Radiologia Medica最新文献

Purpose: To examine how reading grade levels affect stakeholder preferences based on a trade-off between accuracy and readability.

Material and methods: A retrospective study of 500 radiology reports from academic and community hospitals across five imaging modalities was conducted. Reports were transformed into 11 reading grade levels (7-17) using Gemini. Accuracy, readability, and preference were rated on a 5-point scale by radiologists, physicians, and laypersons. Errors (generalizations, omissions, hallucinations) and potential changes in patient management (PCPM) were identified. Ordinal logistic regression analyzed preference predictors, and weighted kappa measured interobserver reliability.

Results: Preferences varied across reading grade levels depending on stakeholder group, modality, and clinical setting. Overall, preferences peaked at grade 16, but declined at grade 17, particularly among laypersons. Lower reading grades improved readability but increased errors, while higher grades improved accuracy but reduced readability. In multivariable analysis, accuracy was the strongest predictor of preference for all groups (OR: 30.29, 33.05, and 2.16; p <0 .001), followed by readability (OR: 2.73, 1.70, 2.01; p <0.001).

Conclusion: Higher-grade levels were generally preferred due to better accuracy, with a range of 12-17. Further increasing grade levels reduced readability sharply, limiting preference. These findings highlight the limitations of unsupervised LLM transformations and suggest the need for hybrid approaches that maintain original reports while incorporating explanatory content to balance accuracy and readability.

Purpose: To evaluate the effectiveness of IL-17 and IL-23 inhibitors in psoriatic nail and enthesis involvement by ultrasonography with the use of high-frequency probes (HFUS). To correlate the obtained HFUS findings with disease activity of patients with psoriatic arthritis (PsA).

Material and methods: Consecutive early naïve patients with PsA underwent HFUS on nails and entheses before and after 24 weeks of treatment with IL-17 or IL-23 inhibitor. The Brown University Nail Enthesis Scale (BUNES), considering morphometry and Power Doppler (PD), and the Madrid Sonography Enthesitis Index (MASEI) score were used to evaluate these features. HFUS findings were correlated with the extension of the disease on skin by Psoriasis Area and Severity Index (PASI) and joints by Disease Activity Index for Psoriatic Arthritis (DAPSA).

Results: Twenty early naïve patients with PsA were treated for 24 weeks with an IL-17 or IL-23 inhibitor. A significant reduction of BUNES PD was observed considering the whole cohort of patients receiving these drugs (p = 0.044), whereas, despite a trend, no significant difference was reported comparing BUNES morphometry. The BUNES PD correlated with PASI (r = 0.466, p = 0.030) and with DAPSA (r = 0.444, p = 0.032), whereas BUNES morphometry did not. A significant reduction of MASEI was observed considering the whole assessed cohort of patients treated with these drugs (p = 0.045). The MASEI correlated with both PASI (r = 0.429, p = 0.037) and DAPSA (r = 0.499, p = 0.017).

Conclusions: This proof-of-concept study demonstrated that the assessment by HFUS may provide additional accurate information about the effectiveness of IL-17 and IL-23 inhibitors in psoriatic nail and enthesis involvement.

Over the past decades, neoadjuvant systemic treatment (NAT) has been increasingly adopted in early-stage breast cancer (BC), highlighting the need for a more accurate assessment of treatment response. Imaging tools such as [¹⁸F]2-fluoro-2-deoxy-D-glucose ([¹⁸F]FDG) positron emission tomography combined with computed tomography (PET/CT) may enhance diagnostic accuracy in this context. By comprehensively reviewing the available literature, [¹⁸F]FDG PET/CT generally shows good sensibility but lower specificity for predicting and evaluating pathological complete response (pCR), respectively, during NAT and preoperatively, in both the breast and lymph nodes. Thereby its use may support timely escalation of systemic treatment or surgery in patients with poor metabolic response. However, definitive conclusions are limited by small, heterogeneous studies with variable patient selection, timing, and response definitions. Consequently, while international guidelines remain inconsistent, further evidence is needed to define its role in response assessment, establish the optimal use in clinical practice, and clarify its integration into (de)-escalation strategies.

