Objectives: A substantial number of incidental pulmonary embolisms (iPEs) in computed tomography scans are missed by radiologists in their daily routine. This study analyzes the radiological reports of iPE cases before and after implementation of an artificial intelligence (AI) algorithm for iPE detection. Furthermore, we investigate the anatomic distribution patterns within missed iPE cases and mortality within a 90-day follow-up in patients before and after AI use. Materials and Methods: This institutional review board–approved observational single-center study included 5298 chest computed tomography scans performed for reasons other than suspected pulmonary embolism (PE). We compared 2 cohorts: cohort 1, consisting of 1964 patients whose original radiology reports were generated before the implementation of an AI algorithm, and cohort 2, consisting of 3334 patients whose scans were analyzed after the implementation of an Food and Drug Administration–approved and CE-certified AI algorithm for iPE detection (Aidoc Medical, Tel Aviv, Israel). For both cohorts, any discrepancies between the original radiology reports and the AI results were reviewed by 2 thoracic imaging subspecialized radiologists. In the original radiology report and in case of discrepancies with the AI algorithm, the expert review served as reference standard. Sensitivity, specificity, prevalence, negative predictive value (NPV), and positive predictive value (PPV) were calculated. The rates of missed iPEs in both cohorts were compared statistically using STATA (Version 17.1). Kaplan-Meier curves and Cox proportional hazards models were used for survival analysis. Results: In cohort 1 (mean age 70.6 years, 48% female [n = 944], 52% male [n = 1020]), the prevalence of confirmed iPE was 2.2% (n = 42), and the AI detected 61 suspicious iPEs, resulting in a sensitivity of 95%, a specificity of 99%, a PPV of 69%, and an NPV of 99%. Radiologists missed 50% of iPE cases in cohort 1. In cohort 2 (mean age 69 years, 47% female [n = 1567], 53% male [n = 1767]), the prevalence of confirmed iPEs was 1.7% (56/3334), with AI detecting 59 suspicious cases (sensitivity 90%, specificity 99%, PPV 95%, NPV 99%). The rate of missed iPEs by radiologists dropped to 7.1% after AI implementation, showing a significant improvement (P < 0.001). Most overlooked iPEs (61%) were in the right lower lobe. The survival analysis showed no significantly decreased 90-day mortality rate, with a hazards ratio of 0.95 (95% confidence interval, 0.45–1.96; P = 0.88). Conclusions: The implementation of an AI algorithm significantly reduced the rate of missed iPEs from 50% to 7.1%, thereby enhancing diagnostic accuracy. Despite this improvement, the 90-day mortality rate remained unchanged. These findings highlight the AI tool's potential to assist radiologists in accurately identifying iPEs, although its implementation does not significantly affect short-term survival. Notably, most missed iPEs were located in the right lower lobe, suggesting that radiologists should pay particular attention to this area during evaluations.

Background: After breast conserving surgery (BCS), surgical clips indicate the tumor bed and, thereby, the most probable area for tumor relapse. The aim of this study was to investigate whether a U-Net-based deep convolutional neural network (dCNN) may be used to detect surgical clips in follow-up mammograms after BCS. Methods: 884 mammograms and 517 tomosynthetic images depicting surgical clips and calcifications were manually segmented and classified. A U-Net-based segmentation network was trained with 922 images and validated with 394 images. An external test dataset consisting of 39 images was annotated by two radiologists with up to 7 years of experience in breast imaging. The network’s performance was compared to that of human readers using accuracy and interrater agreement (Cohen’s Kappa). Results: The overall classification accuracy on the validation set after 45 epochs ranged between 88.2% and 92.6%, indicating that the model’s performance is comparable to the decisions of a human reader. In 17.4% of cases, calcifications have been misclassified as post-operative clips. The interrater reliability of the model compared to the radiologists showed substantial agreement (κ_reader1 = 0.72, κ_reader2 = 0.78) while the readers compared to each other revealed a Cohen’s Kappa of 0.84, thus showing near-perfect agreement. Conclusions: With this study, we show that surgery clips can adequately be identified by an AI technique. A potential application of the proposed technique is patient triage as well as the automatic exclusion of post-operative cases from PGMI (Perfect, Good, Moderate, Inadequate) evaluation, thus improving the quality management workflow.

Background: Preoperative side-specific identification of extracapsular extension (ECE) is important for selecting an appropriate nerve-sparing strategy at radical prostatectomy. Patients with multiparametric magnetic resonance imaging (mpMRI)-defined capsular contact represent a clinically challenging subgroup because contact raises concern for ECE but does not uniformly indicate extraprostatic disease. We aimed to develop a side-specific nomogram for individualized ECE prediction and perform preliminary internal validation in this selected population. Materials and Methods: We retrospectively analyzed 323 prostate lobes from 286 patients with biopsy-proven, non-metastatic prostate cancer and mpMRI-defined capsular contact who underwent robot-assisted radical prostatectomy between 2015 and 2021 at a single institution. The dataset was randomly split into training (70%) and testing (30%) cohorts. Three multivariable logistic-regression models were developed and compared. Discrimination was assessed using the area under the receiver operating characteristic curve (AUC-ROC), calibration by intercept and slope, and clinical utility by decision curve analysis. A nomogram was derived from the best-performing model in the internal split-sample comparison. Results: Side-specific ECE was present in 110/323 lobes (34.1%). Among the candidate models, the forward-selection model showed the most favorable apparent performance, with an AUC-ROC of 0.85 in training and 0.83 in testing, together with good test-set calibration (intercept 0.24; slope 0.97). The final model included a capsular contact length ≥10 mm, percentage tumor involvement in positive biopsy cores, number of positive biopsy cores, and index lesion size. At a 10% predicted risk threshold, 32% of lobes were classified as low risk, with an observed ECE rate of about 5%. Conclusions: We developed a side-specific nomogram tailored to patients with mpMRI-defined capsular contact and performed preliminary internal validation. The model may aid preoperative side-specific risk assessment relevant to nerve-sparing planning, but external validation and assessment of clinical impact are required before clinical adoption.

Purpose: To investigate the performance of LLMs in radiology numerical tasks and perform a comprehensive error analysis. Materials and Methods: We defined six tasks: extracting 1-minimum T-score from DEXA report, 2-maximum common bile duct (CBD) diameter from ultrasound report, and 3-maximum lung nodule size from CT report, and judging 1-presence of a highly hypermetabolic region on a PET report, 2-whether a patient is osteoporotic based on a DEXA report, and 3-whether a patient has a dilated CBD based on an ultrasound report. Reports were extracted from the MIMIC III and our institution’s databases, and the ground truths were extracted manually. The models used were Llama 3.1 8b, DeepSeek R1 distilled Llama 8b, OpenAI o1-mini, and OpenAI GPT-5-mini. We manually reviewed all incorrect outputs and performed a comprehensive error analysis. Results: In extraction tasks, while Llama showed relatively variable results (ranging 86%-98.7%) across tasks, other models performed consistently well (accuracies >95%). In judgement tasks, the lowest accuracies of Llama, DeepSeek, o1-mini, and GPT-5-mini were 62.0%, 91.7%, 91.7%, and 99.0%, respectively, while o1-mini and GPT-5-mini did reach 100% performance in detecting osteoporosis. We found no mathematical errors in the outputs of o1-mini and GPT-5-mini. Answer-only output format significantly reduced performance in Llama and DeepSeek but not in o1-mini or GPT-5-mini. Conclusion: True reasoning models perform consistently well in radiology numerical tasks and show no mathematical errors. Simpler non-true reasoning models may also achieve acceptable performance depending on the task.