Carlo Cosimo Quattrocchi

Background: For radiology residents, the steep learning curve of cross-sectional anatomy (especially in CT and MRI) demands more efficient and engaging educational tools. In recent years, game-based learning (GBL) and gamification have emerged as powerful strategies to enhance postgraduate education by leveraging ‘active recall’ and ‘spaced repetition’ within a competitive framework. Here we describe the context of ANATOMIADI and assess the perceived educational impact. Materials and methods: Image datasets were anonymized, archived, and manually labeled to highlight specific anatomical structures. Over 400 unique games were developed, categorized by anatomical system and tiered into three levels of difficulty. A structured feedback survey was designed and distributed to the participants after the event to capture data on different domains regarding the educational value, gamification and engagement, platform usability and team collaboration, technical workflow, logistics, scientific accuracy, fairness, and quality assessment. Results: ANATOMIADI challenge registered an attendance of 141 participants representing 28 residency programs across Italy. The evaluation of the event’s perceived value yielded a unanimous positive response; indeed, 100% of the participants recommended that the competition be repeated in future academic years. Based on the required level of knowledge, the event was recommended to residents in their 3rd (54/63 responses) and 4th year (48/63 responses) of postgraduate education. Conclusion: By integrating high-fidelity imaging with interactive game mechanics, the ANATOMIADI challenge not only fostered anatomical learning but also built the foundation for a more collaborative and technologically adept generation of radiologists. Key Points: Question: In the era of high-resolution multidetector CT and advanced MRI, the volume of anatomical data that a resident in radiology must process is unprecedented. Findings: We developed a context using image-based puzzle games to challenge different residency schools in radiology on imaging-based anatomical structures and rules. Critical relevance statement: ANATOMIADI is the first national competition based on radiological anatomy and dedicated to residents. By using an inclusive “twinning” framework among residency programs, it transforms dense theoretical study into a highly motivating, collaborative, and social learning experience.

Extreme alpine summer sports are increasingly popular and expose participants to high-energy trauma in remote mountain environments. This pictorial essay reviews the emergency radiology of severe acute injuries associated with down-hill mountain biking, rock climbing, paragliding, BASE jumping, canyoning, and rafting, with emphasis on mechanism-based imaging interpretation. Injury patterns differ across disciplines but are largely determined by velocity, fall height, landing posture, impact surface, axial loading, torsional forces, and water-related hazards. Down-hill mountain biking commonly produces extremity, thoracic, craniofacial, abdominal, and spinal injuries after high-speed crashes or handlebar impact. Rock climbing and paragliding frequently involve falls from height and hard landings, leading to thoracolumbar fractures, pelvic trauma, calcaneal or ankle injuries, and, in severe cases, neurologic compromise or visceral injury. BASE jumping is associated with high-velocity landing trauma, particularly involving the lower limbs, pelvis, and spine. Canyoning and rafting combine blunt trauma with environmental risks such as submersion, aspiration, hypothermia, and drowning-related complications. In high-energy trauma or polytrauma, whole-body computed tomography is the cornerstone of emergency assessment, enabling rapid evaluation of head, spine, chest, abdomen, and pelvis. Radiography remains useful for isolated appendicular injuries, whereas magnetic resonance imaging is essential for spinal cord, ligamentous, marrow, and selected soft-tissue injuries. Awareness of sport-specific mechanisms helps radiologists optimize image selection, maintain an appropriate search pattern, recognize injuries that may coexist after axial loading, and communicate urgent findings promptly. A mechanism-oriented approach may improve diagnostic accuracy, guide multidisciplinary management, and reduce missed injuries in patients presenting after alpine summer extreme sports trauma.

Parkinson’s disease (PD) may benefit from non-pharmacological motor–cognitive rehabilitation, but sensitive neuroimaging markers of training-related brain changes remain limited. This study investigated whether 4 weeks of daily Quadrato Motor Training (QMT) modulate resting-state functional connectivity (FC) in PD and secondarily explored whether whole-brain radiomic features derived from T1-weighted and fractional anisotropy (FA) images could detect pre–post differences over this short intervention interval. Fifty patients with idiopathic PD were randomized to QMT or a SHAM repetitive stepping condition, and 48 completed the protocol (25 SHAM, 23 QMT). MRI was acquired at baseline and after 4 weeks and included resting-state fMRI, 3D T1-weighted imaging, and diffusion-derived FA maps. Resting-state fMRI was analyzed using independent component analysis and dual regression, whereas an IBSI-compliant radiomics workflow and machine-learning models were used for exploratory scan-level classification. Compared with baseline, the SHAM group showed reduced synchronization across several resting-state networks, whereas the QMT group showed increased synchronization in the right sensorimotor and frontoparietal networks and no significant reductions. Between-group analyses showed lower delta-FC in SHAM than QMT in the cerebellar and sensorimotor networks. In contrast, radiomics showed limited discrimination between pre- and post-QMT scans; the best model achieved a ROC-AUC of 0.65 with near-chance accuracy, and no selected predictor remained significant after multiple-comparison correction. These findings suggest that QMT may support short-term functional network stability or task-relevant reorganization in PD relative to the SHAM condition, whereas whole-brain structural radiomics appears less sensitive for detecting early training-related effects in this setting.

