Visualization of deep networks trained for bipolardisorder classification by using fnirs measurements

Download

12626150.pdf

Date

2021-2-03

Author

Oğuzhan, Babacan

Metadata

Show full item record

This work is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License.

Item Usage Stats

298
views

310
downloads

Deep learning applications have achieved impressive performances on many medi-cal problems such as classification of disorders, effects of a treatment or unspottedsymptoms of a disease, etc. While modern deep learning progress is impressive insuch areas, genuine understandings of its working principles are not clear. For thatmatter, the term black box has often been associated with deep learning algorithms.The majority of previous studies have concentrated on networks’ successes and havecomputed their performances in terms of accuracy levels. However, this thesis fo-cuses on disintegrating the internal working mechanisms of neural networks into in-tuitive and understandable components. It makes them easy to understand and tointerpret from medical experts’ perspectives. With this purpose in mind, pre-trainedConvolutional Neural Networks and Residual Neural Networks are utilized by usingtime-series neuroimaging data, i.e. Functional Near-Infrared Spectroscopy (fNIRS)measurements, belonging to two classes, namely healthy and bipolar, and their visu-alization outputs are attained. Since these outputs are complex time-series data, theyare analyzed by statistical methods such as chi-square and t-tests so that the intrinsicfeatures of healthy and bipolar subjects specific to their classes are obtained. Results are compared with previous medical studies and are analyzed so that potential reasonsbehind the classification results are provided. The contribution of this thesis is pro-viding an inference about visualization outcomes of different neural networks, whichare trained for the bipolar disorder classification using fNIRS data. Therefore, thisstudy tries to fill the void between medical researchers and deep learning experts.

Subject Keywords

fNIRS, Derin Öğrenme, Bipolar Bozukluk Hastalığı, Sınıflandırma, Görselleştirme, Sınıf Aktivasyon Haritası

URI

https://hdl.handle.net/11511/89581

Collections

Graduate School of Natural and Applied Sciences, Thesis

Suggestions

OpenMETU
Core

Deep learning for the classification of bipolar disorder using fNIRS measurements Evgin, Haluk Barkın; Ulusoy, İlkay; Department of Electrical and Electronics Engineering (2021-2-3) Functional Near-Infrared Spectroscopy (fNIRS) is a neural imaging method that is proved to be prominent in the classification of psychiatric disorders, and assertive accuracy results are being obtained using fNIRS. High temporal resolution, feasibility, and partial endurance to head movements are the traits that are highlighting fNIRS among other imaging methods. fNIRS data is a one dimensional multi-channeled time series. In this thesis, bipolar disorder is classified using some state of the art deep learn...
Simulation of Transmembrane Potential Propagation in Normal and Ischemic Tissue Using Aliev Panfilov Model Seyedebrahimi, Mehdi; Serinağaoğlu Doğrusöz, Yeşim (2016-11-05) Simulation of Transmembrane Potential Propagation in Normal and Ischemic Tissue Using Aliev Panfilov Model
Analysis of factors affecting baseline SF-36 Mental Component Summary in Adult Spinal Deformity and its impact on surgical outcomes Mmopelwa, Tiro; Ayhan, Selim; Yuksel, Selcen; Nabiyev, Vugar; Niyazi, Asli; Pellise, Ferran; Alanay, Ahmet; Sanchez Perez Grueso, Francisco Javier; Kleinstuck, Frank; Obeid, Ibrahim; Acaroglu, Emre (AVES Publishing Co., 2018-5) Objectives: To identify the factors that affect SF-36 mental component summary (MCS) in patients with adult spinal deformity (ASD) at the time of presentation, and to analyse the effect of SF-36 MCS on clinical outcomes in surgically treated patients. Methods: Prospectively collected data from a multicentric ASD database was analysed for baseline parameters. Then, the same database for surgically treated patients with a minimum of 1-year follow-up was analysed to see the effect of baseline SF-36 MCS on t...
Describing Morphological Changes of Corpus Callosum via Shape Grammar Based Approach Turgut, Umut Orcun; Gökçay, Didem (2015-10-18) Despite modern imaging technologies, problems are faced in quantitative brain morphology studies. Since the structural and functional organization of the human brain is complex, advanced methods are needed. Current methods are incapable of detecting complete shape anomalies. Moreover, the rapidly increasing volume of image data forces development of image analysis methodologies that can be processed fast and locally. All of these requirements create the need for an advanced shape analysis technique to chara...
Computational modeling of coupled cardiac electromechanics incorporating cardiac dysfunctions Berberoglu, Ezgi; Solmaz, H. Onur; Göktepe, Serdar (Elsevier BV, 2014-11-01) Computational models have huge potential to improve our understanding of the coupled biological, electrical, and mechanical underpinning mechanisms of cardiac function and diseases. This contribution is concerned with the computational modeling of different cardiac dysfunctions related to the excitation-contraction coupling in the heart. To this end, the coupled problem of cardiac electromechanics is formulated through the conservation of linear momentum equation and the excitation equation formulated in th...

Citation Formats

B. Oğuzhan, “Visualization of deep networks trained for bipolardisorder classification by using fnirs measurements,” M.S. - Master of Science, Middle East Technical University, 2021.