Abstract

Dr. Tejaswini G. V., Vasudev Purushottam Pai, Sanivarapu Radhika, Dr. Darshan Bhushan Deshmukh, Dr. Vaibhav Ramkishan Khandade, Dr. Rahul Laxman Jadhao, P. Joanna Grace, Pratiksha Bhandare, Anurag Ravi Sattigeri

ABSTRACT

In order to improve cancer detection through medical imaging, artificial intelligence (AI) and machine learning (ML) have become essential. Despite their importance, traditional imaging techniques frequently have issues with sensitivity, accuracy, and process inefficiencies. Imaging modalities such as CT, MRI, PET, and mammography are changing how malignancies are identified and studied thanks to AI and ML approaches, especially deep learning and convolutional neural networks (CNNs). These technologies have the potential to significantly improve clinical decision-making by automating lesion diagnosis, increasing diagnostic accuracy, and aiding in treatment response prediction. Prominent research shows that AI can do some diagnostic tasks on par with or even better than radiologists. Notwithstanding these developments, obstacles to wider use include issues with data quality, model generalization, and ethical considerations. In order to improve early detection, diagnostic accuracy, and patient outcomes in oncology, this study emphasizes the existing uses, difficulties, and potential future developments of AI and ML in cancer imaging.