Purpose: To assess whether residence status influences the use of radiological services in emergency departments (EDs) in a high-tourism region of Northern Italy. Methods: This retrospective study analyzes all ED visits in the Autonomous Province of Trento from January 1, 2018 to December 31, 2024. Patients were categorized as residents or non-residents based on municipality of residence. Demographic, clinical, and contextual variables were extracted from the ED database. Regression models (OLS, Poisson, negative binomial, and logistic) were applied to evaluate determinants of radiological examination volume and workload, and the impact of residence status, including interaction with triage priority codes. Results: The sample includes 738,864 patients who underwent at least one radiological examination (overall volume of 1,474,937 imaging examinations). Non-residents accounted for 18.2% of patients and 20% of all radiological examinations. On average, they underwent significantly more imaging per visit than residents (2.19 vs. 1.95), even after controlling for confounding variables. Differences were most pronounced in high-priority cases: non-residents with red triage codes received nearly four additional examinations. Skeletal imaging was particularly over-represented among non-residents, consistent with trauma-related visits during tourism. Logistic regression showed non-residents had 31.9% higher odds of undergoing disproportionately high imaging volumes. Conclusion: Residence status significantly influences diagnostic imaging use in emergency settings. Non-residents, particularly in severe clinical conditions, undergo more extensive radiological evaluation. This likely reflects diagnostic uncertainty and lack of prior medical history. Findings underscore the need for adaptive resource planning in touristic areas and call for further studies on clinical appropriateness and outcome impact.

Objectives: To analyze the quality and appropriateness of head CT referrals from the emergency department (ED) of a single hospital in Italy. Materials and methods: A quality care study was designed to retrospectively identify consecutive head CT referrals generated from the ED of a tertiary hospital between January 1 and April 30, 2022. Referral quality was assessed using the Reason for Exam Imaging Reporting and Data System (RI-RADS), while referral appropriateness was evaluated according to the American College of Radiology (ACR) criteria. Results: We included 2908 imaging requests, of which 620 (21%) were adequate (RI-RADS A or B) and 2288 (79%) were inadequate (RI-RADS C or D) in terms of quality. In 410 cases, it was not possible to evaluate the appropriateness of the requests according to the ACR guidelines due to the lack of clinical data. Among the 2498 evaluable requests, 25% were classified as usually not appropriate. Of the requests with RI-RADS A or B, 84% were appropriate. Conversely, among the evaluable requests with RI-RADS C or D, the percentage of appropriate requests dropped to 70%. Of all patients with inappropriate requests, 98% did not suffer from acute cerebral diseases according to imaging, with headache and syncope being the primary clinical indications. Analysis of positivity rates revealed a significant difference between appropriate and inappropriate CT scans (11% vs 1%; p-value < 0.001). Conclusion: The recent increase in head CT scan requests in the ED is not completely justified and could be mitigated by improving the quality and appropriateness of referrals. Critical relevance statement: Excessive head CT requests in the ED cause needless radiation, pollution, and costs. Integrating guidelines and prospective justification with clear documentation in patient records, along with improved staff training and a no-blame culture, are key to reducing unnecessary imaging. Key Points: RI-RADS scores the quality, while the ACR criteria assess the appropriateness of imaging referrals. Most ED head CT requests lacked quality (especially lacking a specific diagnostic question) and were often clinically inappropriate. Appropriate head CT indication strongly predicted finding acute cerebral pathology on imaging. Graphical

Susceptibility-weighted imaging (SWI) is a magnetic resonance imaging (MRI) sequence sensitive to substances that alter the local magnetic field, such as calcium and iron, allowing phase information to distinguish between them. SWI is a 3D gradient–echo sequence with high spatial resolution that leverages both phase and magnitude effects. The interaction of paramagnetic (such as hemosiderin and deoxyhemoglobin), diamagnetic (including calcifications and minerals), and ferromagnetic substances with the local magnetic field distorts it, leading to signal changes. Neurodegenerative diseases are typically characterized by the progressive loss of neurons and their supporting cells within the neurovascular unit. This cellular decline is associated with a corresponding deterioration of both cognitive and motor abilities. Many neurodegenerative disorders are associated with increased iron accumulation or microhemorrhages in various brain regions, making SWI a valuable diagnostic tool in clinical practice. Suggestive SWI findings are known in Parkinson’s disease, Lewy body dementia, atypical parkinsonian syndromes, multiple sclerosis, cerebral amyloid angiopathy, amyotrophic lateral sclerosis, hereditary ataxias, Huntington’s disease, neurodegeneration with brain iron accumulation, and chronic traumatic encephalopathy. This review will assist radiologists in understanding the technical framework of SWI sequences for a correct interpretation of currently established MRI findings and for its potential future clinical applications.

