The most serious sort of cancer that affects
women most frequently in modern times is breast cancer
(BC). If it is not detected in the beginning stages, the
death rate is significant. Breast cancer affects around
12% of woman, and the percentage is continually rising.
The invention of a ML-based breast cancer classification
system that can identify the disease from a patient's
digital scan is artificial intelligence's greatest
contribution to healthcare. Breast cancer is found using
the mammography method however, radiologists'
interpretations vary greatly. Fine needle aspiration
cytology is commonly used in the diagnosis of breast
cancer (FNAC). Uniform cell size, if the tumour has a
consistent cell shape and other factors are taken into
account, the prediction will determine if the tumour is
benign or malignant. We have gathered both the
characteristics of breast cancer cells and cells from
healthy individuals. We were able to differentiate
between malignant and benign employing a supervised
machine learning classifier system to identify tumours.
However, by taking the right medications, needless
therapy can be avoided if patients are correctly
recognised early on employing ML approaches. Though
computer vision, ML technologies have demonstrated a
high level of accuracy in healthcare applications,
Physical examinations shouldn't solely be conducted
using these systems. These are meant to support doctors,
not replace them. Machine learning has a distinct
advantage in that it can find relevant breast cancer
features in large datasets. In predictive modelling and
pattern recognition, the technique is extensively used.
Assessing each classifier's effectiveness in terms of
accuracy, precision, and recall is the project's main
objective. Examining the effectiveness, accuracy, and
early identification of breast cancer using different
machine learning classifiers is the goal.
Breast Cancer (BC), Mammography, Fine Needle Aspiration Cytology(FNAC).