دانشگاه آزاد اسلامی واحد تهران جنوب

صفحه اصلی / نخستین همایش هوش مصنوعی و پژوهش های نوظهور: همگرایی انسان و سیستم های هوشمند

Using 2D-DOST coefficients on Thermal Images for Breast Cancer Detection

نویسندگان :

Ainaz Daneshdoust¹ Sedigheh Ghofrani² Mahdi Eslami³ Iman Ahanian⁴

1- آزاد اسلامی واحد تهران جنوب 2- آزاد اسلامی واحد تهران جنوب 3- آزاد اسلامی واحد علوم و تحقیقات 4- آزاد اسلامی واحد تهران جنوب

کلمات کلیدی :

Breast Cancer،2D-DOST،Thermogram Breast،Feature Extraction

چکیده :

Early detection of breast cancer is necessary for improving patient survival rates. Infrared thermography, as a non-invasive and cost-effective imaging method, was used in this study to detect breast abnormalities. This paper proposes a feature extraction method based on 2D-DOST coefficients, which effectively encode spatial-frequency information from thermal images. These features are classified using an SVM to discriminate between healthy and sick cases. Experimental results demonstrate that the proposed model achieves a classification accuracy of 95%, sensitivity of 93%, specificity of 97%, F1 score of 95%, and an area under the ROC curve of 94.81%. These findings highlight the potential of combining 2D-DOST-based feature extraction with machine learning techniques as a reliable computer-aided diagnostic tool for early breast cancer detection.