Large multimodal foundation model for radiation oncology

Large multimodal foundation model for radiation oncology. Image courtesy of Chenbin Liu


December 20, 2023 — An estimated 600,000 people in the United States succumb to cancer every year. Beyond surgery, chemotherapy, and immunotherapy, radiotherapy has shown to be a  standard and effective treatment option for nearly 50-70 percent of cancer patients.

Radiotherapy treatment involves six basic stages: initial consultation, simulation, treatment planning, treatment delivery, treatment verification and patient follow-up. With the emergence of Artificial intelligence (AI), radiotherapy is undergoing substantial transformation. AI achieves human-level accuracy in the auto-segmentation, tumor staging, image registration, automatic treatment planning, quality assurance and outcomes prediction, which greatly improves the accuracy, precision, and efficiency of radiation therapy.

According to a recent review published in the KeAi journal Meta-Radiology, pioneering AGI models, such as GPT-4 and PaLM 2, along with large vision models (LVMs) like the Segment Anything Model (SAM), are capable of processing extensive texts and imaging data, respectively. AGI, distinguished by its advanced capabilities in few-shot and zero-shot learning, offers a pathway towards developing highly robust and generalizable AI models. These models are imperative for seamless and effective integration into the various facets of radiation oncology.

They found that the fusion of vision data with LLMs also creates powerful multimodal models that elucidate nuanced clinical patterns. Together, AGI has the potential to catalyze a shift towards data-driven, personalized radiation therapy. The authors stressed that these models should complement human expertise and care.

The findings provide an overview of how AGI can transform radiation oncology to elevate the standard of patient care, with the key insight being AGI’s ability to exploit multimodal clinical data at scale. In addition, the researchers explore the future directions of AGI in radiation oncology and discuss potential developments and bottlenecks in this field. These advancements in clinical applications will further enhance the effectiveness of radiation therapy, bringing more positive outcomes for cancer patients.

For more information: https://www.mayoclinic.org/


Related Content

Feature | Breast Imaging

Despite decades of progress in breast imaging, one challenge continues to test even the most skilled radiologists ...

Time October 24, 2025
arrow
Feature | Kyle Hardner

Radiotherapy contributes to about 40% of all cancer cures but still lags behind systemic therapy in funding and ...

Time October 21, 2025
arrow
News | Contrast Media

Oct. 21, 2025 — Subtle Medical, Inc., a provider of AI-powered medical imaging solutions, has announced positive ...

Time October 21, 2025
arrow
News | Artificial Intelligence

Oct. 20, 2025 — Viz.ai has launched of Viz Assist, a suite of autonomous AI agents that significantly enhance how care ...

Time October 20, 2025
arrow
News | CT Angiography (CTA)

Oct. 9, 2025 — RapidAI recently announced that its Lumina 3D built on the Rapid Enterprise Platform has been named to ...

Time October 16, 2025
arrow
News | Point-of-Care Ultrasound (POCUS)

Oct. 15, 2025 — GE HealthCare has announced the latest advancement in its Venue family of point-of-care ultrasound ...

Time October 16, 2025
arrow
News | RSNA 2025

Oct. 7, 2025 — RSNA Ventures, a mission-aligned subsidiary of Radiological Society of North America (RSNA), has ...

Time October 08, 2025
arrow
News | RSNA 2025

Oct. 7, 2025 – Clairity Inc., a leader in AI-based breast cancer risk prediction, will make five scientific ...

Time October 07, 2025
arrow
News | Magnetic Resonance Imaging (MRI)

Oct. 6, 2025 — Hyperfine, Inc. has launched the Portable Ultra-Low-Field Scientific Exchange (PULSE), a subscription ...

Time October 06, 2025
arrow
News | Mammography

Sept. 26, 2025 — Data from two groundbreaking studies evaluating the performance of Hologic’s artificial intelligence ...

Time October 02, 2025
arrow
Subscribe Now