Genomics at the Nexus of AI, Computer Vision, and Machine Learning

13AI Applications in Analyzing Gene Expression for Cancer Diagnosis: A Comprehensive Review

Poorva Agrawal^*, Gagandeep Kaur, Vansh Gupta, Kruthika Agarwal, Latika Pinjarkar and Seema Patil

Symbiosis Institute of Technology, Nagpur Campus, Symbiosis International (Deemed University), Pune, India

Abstract

In the domain of cancer detection, machine learning (ML), deep learning (DL), and transfer learning (TL) have become innovative instruments that hold great promise for early diagnosis and improved outcomes for patients. Massive amounts of medical data, such as genetic information, imaging data, and clinical records, can be swiftly checked by ML algorithms to find tendencies and mutations that can point to cancer. Accurate detection of carcinoma can be further improved by developing intelligent systems that can read and learn from complex data by artificial intelligence (AI). This more general term includes ML. Cancer detection relies heavily on TL, an ML technique that uses pre-trained models to speed learning, especially in small datasets. Data preprocessing, feature extraction, model training, and model evaluation contain significant phases in applying ML, DL, and TL in cancer detection. The chapter aims to offer insights into the current state of AI applications in the field, exploring their efficacy and potential impact on enhancing the accuracy and efficiency of cancer diagnosis by examining gene expression patterns.

Keywords: Cancer diagnosis, gene expression, DNA, machine ...