Radiology-Artificial Intelligence最新文献

Purpose To develop an adaptive dual-task deep learning model (ThyNet-S) for detection and classification of thyroid lesions at US screening. Materials and Methods This retrospective study used a multicenter dataset comprising 35 008 thyroid US images of 23 294 individual examinations (mean age, 40.4 years ± 13.1 [SD]; 17 587 female) from seven medical centers from January 2009 to December 2021. Of these, 29 004 images were used for model development and 6004 images for validation. The model determined cancer risk for each image and automatically triaged images with normal thyroid and benign nodules by dynamically integrating lesion detection through pixel-level feature analysis and lesion classification through deep semantic features analysis. Diagnostic performance of screening assisted by the model (ThyNet-S triaged screening) and traditional screening (radiologists alone) was assessed by comparing sensitivity, specificity, accuracy, and area under the receiver operating characteristic curve using the McNemar test and DeLong test. The influence of ThyNet-S on radiologist workload and clinical decision-making was also assessed. Results ThyNet-S-assisted triaged screening achieved a higher area under the receiver operating characteristic curve than original screening with six senior and six junior radiologists (0.93 vs 0.91 and 0.92 vs 0.88, respectively; all P < .001). The model improved sensitivity for junior radiologists (88.2% vs 86.8%; P < .001). Notably, the model reduced radiologists' workload by triaging 60.4% of cases as not potentially malignant, which did not require further interpretation. The model simultaneously decreased the unnecessary fine needle aspiration rate from 38.7% to 14.9% and 11.5% when used independently or in combination with the Thyroid Imaging Reporting and Data System, respectively. Conclusion ThyNet-S improved the efficiency of thyroid cancer screening and optimized clinical decision-making. Keywords: Artificial Intelligence, Adaptive, Dual Task, Thyroid Cancer, Screening, Ultrasound Supplemental material is available for this article. © RSNA, 2025.

Purpose To develop a longitudinally aware segmentation network (LAS-Net) that can quantify serial PET/CT images for pediatric patients with Hodgkin lymphoma. Materials and Methods This retrospective study included baseline (PET1) and interim (PET2) PET/CT images from 297 pediatric patients enrolled in two Children's Oncology Group clinical trials (AHOD1331 and AHOD0831). The internal dataset included 200 patients (enrolled between March 2015 and August 2019; median age, 15.4 years [range, 5.6-22.0 years]; 107 male), and the external testing dataset included 97 patients (enrolled between December 2009 and January 2012; median age, 15.8 years [range, 5.2-21.4 years]; 59 male). LAS-Net incorporates longitudinal cross-attention, allowing relevant features from PET1 to inform the analysis of PET2. The model's lesion segmentation performance on PET1 images was evaluated using Dice coefficients, and lesion detection performance on PET2 images was evaluated using F1 scores. In addition, quantitative PET metrics, including metabolic tumor volume (MTV) and total lesion glycolysis (TLG) in PET1, as well as qPET and percentage difference between baseline and interim maximum standardized uptake value (∆SUV_max) in PET2, were extracted and compared against physician-derived measurements. Agreement between model and physician-derived measurements was quantified using Spearman correlation, and bootstrap resampling was used for statistical analysis. Results LAS-Net detected residual lymphoma on PET2 scans with an F1 score of 0.61 (precision/recall: 0.62/0.60), outperforming all comparator methods (P < .01). For baseline segmentation, LAS-Net achieved a mean Dice score of 0.77. In PET quantification, LAS-Net's measurements of qPET, ∆SUV_max, MTV, and TLG were strongly correlated with physician measurements, with Spearman ρ values of 0.78, 0.80, 0.93, and 0.96, respectively. The quantification performance remained high, with a slight decrease, in an external testing cohort. Conclusion LAS-Net demonstrated significant improvements in quantifying PET metrics across serial scans in pediatric patients with Hodgkin lymphoma, highlighting the value of longitudinal awareness in evaluating multi-time-point imaging datasets. Keywords: Pediatrics, PET/CT, Lymphoma, Segmentation, Quantification, Supervised Learning, Convolutional Neural Network (CNN), Quantitative PET, Longitudinal Analysis, Deep Learning, Image Segmentation Supplemental material is available for this article. Clinical trial registration no. NCT02166463 and NCT01026220 © RSNA, 2025 See also commentary by Khosravi and Gichoya in this issue.

