Diagnosis of Mild Cognitive Impairment (MCI) Using a CNN-LSTM Hybrid Algorithm

  • سال انتشار: 1403
  • محل انتشار: بیست و دومین کنفرانس ملی علوم و مهندسی کامپیوتر و فناوری اطلاعات
  • کد COI اختصاصی: CECCONF22_004
  • زبان مقاله: انگلیسی
  • تعداد مشاهده: 268
دانلود فایل این مقاله

نویسندگان

Sara Yousefi Javan

Department of Computer Engineering, Mashhad Branch, Islamic Azad University, Mashhad, Iran

Mahboobeh Houshmand

Department of Computer Engineering, Mashhad Branch, Islamic Azad University, Mashhad, Iran

Seyyed Abed Hosseini

Department of Electrical Engineering, Mashhad Branch, Islamic Azad University, Mashhad, Iran

چکیده

In recent years, the global increase in life expectancy has highlighted the importance of diagnosing Alzheimer's disease (AD). The onset of mild cognitive impairment (MCI) can indicate a progression towards irreversible mental decline, including AD and dementia. Consequently, early detection of MCI has become a focal point for researchers, as intervening at this stage can halt its advancement and facilitate effective treatment. Traditionally, biochemical and psychological tests have been used for diagnosis. However, an emerging approach involves analyzing Magnetic Resonance Imaging (MRI) scans to detect structural changes in the brain associated with AD. In this study, brain MRI images are pre-processed using the Statistical Parametric Mapping (SPM) toolbox. Subsequently, the gray matter (GM) is segmented and input into a ConvolutionalNeural Network (CNN) for analysis. The Alzheimer's Disease Neuroimaging Initiative (ADNI) dataset is utilized for this purpose. The results demonstrate that the proposed method achieves an accuracy exceeding ۹۵% in classifying three categories: Normal Control (NC), AD, and MCI. This underscores the potential of MRI-based approaches forearly and accurate diagnosis of AD, paving the way for timely interventions and improved patient outcomes.

کلیدواژه ها

Alzheimer’s Disease, Brain MRI , Convolutional Neural Network, Statistical Parametric Mapping (SPM)

مقالات 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.