A Review of Artificial Intelligence Models for Breast Cancer Detection

سال انتشار: 1404
نوع سند: مقاله کنفرانسی
زبان: انگلیسی
مشاهده: 139

متن کامل این مقاله منتشر نشده است و فقط به صورت چکیده یا چکیده مبسوط در پایگاه موجود می باشد.
توضیح: معمولا کلیه مقالاتی که کمتر از ۵ صفحه باشند در پایگاه سیویلیکا اصل مقاله (فول تکست) محسوب نمی شوند و فقط کاربران عضو بدون کسر اعتبار می توانند فایل آنها را دریافت نمایند.

استخراج به نرم افزارهای پژوهشی:

لینک ثابت به این مقاله:

شناسه ملی سند علمی:

AIMS02_618

تاریخ نمایه سازی: 29 تیر 1404

چکیده مقاله:

Background and Aims: The most common cancer among women and leading cause of female mortality worldwide is breast cancer. Early detection highly improves treatment outcome. Over the last two years, with the advent of artificial intelligence (AI), more specifically deep learning, there have been new opportunities to improve the precision and effectiveness of breast cancer diagnosis and screening. Methods: In this narrative review, an extensive search was conducted in the PubMed database and Google Scholar search engine using English keywords including artificial intelligence, breast cancer, breast cancer detection. ۴۷۰ articles were found. After removing duplicates, outdated studies, and irrelevant content, ۱۱ articles published between ۲۰۲۰ and ۲۰۲۵ were selected for analysis and review. Results: Breast cancer detection has been significantly improved by artificial intelligence, particularly through deep learning models in digital mammography and tomosynthesis. The AI approaches are better than traditional CAD algorithms since they reduce false positives and their performance is equal to or superior to that of expert radiologists. They are especially helpful in detecting hard-to-detect cases such as interval and high-grade invasive cancers. Beyond mammography, AI has proved useful in ultrasound, MRI, and infrared thermography, increasing access and diagnostic precision. In pathology, AI assists in tumor categorization, biomarker identification, and treatment prediction, allowing customized therapy. AI also enhances workflow efficiency and reduces diagnostic inconsistency. Obstacles to its entire potential, such as data variability, clinical credibility, and ethics, remain and must be addressed to allow effective clinical use. Conclusion: AI has already shown great potential to enhance detection, diagnosis, and treatment planning of breast cancer. While current models are truly impressive in their performance, especially in imaging, more research, clinical integration, and validation must be conducted. AI can indeed be a top-notch resource in improving early detection and patient outcome in the treatment of breast cancer with judicious application.

نویسندگان

Elahe Karimipour

Student Research Committee, school of nursing and midwifery, Ahvaz Jundishapur University of Medical Science, Ahvaz, Iran

Haniye Karimipour

Medical Student, Student Research Committee, Ahvaz Jundishapour University of Medical Science, Ahvaz, Iran