Evaluating GPT-V4 (GPT-4 with Vision) on Detection of Radiologic Findings on Chest Radiographs.

Background Generating radiologic findings from chest radiographs is pivotal in medical image analysis. The emergence of OpenAI's generative pretrained transformer, GPT-4 with vision (GPT-4V), has opened new perspectives on the potential for automated image-text pair generation. However, the application of GPT-4V to real-world chest radiography is yet to be thoroughly examined. Purpose To investigate the capability of GPT-4V to generate radiologic findings from real-world chest radiographs. Materials and Methods In this retrospective study, 100 chest radiographs with free-text radiology reports were annotated by a cohort of radiologists, two attending physicians and three residents, to establish a reference standard. Of 100 chest radiographs, 50 were randomly selected from the National Institutes of Health (NIH) chest radiographic data set, and 50 were randomly selected from the Medical Imaging and Data Resource Center (MIDRC). The performance of GPT-4V at detecting imaging findings from each chest radiograph was assessed in the zero-shot setting (where it operates without prior examples) and few-shot setting (where it operates with two examples). Its outcomes were compared with the reference standard with regards to clinical conditions and their corresponding codes in the International Statistical Classification of Diseases, Tenth Revision (ICD-10), including the anatomic location (hereafter, laterality). Results In the zero-shot setting, in the task of detecting ICD-10 codes alone, GPT-4V attained an average positive predictive value (PPV) of 12.3%, average true-positive rate (TPR) of 5.8%, and average F1 score of 7.3% on the NIH data set, and an average PPV of 25.0%, average TPR of 16.8%, and average F1 score of 18.2% on the MIDRC data set. When both the ICD-10 codes and their corresponding laterality were considered, GPT-4V produced an average PPV of 7.8%, average TPR of 3.5%, and average F1 score of 4.5% on the NIH data set, and an average PPV of 10.9%, average TPR of 4.9%, and average F1 score of 6.4% on the MIDRC data set. With few-shot learning, GPT-4V showed improved performance on both data sets. When contrasting zero-shot and few-shot learning, there were improved average TPRs and F1 scores in the few-shot setting, but there was not a substantial increase in the average PPV. Conclusion Although GPT-4V has shown promise in understanding natural images, it had limited effectiveness in interpreting real-world chest radiographs. © RSNA, 2024 Supplemental material is available for this article.

The Role of Chest Radiography in Lung Cancer.

Chest radiography is one of the most commonly performed imaging tests, and benefits include accessibility, speed, cost, and relatively low radiation exposure. Lung cancer is the third most common cancer in the United States and is responsible for the most cancer deaths. Knowledge of the role of chest radiography in assessing patients with lung cancer is important. This article discusses radiographic manifestations of lung cancer, the utility of chest radiography in lung cancer management, as well as the limitations of chest radiography and when computed tomography (CT) is indicated.

ACR Lung-RADS v2022: Assessment Categories and Management Recommendations.

The American College of Radiology created the Lung CT Screening Reporting and Data System (Lung-RADS) in 2014 to standardize the reporting and management of screen-detected pulmonary nodules. Lung-RADS was updated to version 1.1 in 2019 and revised size thresholds for nonsolid nodules, added classification criteria for perifissural nodules, and allowed for short-interval follow-up of rapidly enlarging nodules that may be infectious in etiology. Lung-RADS v2022, released in November 2022, provides several updates including guidance on the classification and management of atypical pulmonary cysts, juxtapleural nodules, airway-centered nodules, and potentially infectious findings. This new release also provides clarification for determining nodule growth and introduces stepped management for nodules that are stable or decreasing in size. This article summarizes the current evidence and expert consensus supporting Lung-RADS v2022.

The 2023 American Association for Thoracic Surgery (AATS) Expert Consensus Document: Management of subsolid lung nodules.

