AI in Imaging—New Perspectives, 2nd Edition

Background and Objectives: Contrast-enhanced mammography (CEM) provides both morphological and functional information and may reflect breast cancer biology similarly to Magnetic Resonance Imaging (MRI). Materials and Methods: This single-center retrospective study included 399 women with Breast Imaging Reporting and Data System (BI-RADS) category 0 screening mammograms who subsequently underwent CEM. A total of 76 malignant lesions (68 invasive cancers, 8 ductal carcinoma in situ (DCIS)) with complete imaging and pathology data were analyzed. Invasive cancers were classified into luminal A, luminal B, luminal B/Human Epidermal Growth Factor Receptor 2 (HER2)-positive, HER2-enriched, and triple-negative, and grouped as luminal (Group 1) versus HER2-positive/triple-negative (Group 2). Results: Luminal subtypes predominated (47 of 68, 69%), while 21 of 68 (31%) were HER2-positive or triple-negative. Most cancers appeared as masses with spiculated margins and heterogeneous enhancement. Significant differences were observed in mass shape (p = 0.03) and internal enhancement (p = 0.01). Luminal tumors were more often irregular and spiculated with heterogeneous enhancement, whereas the HER2-positive/triple-negative tumors more frequently appeared round with rim or homogeneous enhancement. Deep learning-derived malignancy scores (iCAD ProFound AI^®) demonstrated good diagnostic performance (area under the curve (AUC) = 0.744, 95% confidence interval (CI) 0.654–0.821, p < 0.001). The median AI score was significantly higher in malignant compared with benign lesions (70% [interquartile range (IQR) 47–93] vs. 38% [IQR 25–61]; Mann–Whitney U test, p < 0.001). Among malignant lesions, iCAD scores varied across molecular subtypes, with higher median values observed in Group 1 versus Group 2 (87% vs. 55%), although the difference was not statistically significant (Mann–Whitney U test, p = 0.35). Conclusions: CEM features mirrored subtype-specific phenotypes previously described with MRI, supporting its role as a practical tool for enhanced tumor characterization. Although certain imaging and AI-derived parameters differed descriptively across subtypes, no statistically significant differences were observed. As deep-learning models continue to evolve, the integration of AI-enhanced CEM into clinical workflows holds strong potential to improve lesion characterization and risk stratification in personalized breast cancer diagnostics. Full article

Background and Objectives: To validate a computed tomography (CT) measure of tendon yaw (TY) and determine its diagnostic specificity, precision, and clinical relevance in recurrent patellar instability (RPI) in comparison with standard imaging tests (SIT1, SIT2), femoral trochlear dysplasia (FTD), and vastus medialis obliquus (VMO) morphology. Materials and Methods: This retrospective cross-sectional study included 113 subjects (187 knees) examined using a standardized CT protocol for RPI following strict exclusion criteria. TY, SIT1, and SIT2 were measured using predefined axial landmarks. VMO cross-sectional area was assessed at three standardized levels. Diagnostic performance, measurement precision, and interrater agreement were evaluated. Results: TY significantly distinguished recurrent dislocators from nondislocators (p = 0.003) and was independent of age, sex, laterality, and femoral, tibial, or knee rotation (p ≥ 0.42). A threshold of ≥22° demonstrated high diagnostic specificity (92%; 95% CI, 85–97%), with a normal cutoff defined as ≤12°. Measurement precision was approximately 90%. SIT1 and SIT2 were influenced by femoral and knee rotation but not tibial rotation. All imaging tests were associated with FTD (p < 0.0001). No significant correlation was found between any imaging test and VMO area, although VMO was reduced in recurrent dislocators and in women. Conclusions: TY is a direct and highly specific CT measure of extensor mechanism yaw (z-axis rotation) that avoids indirect osseous and soft-tissue surrogates, supporting confirmatory diagnostic assessment and preoperative planning in RPI. Full article

Background and Objectives: It is unknown whether the tibial tuberosity–tibial intercondylar midpoint (TT–TIM) distance can be interchangeably measured on axial computed tomography (CT) and magnetic resonance imaging (MRI). The objective of this retrospective cross-sectional comparative study was to evaluate the intermethod agreement of the TT–TIM distance on axial CT and MRI and its bias towards tibial rotation (TR), age, sex, and body side. Materials and Methods: On axial CT and MRI of 15 consecutive knee pairs where each pair belonged to the same patient with no pathology affecting the tibial circumference and tibial tuberosity, TT–TIM distance and TR were measured by two blinded radiologists at 2-week intervals. Upon checking the symmetry of distributions (Shapiro–Wilk test), differences between matched knee pairs (Wilcoxon signed-rank test), intermethod (Bland–Altman plot) and interrater agreement (intraclass correlation coefficient [ICC]), and correlations (Spearman rank correlation) were assessed. Results: The mean intermethod difference in TT–TIM distance was not statistically significant (−0.4 mm [−1.82, 0.96]; p = 0.52). The TT–TIM distance did not differ between knee pairs (p = 0.68), its interrater agreement was almost perfect (ICC > 0.81), and no bias towards TR (p > 0.66), age (p > 0.14), sex (p = 0.66), and body side (p > 0.37) was found. Conclusions: The TT–TIM distance can be interchangeably measured on axial CT and MRI with almost perfect interrater agreement, unbiased towards TR, age, sex, and body side. Full article

