Medical Visual Question Answering in Brain MRI Images Using Machine Learning

نوع: Type: thesis

مقطع: Segment: masters

عنوان: Title: Medical Visual Question Answering in Brain MRI Images Using Machine Learning

ارائه دهنده: Provider: hamed shabani

اساتید راهنما: Supervisors: Dr. Hassan Khotanlou, Dr. Muharram Mansoorizadeh

اساتید مشاور: Advisory Professors:

اساتید ممتحن یا داور: Examining professors or referees: Dr. Mirhossein Dezfoolyan, Dr. Mahlaqa Afrasiabi

زمان و تاریخ ارائه: Time and date of presentation: 2024

مکان ارائه: Place of presentation: دانشکده مهندی سالن آمفی تئاتر

چکیده: Abstract: Answering medical questions from medical images, especially in the field of brain MRI, is a complex and multifaceted challenge that has attracted research attention from the computer vision and natural language processing communities. In this study, we introduce an improved dataset and innovative models specifically designed to answer specialized questions about MRI images of brain tumors. To develop this system, we have used the BRATS2013, BRATS2017, BRATS2021, IXI and Jun Cheng authoritative datasets, which contain comprehensive and detailed information about brain tumors. Our system uses advanced attention mechanisms and powerful pre-trained models such as BERT, Net-B7 and ResNet-152 to propose and analyze text and image features with high accuracy and efficiency. This research presents evaluation results in the analysis of brain tumors with special focus on MRI of brain tumors and application of visual question answering techniques. The obtained results show the accuracy and high scores of BLEU, which proves the potential and the models with the proposed capabilities in improving the process of interpreting MRI scans of brain tumors and helping medical decisions. These systems can be used as an important step in the development of artificial intelligence tools for more accurate diagnosis and treatment of brain tumors.

فایل: ّFile: Download فایل