Меню
No. 4 (25) - 2024 / 2024-12-31 / Number of views: 2
Authors
Keywords
Link to DOI:
How to quote
This study focuses on researching and developing methods for the efficient detection of breast pathologies using modern machine learning technologies, specifically You Only Look Once (YOLOv8) and Faster Region-based Convolutional Neural Network (R-CNN). The paper provides an analysis of existing approaches to diagnosing breast diseases and evaluates their effectiveness. The YOLOv8 and Faster R-CNN architectures are employed to develop models for detecting pathologies in mammography images. The research classifies and analyzes identified breast pathologies at six different levels, considering varying degrees of severity and characteristics of the diseases. This method enables a more accurate assessment of disease progression and offers additional insights for more personalized treatment planning. Classification results across these levels can enhance medical decision-making quality and provide doctors with more precise information, ultimately improving the overall efficiency of breast disease diagnosis and treatment. Experimental results show high accuracy and rapid image processing, enabling fast and reliable detection of potential breast pathologies. The findings confirm the effectiveness of machine learning algorithms in medical diagnostics, highlighting the potential for further advancements in automated breast disease detection systems to enhance early diagnosis and treatment outcomes.