OBJECTIVE: Lung cancers that present as radiographic subsolid nodules represent a subtype with distinct biological behavior and outcomes. The objective of this document is to review the existing literature and report consensus among a group of multidisciplinary experts, providing specific recommendations for the clinical management of subsolid nodules. METHODS: The American Association for Thoracic Surgery Clinical Practice Standards Committee assembled an international, multidisciplinary expert panel composed of radiologists, pulmonologists, and thoracic surgeons with established expertise in the management of subsolid nodules. A focused literature review was performed with the assistance of a medical librarian. Expert consensus statements were developed with class of recommendation and level of evidence for each of 4 main topics: (1) definitions of subsolid nodules (radiology and pathology), (2) surveillance and diagnosis, (3) surgical interventions, and (4) management of multiple subsolid nodules. Using a modified Delphi method, the statements were evaluated and refined by the entire panel. RESULTS: Consensus was reached on 17 recommendations. These consensus statements reflect updated insights on subsolid nodule management based on the latest literature and current clinical experience, focusing on the correlation between radiologic findings and pathological classifications, individualized subsolid nodule surveillance and surgical strategies, and multimodality therapies for multiple subsolid lung nodules. CONCLUSIONS: Despite the complex nature of the decision-making process in the management of subsolid nodules, consensus on several key recommendations was achieved by this American Association for Thoracic Surgery expert panel. These recommendations, based on evidence and a modified Delphi method, provide guidance for thoracic surgeons and other medical professionals who care for patients with subsolid nodules.

Clinical, Cultural, Computational, and Regulatory Considerations to Deploy AI in Radiology: Perspectives of RSNA and MICCAI Experts.

The Radiological Society of North of America (RSNA) and the Medical Image Computing and Computer Assisted Intervention (MICCAI) Society have led a series of joint panels and seminars focused on the present impact and future directions of artificial intelligence (AI) in radiology. These conversations have collected viewpoints from multidisciplinary experts in radiology, medical imaging, and machine learning on the current clinical penetration of AI technology in radiology and how it is impacted by trust, reproducibility, explainability, and accountability. The collective points-both practical and philosophical-define the cultural changes for radiologists and AI scientists working together and describe the challenges ahead for AI technologies to meet broad approval. This article presents the perspectives of experts from MICCAI and RSNA on the clinical, cultural, computational, and regulatory considerations-coupled with recommended reading materials-essential to adopt AI technology successfully in radiology and, more generally, in clinical practice. The report emphasizes the importance of collaboration to improve clinical deployment, highlights the need to integrate clinical and medical imaging data, and introduces strategies to ensure smooth and incentivized integration. Keywords: Adults and Pediatrics, Computer Applications-General (Informatics), Diagnosis, Prognosis © RSNA, 2024.

Enhancing NSCLC recurrence prediction with PET/CT habitat imaging, ctDNA, and integrative radiogenomics-blood insights.

While we recognize the prognostic importance of clinicopathological measures and circulating tumor DNA (ctDNA), the independent contribution of quantitative image markers to prognosis in non-small cell lung cancer (NSCLC) remains underexplored. In our multi-institutional study of 394 NSCLC patients, we utilize pre-treatment computed tomography (CT) and 18F-fluorodeoxyglucose positron emission tomography (FDG-PET) to establish a habitat imaging framework for assessing regional heterogeneity within individual tumors. This framework identifies three PET/CT subtypes, which maintain prognostic value after adjusting for clinicopathologic risk factors including tumor volume. Additionally, these subtypes complement ctDNA in predicting disease recurrence. Radiogenomics analysis unveil the molecular underpinnings of these imaging subtypes, highlighting downregulation in interferon alpha and gamma pathways in the high-risk subtype. In summary, our study demonstrates that these habitat imaging subtypes effectively stratify NSCLC patients based on their risk levels for disease recurrence after initial curative surgery or radiotherapy, providing valuable insights for personalized treatment approaches.

Synthetic PET from CT improves diagnosis and prognosis for lung cancer: Proof of concept.

[18F]Fluorodeoxyglucose positron emission tomography (FDG-PET) and computed tomography (CT) are indispensable components in modern medicine. Although PET can provide additional diagnostic value, it is costly and not universally accessible, particularly in low-income countries. To bridge this gap, we have developed a conditional generative adversarial network pipeline that can produce FDG-PET from diagnostic CT scans based on multi-center multi-modal lung cancer datasets (n = 1,478). Synthetic PET images are validated across imaging, biological, and clinical aspects. Radiologists confirm comparable imaging quality and tumor contrast between synthetic and actual PET scans. Radiogenomics analysis further proves that the dysregulated cancer hallmark pathways of synthetic PET are consistent with actual PET. We also demonstrate the clinical values of synthetic PET in improving lung cancer diagnosis, staging, risk prediction, and prognosis. Taken together, this proof-of-concept study testifies to the feasibility of applying deep learning to obtain high-fidelity PET translated from CT.