AI Transforms Global Cancer Care with New Tech

This initiative aims to standardize CT-based contouring, addressing the inherent limitations of CT tissue contrast compared to MRI. The integration of AI is expected to significantly improve the accuracy and consistency of treatment planning.

This significant constraint impacts the precision of radiotherapy for prostate cancer patients. AI solutions are being explored to bridge this gap, aiming to provide comprehensive treatment planning even when MRI information is scarce.

This effort involved radiation oncologists and medical physicists from various anchor centers. The primary goal is to create standardized guidelines that can be implemented effectively in low- and middle-income countries, fostering consistency in treatment approaches.

Kazakhstan has seen a significant increase in its radiation medicine infrastructure, with 10 nuclear medicine centers operational by 2026. This expansion includes 17 PET scanners, five production sites, and 29 linear accelerators. This growth represents a massive scale-up of national capacity in radiation medicine from 2010 to 2026.

Kazakhstan's National Research Oncology Center (NROC) operates as a full-cycle platform, integrating advanced radiotherapy with theranostics. The country launched the first proton therapy center in Central Asia in 2025, treating over 150 patients since its inception. NROC also produces FDG and plans to introduce 10 more radiopharmaceuticals within five years, solidifying its role in advanced cancer treatment.

Kazakhstan plans to strengthen radiation medicine across Central Asia over the next five years, with support from the IAEA. The IAEA signed a three-year practical arrangement in May 2026 to coordinate cancer care in the region. The initiative focuses on standardization, education, and expert support, aiming to prevent errors in equipment launching for new centers.

Malnutrition is identified as a contributing factor, leading to chemotherapy intolerance and increased infection risk. Traditional metrics like BMI are often insufficient to capture critical changes in body composition.

Children with cancer often experience a lag in nutritional recovery despite clinical improvements after treatment. While they require 10-20% more energy, their consumption often falls by 40-60%. Nutritional deficits can persist for up to 12 months post-treatment, with lean muscle mass loss being a major concern for long-term health. Studies show that even 10 years after treatment, survivors exhibit altered body composition and excess adiposity, highlighting a need for sustained nutritional support.

Radiation therapy has advanced significantly, moving from simple beams to complex arc therapy and achieving sub-millimeter accuracy. The introduction of hybrid machines, such as CT-MRI Linacs, represents a major technological shift. AI is now being utilized for auto-segmentation, dose distribution, and toxicity modeling, enabling adaptive radiation therapy with daily plan adjustments based on scans.

This technological capability allows for a more focused and intense treatment, drawing comparisons to single-session surgical procedures. The goal is to maximize therapeutic effect while minimizing patient visits.

This innovative approach is believed to enable safe dose escalation, significantly reducing treatment times while sparing healthy tissues. The technology holds promise for revolutionizing the efficiency and safety of radiation therapy.

Artificial intelligence is expanding its role in medicine beyond classification and diagnosis, moving towards predictive capabilities based on multimodal data. This includes combining imaging data with genetic expression and biopsy results. In breast cancer, this approach allows for personalized therapy predictions, potentially sparing patients from unnecessary surgeries or ineffective chemotherapy by tailoring treatments to individual profiles.

SingHealth has established four campus-based innovation centers across its healthcare campuses, supported by a $50 million philanthropic donation. These centers foster collaborations between clinicians, industrial partners, and academic institutions. The primary goal is to translate research findings directly into clinical practice, ensuring that innovations have a tangible impact on patient care.

Overcoming this requires robust infrastructure, well-trained staff, and adherence to GMP (Good Manufacturing Practice) quality assurance. National and regional programs, alongside the integration of public universities and delivery systems, are crucial for successfully translating innovative ideas into clinical practice.

The production of alpha-particle emitting radionuclides is concentrated in the Global North, specifically North America, Europe, and the Asia-Pacific region (China, Korea, Japan, and Australia). Africa and Latin America currently lack any production sites for these critical components. This geographic inequity raises concerns about fair access to emerging theranostics technology in oncology.

Manual contouring in radiotherapy is both time-consuming and highly variable among clinicians. AI implementation offers a solution by standardizing the contouring process, which significantly reduces inter-observer variability. This not only enhances consistency but also saves valuable time for clinical teams, allowing them to focus on other critical aspects of patient care.

AI is actively used in clinical settings, with doctors employing it to enhance patient outcomes. Evidence supports improved surgical accuracy and longer survival times, showing AI's tangible benefits. It contributes to earlier cancer detection and reduces unnecessary biopsies, validating its clinical introduction for evidence-based practice.

Academic medicine provides a comprehensive model to integrate research, education, and clinical care. The 'triple threat' clinician, adept at delivering outstanding clinical care, educating the next generation, and conducting groundbreaking research, is central to this approach. This model aims to cultivate a supportive culture and system, foundational for advancing future patient care through human capital and institutional belief.

Several challenges impede the implementation of AI tools in clinical care, including strained IT infrastructure and departmental resources. Workflow integration is another hurdle, as adapting existing processes to accommodate new technology can cause operational slowdowns. Furthermore, the representativeness and potential bias of data are critical concerns, necessitating global validation projects, such as the IAEA's Sora project, to ensure the reliability of AI solutions. Addressing these issues requires comprehensive planning and support.

Successful integration requires training the entire team and the broader ecosystem involved in patient care. Additionally, aligning incentive systems, including financial remuneration, is essential to minimize resistance and foster widespread acceptance of these transformative technologies.