A Review on Computational Methods for Breast Cancer Detection in Ultrasound Images Using Multi-Image Modalities

Breast cancer is a kind of cancer that develops and propagates from tissues of the breast and slowly transcends the whole body, this type of tumor is found in both sexes. Early detection of this disease is very important as at this stage it can be controlled by giving patients the required treatment and their valuable life can be saved. Researchers and scientists according to various studies have found methods to detect cancer at the initial stages, however, misperception in identifying skeptical lesions can be due to poor image quality and diverse breast density. Breast cancer (BC) is still a major concern for world health, necessitating ongoing innovation in early diagnosis and detection. Breast cancer diagnosis has made significant strides in recent years, especially with the incorporation of multi-modal imaging modalities. This article provides a summary of the most recent methods and advancements in multi-modal imaging for the detection of breast cancer. When radiomics, a quantitative study of imaging data, is integrated with machine learning and deep learning algorithms, breast lesions have demonstrated potential. These techniques can help distinguish between benign and malignant tumours, providing physicians with crucial information.At various phases of breast cancer detection, new methods have been developed for enhancement, segmentation, feature extraction, and classification employing multiple picture modalities. This review paper's objective is to represent all prior research in the area of breast cancer categorization utilising many imaging modalities. This paper provides a thorough and rigorous examination of current trends in the field of BC detection and classification.