Deep Learning and Radiomics for Cancer Diagnosis, Staging, and Treatment Response

Dear Colleagues, 

Cancer remains one of the leading causes of morbidity and mortality worldwide, necessitating continuous innovation in its diagnosis, staging, and treatment monitoring. Traditional diagnostic techniques often rely on the qualitative assessment and visual interpretation of medical images, which can be subject to inter-observer variability and limited sensitivity, especially in the early stages. In recent years, two powerful technological paradigms—radiomics and deep learning—have emerged as transformative tools in oncologic imaging, offering unprecedented opportunities for enhancing precision in cancer care.

Radiomics enables the extraction of a large number of quantitative features from standard medical images (CT, MRI, PET, etc.), capturing hidden patterns related to the tumor phenotype, heterogeneity, and microenvironment. When combined with deep learning models, especially convolutional neural networks (CNNs), these features can be used to build robust, non-invasive biomarkers for predicting tumor behavior, stratifying risk, and personalizing therapy.

This research area is rapidly evolving and holds significant promise with regard to integrating imaging into other omics data, electronic health records (EHRs), and real-time clinical decision systems. It addresses critical gaps in oncology, such as improving early detection, assessing treatment efficacy, and predicting disease recurrence.

This Special Issue will bring together cutting-edge research that advances the integration of radiomics and deep learning in cancer imaging and foster translation from computational models to clinical applications.

We are pleased to invite you to contribute to this Special Issue of Cancers, "Deep Learning and Radiomics for Cancer Diagnosis, Staging, and Treatment Response". This Special Issue will present the latest advances in artificial intelligence, particularly the synergistic use of radiomics and deep learning, to improve diagnostic accuracy, staging precision, and treatment monitoring in oncology.

This topic is highly relevant to the scope of Cancers, which focuses on the clinical, translational, and basic science aspects of cancer research. Radiomics and deep learning are rapidly transforming cancer imaging by enabling the extraction of high-dimensional, quantitative biomarkers from standard imaging modalities such as CT, MRI, PET, and ultrasound. These approaches support early detection, risk stratification, therapy response assessment, and long-term outcome prediction, all of which align with the journal's focus on innovative methodologies that enhance clinical cancer management.

For this Special Issue, we welcome original research, technical advances, and comprehensive reviews that demonstrate scientific rigor, clinical relevance, and methodological innovation. Submissions involving multimodal integration (e.g., the integration of imaging into genomics or pathology), real-world validation, or explainable AI approaches are particularly encouraged.

This Special Issue will bring together cutting-edge research and comprehensive reviews that explore the integration of deep learning and radiomics into oncologic imaging, with the goal of enhancing cancer diagnosis, staging accuracy, and treatment response assessment.

We welcome the submission of original research articles, systematic reviews, and technical advances that contribute to the development, validation, and clinical translation of intelligent imaging-based solutions for cancer care.

Research areas may include, but are not limited to, the following:

• Radiomic feature extraction and selection for cancer characterization;
• Deep learning architectures for tumor detection, segmentation, and classification;
• Multimodal imaging analysis (e.g., PET/CT, MRI + clinical/genomic data integration);
• Prediction models for treatment response, recurrence, and survival;
• Longitudinal and real-world applications of AI in cancer imaging;
• Explainable and interpretable AI in radiology and oncology workflows;
• Federated learning and privacy-preserving AI in medical imaging;
• Standardization and reproducibility of radiomic pipelines;
• Integration of imaging biomarkers into electronic health records (EHRs);
• AI-based clinical decision support systems in oncology.

We particularly encourage contributions that include clinical validation, novel datasets, or interdisciplinary approaches that bridge imaging, oncology, and data science.

We look forward to receiving your valuable contributions and advancing the frontiers of AI-powered cancer imaging.

Dr. Mohamed Shehata
Prof. Dr. Mostafa Elhosseini
Dr. Mahmoud Badawy
Dr. Hanaa ZainEldin
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 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. Cancers 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 2900 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
• deep learning
• cancer imaging
• diagnosis
• staging
• treatment response
• machine learning
• medical image analysis
• precision oncology
• federated learning
• AI in healthcare