Retrieval-augmented generation (RAG) is a strategy to improve the performance of large language models (LLMs) by providing an LLM with an updated corpus of knowledge that can be used for answer generation in real time. RAG may improve LLM performance and clinical applicability in radiology by providing citable, up-to-date information without requiring model fine-tuning. In this retrospective study, a radiology-specific RAG system was developed using a vector database of 3689 RadioGraphics articles published from January 1999 to December 2023. Performance of five LLMs with (RAG-Systems) and without RAG on a 192-question radiology examination was compared. RAG significantly improved examination scores for GPT-4 (OpenAI; 81.2% vs 75.5%, P = .04) and Command R+ (Cohere; 70.3% vs 62.0%, P = .02), but not for Claude Opus (Anthropic), Mixtral (Mistral AI), or Gemini 1.5 Pro (Google DeepMind). RAG-Systems performed significantly better than pure LLMs on a 24-question subset directly sourced from RadioGraphics (85% vs 76%, P = .03). RAG-Systems retrieved 21 of 24 (87.5%, P < .001) relevant RadioGraphics references cited in the examination's answer explanations and successfully cited them in 18 of 21 (85.7%, P < .001) outputs. The results suggest that RAG is a promising approach to enhance LLM capabilities for radiology knowledge tasks, providing transparent, domain-specific information retrieval. Keywords: Computer Applications-General (Informatics), Technology Assessment Supplemental material is available for this article. © RSNA, 2025 See also commentary by Mansuri and Gichoya in this issue.

Purpose To develop and evaluate a multilabel deep learning network to identify and quantify acute and chronic brain lesions at multisequence MRI after acute ischemic stroke (AIS) and assess relationships between clinical and model-extracted radiologic features of the lesions and patient prognosis. Materials and Methods This retrospective study included patients with AIS from multiple centers, who experienced stroke onset between September 2008 and October 2022 and underwent MRI as well as thrombolytic therapy and/or treatment with antiplatelets or anticoagulants. A SegResNet-based deep learning model was developed to segment core infarcts and white matter hyperintensity (WMH) burdens on diffusion-weighted and fluid-attenuated inversion recovery images. The model was trained, validated, and tested with manual labels (260, 60, and 40 patients in each dataset, respectively). Radiologic features extracted from the model, including regional infarct size and periventricular and deep WMH volumes and cluster numbers, combined with clinical variables, were used to predict favorable versus unfavorable patient outcomes at 7 days (modified Rankin Scale [mRS] score). Mediation analyses explored associations between radiologic features and AIS outcomes within different treatment groups. Results A total of 1008 patients (mean age, 67.0 years ± 11.8 [SD]; 686 male, 322 female) were included. The training and validation dataset comprised 702 patients with AIS, and the two external testing datasets included 206 and 100 patients, respectively. The prognostic model combining clinical and radiologic features achieved areas under the receiver operating characteristic curve of 0.81 (95% CI: 0.74, 0.88) and 0.77 (95% CI: 0.68, 0.86) for predicting 7-day outcomes in the two external testing datasets, respectively. Mediation analyses revealed that deep WMH in patients treated with thrombolysis had a significant direct effect (17.7%, P = .01) and indirect effect (10.7%, P = .01) on unfavorable outcomes, as indicated by higher mRS scores, which was not observed in patients treated with antiplatelets and/or anticoagulants. Conclusion The proposed deep learning model quantitatively analyzed radiologic features of acute and chronic brain lesions, and the extracted radiologic features combined with clinical variables predicted short-term AIS outcomes. WMH burden, particularly deep WMH, emerged as a risk factor for poor outcomes in patients treated with thrombolysis. Keywords: MR-Diffusion Weighted Imaging, Thrombolysis, Head/Neck, Brain/Brain Stem, Stroke, Outcomes Analysis, Segmentation, Prognosis, Supervised Learning, Convolutional Neural Network (CNN), Support Vector Machines Supplemental material is available for this article. © RSNA, 2025.