This chapter looks at several commonly used breast cancer datasets, whether they are text or images, as well as related works demonstrating previous efforts for breast cancer diagnosis. Wisconsin breast cancer dataset downloaded from the UCI machine learning repository in this part. This dataset is utilized to separate between cancerous and benign tumors. The breast carcinoma subtyping dataset is a vast collection of annotated Hematoxylin and Eosin-stained pictures designed to aid in the diagnosis of breast lesions. The breast cancer semantic segmentation dataset comprises approximately 20,000 tissue region segmentation annotations from the cancer genome Atlas breast cancer pictures. The breast cancer histopathological image classification is made up of 9109 microscopic images of breast tumor tissue collected from 82 people at various magnification levels. PatchCamelyon is a dataset for picture categorization. It is made up of 327.680 color pictures taken from lymph node histopathologic scans.