Fractal texture analysis for automated breast cancer detection.

Breast cancer is the most common type of cancer in women all over the world. In 2023, there will be approximately 2.2 million new cases of breast cancer, with 662000 deaths worldwide. As of the end of 2021, 7.9 million women had been diagnosed with breast cancer in the previous five years, making it the world's second most common cancer. Primary breast cancer detection is critical for increasing survival rates. After 5 years, breast cancer survival rates range from more than 93% in developed countries to 63% in India and 42% in South Africa. Early detection and treatment have been shown in developed countries to be effective and should be expanded to other countries [1]. Mammography is the utmost operative method for detecting early-stage breast cancer that is presently available. Naturally, a radiologist will look for signs of cancer in a mammogram. Radiologists are directed by the computer-aided diagnosis system to re-examine the mammogram for any suspicious areas. The computer programme can analyse the mammogram and detect abnormalities. The goal of this paper is to look into the value of textural properties, specifically fractal textures, in describing benign and malignant microcalcifications, as well as their role in improving classification accuracy. To investigate classification and labelling, textural measures were used. For fractal analysis, the differential box counting method, Fractal dimensions, and the Gray level Difference Method were used (GLDM). Fractal measures were used to classify and label benign and malignant microcalcifications. The importance of fractal texture measures in achieving automated Breast cancer detection and classification accuracy is emphasised in this paper. [ABSTRACT FROM AUTHOR]