Deep Learning Techniques for Cancer Imaging
Cancer presents a unique circumstance for medical decisions due to not only its various types of disease growth, but also the requirement for early, fast and proper detection of the individual patient’s condition, their capability to receive treatment, and their responses to treatment. Despite advances in technology, correct detection, categorization, and monitoring of cancers remains a challenge. The majority of radiological disease analysis is based on visual examinations, which can be supplemented by intelligent computing techniques. Deep Learning (DL) approaches have the potential to bring about significant advances in the analysis and interpretation of cancer images by medical experts. These include prediction of cancer susceptibility, prediction of cancer recurrence, prediction of the stage and grade of cancer, tracking tumor development, etc. Proper monitoring of the impact of the disease and the corresponding treatment on surrounding tissues is another big challenge in the case of a cancer diagnosis. DL has the potential to automate image interpretation procedures, the clinical workflow of radiological detection, and management decisions on whether or not to administer an intervention.

This Special Issue aims to publish the latest developments in research on all facets of DL-empowered cancer imaging. This special issue especially welcomes submissions that depict the end-to-end technological viewpoint that uses automated informatics systems to solve single or multiple cases of healthcare advancements based on cancer imaging. Papers describing new deep learning algorithms based on cancer imaging are especially welcome. The papers will be chosen based on their scientific merit, contribution to the field of deep learning-based image processing, and importance to cancer detection and diagnosis. To establish the effectiveness of any proposed approach, authors should use the relevant cancer imaging datasets.

With Jyotismita Chaki as the Lead Guest Editor and Victor Albuquerque and Marcin Woźniak as Guest Editors, submissions must be made through ScholarOne by 28 February 2023.