Assoc. Prof. Yeşim Aydın Son will give a seminar on “Multi-step RF Modeling and Ensemble Approach for prioritization of risk SNVs Early and Differential Diagnosis of Late-Onset Alzheimer’s Disease (LOAD)” on 25 October at 13:40. The abstract of the talk and a short bio is shared below.

Bio:
Assoc. Prof. Yeşim Aydın Son is a medical scientist holding an M.D. and a Ph.D. in Genome Sciences and Technologies. She is a full-time faculty member and head of the Health Informatics Department in the Graduate School of Informatics, METU. Her research focus is the modeling of chronic and complex diseases, such as cancer and neurodegenerative diseases, based on integrated genomic and clinical data. Dr. Aydın Son integrates genome sciences and biomedical informatics interpreting high throughput molecular data through computational techniques and contributes to personalized medicine using data mining techniques, systems biology approaches, and molecular interactions.

Abstract:
LOAD is the most common type of dementia in the aging population, whose diagnosis is limited by clinical scales with high inter-application variability, costly imaging methods, and interventional tests. LOAD has a complex genetic etiology and the molecular mechanisms involved are still unclear. GWAS examines the statistical interactions of variants of individuals by univariate analysis. Machine learning algorithms can capture hidden, novel, and significant patterns by considering nonlinear interactions where multiple variants determine the risk. The optimized LOAD-RF-RF models were created with 74.0, 72.1%, and 85.1% accuracy rates for ADNI, NCRAD, and GenADA datasets, and LOAD-RF-RF models identified a total of 719 variants as highly associated with LOAD. For the meta-analysis, an ensemble scoring algorithm was developed that prioritizes consecutive, common genomic-located variants in three predictive models at gene and LD levels. The protein-coding variants prioritized were selected for experimental validation based on their relationship with LOAD-related biological pathways after network, PPI, and enrichment analysis. For a total of 32 variants, pyrosequencing primers are designed and optimized. Model performance analysis is done with a case-control group of 43 LOAD diagnosed and 38 healthy participants, where 12 variants classified the LOAD risk with 79% precision and 7 protective variants presented a classification performance with 76% precision. A total of 26 variants were also found to be distinctive in the European non-Finnish (NFE) population. (Founding: TUBİTAK 1003 216S468)

Beste Altınay will give a seminar on “MFDM: MRI Free Decision Model for Diagnosis and Treatment Selection in Patients with Low Back and Neck Pain” on 31 May at 12:45. The abstract of the talk and a short bio is shared below.

Bio:
Beste Mimaroğlu Altınay is currently a PhD Candidate at the Department of Medical Informatics, Middle East Technical University. She received her B.S. degree in Computer Engineering from Başkent University. She worked as a software specialist in the field of Hospital Information Management Systems. Afterwards, she worked as a research assistant in the Department of Management Information Systems at Cumhuriyet University and has been working as an IT Software Manager at Social Sciences University of Ankara since 2013.

Abstract:
Low back pain (LBP) and neck pain (NP) is a worldwide public health problem that affects life quality. Our goal was to develop a machine learning model that can direct LBP and NP patients for the appropriate treatment without magnetic resonance imaging (MRI) findings, thus reducing the demand for MRI and its burden on the health system. To evaluate the treatment outcomes, demographic information, clinical findings, and preoperative evaluation of pain, movement restriction, and pain data duration are analyzed from patient data in the pain clinic. Support Vector Machine (SVM) models are built by analyzing ten different attributes from 1482 patient data to classify correct treatment: drug, RF/IDET, or surgical intervention. The stepwise model proposed here classifies drug therapy patients with an 84% success ratio and can direct patients to surgery or RF/IDET with a 74.47% success ratio without MRI results. The proposed MRI Free Decision Model (MFDM) can be utilized in primary healthcare facilities to direct the patients to the appropriate treatment options without MRI, reducing the cost and load on the healthcare system while benefiting the patient by reducing the time to initiate the treatment.

Dr. Burçak Otlu will give a seminar on “Evaluating topography of mutational signatures using SigProfilerTopography” on 24 May at 12:45. The abstract of the talk and a short bio is shared below.

Bio:
Burçak Otlu is a computer scientist with several years of experience in computational biology. She has been working as a postdoctoral scholar in UC San Diego, Cellular and Molecular Medicine Department since March 2018. She is working on mutational signatures and topography of somatic mutations across the genome. She is an academic fellow at the Department of Health Informatics at Middle East Technical University. Formerly, she was a visiting scholar in UC San Diego, Computer Science, and Engineering Department between August 2017 and February 2018. She received her Ph.D. from Middle East Technical University, Computer Engineering Department where she focused on developing tools and techniques for assessing the functional relevance of genomic loci. Prior to coming to UC San Diego, she has worked as a teaching assistant in the same department for several years. Previously, she has also worked in the private sector as a software engineer.

