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.

Objectives: Incidentally detected pulmonary nodules present a challenge in clinical routine with demand for reliable support systems for risk classification. We aimed to evaluate the performance of the lung-cancer-prediction-convolutional-neural-network (LCP-CNN), a deep learning-based approach, in comparison to multiparametric statistical methods (Brock model and Lung-RADS®) for risk classification of nodules in cohorts with different risk profiles and underlying pulmonary diseases. Materials and methods: Retrospective analysis was conducted on non-contrast and contrast-enhanced CT scans containing pulmonary nodules measuring 5–30 mm. Ground truth was defined by histology or follow-up stability. The final analysis was performed on 297 patients with 422 eligible nodules, of which 105 nodules were malignant. Classification performance of the LCP-CNN, Brock model, and Lung-RADS® was evaluated in terms of diagnostic accuracy measurements including ROC-analysis for different subcohorts (total, screening, emphysema, and interstitial lung disease). Results: LCP-CNN demonstrated superior performance compared to the Brock model in total and screening cohorts (AUC 0.92 (95% CI: 0.89–0.94) and 0.93 (95% CI: 0.89–0.96)). Superior sensitivity of LCP-CNN was demonstrated compared to the Brock model and Lung-RADS® in total, screening, and emphysema cohorts for a risk threshold of 5%. Superior sensitivity of LCP-CNN was also shown across all disease groups compared to the Brock model at a threshold of 65%, compared to Lung-RADS® sensitivity was better or equal. No significant differences in the performance of LCP-CNN were found between subcohorts. Conclusion: This study offers further evidence of the potential to integrate deep learning-based decision support systems into pulmonary nodule classification workflows, irrespective of the individual patient risk profile and underlying pulmonary disease. Key Points: Question Is a deep-learning approach (LCP-CNN) superior to multiparametric models (Brock model, Lung-RADS®) in classifying pulmonary nodule risk across varied patient profiles? Findings LCP-CNN shows superior performance in risk classification of pulmonary nodules compared to multiparametric models with no significant impact on risk profiles and structural pulmonary diseases. Clinical relevance LCP-CNN offers efficiency and accuracy, addressing limitations of traditional models, such as variations in manual measurements or lack of patient data, while producing robust results. Such approaches may therefore impact clinical work by complementing or even replacing current approaches.

Automated image analysis plays an increasing role in radiology in detecting and quantifying image features outside of the perception of human eyes. Common AI-based approaches address a single medical problem, although patients often present with multiple interacting, frequently subclinical medical conditions. A holistic imaging diagnostics tool based on artificial intelligence (AI) has the potential of providing an overview of multi-system comorbidities within a single workflow. An interdisciplinary, multicentric team of medical experts and computer scientists designed a pipeline, comprising AI-based tools for the automated detection, quantification and characterization of the most common pulmonary, metabolic, cardiovascular and musculoskeletal comorbidities in chest computed tomography (CT). To provide a comprehensive evaluation of each patient, a multidimensional workflow was established with algorithms operating synchronously on a decentralized Joined Imaging Platform (JIP). The results of each patient are transferred to a dedicated database and summarized as a structured report with reference to available reference values and annotated sample images of detected pathologies. Hence, this tool allows for the comprehensive, large-scale analysis of imaging-biomarkers of comorbidities in chest CT, first in science and then in clinical routine. Moreover, this tool accommodates the quantitative analysis and classification of each pathology, providing integral diagnostic and prognostic value, and subsequently leading to improved preventive patient care and further possibilities for future studies.

