Search research articles

ABOUT JoVE

Overview Leadership Blog JoVE Help Center

AUTHORS

Publishing Process Editorial Board Scope & Policies Peer Review FAQ Submit

LIBRARIANS

Testimonials Subscriptions Access Resources Library Advisory Board FAQ

RESEARCH

JoVE Journal Methods Collections JoVE Encyclopedia of Experiments Archive

EDUCATION

JoVE Core JoVE Business JoVE Science Education JoVE Lab Manual Faculty Resource Center Faculty Site

Terms & Conditions of Use

Related Concept Videos

Positron Emission Tomography

Positron Emission Tomography

Positron emission tomography (PET) is a medical imaging technique involving radiopharmaceuticals — substances that emit short-lived radiation. Although the first PET scanner was introduced in 1961, it took 15 more years before radiopharmaceuticals were combined with the technique and revolutionized its potential.
One of the main requirements of a PET scan is a positron-emitting radioisotope, which is produced in a cyclotron and then attached to a substance used by the part of the body...

You might also read

Related Articles

Articles linked to this work by shared authors, journal, and citation graph.

Sort by

Same author

Proton Beam Therapy for Testicular Seminoma: Clinical Outcomes and Toxicity From the Proton Collaborative Group Prospective Registry.

Cureus·2026

Same author

Aperture-collimated proton LATTICE radiotherapy with a GRID-like entrance pattern: a compact and robust delivery strategy.

Physics in medicine and biology·2026

Same author

Modern proton therapy in prostate cancer: precision in practice.

Frontiers in oncology·2026

Same author

Novel use of peak optimized particle therapy for the delivery of three-dimensional spatially fractionated radiotherapy.

Frontiers in oncology·2026

Same author

Feasibility and Outcomes of Perirectal Spacer Implantation in Previously Treated Prostate Cancer Patients Undergoing Salvage Proton Therapy Radiation.

Advances in radiation oncology·2026

Same author

Pencil beam scanning proton lattice radiotherapy: single-field versus multi-field optimization.

Frontiers in oncology·2026

Search research articles

Related Experiment Video

Updated: Jan 8, 2026

Author Spotlight: Improving Radiation Therapy Access with Radiation Planning Assistant

Author Spotlight: Improving Radiation Therapy Access with Radiation Planning Assistant

Published on: October 6, 2023

ChatGPT Versus DeepSeek: Assessing Artificial Intelligence Performance on Radiation Oncology Examination Questions.

Ronald Chow^1,2,3, Ajay Zheng¹, Chenxi Gao¹

¹Department of Radiation Oncology, New York Proton Center, New York, New York.

Advances in Radiation Oncology

|December 17, 2025

Summary

DeepSeek-R1, a new large language model, shows lower accuracy and slower response times than ChatGPT for medical questions. Despite being more cost-effective, its medical accuracy requires careful evaluation before clinical use.

More Related Videos

Positron Emission Tomography-based Dose Painting Radiation Therapy in a Glioblastoma Rat Model using the Small Animal Radiation Research Platform

Positron Emission Tomography-based Dose Painting Radiation Therapy in a Glioblastoma Rat Model using the Small Animal Radiation Research Platform

Published on: March 24, 2022

Detection and Isolation of Cancer in Prostate Biopsies Using Stimulated Raman Histology and Artificial Intelligence

Detection and Isolation of Cancer in Prostate Biopsies Using Stimulated Raman Histology and Artificial Intelligence

Published on: June 10, 2025

Related Experiment Videos

Last Updated: Jan 8, 2026

Author Spotlight: Improving Radiation Therapy Access with Radiation Planning Assistant

Author Spotlight: Improving Radiation Therapy Access with Radiation Planning Assistant

Published on: October 6, 2023

Positron Emission Tomography-based Dose Painting Radiation Therapy in a Glioblastoma Rat Model using the Small Animal Radiation Research Platform

Positron Emission Tomography-based Dose Painting Radiation Therapy in a Glioblastoma Rat Model using the Small Animal Radiation Research Platform

Published on: March 24, 2022

Detection and Isolation of Cancer in Prostate Biopsies Using Stimulated Raman Histology and Artificial Intelligence

Detection and Isolation of Cancer in Prostate Biopsies Using Stimulated Raman Histology and Artificial Intelligence

Published on: June 10, 2025

Area of Science:

Artificial Intelligence in Medicine
Natural Language Processing
Medical Education Technology

Background:

Large language models (LLMs) are increasingly evaluated for medical question-answering capabilities.
The performance of the newly released DeepSeek LLM in the medical domain remains unassessed.
This study marks the first evaluation of DeepSeek's accuracy for medical inquiries.

Purpose of the Study:

To assess the medical accuracy of the DeepSeek-R1 large language model.
To compare DeepSeek-R1's performance against ChatGPT on radiation oncology examination questions.
To evaluate response time, token usage, and cost-effectiveness of both LLMs.

Main Methods:

600 radiation oncology multiple-choice questions were used to test DeepSeek-R1 and ChatGPT.
Accuracy, prompt/completion tokens, and run time were recorded for each model.
Performance was analyzed across question categories, with a Type I error rate of 0.05.

Main Results:

DeepSeek-R1 achieved 84.0% accuracy (59s/question), with lower performance on landmark studies (74.2%).
ChatGPT o1 achieved 89.0% accuracy (10s/question), with high accuracy on landmark studies (93.5%).
DeepSeek-R1 was more costly per token but significantly cheaper overall ($1.56 vs $37.96 at Feb 2025 prices).

Conclusions:

DeepSeek-R1 is less accurate and slower than ChatGPT o1 but substantially more cost-effective.
The choice between models requires balancing accuracy and efficiency goals against financial considerations.
Further analysis is needed to determine the optimal implementation of these LLMs in medical contexts.