Abstract:
Mutations are found on the genomes of all cancerous and normal somatic cells. These mutations were generated by the activities of endogenous and exogenous mutational processes which were operative throughout the cell lineage. Mutational processes imprint characteristic patterns of somatic mutations, termed, mutational signatures. To exemplify, mutational signature associated with tobacco smoking causes C>A mutations prominently on the transcribed strand, whereas mutational signature due to exposure to ultraviolet light results in C>T mutations on the untranscribed strand during DNA transcription. Previous analyses have demonstrated that somatic mutations in cancer are not uniformly distributed across the landscape of the genome. Importantly, mutational signatures imprinted by different mutational processes exhibit distinct topographical properties including to be located on (i) early or late replicating regions, (ii) genic or intergenic regions, (iii) transcribed strand or untranscribed strand of DNA with respect to the transcription process, (iv) leading or lagging strand of DNA in regard to DNA replication. Remarkably, mutational signatures may accumulate somatic mutations preferably at nucleosome occupied loci, chromatin accessible regions, transcription factor binding sites, and histone modification sites. Here, I present SigProfilerTopography, the most advanced tool for evaluating the topography of mutational signatures. SigProfilerTopography allows examining all types of mutational signatures and reveals topographical dependencies related to chromatin accessibility, nucleosome occupancy, histone modifications, transcription factor binding sites, replication timing, transcription strand bias, replication strand bias, and processivity. The tool also allows performing user-defined custom analysis based on custom assays. Having augmented with realistic simulated mutations, SigProfilerTopography assesses the significance of its findings which finally characterizes the mutational signatures and gives insight about their underlying biological mechanisms.

Kuntay Aktaş ve Osman Tunç, 17 Mayıs 12:45'te "Medikal 3D Printing - Tanı, Tedavi ve Cerrahide Kişiye Özel 3 Boyutlu Çözümler" başlıklı sunumlarını gerçekleştireceklerdir. Sunum özeti ve sunucuların kısa özgeçmişleri aşağıda paylaşılmıştır.

Özgeçmiş:
Kuntay Aktaş
Makina Mühendisliği’nden mezun olduktan sonra Medikal, Havacılık ve Savunma Sanayi alanında bir çok projede yer aldı. Btech Innovation’ın kurucu ortağı, Yönetim Kurulu Başkanı ve CEO’sudur.
Osman Tunç
Makine Mühendisliğini tamamladıktan sonra bir çok medikal proje içerisinde yer aldı. Anatomik Modelleme ve Medikal 3D Printing alanında birçok eğitim verdi.

Özet:
Manyetik Rezonans Görüntüleme ve Bilgisayarlı Tomografi cihazlarından alınan 2 boyutlu radyolojik verilerin medikal görüntü işleme yazılımlarında 3 boyutlu olarak modellemeleri gerçekleştirilmektedir. Elde edilen 3 boyutlu anatomik yapıların defekt ya da patolojileri üzerinde ilgili cerrahi ekiple ameliyat öncesi sanal cerrahi planlamaları yapılarak kişiye özel çözümler üretilmektedir. Bu çözümler medikal model, kişiye özel cerrahi kılavuz ya da kişiye özel protez olabilmektedir. Organizasyon kapsamında tasarım ve üretim sürecinin klinik uygulamalarını içeren bir sunum gerçekleştirilecektir.

Ahmet Görkem Er will give a seminar on “Informatics in the Pandemic Era” on 26 April at 12:45. The abstract of the talk and a short bio is shared below.

Bio:
Ahmet Gorkem Er is a clinical fellow in the Department of Infectious Diseases and Clinical Microbiology at Hacettepe University and a Ph.D. student in Medical Informatics at METU. He holds an M.D. degree from Istanbul University Istanbul Faculty of Medicine and took his internal medicine residency training from Hacettepe University. He believes in interdisciplinary academic research and mainly focuses on implementing health informatics approaches into the medical field.

Abstract:
COVID-19 pandemic continues to impact all aspects of our lives. An interdisciplinary approach where clinicians and informaticians work together is crucial to control the pandemic. From diagnosis to treatment to protective measures, informatics is central to COVID-19 research and for the delivery of healthcare to the patients. Ahmet Görkem Er will highlight the importance of health informatics by giving examples in the pandemic era.

Utku Kaya will give a seminar on “AI Based Medical Device Development ” on 12 April at 12:45. The abstract of the talk and a short bio is shared below.

Bio:
Utku Kaya (BSc, Electrical & Electronics Engineering, METU), has first been involved in the software industry during his undergraduate years. After 10+ years of software engineering experience, he joined Oracle Turkey where he executed numerous public sector projects for 8 years. In 2019 he founded SmartAlpha, an AI start-up that aims to democratize AI in healthcare globally.

Abstract:
Industry experts agree that AI will revolutionize healthcare in near future. But who will develop these revolutionary tools: Engineers or clinicians? Utku Kaya, the founder of SmartAlpha, believes that the development of such impactful tools requires a transdiciplinary approach where engineers and clinicians understand and serve for each other during the entire production process. This journey to a high impact success is challenging due to strict regulatory needs, massive data dependencies and market complexity.
Utku Kaya outlines the path to develop an AI-in-healthcare solution from idea to product.

Dr. Ulaş Çiftçioğlu will give a seminar on “Neuroscience and Data Science” on 29 March at 12:45. The abstract of the talk and a short bio is shared below.

