Summary: Techniques of artificial intelligence (AI) are increasingly used in the treatment of patients, such as providing a diagnosis in radiological imaging, improving workflow by triaging patients or providing an expert opinion based on clinical symptoms; however, such AI techniques also hold intrinsic risks as AI algorithms may point in the wrong direction and constitute a black box without explaining the reason for the decision-making process.This article outlines a case where an erroneous ChatGPT diagnosis, relied upon by the patient to evaluate symptoms, led to a significant treatment delay and a potentially life-threatening situation. With this case, we would like to point out the typical risks posed by the widespread application of AI tools not intended for medical decision-making.

In DCE-MRI, the degree of contrast uptake in normal fibroglandular tissue, i.e., background parenchymal enhancement (BPE), is a crucial biomarker linked to breast cancer risk and treatment outcome. In accordance with the Breast Imaging Reporting & Data System (BI-RADS), it should be visually classified into four classes. The susceptibility of such an assessment to inter-reader variability highlights the urgent need for a standardized classification algorithm. In this retrospective study, the first post-contrast subtraction images for 27 healthy female subjects were included. The BPE was classified slice-wise by two expert radiologists. The extraction of radiomic features from segmented BPE was followed by dataset splitting and dimensionality reduction. The latent representations were then utilized as inputs to a deep neural network classifying BPE into BI-RADS classes. The network’s predictions were elucidated at the radiomic feature level with Shapley values. The deep neural network achieved a BPE classification accuracy of 84 ± 2% (p-value < 0.00001). Most of the misclassifications involved adjacent classes. Different radiomic features were decisive for the prediction of each BPE class underlying the complexity of the decision boundaries. A highly precise and explainable pipeline for BPE classification was achieved without user- or algorithm-dependent radiomic feature selection.

Objective: This study develops a BI-RADS-like scoring system for vascular microcalcifications in mammographies, correlating breast arterial calcification (BAC) in a mammography with coronary artery calcification (CAC), and specifying differences between microcalcifications caused by BAC and microcalcifications potentially associated with malignant disease. Materials and Methods: This retrospective single-center cohort study evaluated 124 consecutive female patients (with a median age of 57 years). The presence of CAC was evaluated based on the Agatston score obtained from non-enhanced coronary computed tomography, and the calcifications detected in the mammography were graded on a four-point Likert scale, with the following criteria: (1) no visible or sporadically scattered microcalcifications, (2) suspicious microcalcification not distinguishable from breast arterial calcification, (3) minor breast artery calcifications, and (4) major breast artery calcifications. Inter-rater agreement was assessed in three readers using the Fleiss’ kappa, and the correlation between CAC and BAC was evaluated using the Spearman’s rank-order and by the calculation of sensitivity/specificity. Results: The reliability of the visual classification of BAC was high, with an overall Fleiss’ kappa for inter-rater agreement of 0.76 (ranging between 0.62 and 0.89 depending on the score). In 15.1% of patients, a BAC score of two was assigned indicating calcifications indistinguishable regarding vascular or malignant origin. In 17.7% of patients, minor or major breast artery calcifications were found (BAC 3–4). BAC was more prevalent among the patients with CAC (p < 0.001), and the severity of CAC increased with the BAC score; in the group with a BAC score of one, 15% of patients exhibited mild and severe CAC, in those with a BAC of two, this was 31%, in those with BAC of three, this was 38%, and in those with a BAC of four, this was 44%. The sensitivity for detecting CAC, based on the mammographic BAC score, was 30.3% at a specificity of 96.7%. Conclusions: The standardized visual grading of BAC in mammographies on a four-point scale is feasible with substantial interobserver agreement, potentially improving the treatment of patients with suspicious microcalcifications and CAC.

Objective: To investigate the prevalence and progression of macrocalcifications or sporadic scattered microcalcifications, breast arterial calcifications (BAC) and grouped microcalcifications in women undergoing lung transplantation (LTX). Materials and Methods: In this retrospective single-center cohort study, 176 adult female patients who underwent mammography between 2008 and 2025 were included: 82 LTX recipients and 94 age-matched controls. Mammographic findings were assessed using standardized BI-RADS criteria and a visual BAC scoring system. Clinical and demographic data were extracted from electronic medical records. Multivariable logistic regression and cumulative incidence analysis were used to evaluate associations and progression patterns. Interobserver agreement was assessed using Fleiss’ kappa. Results: BAC and grouped microcalcifications were significantly more prevalent in the LTX group in the last mammography (BAC: OR 6.57, 95% CI 2.34–20.7; microcalcifications: OR 14.6, 95% CI 3.93–73.9; both p < 0.001). Cumulative incidence analysis showed accelerated progression of BAC and grouped microcalcifications in LTX recipients (p ≤ 0.01), while macrocalcifications or sporadic scattered microcalcification progression did not differ significantly. BAC was often more extensive and potentially mimicked malignant findings. Interobserver agreement was highest for the four-level BAC scoring system (κ = 0.61), followed by BAC presence (κ = 0.59) and macrocalcifications (κ = 0.51), while grouped microcalcifications showed only fair agreement (κ = 0.33). Conclusions: Lung transplant recipients demonstrate significantly higher prevalence and faster progression of BAC and grouped microcalcifications compared to controls, complicating mammographic interpretation. Given their elevated risk of aggressive malignancies and diagnostic overlap between benign and suspicious calcifications, transplant recipients may benefit from tailored screening strategies.

