A Textural Approach for Recognizing Architectural Distortion In Mammograms

سال انتشار: 1392
نوع سند: مقاله کنفرانسی
زبان: انگلیسی
مشاهده: 1,090

فایل این مقاله در 5 صفحه با فرمت PDF قابل دریافت می باشد

این مقاله در بخشهای موضوعی زیر دسته بندی شده است:

استخراج به نرم افزارهای پژوهشی:

لینک ثابت به این مقاله:

شناسه ملی سند علمی:

ICMVIP08_183

تاریخ نمایه سازی: 9 بهمن 1392

چکیده مقاله:

Breast cancer is considered as the mostimportant cause of death among women. Architecturaldistortions are very important signs of breast cancer and earlydetection of them is a rewarding work. In this paper wepropose a method to recognize architectural distortion fromnormal parenchyma. In our proposed method, appropriatefeatures are extracted by the analysis of oriented textures withthe application of orientation component of recent the state-ofthe-art local texture descriptor called Monogenic BinaryCoding (MBC). In addition, we transform Region of Interests(ROIs) to polar coordinates in order to highlight some specificpatterns in mammograms. Various classifiers are used over aset of mammograms from Digital Database for ScreeningMammography (DDSM). The results show that proposedmethod is very encouraging. The best performance achieved is91.25% in terms of the average accuracy using the NearestNeighbor classifier.

نویسندگان

Elham Mohammad

Department of Electrical Engineering Amirkabir University of Technology

Emad Fatemizade

Department of Electrical Engineering Biomedical Engineering GroupSharif University of Technology

Hamid Sheikhzade

Department of Electrical Engineering Amirkabir University of Technology

Sahar Khoubani

Department of Electrical Engineering Amirkabir University of Technology