The integration of Artificial Intelligence (AI) into oncology is transforming cancer care, offering a new frontier in early detection, diagnosis, treatment planning, patient monitoring and drug discovery. With the increasing complexity of cancer and the exponential growth of healthcare data, traditional approaches are often insufficient to provide timely and accurate decisions. Emerging AI technologies – ranging from deep learning and natural language processing to radiomics and AI-assisted genomics – are now enabling a more data-driven, precise and personalized approach to cancer management. This chapter explores how cutting-edge AI technologies are reshaping every stage of the cancer care continuum. In diagnostics, AI models demonstrate expert-level performance in interpreting medical imaging, histopathology slides and genomic data. In treatment, AI supports oncologists in developing personalized protocols, predicting treatment responses and minimizing adverse effects. AI is also revolutionizing drug discovery by identifying novel compounds and accelerating clinical trials through patient matching algorithms. Furthermore, AI-driven virtual assistants and wearable-integrated monitoring systems are empowering patients, enhancing communication and reducing hospital readmissions. Despite these advancements, challenges such as algorithmic bias, data privacy concerns, lack of transparency and the need for clinical validation hinder full-scale integration. The ethical implications of decision-making automation and the trustworthiness of AI systems remain key concerns. Nonetheless, the future of AI in oncology is promising, driven by continued innovation, interdisciplinary collaboration and regulatory evolution. This chapter presents a comprehensive overview of current and emerging AI applications in cancer care, critically analyzing their potential, limitations and the roadmap ahead. Cancer remains one of the most formidable health challenges of the 21st century, accounting for nearly 10 million deaths annually, according to the World Health Organization (WHO) (Ibraheem et al. 2025). Its rising incidence, coupled with the increasing complexity of diagnosis and treatment, demands continual innovation in medical research and clinical practices. While traditional diagnostic and therapeutic approaches have improved survival rates over the decades, they often struggle to accommodate the vast heterogeneity of cancer across different individuals. Factors such as tumor biology, genetic mutations and variable responses to treatment make one-size-fits-all strategies ineffective for many patients. Recent years have witnessed a dramatic surge in the use of Artificial Intelligence (AI) to tackle these challenges (Bohr and Memarzadeh 2020). AI technologies – particularly those powered by machine learning (ML), deep learning (DL) and natural language processing (NLP) – are rapidly transforming the oncology landscape. These tools are designed to replicate human cognitive functions such as learning, reasoning, pattern recognition and decision-making. Crucially, AI systems can analyze vast and complex datasets – including imaging studies, histopathological slides, genomic sequences, clinical notes and electronic health records (EHRs) – with a level of speed, accuracy and scalability that exceeds traditional methods. The convergence of AI and oncology is facilitating a shift toward precision medicine, where diagnostics and treatments are tailored to the individual characteristics of each patient (Sherani et al. 2024). AI models can now assist in the early detection of tumors, automate image analysis, predict therapeutic responses, monitor treatment outcomes and even support drug discovery efforts. These innovations promise to enhance clinical decision-making, reduce diagnostic errors and improve patient outcomes. This chapter explores the cutting-edge AI technologies that are shaping the future of cancer care. It examines their applications across the entire cancer care continuum – from prevention and diagnosis to treatment and follow-up – while also discussing the associated challenges, ethical considerations and the roadmap for integration into mainstream clinical practice (Mao et al. 2022). Through this comprehensive review, this chapter underscores the transformative potential of AI in achieving more accurate, efficient and personalized oncology care. Early detection of cancer significantly improves treatment outcomes and survival rates. However, conventional diagnostic methods often rely heavily on subjective interpretation, which may lead to variability in assessments and delayed diagnoses (Pascoal et al. 2022). Emerging AI technologies, particularly those based on machine learning and deep learning, have demonstrated remarkable potential in enhancing the precision, speed and consistency of cancer detection. AI can process vast amounts of clinical and imaging data to identify subtle patterns indicative of malignancy – patterns often invisible to the human eye. Medical imaging modalities such as computed tomography (CT), magnetic resonance imaging (MRI), positron emission tomography (PET) and mammography are foundational tools in oncology (Grueneisen et al. 2015) Traditionally, radiologists interpret these images manually, but AI has brought transformative advancements in this domain. Deep learning, especially through convolutional neural networks (CNNs), has enabled the development of highly accurate image analysis systems. These models learn from thousands of annotated images to identify tumors, assess tumor size and shape, and even distinguish between cancerous and non-cancerous lesions. One landmark achievement came from Google Health’s AI model, which was trained on over 90,000 mammograms (Daraghmeh 2024). The system not only matched but, in some cases, surpassed expert radiologists in detecting breast cancer, reducing both false positives and false negatives. Similar approaches are being applied to lung, prostate and brain cancer screening. These models continue to improve through federated learning and transfer learning strategies, which allow algorithms to learn from diverse, decentralized datasets without compromising patient privacy. Radiomics is the process of extracting high-dimensional quantitative features from medical images, including texture, shape