Background/Objectives: Large language models (LLMs), such as ChatGPT, have emerged as potential clinical support tools to enhance precision in personalized patient care, but their reliability in radiological image interpretation remains uncertain. The primary aim of our study was to evaluate the diagnostic accuracy of ChatGPT-4o in interpreting chest X-rays (CXRs) and abdominal X-rays (AXRs) by comparing its performance to expert radiology findings, whilst secondary aims were diagnostic confidence and patient safety. Methods: A total of 500 X-rays, including 257 CXR (51.4%) and 243 AXR (48.5%), were analyzed. Diagnoses made by ChatGPT-4o were compared to expert interpretations. Confidence scores (1–4) were assigned and responses were evaluated for patient safety. Results: ChatGPT-4o correctly identified 345 of 500 (69%) pathologies (95% CI: 64.81–72.9). For AXRs 175 of 243 (72.02%) pathologies were correctly diagnosed (95% CI: 66.06–77.28), while for CXRs 170 of 257 (66.15%) were accurate (95% CI: 60.16–71.66). The highest detection rates among CXRs were observed for pulmonary edema, tumor, pneumonia, pleural effusion, cardiomegaly, and emphysema, and lower rates were observed for pneumothorax, rib fractures, and enlarged mediastinum. AXR performance was highest for intestinal obstruction and foreign bodies, and weaker for pneumoperitoneum, renal calculi, and diverticulitis. Confidence scores were higher for AXRs (mean 3.45 ± 1.1) than CXRs (mean 2.48 ± 1.45). All responses (100%) were considered to be safe for the patient. Interobserver agreement was high (kappa = 0.920), and reliability (second prompt) was moderate (kappa = 0.750). Conclusions: ChatGPT-4o demonstrated moderate accuracy for the interpretation of X-rays, being higher for AXRs compared to CXRs. Improvements are required for its use as efficient clinical support tool.

Background: A better understanding of the peritumoral stroma changes due to tumour invasion using non-invasive diagnostic methods may improve the differentiation between benign and malignant breast lesions. This study aimed to assess the correlation between breast lesion differentiation and intra- and peritumoral shear-wave elastography (SWE) gradients. Methods: A total of 135 patients with newly diagnosed breast lesions were included. Intratumoral, subsurface, and three consecutive peritumoral SWE value measurements (with three repetitions) were performed. Intratumoral, interface, and peritumoral gradients (Gradient 1 and Gradient 2) were calculated using averaged SWE values. Statistical analysis included descriptive statistics and an ordinary one-way ANOVA to compare overall and individual gradients among Breast Imaging-Reporting and Data System (BI-RADS) 2, 3, and 5 groups. Results: Malignant tumours showed higher average SWE velocity values at the tumour centre (BI-RADS 2/3: 4.1 ± 1.8 m/s vs. BI-RADS 5: 4.9 ± 2.0 m/s, p = 0.04) and the first peritumoral area (BI-RADS 2/3: 3.4 ± 1.8 m/s vs. BI-RADS 5: 4.3 ± 1.8 m/s, p = 0.003). No significant difference was found between intratumoral gradients (0.03 ± 0.32 m/s vs. 0.0 ± 0.28 m/s; p > 0.999) or gradients across the tumour–tissue interface (−0.17 ± 0.18 m/s vs. −0.13 ± 0.35 m/s; p = 0.202). However, the first peritumoral gradient (−0.16 ± 0.24 m/s vs. −0.35 ± 0.31 m/s; p < 0.0001) and the second peritumoral gradient (−0.11 ± 0.18 m/s vs. −0.22 ± 0.28 m/s; p = 0.037) were significantly steeper in malignant tumours. The AUC was best for PTG1 (0.7358) and PTG2 (0.7039). A threshold value for peritumoral SWI PT1 above 3.76 m/s and for PTG1 below −0.238 m/s·mm⁻¹ indicated malignancy in 90.6% of cases. Conclusions: Evaluating the peritumoral SWE gradient may improve the diagnostic pre-test probability, as malignant tumours showed a significantly steeper curve of the elasticity values in the peritumoral stroma compared to the linear regression with a relatively flat curve of benign lesions.

Background: Compared to conventional 2D mammography, digital breast tomosynthesis (DBT) offers greater breast lesion detection rates. Ring-like hypodense artifacts surrounding dense lesions are a common byproduct of DBT. This study’s purpose was to assess whether minuscule changes spanning this halo—termed the “broken halo sign”—could improve lesion classification. Methods: This retrospective study was approved by the local ethics review board. After screening 288 consecutive patients, DBT studies of 191 female participants referred for routine mammography with a subsequent histologically verified finding of the breast were assessed. Examined variables included patient age, histological diagnosis, architectural distortion, maximum size, maximum halo depth, conspicuous margins, irregular shape and broken halo sign. Results: While a higher halo strength was indicative of malignancy in general (p = 0.031), the broken halo sign was strongly associated with malignancy (p < 0.0001, odds ratio (OR) 6.33), alongside architectural distortion (p = 0.012, OR 3.49) and a diffuse margin (p = 0.006, OR 5.49). This was especially true for denser breasts (ACR C/D), where the broken halo sign was the only factor predicting malignancy (p = 0.03, 5.22 OR). Conclusion: DBT-associated halo artifacts warrant thorough investigation in newly found breast lesions as they are associated with malignant tumors. The “broken halo sign”—the presence of small lines of variable diameter spanning the peritumoral areas of hypodensity—is a strong indicator of malignancy, especially in dense breasts, where architectural distortion may be obfuscated due to the surrounding tissue.