Acute chest pain is a common and challenging reason for emergency department visits and requires prompt and systematic evaluation to address potential life-threatening conditions, minimize risks and manage emergency department overcrowding. This updated consensus statement outlines the appropriate management of patients presenting to the emergency department with acute chest pain, emphasizing the timing and utility of non-invasive advanced imaging (particularly coronary computed tomography angiography) aiming to improve rapid and accurate diagnosis of both cardiac or non-cardiac causes improving patient safety, outcomes, and resource utilization efficiency. The writing committee was composed of members and experts from both the Italian Society of Cardiology (SIC) and the Italian Society of Medical and Interventional Radiology (SIRM) who worked jointly to create a cohesive approach in the field of acute chest pain. This structured approach may streamline diagnostic workflows in the emergency setting and support earlier, more appropriate patient management.

Purpose: Immunotherapy-based neoadjuvant chemoradiotherapy (iNCRT) has recently emerged for proficient mismatch repair/microsatellite stable (pMMR/MSS) locally advanced rectal cancer (LARC). Accurate identification of pathological complete response for primary tumor (ptPCR) post-treatment is critical for selecting patients eligible for watch-and-wait strategies. This study aimed to evaluate arterial-phase mucosal linear enhancement (AMLE) on contrast-enhanced T1-weighted imaging (CE-T1WI) for predicting ptPCR after iNCRT in pMMR/MSS LARC, compared to conventional T2-weighted/diffusion-weighted imaging (T2DWI) and rectal endoscopy.

Methods: This retrospective study included patients with pMMR/MSS LARC who underwent total mesorectal excision after iNCRT between July 2022 and Oct 2024 at a tertiary referral academic center. Preoperative re-staging examinations were rectal endoscopy and MRI, included T2DWI and arterial-phase CE-T1WI for primary tumor assessment. Baseline and post-therapy features associated with ptPCR were identified using univariate and multivariable regression analysis. Diagnostic performance of endoscopy and different MRI protocols to identify ptPCR after iNCRT was evaluated using ROC curves.

Results: In total, 75 patients (mean age, 57 years ± 10 [SD]; 54 male patients) were assessed. At histopathology, 29 patients achieved ptPCR. AMLE was more common in the ptPCR group than in the non-ptPCR group after iNCRT (75.9% vs 15.2%, respectively; P < 0.001). AMLE was associated with higher odds of ptPCR in the multivariable regression analysis (odds ratio, 19.14; 95% CI 4.03, 90.87; P = 0.001). And AMLE exhibited the best diagnostic performance in identifying ptPCR after iNCRT, with highest sensitivity, specificity, PPV, NPV, and AUC (0.80; 95% CI 0.70, 0.89).

Conclusion: AMLE at CE-TlWI of rectal MRI could be a potential indicator of ptPCR after a new iNCRT in pMMR/MSS LARC, suggesting a relatively credible preoperative evaluation strategy for this group of patients in clinical practice to accurately exclude residual tumors and select watch-and-wait approach, avoiding unnecessary surgery.

Purpose: To assess the performance of state-of-the-art large language models in classifying vertebral metastasis stability using the Spinal Instability Neoplastic Score (SINS) compared to human experts, and to evaluate the impact of task-specific refinement including in-context learning on their performance.

Material and methods: This retrospective study analyzed 100 synthetic CT and MRI reports encompassing a broad range of SINS scores. Four human experts (two radiologists and two neurosurgeons) and four large language models (Mistral, Claude, GPT-4 turbo, and GPT-4o) evaluated the reports. Large language models were tested in both generic form and with task-specific refinement. Performance was assessed based on correct SINS category assignment and attributed SINS points.

Results: Human experts demonstrated high median performance in SINS classification (98.5% correct) and points calculation (92% correct), with a median point offset of 0 [0-0]. Generic large language models performed poorly with 26-63% correct category and 4-15% correct SINS points allocation. In-context learning significantly improved chatbot performance to near-human levels (96-98/100 correct for classification, 86-95/100 for scoring, no significant difference to human experts). Refined large language models performed 71-85% better in SINS points allocation.

Conclusion: In-context learning enables state-of-the-art large language models to perform at near-human expert levels in SINS classification, offering potential for automating vertebral metastasis stability assessment. The poor performance of generic large language models highlights the importance of task-specific refinement in medical applications of artificial intelligence.

