Interactive Medical Image Segmentation using Active Contour with Improved F Energy in Level-Set Tuning
Publish place: majlesi Journal of Electrical Engineering، Vol: 16، Issue: 2
Publish Year: 1401
نوع سند: مقاله ژورنالی
زبان: English
View: 329
This Paper With 10 Page And PDF Format Ready To Download
- Certificate
- من نویسنده این مقاله هستم
این Paper در بخشهای موضوعی زیر دسته بندی شده است:
استخراج به نرم افزارهای پژوهشی:
شناسه ملی سند علمی:
JR_MJEE-16-2_002
تاریخ نمایه سازی: 3 آذر 1401
Abstract:
Segmentation is a fundamental element in medical image processing (MIP) and has been extensively researched and developed to aid in clinical interpretation and utilization. This article discusses a method for segmenting abnormal masses or tumors in medical images that is both robust and effective. We suggested a method based on Active Contour (AC) and modified Level-set techniques to detect malignancies in magnetic resonance imaging (MRI), mammography, and computed tomography (CT). To segment malignant masses, the active contour approach, the energy function, the level-set method, and the proposed F function are employed. The system was evaluated using ۱۶۰ medical images from two databases, including ۸۰ mammograms and ۸۰ MRI brain scans. The algorithm for segmenting suspicious segments has an accuracy, recall, and precision of ۹۶.۲۵%, ۹۵.۶۰%, and ۹۵.۷۱%, respectively. By adding this technique into tissue imaging devices, the accuracy of diagnosing images with a relatively large volume that are evaluated fast is increased. Cost savings, time savings, and high precision are all advantages of the approach that set it apart from similar systems.
Keywords:
Authors
Khosro Rezaee
Department of Biomedical Engineering, Meybod University, Meybod, Iran.
Mohammad Khalil Nakhl Ahmadi
Islamic Azad University, Torbat-e Jam Branch, Torbat, Iran.
Maryam Saberi Anari
Department of Computer Engineering, Technical and Vocational University (TVU), Tehran, Iran.
مراجع و منابع این Paper:
لیست زیر مراجع و منابع استفاده شده در این Paper را نمایش می دهد. این مراجع به صورت کاملا ماشینی و بر اساس هوش مصنوعی استخراج شده اند و لذا ممکن است دارای اشکالاتی باشند که به مرور زمان دقت استخراج این محتوا افزایش می یابد. مراجعی که مقالات مربوط به آنها در سیویلیکا نمایه شده و پیدا شده اند، به خود Paper لینک شده اند :