A Review of Machine Learning Techniques Being Used For Blood Cancer Detection

Main Article Content

Anam Gupta, Pooja Sharma


The cancer therapy test was aimed at targeting various treatments in the manner of which genetic tumors are composed, amplifying viability and limiting the quality of poisoning. In order to facilitate malignancy therapy, changes in cancer classifications have become critical. Machine learning (ML) and deep learning (DL) methods have been a cornerstone of the toolset for the study of vast quantities of weakly associated or high-dimensional data for more than a decade. Growth characterization has been focused mainly on tumor morphological presentation, but this has real restrictions. Comparative histopathological presentation tumors may follow radically modified therapeutic paths and display distinctive therapy reactions. In a few instances, the isolation of morphologically similar tumors into subtypes of distinct pathogenesis has explained certain clinical heterogeneity. Classification of malignancy has become challenging to a small degree because, as compared to ordered and rational methodologies for perceiving tumor subtypes, it is genuinely based on precise natural bits of information. In view of the worldwide gene articulation analysis to handle the malignancy gene articulation results, a few methodologies are proposed here. Few methods were proposed for clustering and characterization

Article Details

How to Cite
Anam Gupta, Pooja Sharma. (2021). A Review of Machine Learning Techniques Being Used For Blood Cancer Detection. Annals of the Romanian Society for Cell Biology, 7796 –. Retrieved from https://annalsofrscb.ro/index.php/journal/article/view/3436