Vision-Based ChatGPT Shows Deficits Interpreting Radiologic Images

Researchers evaluating the performance of ChatGPT-4 Vision found that the model performed well on text-based radiology exam questions but struggled to answer image-related questions accurately. The study's results were published today in Radiology, a journal of the Radiological Society of North America (RSNA).

Chat GPT-4 Vision is the first version of the large language model that can interpret both text and images.

"ChatGPT-4 has shown promise for assisting radiologists in tasks such as simplifying patient-facing radiology reports and identifying the appropriate protocol for imaging exams," said Chad Klochko, M.D., musculoskeletal radiologist and artificial intelligence (AI) researcher at Henry Ford Health in Detroit, Michigan. "With image processing capabilities, GPT-4 Vision allows for new potential applications in radiology."

For the study, Dr. Klochko’s research team used retired questions from the American College of Radiology’s Diagnostic Radiology In-Training Examinations, a series of tests used to benchmark the progress of radiology residents. After excluding duplicates, the researchers used 377 questions across 13 domains, including 195 questions that were text-only and 182 that contained an image.

GPT-4 Vision answered 246 of the 377 questions correctly, achieving an overall score of 65.3%. The model correctly answered 81.5% (159) of the 195 text-only queries and 47.8% (87) of the 182 questions with images.

"The 81.5% accuracy for text-only questions mirrors the performance of the model’s predecessor," he said. "This consistency on text-based questions may suggest that the model has a degree of textual understanding in radiology."

Genitourinary radiology was the only subspecialty for which GPT-4 Vision performed better on questions with images (67%, or 10 of 15) than text-only questions (57%, or 4 of 7). The model performed better on text-only questions in all other subspecialties.

The model performed best on image-based questions in the chest and genitourinary subspecialties, correctly answering 69% and 67% of the image-containing questions, respectively. The model performed lowest on image-containing questions in the nuclear medicine domain, correctly answering only 2 of 10 questions.

The study also evaluated the impact of various prompts on the performance of GPT-4 Vision.

  • Original: You are taking a radiology board exam. Images of the questions will be uploaded. Choose the correct answer for each question.
  • Basic: Choose the single best answer in the following retired radiology board exam question.
  • Short instruction: This is a retired radiology board exam question to gauge your medical knowledge. Choose the single best answer letter and do not provide any reasoning for your answer.
  • Long instruction: You are a board-certified diagnostic radiologist taking an examination. Evaluate each question carefully and if the question additionally contains an image, please evaluate the image carefully in order to answer the question. Your response must include a single best answer choice. Failure to provide an answer choice will count as incorrect.
  • Chain of thought: You are taking a retired board exam for research purposes. Given the provided image, think step by step for the provided question.

Although the model correctly answered 183 of 265 questions with a basic prompt, it declined to answer 120 questions, most of which contained an image.

"The phenomenon of declining to answer questions was something we hadn’t seen in our initial exploration of the model," Dr. Klochko said.

The short instruction prompt yielded the lowest accuracy (62.6%).

On text-based questions, chain-of-thought prompting outperformed long instruction by 6.1%, basic by 6.8%, and original prompting style by 8.9%. There was no evidence to suggest performance differences between any two prompts on image-based questions.

"Our study showed evidence of hallucinatory responses when interpreting image findings," Dr. Klochko said. "We noted an alarming tendency for the model to provide correct diagnoses based on incorrect image interpretations, which could have significant clinical implications."

Dr. Klochko said his study’s findings underscore the need for more specialized and rigorous evaluation methods to assess large language model performance in radiology tasks.

"Given the current challenges in accurately interpreting key radiologic images and the tendency for hallucinatory responses, the applicability of GPT-4 Vision in information-critical fields such as radiology is limited in its current state," he said.

Hayden N, Gilbert S, Poisson LM, Griffith B, Klochko C.
Performance of GPT-4 with Vision on Text- and Image-based ACR Diagnostic Radiology In-Training Examination Questions.
Radiology. 2024 Sep;312(3):e240153. doi: 10.1148/radiol.240153

Most Popular Now

Philips Foundation 2024 Annual Report: E…

Marking its tenth anniversary, Philips Foundation released its 2024 Annual Report, highlighting a year in which the Philips Foundation helped provide access to quality healthcare for 46.5 million people around...

New AI Transforms Radiology with Speed, …

A first-of-its-kind generative AI system, developed in-house at Northwestern Medicine, is revolutionizing radiology - boosting productivity, identifying life-threatening conditions in milliseconds and offering a breakthrough solution to the global radiologist...

Scientists Argue for More FDA Oversight …

An agile, transparent, and ethics-driven oversight system is needed for the U.S. Food and Drug Administration (FDA) to balance innovation with patient safety when it comes to artificial intelligence-driven medical...

New Research Finds Specific Learning Str…

If data used to train artificial intelligence models for medical applications, such as hospitals across the Greater Toronto Area, differs from the real-world data, it could lead to patient harm...

Giving Doctors an AI-Powered Head Start …

Detection of melanoma and a range of other skin diseases will be faster and more accurate with a new artificial intelligence (AI) powered tool that analyses multiple imaging types simultaneously...

AI Agents for Oncology

Clinical decision-making in oncology is challenging and requires the analysis of various data types - from medical imaging and genetic information to patient records and treatment guidelines. To effectively support...

Patients say "Yes..ish" to the…

As artificial intelligence (AI) continues to be integrated in healthcare, a new multinational study involving Aarhus University sheds light on how dental patients really feel about its growing role in...

Brains vs. Bytes: Study Compares Diagnos…

A University of Maine study compared how well artificial intelligence (AI) models and human clinicians handled complex or sensitive medical cases. The study published in the Journal of Health Organization...

'AI Scientist' Suggests Combin…

An 'AI scientist', working in collaboration with human scientists, has found that combinations of cheap and safe drugs - used to treat conditions such as high cholesterol and alcohol dependence...

Start-ups in the Spotlight at MEDICA 202…

17 - 20 November 2025, Düsseldorf, Germany. MEDICA, the leading international trade fair and platform for healthcare innovations, will once again confirm its position as the world's number one hotspot for...