Purpose: Evidence supporting the reliability of magnetic resonance imaging (MRI) Neck Imaging Reporting and Data System (NI-RADS) is currently limited. This study aims to evaluate the interrater agreement of MRI NI-RADS among radiologists with varying levels of expertise in nasopharyngeal carcinoma (NPC) patients. Material and methods: We designed an observational retrospective study to identify follow-up MRIs in patients who had undergone radiation therapy. Five radiologists (2 head and neck experts, 1 general radiologist, and 2 residents in radiology) scored each MRI using NI-RADS. Kappa (κ) and percentage of agreement (POA) were calculated for the ultimate score and for each individual feature of the NI-RADS (primary tumor size, signal on T2-weighted images, contrast enhancement, diffusion restriction, and lymph node size). Agreement was analyzed also separately for the first follow-up MRI and subsequent scans. Results: Thirty patients were included (a total of 97 MRIs per rater). Interreader agreement between all readers was moderate for NI-RADS (κ = 0.41; POA = 81%). The first follow-up showed a low reliability between the head and neck expert radiologist and the two radiology residents for both primary tumor contrast enhancement and size assessment (κ = 0.02; POA = 31% and κ = 0.17; POA = 38%, respectively), while there was a high level of agreement in the analysis of diffusion-weighted imaging (DWI) (κ = 0.79; POA = 96%). Conclusion: MRI NI-RADS has a moderate interrater agreement in NPC patients after radiation therapy. Educational effort should focus on the assessment and interpretation of primary tumor contrast enhancement and size in the first examination performed after treatment, by also considering information derived from DWI.

Standardized frameworks for interpreting medical images, such as the radiological Reporting and Data Systems (RADS), are designed to improve the consistency and accuracy of radiological assessments across different imaging modalities, anatomical locations, and disease processes. Clear communication and information sharing between radiologists and referring physicians, including surgeons, is a key goal of the RADS guidelines. Therefore, familiarity with these guidelines is crucial for all physicians involved in patient care. This review synthesizes current RADS guidelines relevant to surgical practice. Our analysis identified 28 radiological RADS with potential applications in surgical workflows, primarily in oncology. Of the RADS examined, nine were validated by the American College of Radiology (ACR), one was validated through a collaboration between the ACR and other scientific societies, and seventeen were developed by other scientific organizations. Numerous surgical specialties may encounter RADS in clinical practice, including neurosurgery, head and neck surgery, cardiovascular surgery, thoracic surgery, endocrine surgery, breast surgery, gastrointestinal surgery, hepatobiliary surgery, gynecological surgery, urological surgery, orthopedic surgery, emergency surgery, and surgical oncology. The effective utilization and validation of RADS necessitates close collaboration between radiologists and surgeons, coupled with widespread education for all healthcare professionals involved in patient care. Artificial intelligence software will play an important role in facilitating the dissemination and use of RADS in clinical practice.

The high volume of emergency room patients often necessitates head CT examinations to rule out ischemic, hemorrhagic, or other organic pathologies. A system that enhances the diagnostic efficacy of head CT imaging in emergency settings through structured reporting would significantly improve clinical decision making. Currently, no AI solutions address this need. Thus, our research aims to develop an automatic radiology reporting system by directly analyzing brain anomalies in head CT data. We propose a multi-branch CNN-LSTM fusion network-driven system for enhanced radiology reporting in emergency settings. We preprocessed head CT scans by resizing all slices, selecting those with significant variability, and applying PCA to retain 95% of the original data variance, ultimately saving the most representative five slices for each scan. We linked the reports to their respective slice IDs, divided them into individual captions, and preprocessed each. We performed an 80-20 split of the dataset for ten times, with 15% of the training set used for validation. Our model utilizes a pretrained VGG16, processing groups of five slices simultaneously, and features multiple end-to-end LSTM branches, each specialized in predicting one caption, subsequently combined to form the ordered reports after a BERT-based semantic evaluation. Our system demonstrates effectiveness and stability, with the postprocessing stage refining the syntax of the generated descriptions. However, there remains an opportunity to empower the evaluation framework to more accurately assess the clinical relevance of the automatically-written reports. Part of future work will include transitioning to 3D and developing an improved version based on vision-language models.