Dear Colleagues,

Cancer is one of the major causes of death in the world. Recently, AI has widely been used in artificial intelligence (AI). In the past, AI has shown itself as a complex tool and a solution assisting medical professionals in the diagnosis/prognosis of different cancers in various cancer imaging modalities. However, AIs are still black boxes that do not help the decision-making process for physicians and doctors. The poor explainability causes distrust from clinicians/doctors, who train to make an explainable diagnosis. Thus, there is an urgent need for novel methodologies to improve the explainability of existing AI methods used routinely in clinical practices. Particularly, explainable deep learning (DL) methods will help to interpret the diagnosis to both patients and physicians. This Special Issue highlights advances in explainable AI models and methods in cancer imaging in all its diversity, covering both conventional and new explainable deep learning methods in oncology.

Keywords:

oncological imaging
tumor detection and diagnosis
omics
supervised and unsupervised learning
kernel methods
deep neural networks
mathematical modeling
graph neural network
attention neural network

Participating Journals:

Applied Sciences
Cancers
Cells
Electronics
Sensors