Background The latest large language models (LLMs) solve unseen problems via user-defined text prompts without the need for retraining, offering potentially more efficient information extraction from free-text medical records than manual annotation. Purpose To compare the performance of the LLMs ChatGPT and GPT-4 in data mining and labeling oncologic phenotypes from free-text CT reports on lung cancer by using user-defined prompts. Materials and Methods This retrospective study included patients who underwent lung cancer follow-up CT between September 2021 and March 2023. A subset of 25 reports was reserved for prompt engineering to instruct the LLMs in extracting lesion diameters, labeling metastatic disease, and assessing oncologic progression. This output was fed into a rule-based natural language processing pipeline to match ground truth annotations from four radiologists and derive performance metrics. The oncologic reasoning of LLMs was rated on a five-point Likert scale for factual correctness and accuracy. The occurrence of confabulations was recorded. Statistical analyses included Wilcoxon signed rank and McNemar tests. Results On 424 CT reports from 424 patients (mean age, 65 years ± 11 [SD]; 265 male), GPT-4 outperformed ChatGPT in extracting lesion parameters (98.6% vs 84.0%, P < .001), resulting in 96% correctly mined reports (vs 67% for ChatGPT, P < .001). GPT-4 achieved higher accuracy in identification of metastatic disease (98.1% [95% CI: 97.7, 98.5] vs 90.3% [95% CI: 89.4, 91.0]) and higher performance in generating correct labels for oncologic progression (F1 score, 0.96 [95% CI: 0.94, 0.98] vs 0.91 [95% CI: 0.89, 0.94]) (both P < .001). In oncologic reasoning, GPT-4 had higher Likert scale scores for factual correctness (4.3 vs 3.9) and accuracy (4.4 vs 3.3), with a lower rate of confabulation (1.7% vs 13.7%) than ChatGPT (all P < .001). Conclusion When using user-defined prompts, GPT-4 outperformed ChatGPT in extracting oncologic phenotypes from free-text CT reports on lung cancer and demonstrated better oncologic reasoning with fewer confabulations. © RSNA, 2023 Supplemental material is available for this article. See also the editorial by Hafezi-Nejad and Trivedi in this issue.

Deep Learning has been proposed as promising tool to classify malignant nodules. Our aim was to retrospectively validate our Lung Cancer Prediction Convolutional Neural Network (LCP-CNN), which was trained on US screening data, on an independent dataset of indeterminate nodules in an European multicentre trial, to rule out benign nodules maintaining a high lung cancer sensitivity. The LCP-CNN has been trained to generate a malignancy score for each nodule using CT data from the U.S. National Lung Screening Trial (NLST), and validated on CT scans containing 2106 nodules (205 lung cancers) detected in patients from from the Early Lung Cancer Diagnosis Using Artificial Intelligence and Big Data (LUCINDA) study, recruited from three tertiary referral centers in the UK, Germany and Netherlands. We pre-defined a benign nodule rule-out test, to identify benign nodules whilst maintaining a high sensitivity, by calculating thresholds on the malignancy score that achieve at least 99 % sensitivity on the NLST data. Overall performance per validation site was evaluated using Area-Under-the-ROC-Curve analysis (AUC). The overall AUC across the European centers was 94.5 % (95 %CI 92.6-96.1). With a high sensitivity of 99.0 %, malignancy could be ruled out in 22.1 % of the nodules, enabling 18.5 % of the patients to avoid follow-up scans. The two false-negative results both represented small typical carcinoids. The LCP-CNN, trained on participants with lung nodules from the US NLST dataset, showed excellent performance on identification of benign lung nodules in a multi-center external dataset, ruling out malignancy with high accuracy in about one fifth of the patients with 5-15 mm nodules.

Due to technical advances in pulmonary MRI, the Fleischner Society offers its consensus recommendations for the clinical use of MRI in evaluating patients with common lung disorders. Pulmonary MRI provides structural and quantitative functional images of the lungs without ionizing radiation, but it has had limited clinical use due to low signal intensity from the lung parenchym...

Rationale: Early onset and progression of lung disease in children with cystic fibrosis (CF) indicates that sensitive noninvasive outcome measures are needed for diagnostic monitoring and early intervention clinical trials. The lung clearance index (LCI) and chest magnetic resonance imaging (MRI) were shown to detect early lung disease in CF; however, the relationship between the two measures remains unknown. Objectives: To correlate the LCI with abnormalities detected by MRI and compare the sensitivity of the two techniques to detect responses to therapy for pulmonary exacerbations in children with CF. Methods: LCI determined by age-adapted multiple breath washout techniques and MRI studies were performed in 97 clinically stable children with CF across the pediatric age range (0.2–21.1 yr). Furthermore, LCI (n = 26) or MRI (n = 10) were performed at the time of pulmonary exacerbation and after antibiotic therapy. MRI was evaluated using a dedicated morphofunctional score. Measurements and Main Results: The LCI correlated with the global MRI score as well as MRI-defined airway wall abnormalities, mucus plugging, and abnormal lung perfusion in infants and toddlers (P < 0.05 to P < 0.001) and in older children (P < 0.001) with CF. LCI and MRI were sensitive to detect response to antibiotic therapy for pulmonary exacerbations. Conclusions: Our results indicate that LCI and MRI may be useful complementary tools for noninvasive monitoring and as quantitative endpoints in early intervention trials in children with CF. In this context, MRI enables detection of disease heterogeneity, including regional mucus plugging associated with abnormal lung perfusion in early CF lung disease. Clinical trial registered with www.clinicaltrials.gov (NCT 02270476).

Increasing use of molecular targeting agents and immune checkpoint inhibitors has increased the frequency and broadened the spectrum of lung toxicity, particularly in patients with cancer. In this position paper from the Fleischner Society, the authors provide diagnostic criteria and management recommendations of drug-related pneumonitis for radiologists, clinicians, clinical trialists, and trial sponsors.

In Europe, lung cancer ranks third among the most common cancers, remaining the biggest killer. Since the publication of the first European Society of Radiology and European Respiratory Society joint white paper on lung cancer screening (LCS) in 2015, many new findings have been published and discussions have increased considerably. Thus, this updated expert opinion represents a narrative, non-systematic review of the evidence from LCS trials and description of the current practice of LCS as well as aspects that have not received adequate attention until now. Reaching out to the potential participants (persons at high risk), optimal communication and shared decision-making will be key starting points. Furthermore, standards for infrastructure, pathways and quality assurance are pivotal, including promoting tobacco cessation, benefits and harms, overdiagnosis, quality, minimum radiation exposure, definition of management of positive screen results and incidental findings linked to respective actions as well as cost-effectiveness. This requires a multidisciplinary team with experts from pulmonology and radiology as well as thoracic oncologists, thoracic surgeons, pathologists, family doctors, patient representatives and others. The ESR and ERS agree that Europe's health systems need to adapt to allow citizens to benefit from organised pathways, rather than unsupervised initiatives, to allow early diagnosis of lung cancer and reduce the mortality rate. Now is the time to set up and conduct demonstration programmes focusing, among other points, on methodology, standardisation, tobacco cessation, education on healthy lifestyle, cost-effectiveness and a central registry.