska, Jiří (referee) ; Rajmic, Pavel (advisor)
In thesis themes of typography and computer font of OpenType format is described in details. At the beginning attention is paid to historical development of typeface, where stress is laid mainly on development of Roman and white letter with their characteristics. Having presented basis of typography work is concentrated on topic of digital font with emphasis on possibilities of OpenType format. Further its characteristics and advantages were listed compared to another formats and it was evaluated as format appropriate also for creating font in education process. Letterspacing and kerning were mentioned between basic graphical modifications in creating fonts. In theoretical part of the thesis they were examined in available programs designed for creating font in OpenType format. Except free available means into summary were included also commercial types due to absence of more advanced instruments and functions with free available applications. In evaluation was found that the most convenient for education is Fontlab Fontographer commercial program, free Type lite and Fontforge indicated for Open-source platform. Practical part of the thesis is focused on two chosen programs for creating main font characteristics. The goal was to detect if it is possible to reach identical results when using both programs. Fontographer program enabled to use wide tool palette dedicated to vector graphic processing by means of Adobe Illustrator similar instrument. In the case of Type lite program there were rather less instruments, what is sufficient for elementary work and familiarization with creating of digital typeface. Freeware shortage is basic absence of kerning, spacing or hinting functions. Comparing program possibilities, it falls that freeware programs based on OS Windows with their functionality are sufficient only for entry level users. The best option within free available programs is Fontforge for OS Linux which supports mentioned typographic functions. Fontographer was recommended for teaching of basic characteristics of OpenType font format. Another goal of the thesis was creating of recommended work procedure for creating basic characteristics of OpenType font for students, that is enclosed at the end of the thesis.
|
|
|
Structural and functional connectivity assessment in patients with Parkinson's disease
Klobušiaková, Patrícia ; Keller, Jiří (referee) ; Mekyska, Jiří (advisor)
Early changes in visuospatial functions predict dementia in Parkinson’s disease (PD). The aim of this work is to assess both structural and functional connectivity of the fasciculus longitudinalis inferior (ILF), which is engaged in visuospatial processing, in PD patients in comparison to healthy controls, and to find associations between connectivity changes and cognitive performance in the patient groups with or without mild cognitive impairment (MCI). To achieve our goal we recruited PD patients with normal cognition (PD-NC, n = 23) and PD with MCI (PD-MCI, n = 21) as well as healthy controls (HC, n = 48). Bidirectional iterative parcellation was used to isolate ILF tracts and their respective endpoints (occipital lobe and anterior temporal lobe) in each subject. The endpoints then served as regions of interest for functional connectivity calculation. We found ILF microstructural connectivity impairment in PD-MCI group, as measured by mean diffusivity, fractional anisotropy and radial diffusivity. In addition, the functional connectivity of ILF tracts was decreased already in the PD-NC. Both structural and functional connectivity deterioration was associated with visuospatial dysfunction in PD-MCI. These changes could serve as potential markers of disease progression or treatment effects monitoring.
|
|
|
Image fusion in thermal spectrum
Petrásek, Daniel ; Dvořák, Pavel (referee) ; Mekyska, Jiří (advisor)
In this paper, there is mentioned necessary theory of image processing and fusion, which belongs to a group of the most used ways of image processing in the present. In the first part there is mentioned basic findings of image and electromagnetic spectrum. In the second part there is discussed some facts of infrared radiation, thermal cameras, then it is continued with elementary methods of image focus evaluation, segmentation and noise thresholding. In next part there is introduced scheme of image fusion system and basic idea of its implementation. In the end of this thesis there is described implemented system of image fusion, detailed description of reached results, thesis rating and few ideas of improving whole system.
|
|
|
Diagnosis and progress monitoring of Parkinson’s disease using dysgraphia analysis methods
Markovič, Michal ; Galáž, Zoltán (referee) ; Mekyska, Jiří (advisor)
Parkinson’s disease causes among other symptoms also writing disorder. Parkinson's dysgrafia is disease the writing of parkinsonics. The aim of the work is to show the importance of examinig the parametres of Parkinson's dysgrafia and to find writing parametres, which could distinguish healthy subjects from the pacient and also it could monitoring progress of pakinson's disease. Some of the parametrs showed marked differences and therefore could distinguish healthy people from those with Parkinson’s disease.
|
guest ::
RSS feed.