Artifical intelligence technology in cancer imaging: Clinical challenges for detection of lung and breast cancer

Abstract

Abstract. In the domain of Artificial Intelligence, deep learning is part of a broader family of machine learning methods based on deep neural networks, deep belief networks, recurrent neural networks and convolutional neural networks that have been applied to fields including computer vision, medical image analysis, histopathological diagnosis, with results comparable to and in some cases superior to human experts. This study shows that these methods applied to medical imaging can assist pathologists in the detection of cancer subtype, gene mutations and/or metastases for applying appropriate therapies. Results show that trajectories of AI technology applied in cancer imaging seems to be driven by high rates of mortality of some types of cancer in order to improve detection and characterization of cancer to apply efficiently anticancer therapies. This new technology can generate a technological paradigm shift for diagnostic assessment of any cancer type. However, application of these methods to medical imaging requires further assessment and validation to support the efficiency of the workflow of pathologists in clinical practice and improve overall healthcare sector.

Keywords. Artificial intelligence, Diagnostic assessment, Histopathology images, Deep learning algorithms, Cancer, Clinical challenges.

JEL. O32, O33.