Artificial Intelligence in Cancer Diagnosis and Prognosis

Dear Colleagues,

Advances in digital technologies and artificial intelligence have enabled significant transformations in cancer diagnosis and prognosis. The increasing availability of high-resolution medical imaging, electronic health records, wearable devices and large-scale clinical databases has created an excellent environment for computational oncology. This further enables the integration of medical expertise with advanced algorithms, computing infrastructure and decision-support systems, enabling a new generation of intelligent diagnostic workflows.

Recent developments in machine learning, including deep learning, computer vision, natural language processing and signal processing, have significantly enhanced the capabilities of artificial intelligence in oncology. Today, these models are increasingly applied for tumor detection and classification as well as for grading, risk stratification, treatment response prediction and survival modeling. In particular, large multimodal models are a powerful tool in medicine, capable of integrating heterogeneous data sources into unified predictive and reasoning systems. Even with the evolution of artificial intelligence methods, important engineering and translational challenges remain. These challenges include problems with data heterogeneity, limited annotations, interpretability and explainability issues, robustness to noise and bias and the scalability of training pipelines. Addressing these challenges requires interdisciplinary research combining algorithmic innovation, system-level engineering and rigorous clinical validation.

This Special Issue welcomes submissions of recent original research articles and reviews presenting novel methodologies, computational frameworks, experimental studies, and real-world applications of artificial intelligence in cancer care.

Recommended topics include, but are not limited to, the following:

• Artificial intelligence methods for cancer detection, classification and grading
• Computational pathology and digital cytology
• Physiological signal analysis in oncology (e.g., ECG, wearable data)
• Large multimodal models in medicine
• Multimodal data fusion for precision oncology
• Survival analysis and risk stratification using machine learning
• Weakly supervised, self-supervised and foundation models
• Explainable and trustworthy AI in oncology
• Uncertainty quantification and robustness evaluation
• Federated learning and privacy-preserving artificial intelligence
• Artificial intelligence applications in clinical decision-support systems
• Gigapixel image processing in whole-slide imaging
• Patch-based and multi-scale learning strategies for WSI
• Slide-level aggregation and multiple instance learning
• Automated grading and malignancy assessment in digital pathology
• Fine-needle aspiration cytology classification and malignancy prediction
• Nuclear and cellular morphology quantification in cytological images
• Hybrid CNN–Transformer architectures for pathology and cytology
• Weakly supervised learning for slide- and patient-level prediction
• Integration of WSI and FNA data with radiology and clinical records
• Explainable AI for histopathological and cytological decision support
• Domain adaptation across laboratories and staining protocols
• Efficient model training and compression for large pathology datasets
• Quantum machine learning for cancer diagnosis and prognosis
• High-performance and quantum-ready computing pipelines for oncology

Dr. Lukasz Jelen
Prof. Dr. Michał Jeleń
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 250 words) can be sent to the Editorial Office for assessment.

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-anonymized peer-review process. A guide for authors and other relevant information for submission of manuscripts is available on the Instructions for Authors page. Applied Sciences 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 2400 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.

• artificial intelligence
• deep learning
• medical image analysis
• whole-slide imaging
• digital pathology
• multiple instance learning
• large multimodal models
• multimodal data fusion
• federated learning
• high-performance computing