Ultra-low-field magnetic resonance imaging (ULF-MRI), operating below 0.2 Tesla, is gaining renewed interest as a re-emerging diagnostic modality in a field dominated by high- and ultra-high-field systems. Recent advances in magnet design, RF coils, pulse sequences, and AI-based reconstruction have significantly enhanced image quality, mitigating traditional limitations such as low signal- and contrast-to-noise ratio and reduced spatial resolution. ULF-MRI offers distinct advantages: reduced susceptibility artifacts, safer imaging in patients with metallic implants, low power consumption, and true portability for point-of-care use. This narrative review synthesizes the physical foundations, technological advances, and emerging clinical applications of ULF-MRI. A focused literature search across PubMed, Scopus, IEEE Xplore, and Google Scholar was conducted up to August 11, 2025, using combined keywords targeting hardware, software, and clinical domains. Inclusion emphasized scientific rigor and thematic relevance. A comparative analysis with other imaging modalities highlights the specific niche ULF-MRI occupies within the broader diagnostic landscape. Future directions and challenges for clinical translation are explored. In a world increasingly polarized between the push for ultra-high-field excellence and the need for accessible imaging, ULF-MRI embodies a modern "David versus Goliath" theme, offering a sustainable, democratizing force capable of expanding MRI access to anyone, anywhere.

Objective: Describe the early non-arthrographic MRI appearance of the acetabular labrum after arthroscopic surgery for femoroacetabular impingement and labrum repair.

Methods: Eleven subjects (12 hips, 8 hips of females; mean age: 25.8 years, SD: 3.0) with a pre-operative MRI demonstrating a labrum tear and symptoms of femoroacetabular impingement were prospectively enrolled. Non-arthrographic images were obtained on a 3 T MRI scanner < 4 weeks after arthroscopic surgery for femoroacetabular impingement. Imaging features of the labrum, capsule, and cartilage were systematically assessed by two independent fellowship-trained musculoskeletal radiologists. Disagreements were resolved through consensus mediated by a musculoskeletal radiologist with 20 + years of experience and expertise in hip imaging.

Results: The appearance of a persistent labral tear and increased intrasubstance signal was observed in all hips. The labrum appeared shortened in 92% (11/12). The geographic distribution of abnormal labral signal corresponded to the same number of labrum quadrants treated surgically in 67% (8/12). There was an even distribution of hips showing abnormal signal across a smaller and larger portion of the labrum than was treated arthroscopically, seen in 17% (2/12), respectively. The appearance of a capsular defect was observed in 92% (11/12).

Conclusion: In the first 4 weeks after arthroscopic labrum repair surgery for femoroacetabular impingement, it is common for the labrum to appear shortened with a persistent appearance of a labrum tear and increased signal in the repaired segment. The capsule often appears discontinuous, even when capsular closure is performed.

Aim: The AI case malignancy score (AI-CMS) represents the AI algorithm's confidence (from 0 to 100%) that a mammography exam is malignant. This work aims to retrospectively evaluate, through simulation on real-world data, a strategy that integrates AI-CMS into a standard screening scenario to reduce the radiologists' workload.

Methods: A total of 89176 consecutive screening exams from the 2023-2024 Reggio Emilia Breast Screening Program (REBSP) were retrospectively considered, which included 479 biopsy-proven cancers (interval cancers were only partially available, therefore false negatives beyond those detected in the real screening workflow could not be assessed). In the proposed strategy, computer-aided detection (CAD) acts as a reader (CR), recalling women with an AI-CMS greater than a predefined threshold (ranging from 5 to 25%). If the first radiologist (HR1) disagrees with CR, the case goes to a second radiologist (HR2) and, in case of human disagreement, to a third radiologist (HR3). For each threshold, final recall rate (RR), cancer detection rate (CDR), number of detected cancers (DC), predictive positive value (PPV) of recalls, false positive rate (FPR), human reading workload, and economic impact were estimated.

Results: At AI-CMS thresholds of 5%, 8%, 10%, 15%, 20%, and 25%, human workload decrease ranged from 13.4% to 36.1%. The final RR decreased between 4.3% and 4.0%, slightly lower than the current 4.4% with human double reading. The PPV ranged from 12.6% to 13.3%, higher than the current PPV of 12.2%. The FPR ranged from 3.8% to 3.5%, down from the current 3.9%. With thresholds up to 5%, no true positive cases were missed, maintaining the CDR of 5.4‰ of those detected by current double reading. Considering CAD payback periods of either 6 or 8 years, financial savings from our strategy ranged from approximately 17800 to over 590,000€.

Conclusion: Integrating AI-CMS support into a standard screening scenario could substantially reduce the screen-reading workload and slightly reduce unnecessary ascertainments without affecting the cancer detection rate. This approach, although limited by its retrospective simulation design and the partial availability of interval cancer data, has also proven to be economically sustainable.