and intensity, which can be correlated with genetic markers and clinical outcomes. When combined with AI, radiomic analysis provides a non-invasive method to characterize tumors at a molecular level. AI-driven radiomics enables: These techniques are particularly valuable in monitoring tumor heterogeneity and evolution over time, offering a new layer of diagnostic insight beyond conventional radiology (Hussain et al. 2024). Histopathological analysis remains the gold standard for cancer diagnosis, involving the microscopic examination of tissue samples. However, manual slide review is time-consuming and subject to intra- and inter-observer variability. AI solutions are now being developed to address these challenges by digitizing and analyzing pathology slides using deep learning algorithms. AI can: In comparative studies, AI algorithms have achieved sensitivity and specificity levels comparable to (or exceeding) human pathologists, particularly in detecting breast, prostate and skin cancers (Rai et al. 2024). One notable example is Lunit INSIGHT, an AI-based pathology solution that analyzes digital histopathology images. It can detect tumor-infiltrating lymphocytes in breast cancer samples – a critical marker for immune response and a predictor of response to immunotherapy. The system supports oncologists by offering quantifiable, reproducible metrics that inform prognosis and treatment planning. Lunit’s tools have been integrated into clinical trials and research studies, demonstrating significant time savings and enhanced diagnostic precision. Moreover, the explainability feature in its platform allows clinicians to understand and trust the AI-generated results, promoting clinical adoption. The emergence of genomics has revolutionized our understanding of cancer as a molecular disease rather than merely a histological anomaly (Bell 2010). Cancer is driven by complex genetic mutations that vary significantly across individuals. The ability to decode the human genome, especially through next-generation sequencing (NGS), has created a deluge of data – offering unprecedented opportunities for individualized cancer care. However, this wealth of data exceeds the analytic capabilities of traditional bioinformatics tools. AI technologies are now stepping in to bridge this gap by rapidly processing, interpreting and translating genomic information into actionable clinical insights. Next-generation sequencing technologies have unlocked access to detailed genetic profiles of cancer patients, identifying single nucleotide polymorphisms (SNPs), copy number variations, gene fusions and other mutations (Krubaa et al. 2024). AI, particularly machine learning algorithms, plays a crucial role in sifting through these massive datasets to uncover meaningful patterns that may indicate cancer subtypes, disease progression or treatment responsiveness. Personalized medicine – or precision oncology – is the tailoring of medical treatment to the individual characteristics of each patient (Jiang and Wang 2010). AI is instrumental in integrating diverse data types – such as genomic, transcriptomic, proteomic, radiologic and clinical data – to create a comprehensive patient profile. AI platforms can evaluate the genomic alterations in a patient’s tumor and cross-reference this information with vast biomedical literature, clinical trial data and treatment guidelines to recommend targeted therapies. For example: These tools are improving treatment efficacy, minimizing adverse reactions and reducing the trial-and-error approach historically common in oncology. Modern AI systems can also draw on EHRs to contextualize genomic data with a patient’s history, co-morbidities and past responses to treatment. This creates a feedback loop where clinical outcomes continuously inform and refine AI models, enhancing predictive accuracy over time. Effective cancer treatment requires a highly individualized approach due to the diverse biological behavior of tumors and varied patient responses. Artificial Intelligence (AI) is increasingly being integrated into oncologic treatment planning to enhance precision, reduce clinician workload and improve clinical outcomes (Dlamini et al. 2020). From radiotherapy to chemotherapy and immunotherapy, AI tools are transforming how treatment protocols are designed, optimized and administered. Radiation therapy is a cornerstone of cancer treatment, used in approximately 50% of all cancer cases. However, the planning process is complex, requiring accurate delineation of tumors and surrounding organs-at-risk (OARs), dose distribution calculations and consideration of tissue tolerance. AI-driven systems, particularly those using deep learning, are significantly improving radiotherapy workflows by: One of the most notable AI contributions is auto-segmentation – the use of convolutional neural networks (CNNs) to delineate tumor boundaries and critical structures on imaging scans such as CT and MRI (Kalantar et al. 2021).
13
Emerging AI Technologies Shaping the Future of Cancer Care
13.1. Introduction
13.2. AI in early detection and diagnosis
13.2.1. Imaging-based diagnostics
13.2.1.1. Deep learning in radiology
13.2.1.2. Radiomics
13.2.2. Pathology and histology
13.2.3. AI-powered histopathology
13.2.4. Case study: Lunit INSIGHT
13.3. AI in genomics and precision medicine
13.3.1. AI-driven genomic analysis
13.3.2. Applications of AI in genomic oncology
13.3.3. Personalized medicine
13.3.4. AI-powered therapeutic decision support
13.3.5. Integration with electronic health records
13.4. AI in treatment planning and optimization
13.4.1. Radiotherapy
13.4.2. AI-enhanced treatment planning
13.4.3. Auto-segmentation
Related posts:
AI-driven Imaging in Oncology and Physiotherapy: A Game-changer in Diagnostics
AI-enhanced Virtual Rehabilitation: The Future of Cancer Recovery
Integrating AI with Physiotherapy to Improve Quality of Life for Cancer Patients
Personalized AI-based Exercise Therapy for Oncology and Physiotherapy Patients
AI-driven Innovations in Biomaterial-based Physiotherapy and Oncology: Personalizing Patient Care Through Intelligent Monitoring and Predictive Rehabilitation
Enhancing Health Data Security and Intelligence with Blockchain and Artificial Intelligence
Stay updated, free articles. Join our Telegram channel
Full access? Get Clinical Tree
