Deep learning-driven diagnostic support in oncological medical imaging: mobile and web health applications

Artificial intelligence, particularly deep learning, has significantly transformed oncological medical imaging by improving the accuracy, efficiency, and reproducibility of disease detection, segmentation, classification, and prognosis across multiple imaging modalities, including magnetic resonance imaging (MRI), computed tomography (CT), ultrasound, histopathology, mammography, thermography, and colposcopy. Simultaneously, advances in mobile health (mHealth) and web-based health platforms have created new opportunities to deliver intelligent diagnostic support beyond specialized clinical settings, facilitating remote screening, telemedicine, and personalized patient care. Despite these advances, important challenges remain regarding model generalizability, explainability, multimodal data integration, clinical validation, interoperability, cybersecurity, regulatory compliance, and equitable deployment in real-world healthcare environments. Addressing these challenges is essential to translate deep learning innovations into trustworthy, scalable, and clinically impactful diagnostic solutions for cancer prevention, early detection, treatment planning, and longitudinal patient monitoring.This Research Topic aims to provide a multidisciplinary forum for presenting recent advances in deep learning-driven diagnostic support systems for oncology, with particular emphasis on mobile and web health applications that enhance accessibility, clinical decision-making, and patient-centered care. We seek contributions that develop, validate, and translate artificial intelligence models capable of supporting clinicians throughout the oncological care pathway, from early screening and diagnosis to prognosis, treatment response assessment, and follow-up.This Research Topic welcomes high-quality submissions covering, but not limited to, deep learning methods for cancer detection, segmentation, classification, prognosis, radiomics, digital pathology, multimodal medical imaging, image reconstruction, image enhancement, explainable AI, uncertainty quantification, federated learning, privacy-preserving AI, synthetic data generation, foundation models, vision-language models, mobile health applications, web-based diagnostic platforms, cloud and edge computing, tele-oncology, wearable sensing technologies, clinical workflow integration, healthcare interoperability, cybersecurity, validation studies, and regulatory frameworks for AI-enabled medical devices.We invite Original Research Articles, Systematic Reviews, Meta-Analyses, Clinical Studies, Methods, Technology Reports, Case Studies, Perspectives, and Mini Reviews that demonstrate methodological innovation, clinical relevance, technical robustness, and translational potential. Interdisciplinary contributions from researchers, clinicians, engineers, computer scientists, and healthcare professionals are strongly encouraged. Topic editors: Yuliana Jiménez-Gaona, Vasudevan Lakshminarayanan Source: https://www.frontiersin.org/research-topics/84085/deep-learning-driven-diagnostic-support-in-oncological-medical-imaging-mobile-and-web-health-applications