Bio:
M. Ulaş Çiftçioğlu is a systems engineer at Aselsan Healthcare Systems. He holds a Ph.D. in Neurobiology from the University of Southern California, an MS degree in Medical Informatics from Middle East Technical University (METU) and a BS degree in Electrical–Electronics Engineering also from METU. His Ph.D. and postdoctoral research at the University of Southern California focused on visual processing in the thalamus of the brain. During his MS, he developed algorithms for tissue segmentation in brain MR images. Prior to his current role, he worked with C. Light Technologies to develop prognostic models for Multiple Sclerosis. Currently, he is working on the development of a clinical MRI system at Aselsan.

Abstract:
The role of the thalamus in processing visual sensory information has traditionally been considered as minimal. However, the thalamus contains various visual nuclei with different connectivity and function. As opposed to the well-studied thalamic dorsal lateral geniculate nucleus (dLGN), the role of the thalamic ventral lateral geniculate nucleus (vLGN) and thalamic reticular nucleus (TRN) in visual processing is relatively unknown. To explore that, we have used electrophysiological, optogenetic, histological, and computational techniques to investigate the physiology and morphology of neurons in these two nuclei. The sensory physiology in these nuclei highlighted the diversity within the thalamus in terms of visual processing and shed light on how they may serve vision.
Multiple Sclerosis (MS) is a neurological disease with various symptoms. Assessment and monitoring of MS is quite expensive and subjective. C. Light Technologies, a medical device company, is developing an eye movement tracking device to ultimately assess neurological diseases in an objective and cost-effective way. I have investigated whether this technology can provide a prognostic value, in addition to the already demonstrated diagnostic value. This pilot study suggested that measurements of eye movement tracking can provide insights on the progression of MS in individual patients.

Assoc. Prof. Devrim Ünay will give a seminar on “MR image processing (macro level) and microscopy image processing (micro level)” on 22 March (Monday) at 13:45. A short bio is shared below.

Bio:
Devrim Ünay received the B.S. degree in electrical and electronics engineering and the M.S. degree in biomedical engineering from Boğaziçi University, Turkey, and the Ph.D. degree in applied sciences from the Faculté Polytechnique de Mons, Belgium. He was a Senior Scientist and a Marie Curie Fellow with the Video Processing and Analysis Group, Philips Research Eindhoven, The Netherlands, a Visiting Researcher with the VPA Laboratory, Faculty of Engineering and Natural Sciences, Sabanci University, Istanbul, Turkey, and a Faculty Member with Biomedical Engineering Department, Faculty of Engineering and Natural Sciences, Bahcesehir University, Istanbul. He served as the Head of the Biomedical Engineering Department, İzmir University of Economics, Turkey. He is currently a Faculty Member at the Electrical and Electronics Engineering Department of Izmir Democracy University, Turkey. He is the co-founder and data scientist at Zoi Data as well. His research interests include biomedical image analysis, computer vision and pattern recognition, content-based information retrieval, machine/deep learning, and machine vision and quality inspection. He has been the PI of 4 national and 1 international projects. He has published 2 books, 4 book chapters, 22 journal papers, several conference proceedings, and holds 2 US patents. He has actively participated in the organizations of ICPR2010 and MICCAI 2016 conferences and co-organized several special sessions in national and international conferences. He is currently serving as a Member of the IEEE Signal Processing Society, Bio Imaging and Signal Processing Technical Committee (BISP TC) for the term 2021-2023, where he served as Associate Member previously.

Kadın Matematikçiler Derneği 8 Mart Dünya Kadınlar Günü çerçevesinde bır etkınlık düzenlemektedir. Etkinliğin ikinci kısmında Yeşim Aydın Son ve Seher Nur Sülkü hocalarımız, Kovid-19 salgınının ülkemizdeki seyrinin olasılıksal bir modellemesi üzerine yaptıkları çalışmaları hakkında 8 Mart saat 14:00'te konuşma vereceklerdir.

Buraya tıklayarak etkinlik hakkında daha fazla bilgi alabilir ve Zoom bağlantısına ulaşabilirsiniz.

Dr. Carlos Trenado will give a seminar on “Performance improvement in humans through neuroscience approaches” on 15 January at 4 pm. The abstract of the talk and a short bio is shared below.

Bio:
Carlos Trenado is a neuroscientist and neurotechnologist with several years of experience in clinical neuroscience. He has been a postdoctoral fellow at the School of Public Health of University of Maryland College Park, University Hospital Freiburg and University Hospital Düsseldorf. He is currently a research fellow at the Systems Neuroscience and Neurotechnology Unit of Saarland University. His research interests include investigation of neural mechanisms of multisensory integration, cognition and perception in humans by using pharmacological, behavioral and neuromodulation interventions as well as computational modeling.

Abstract:
Multisensory integration (MI) refers to simultaneous processing of stimuli from different sensory modalities which gives place to a neural response reflecting fusion of information. Interestingly, previous work has shown that MI favors enhancement on performance in a number of perceptual and behavioral domains. In this respect, I will argue about stochastic resonance as a promising approach to enhance motor and cognitive performance in humans and emphasize some medical and technological applications.