Objective: This study systematically evaluates the association between breast arterial calcifications (BACs) on mammography and systemic vascular calcifications detected by computed tomography (CT) in female lung transplant recipients, representing the first investigation of this relationship in this population. Methods: This retrospective single-center study included 78 female LTX recipients who underwent both digital mammography and thoracoabdominal CT. BACs were graded on a four-point scale. Calcifications in seven arterial territories were visually assessed on CT with a binary scale (“present”, “not present”) and graded on a severity scale of systemic calcifications ranging from no involvement (0) and minor vascular calcification (1–4 vessels) to major vascular calcification (5–10 vessels). Associations between BACs and systemic vascular calcifications were analyzed using correlation, logistic regression, and ROC analysis. Results: BACs were present in 31 of 78 patients (40%). Vascular calcifications were frequent, most often affecting the thoracic aorta (82%), abdominal aorta (76%), and iliac arteries (72–73%). Coronary calcifications were more common in BAC-positive than BAC-negative patients (77% vs. 40%, p = 0.002). BAC grade correlated with the cumulative vascular calcification (ρ = 0.35, p = 0.0017). In ROC analysis, BACs discriminated patients with vascular calcification with fair accuracy (AUC 0.73, 95% CI 0.67–0.79). In multivariable logistic regression adjusted for age, diabetes, chronic kidney disease, and hypertension, BACs remained independently associated with systemic calcification, with an adjusted odds ratio of approximately 2.0 for ≥1 affected vascular territory. Interreader agreement for the 4-level BAC score was excellent with a quadratic-weighted κ of 0.91 and a linear-weighted κ of 0.88. Conclusions: BACs are common in female LTX recipients and independently predict systemic vascular calcifications. Their detection in routine mammography may provide a simple, opportunistic marker to support cardiovascular risk stratification in this high-risk population.

Purpose: Breast cancer screening relies primarily on two-dimensional (2D) digital mammography, which is limited by tissue superposition and compression-related patient discomfort. Dedicated spiral breast computed tomography (BCT) overcomes these limitations by providing isotropic, fully three-dimensional (3D) volumetric images without compression. However, translating artificial intelligence (AI) advancements to 3D BCT lesion detection is hindered by the scarcity of large-scale annotated 3D datasets and substantial computational constraints. The purpose of this study is to evaluate the feasibility of repurposing a pre-trained 2D mammography AI model for 3D BCT malignancy detection without dedicated model retraining. Methods: In this exploratory proof-of-concept study, the dataset comprised BCT examinations of female patients with malignant lesions. We developed a slab projection framework that systematically rotates the BCT volume and extracts overlapping tissue slabs to simulate mammography-like 2D images compatible with the input requirements of the pre-existing 2D mammography model. The 2D inferences were subsequently back-projected to their original 3D spatial coordinates and aggregated via a consensus voting scheme. Optimization and performance evaluation were performed on the same dataset to establish an internal baseline. Object-level detection performance was assessed using the F1 score, and segmentation quality was evaluated using the Dice coefficient. Results: Application of the proposed framework enabled 3D lesion localization in BCT volumes without requiring domain-specific training. An optimal configuration was found with a sparser angular sampling combined with medium slab thickness (45° angular spacing, 50-voxel thickness), which achieved an F1 score of 0.346, with 48.3% precision and 26.9% recall. Evaluation of segmentation quality corroborated these findings, yielding a maximum mean Dice coefficient of 0.336 for the 45°/30-voxel configuration. Conclusions: This exploratory proof-of-concept demonstrates the technical feasibility of adapting a pre-trained 2D mammography AI model to volumetric BCT without architectural modifications or retraining. The reported performance represents an internal same-dataset baseline under substantial domain shift and should not be interpreted as generalizable or clinically deployable performance. These findings provide a foundation for future domain-adapted models and independent external validation of AI-based tumour detection in breast CT.