BACKGROUND AND PURPOSE: 3D MR neurography is a useful diagnostic tool in head and neck disorders, but neurographic imaging remains challenging in this region. Optimal sequences for nerve visualization have not yet been established and may also differ between nerves. While deep learning reconstruction can enhance nerve depiction, particularly at 1.5T, studies in the head and neck are lacking. The purpose of this study was to compare DESS and post-contrast STIR sequences in deep-learning -reconstructed 3D MR neurography of the extraforaminal cranial and spinal nerves at 1.5T. MATERIALS AND METHODS: Eighteen consecutive exams of 18 patients undergoing head-and-neck MRI at 1.5T were retrospectively included (mean age: 51 ± 14 years, 11 female). 3D DESS and post-contrast 3D STIR sequences were obtained as part of the standard protocol, and reconstructed with a prototype deep learning algorithm. Two blinded readers qualitatively evaluated visualization of the inferior alveolar, lingual, facial, hypoglossal, greater occipital, lesser occipital and greater auricular nerves, as well as overall image quality, vascular suppression and artifacts. Additionally, apparent signal-to-noise ratio (aSNR) and contrast-to-noise ratios (aCNR) of the inferior alveolar and greater occipital nerve were measured. Visual ratings and quantitative measurements, respectively, were compared between sequences using Wilcoxon signed-rank test. RESULTS: DESS demonstrated significantly improved visualization of the lesser occipital nerve, greater auricular nerve and proximal greater occipital nerve (p < 0.015). Post-contrast STIR showed significantly enhanced visualization of the lingual nerve, hypoglossal nerve and distal inferior alveolar nerve (p < 0.001). The facial nerve, proximal inferior alveolar nerve and distal greater occipital nerve did not demonstrate significant differences in visualization between sequences (p > 0.08). There was also no significant difference for overall image quality and artifacts. Post-contrast STIR achieved superior vascular suppression, reaching statistical significance for one reader (p = 0.039). Quantitatively, there was no significant difference between sequences (p > 0.05). CONCLUSIONS: Our findings suggest that 3D DESS generally provides improved visualization of spinal nerves, while post-contrast 3D STIR facilitates enhanced delineation of extraforaminal cranial nerves. ABBREVIATIONS: DESS = Dual-echo steady-state; DL = Deep learning; FN = Facial nerve; GAN = Greater auricular nerve; GON = Greater occipital nerve; HN = Hypoglossal nerve; IAN = Inferior alveolar nerve; LN = Lingual nerve; LON = Lesser occipital nerve; MRN = Magnetic resonance neurography

To evaluate the performance of automated Lung Texture Analysis (LTA) in assessing interstitial lung disease (ILD) in systemic sclerosis (SSc) using low-dose photon-counting detector CT (PCD-CT) compared to conventional low-dose energy-integrating detector CT (EID-CT). In this study of a prospectively enrolled SSc cohort, a post-hoc analysis on 186 patients (93 PCD-CT, 93 EID-CT), matched by propensity scoring, was performed. Visual ILD assessment by three expert radiologists served as the reference standard. Image quality assessment was performed using Likert-scales by expert radiologists and signal-to-noise ratios (SNR). Quantitative ILD features and extent were extracted using LTA (Imbio, CALIPER-based). Diagnostic accuracy was assessed using ROC-AUC analysis. LTA-based assessment of ILD on PCD-CT demonstrated a higher AUC for detecting ILD presence (AUC = 0.846) compared to EID-CT (AUC = 0.772). PCD-CT also exhibited superior AUCs in identifying specific ILD features, including ground-glass opacities, reticulation, and honeycombing. However, EID-CT showed higher AUCs than PCD-CT in detecting extensive ILD (>20 % lung involvement; AUC = 0.978 vs. 0.842). Despite significantly lower radiation dose, PCD-CT achieved comparable SNR and superior image quality ratings on Likert-scale. Both EID-CT and PCD-CT demonstrated acceptable to excellent AUC values, indicating their strong applicability in ILD assessment. Further, LTA using PCD-CT consistently provided excellent AUCs for detecting individual ILD features in SSc, supporting its clinical utility despite being trained on PCD-CT data. PCD-CT's enhanced image quality and lower radiation dose make it a promising tool for longitudinal ILD assessment. Further multicenter validation is warranted.

Background Non-small cell lung cancer (NSCLC) is the leading cause of cancer-related deaths. The development of therapies targeting molecular alterations has significantly improved the treatment of NSCLC patients. To identify these targets, tumor phenotyping is required, with tissue biopsies and molecular pathology being the gold standard. Some patients do not respond to targeted therapies and many patients suffer from tumor recurrence, which can in part be explained by tumor heterogeneity. This points out the need for new biomarkers allowing for better tumor phenotyping and monitoring during treatment to assess patient outcome. Method The contents of this review are based on a literature search conducted using the PubMed database in March 2021 and the authors’ experience. Results and Conclusion The use of radiomics and artificial intelligence-based approaches allows for the identification of imaging biomarkers in NSCLC patients for tumor phenotyping. Several studies show promising results for models predicting molecular alterations, with the best results being achieved by combining structural and functional imaging. Radiomics could help solve the pressing clinical need for assessing and predicting therapy response. To reach this goal, advanced tumor phenotyping, considering tumor heterogeneity, is required. This could be achieved by integrating structural and functional imaging biomarkers with clinical data sources, such as liquid biopsy results. However, to allow for radiomics-based approaches to be introduced into clinical practice, further standardization using large, multi-center datasets is required. Key points: Citation Format