Radiomics and Machine Learning in Oncological Diagnosis

Dear Colleagues,

In this new era of technological advances in the medical field, radiomics and machine learning (ML) have emerged as algorithms capable of making predictions or performing decision-making tasks without prior explicit programmed rules.

Radiomics is a multi-step process that converts medical images into extractable data through the mathematical extraction of quantitative parameters that reflect the heterogeneity of the imaged tumor, thus enabling precise diagnosis and staging in cancer imaging. In fact, such a large amount of data can be handled more easily by ML algorithms than traditional statistical methods.

The development of models based on ML radiomics represents an excellent opportunity to extract further value and information from medical imaging, thus improving the clinical and radiological work-up for cancer patients.

Interest in the potential of machine learning and radiomics has grown steadily over the past decade. These techniques have opened the door to innovative applications in predicting patient prognosis and characterizing solid lesions. Machine learning also has the potential to streamline radiologists' clinical workflow by automating repetitive and menial tasks and increasing overall efficiency, for example, by improving the speed of image acquisition without quality loss.

This Special Issue will be open to the collection of original research and review papers focused on radiomics and machine learning in oncology diagnostic imaging, covering insights from clinical radiological workflow optimization (patient screening, image acquisition) to more specific image-based tasks (cancer detection, characterization, treatment monitoring, prediction of prognosis and overall and disease-free survival).

Dr. Roberta Fusco
Dr. Vincenza Granata
Dr. Sergio Venanzio Setola
Guest Editors

Manuscript Submission Information

Manuscripts should be submitted online at www.mdpi.com by registering and logging in to this website. Once you are registered, click here to go to the submission form. Manuscripts can be submitted until the deadline. All submissions that pass pre-check are peer-reviewed. Accepted papers will be published continuously in the journal (as soon as accepted) and will be listed together on the special issue website. Research articles, review articles as well as short communications are invited. For planned papers, a title and short abstract (about 100 words) can be sent to the Editorial Office for announcement on this website.

Submitted manuscripts should not have been published previously, nor be under consideration for publication elsewhere (except conference proceedings papers). All manuscripts are thoroughly refereed through a single-blind peer-review process. A guide for authors and other relevant information for submission of manuscripts is available on the Instructions for Authors page. Diagnostics is an international peer-reviewed open access semimonthly journal published by MDPI.

Please visit the Instructions for Authors page before submitting a manuscript. The Article Processing Charge (APC) for publication in this open access journal is 2600 CHF (Swiss Francs). Submitted papers should be well formatted and use good English. Authors may use MDPI's English editing service prior to publication or during author revisions.

• radiomics
• machine learning
• oncology diagnostic imaging
• cancer detection
• cancer characterization
• cancer treatment monitoring