Leveraging Transfer Learning for High-Accuracy Breast CancerClassification f rom Histopathological Images
Publish place: The 6th International Conference on Electrical Engineering, Computer, Mechanics and Artificial Intelligence
Publish Year: 1403
نوع سند: مقاله کنفرانسی
زبان: English
View: 24
This Paper With 8 Page And PDF Format Ready To Download
- Certificate
- من نویسنده این مقاله هستم
استخراج به نرم افزارهای پژوهشی:
شناسه ملی سند علمی:
EECMAI06_037
تاریخ نمایه سازی: 30 خرداد 1403
Abstract:
Early detection of breast cancer remains an important global health concern. Inthis paper, we present a novel method for classifying breast cancer usinghistopathological images from the BreakHis dataset at ۴۰۰X resolution. Weextract high-level features capturing malignancy patterns using VGG۱۹ andDenseNet۲۰۱. For final classification, these features are concatenated and fed intoan Artificial Neural Network (ANN), which achieves an impressive accuracy of۹۹%. The high accuracy of our methodology demonstrates its potential as aneffective diagnostic tool in the digital pathology era.
Keywords:
Authors
Amir Mohammad Sharafaddini
Department of Computer Science, Shahid Bahonar University of Kerman, Kerman,Box No. ۷۶۱۳۵-۱۳۳, Kerman, Iran.
Najme Mansouri
Department of Computer Science, Shahid Bahonar University of Kerman, Kerman,Box No. ۷۶۱۳۵-۱۳۳, Kerman, Iran