Das invasive duktale Mammakarzinom vom non-specific type (NST) ist der häufigste histologische Brustkrebssubtyp, eine frühzeitige Erkennung ist notwendig, um Metastasierung und eine palliative Situation möglichst zu vermeiden (Tsang. Adv. Anat Pathol 2020; 27: 27–35). Die kontrastmittelunterstützte MRT wird im präoperativen Setting für das lokale Staging bei Brustkrebspatientinnen eingesetzt und ermöglicht daneben die hochsensitive Detektion weiterer potenziell maligner Herde. Sollten weitere malignitätsspezifische Läsionen auffallen, wird im sogenannten Second-Look eine weiterführende Abklärung mittels Sonografie und gegebenenfalls histologische Abklärung mittels Ultraschall- oder MRT-gezielter Biopsie angestrebt. Während in bis zu 60% der Fälle weitere ipsilaterale Tumormanifestationen detektiert werden (Fushimi et al. Surgery Today 2019; 49: 224–230), erfolgt in nur 1–3% der Fälle die simultane Diagnosestellung eines Zweitkarzinoms in der kontralateralen Brust. Diese Situation wird als „synchroner bilateraler Brustkrebs“ bezeichnet (Schulze. Breast Oncology 2023; 31: 947–956). Wir berichten hier über eine 72-jährige Patientin mit synchronem bilateralem Mammakarzinom, bei welcher der bis dahin bildgebend okkulte kontralaterale Zweittumor während der Mamma-MRT im Rahmen des lokoregionären Stagings entdeckt wurde. Dieser konnte mittels Real-time MRT/Ultraschall Fusion (RtMRT/US-Fusion) mit der in Rückenlage angefertigten MR-Bilder lokalisiert und stanzbioptisch verifiziert werden. Received: 07 December 2023 Accepted after revision: 16 June 2024 Article published online: 09 July 2024 © 2024. Thieme. All rights reserved. Georg Thieme Verlag KG Rüdigerstraße 14, 70469 Stuttgart, Germany

Background/Objectives: Coronary artery disease (CAD) remains the leading cause of death worldwide. Traditional cardiovascular risk assessment is based on chronological age and other clinical factors, with inherent limitations and poor accuracy. Objective was to estimate the artificial intelligence (AI)-enhanced biological cardiovascular age calculation derived from coronary computed tomography angiography (CTA) reports using a large language model (LLM), in predicting major adverse cardiovascular events (MACE). Methods: Coronary CTA reports were analyzed using a LLM (ChatGPT-4.0v, OpenAI), from symptomatic patients with suspected CAD who underwent coronary CTA for clinical indications. Patients in which the LLM successfully analyzed the key metrics (1) coronary artery calcium (CAC) score and (2) coronary CTA reports (coronary stenosis severity (CAD-RADS), high-risk anatomy, non-calcified plaque, cardiac function (LVEF and others) were included. Results: 386 CTA reports were uploaded, and 346 (89.6%) included. The mean biological age (bioAGE) was 57.2 ± 10.9 and the chronological 58.5 ± 10.8 years. 137 (39.6%) were women. The intra-individual deviation in bioAGE was high (median: 8.8; IQR 9.98). BioAGE exceeded chronological age in 45.4% patient and was lower or equal in 54.6%) MACE rate was 8.7% comprising 2 deaths, 5 myocardial infarctions, and 22 late revascularizations. The accuracy for prediction of MACE was higher for bioAGE (c = 0.768; 95% CI: 0.681–0.855, p < 0.001) compared to chronological age (c = 0.590; 95% CI: 0.492–0.689, p = 0.102) Conclusions: Biological age calculation from coronary CTA reports using LLM is feasible, yet intra-individual deviations are high. The accuracy for prediction of MACE is improved by bioAGE compared to chronological.

Das invasive duktale Mammakarzinom vom non-specific type (NST) ist der häufigste histologische Brustkrebssubtyp, eine frühzeitige Erkennung ist notwendig, um Metastasierung und eine palliative Situation möglichst zu vermeiden (Tsang. Adv. Anat Pathol 2020; 27: 27–35). Die kontrastmittelunterstützte MRT wird im präoperativen Setting für das lokale Staging bei Brustkrebspatientinnen eingesetzt und ermöglicht daneben die hochsensitive Detektion weiterer potenziell maligner Herde. Sollten weitere malignitätsspezifische Läsionen auffallen, wird im sogenannten Second-Look eine weiterführende Abklärung mittels Sonografie und gegebenenfalls histologische Abklärung mittels Ultraschall- oder MRT-gezielter Biopsie angestrebt. Während in bis zu 60% der Fälle weitere ipsilaterale Tumormanifestationen detektiert werden (Fushimi et al. Surgery Today 2019; 49: 224–230), erfolgt in nur 1–3% der Fälle die simultane Diagnosestellung eines Zweitkarzinoms in der kontralateralen Brust. Diese Situation wird als „synchroner bilateraler Brustkrebs“ bezeichnet (Schulze. Breast Oncology 2023; 31: 947–956). Wir berichten hier über eine 72-jährige Patientin mit synchronem bilateralem Mammakarzinom, bei welcher der bis dahin bildgebend okkulte kontralaterale Zweittumor während der Mamma-MRT im Rahmen des lokoregionären Stagings entdeckt wurde. Dieser konnte mittels Real-time MRT/Ultraschall Fusion (RtMRT/US-Fusion) mit der in Rückenlage angefertigten MR-Bilder lokalisiert und stanzbioptisch verifiziert werden. Article published online: 24 September 2025 © 2025. Thieme. All rights reserved. Georg Thieme Verlag KG Oswald-Hesse-Straße 50, 70469 Stuttgart, Germany