Background and Objectives: Rapid diagnosis is fundamental to acute ischemic stroke management; however, access to neuroradiological expertise remains limited. This scoping review maps the diagnostic accuracy, workflow impact, and cost-effectiveness of leading AI platforms (Brainomix, Aidoc, RapidAI, and Viz.ai), characterizing industry and peer-reviewed metrics. Materials and Methods: Following PRISMA-ScR guidelines, we searched PubMed, Cochrane Library, and HTA repositories for studies (2019–2025). Using a PICO-based framework, 29 studies were included for thematic mapping of the technological landscape. Results: Twenty-nine studies were included. Platforms show high proximal LVO sensitivity (78–97%), while performance for distal/MVO and posterior circulation occlusions was more variable. RapidAI is frequently mapped using historical perfusion trial parameters; however, volumetric discrepancies with platforms like Viz.ai indicate outputs are not interchangeable. Brainomix shows extensive validation for automated NCCT ASPECTS in triage. Aidoc demonstrates operational advantages via worklist prioritization, while. Viz.ai is associated with door-to-puncture time reductions (11–25 min). Economically, cost-effectiveness is driven by improved functional outcomes and expanded access to thrombectomy, rather than labor substitution. Conclusions: AI platforms function as diagnostic safety nets and workflow optimizers. Reported roles, such as perfusion-centric analysis (RapidAI) or workflow coordination (Viz.ai), reflect current research trends rather than definitive technological superiority. Institutional selection should consider these evidence clusters alongside local validation and specific clinical priorities. Full article

Background and Objectives: Accurate evaluation of vulnerable carotid atherosclerotic plaques remains essential for preventing ischemic stroke. Conventional imaging modalities such as ultrasound and computed tomography angiography (CTA) have limited capacity to identify histopathological features of plaque instability, including fibrous cap rupture, lipid-rich necrotic core, and intraplaque hemorrhage. Artificial intelligence (AI) techniques—particularly deep learning (DL) and radiomics—have recently emerged as valuable adjuncts to standard imaging, achieving AUC values of 0.83–0.99 across modalities in identifying vulnerable plaques. This scoping review summarizes the available evidence on the application of AI in the detection and assessment of vulnerable carotid plaques. Methods: A systematic search of the English-language literature was conducted in MEDLINE, SCOPUS, and CENTRAL from 2000 to 30 June 2025, following the PRISMA-ScR framework. Eligible studies applied AI-based approaches (machine learning, deep learning, or radiomics) to evaluate carotid plaque vulnerability using ultrasound, CTA, or MRI. Extracted outcomes included diagnostic performance, correlation with histopathology or neurological events, and predictive modeling for stroke risk. Results: Of 201 records screened, 12 studies met inclusion criteria (ultrasound = 6; CTA = 4; high-resolution MRI = 2; publication years 2021–2025). All reported receiver operating characteristic area-under-the-curve (ROC-AUC) values for endpoints related to plaque vulnerability (symptomatic versus asymptomatic status, presence of intraplaque hemorrhage or lipid-rich necrotic core, fibrous-cap surrogates, and, less frequently, short-term cerebrovascular events). For ultrasound, contrast-enhanced videomics achieved an AUC of 0.87 (10 centers; n = 205), B-mode texture/radiomics reached 0.87 (n = 150), and segmentation-assisted models 0.827 (n = 202); other ultrasound models reported AUCs of 0.88–0.91. For CTA, a symptomatic-plaque machine-learning model yielded AUC 0.89 ( n = 106); a perivascular-adipose-tissue (PVAT) radiomics nomogram achieved AUC 0.836 on external validation; a histology-referenced pilot attained AUC 0.987; and one mild-stenosis TIA model reported ROC performance. For high-resolution MRI (HR-MRI), radiomics-based models showed AUC 0.835–0.864 in single-modality cohorts and up to 0.984 with multi-contrast inputs. Across modalities, AUC ranges were: ultrasound 0.827–0.91, CTA 0.836–0.987 (external 0.836), and HR-MRI 0.835–0.984. Only two out of twelve studies performed external validation; calibration and decision-curve analyses were rarely provided, and most cohorts were single-center, limiting generalizability. Conclusions: AI demonstrates strong potential as a complementary tool for evaluating carotid plaque vulnerability, with high diagnostic performance across imaging modalities. Reported AUCs ranged from 0.83 to 0.99 based primarily on internal or hold-out validation, representing the upper bound of theoretical rather than real-world performance. Nonetheless, large prospective multicenter studies with standardized protocols, histopathological correlation, and external validation are required before clinical integration into stroke prevention pathways. Full article

Technology is increasingly shaping human life, particularly in healthcare, where recent advancements have revolutionized patient care. Despite these advances, the World Health Organization’s (WHO) definition of health remains rooted in traditional notions, raising questions about its adequacy in light of technological progress. This paper explores the conceptual and practical limitations of the current definition and argues for its revision to encompass the role of technology in health. This paper examines the evolving landscape of healthcare technology and its philosophical implications, drawing on theories such as the Extended Health Hypothesis and the Extended Mind Hypothesis. It claims that health extends beyond traditional biological boundaries and includes the influence of technology on well-being. This paper advocates for a re-examination of the WHO definition of health to reflect the integral role of technology in modern healthcare. Recognizing technology as part of health necessitates a broader conceptual framework that acknowledges the interconnectedness of biology, technology, and human well-being. Given technology’s transformative role in healthcare, this paper argues for a revaluation of the WHO’s definition of health to encapsulate the evolving relationship between technology and human well-being. At the end, we propose a new definition recognizing that health is a dynamic state of physical, mental, social, and technological well-being, wherein individuals can achieve optimal quality of life through the harmonious integration of biological, psychological, and technological factors. This state encompasses not only the absence of disease but also the effective utilization of advanced technologies. Full article