A Systematic Approach to Machine Learning for Cancer Classification

Abstract

Cancer is a lethal disease that is frequently brought on by the accumulation of hereditary disorders and many pathological alterations. Cancerous cells are aberrant, life-threatening growths that can appear anywhere on the human body. To determine what might be helpful for its treatment, cancer, also known as a tumour, should be promptly and accurately discovered in the early stages. Even while each approach has its own unique considerations, some of the major causes of mortality include difficult histories, inadequate diagnoses, and inadequate treatment. The study’s objective is to review, categorise, and discuss the most recent advances in machine learning for the identification of leukaemia, breast, brain, lung, and other human body cancers. Clinical practice, “translational medicine”, and the biological study of various diseases, such as cancer, have all been included in the medical applications of AI. “Current AI systems”, which are solely based on ML methodologies, have been used to improve various facets of “clinical practise”, including the “interpretation of genomic data” for the identification of genetic variants based on “high-throughput sequencing technologies” in many medical specialities, such as “pathology, radiology, ophthalmology, and dermatology”. A secondary method of data collection is considered for this research to gather relevant and factual data related to ML approaches use for cancer classification.