Brain tumor detection using improved convolutional neural network
- سال انتشار: 1404
- محل انتشار: دومین کنفرانس بین المللی کامپیوتر، برق، مکانیک و علوم مهندسی
- کد COI اختصاصی: CMELC02_053
- زبان مقاله: انگلیسی
- تعداد مشاهده: 51
نویسندگان
Department of Biomedical Engineering, Islamic Azad University, Tehran Central Science and Research Branch, Tehran, Iran
Department of Biomedical Engineering, Islamic Azad University, Tehran Central Science and Research Branch, Tehran, Iran
چکیده
Brain tumors are a leading global cause of mortality, with only ۱۲% of adults surviving beyond five years. Early and precise diagnosis plays a crucial role in improving patient outcomes. MRI imaging is one of the most effective tools for brain tumor detection, but automated classification methods can significantly enhance diagnostic efficiency. This study proposes an optimized convolutional neural network (CNN) model designed to classify different types of brain tumors with improved accuracy and reduced complexity. By systematically refining network layers, the proposed model extracts deep features while minimizing computational overhead. In this study, an optimized convolutional neural network model is introduced for brain tumor detection. In this study, the feature of improving the layers of the optimized system and automatically reducing the complexity of the model has improved the complexity of the system by ۴۰% and brain tumor images have been detected. The results, validated through ۱۰-fold cross-validation, achieve an average accuracy of ۹۸.۹۲% and sensitivity of ۹۸.۶۲%, demonstrating the effectiveness of the approach. The findings highlight the model’s potential in aiding clinical diagnosis, offering a cost-effective and practical solution for brain tumor classificationکلیدواژه ها
Brain tumor, Convolutional neural network, Optimization, Classificationمقالات مرتبط جدید
اطلاعات بیشتر در مورد COI
COI مخفف عبارت CIVILICA Object Identifier به معنی شناسه سیویلیکا برای اسناد است. COI کدی است که مطابق محل انتشار، به مقالات کنفرانسها و ژورنالهای داخل کشور به هنگام نمایه سازی بر روی پایگاه استنادی سیویلیکا اختصاص می یابد.
کد COI به مفهوم کد ملی اسناد نمایه شده در سیویلیکا است و کدی یکتا و ثابت است و به همین دلیل همواره قابلیت استناد و پیگیری دارد.