Synthetic radiographs, including OpenAI’s ChatGPT-generated ones, are not easily distinguishable from authentic radiographs by either radiologists or large language models; physician training and dedicated tools are crucial to mitigate risks.
Recently, there has been tremendous interest on the use of large language models (LLMs) in radiology. LLMs have been employed for various applications in cancer imaging, including improving reporting speed and accuracy via generation of standardized reports, automating the classification and staging of abnormal findings in reports, incorporating appropriate guidelines, and calculating individualized risk scores. Another use of LLMs is their ability to improve patient comprehension of imaging reports with simplification of the medical terms and possible translations to multiple languages. Additional future applications of LLMs include multidisciplinary tumor board standardizations, aiding patient management, and preventing and predicting adverse events (contrast allergies, MRI contraindications) and cancer imaging research. However, limitations such as hallucinations and variable performances could present obstacles to widespread clinical implementation. Herein, we present a review of the current and future applications of LLMs in cancer imaging, as well as pitfalls and limitations.
There is a growing interest in portable MRI (pMRI) systems for point-of-care imaging, particularly in remote or resource-constrained environments. However, the computational complexity of pMRI, especially in image reconstruction and machine learning (ML) algorithms for enhanced imaging, presents significant challenges. Such challenges can be potentially addressed by harnessing hardware application solutions, though there is little focus in the current pMRI literature on hardware acceleration. This paper bridges that gap by reviewing recent developments in pMRI, emphasizing the role and impact of hardware acceleration to speed up image acquisition and reconstruction. Key technologies such as Graphics Processing Units (GPUs), Field-Programmable Gate Arrays (FPGAs), and Application-Specific Integrated Circuits (ASICs) offer excellent performance in terms of reconstruction speed and power consumption. This review also highlights the promise of AI-powered reconstruction, open low-field pMRI datasets, and innovative edge-based hardware solutions for the future of pMRI technology. Overall, hardware acceleration can enhance image quality, reduce power consumption, and increase portability for next-generation pMRI technology. To accelerate reproducible AI for portable MRI, we propose forming a Low-Field MRI Consortium and an evidence ladder (analytic/phantom validation, retrospective multi-center testing, prospective reader and non-inferiority trials) to provide standardized datasets, benchmarks, and regulator-ready testbeds.
The large language models ChatGPT-o1 and Gemini-2.5-Pro, guided with Oncologically Relevant Findings Reporting and Data System (ONCO-RADS) prompts, accurately extracted and classified incidental findings from whole-body imaging reports and outperformed these strategies without ONCO-RADS prompts and the medical named entity recognition model.