Uncategorized

Artificial general intelligence for radiation


LARGE MULTIMODAL FOUNDATION MODELS FOR RADIATION ONCOLOGY

image: 

LARGE MULTIMODAL FOUNDATION MODELS FOR RADIATION ONCOLOGY


view more 

Credit: CHENBIN LIU

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.

###

Contact the author: Wei Liu, Department of Radiation Oncology, Mayo Clinic, [email protected]

The publisher KeAi was established by Elsevier and China Science Publishing & Media Ltd to unfold quality research globally. In 2013, our focus shifted to open access publishing. We now proudly publish more than 100 world-class, open access, English language journals, spanning all scientific disciplines. Many of these are titles we publish in partnership with prestigious societies and academic institutions, such as the National Natural Science Foundation of China (NSFC).

 


Disclaimer: AAAS and EurekAlert! are not responsible for the accuracy of news releases posted to EurekAlert! by contributing institutions or for the use of any information through the EurekAlert system.



Source link

Leave a Reply

Your email address will not be published. Required fields are marked *