Radiologia Medica最新文献

Theragnostics is the integration of treatment and diagnosis, involving a drug or technology that combines diagnostic imaging with targeted therapy. This approach utilizes imaging to identify specific biological targets, which are then used to deliver therapeutic effects for the benefit of patients. The effectiveness and potential of theragnostics in improving patient outcomes are supported by significant clinical trials and technological innovations. Theragnostics has demonstrated its capacity to deliver targeted and real-time interventions, making it adaptable to diverse clinical domains. Its applications range from visualizing and eradicating tumors to addressing complex neurological disorders and cardiovascular diseases. The integration of nanomaterials and advancements in molecular biology further enhance the capabilities of theragnostics, promising a future where treatments are highly personalized, and diseases are understood and managed at a molecular level previously unattainable. Our comprehensive overview focuses on the current advancements in theragnostics applications across different disease domains. We highlight the role of molecular imaging technologies, such as PET/CT scans, in early diagnosis and treatment. Additionally, we explore the potential of chemokines as molecular imaging targets in systemic inflammatory diseases and central nervous system pathologies. In conclusion, the progression of theragnostics represents a transformative phase in medical practice, providing new avenues for precise treatment and improved patient outcomes. Its multidisciplinary nature and continuous innovation have the potential to profoundly impact the future of medical research and clinical practice, as well as revolutionizing the treatment and management of a wide array of diseases.

Purpose: The distribution analysis of the morphologic characteristics and spatial relations among brain metastases (BMs) to guide screening and early diagnosis.

Material and methods: This retrospective study analysed 4314 BMs across 30 brain regions from MRIs of 304 patients. This paper proposed a unified analysis model based on persistent homology (PH) and graph modelling to provide a comprehensive portrait of BMs distribution. Spatial relationships are quantified through dynamic multiple-scale graphs constructed with Rips filtration. The multi-scale centrality importance and clustering coefficients are extracted to decode BMs spatial relations. Morphologic BMs characteristics are further analysed by varying radius and volume values that are considered as clinically influential factors. Finally, two-tailed proportional hypothesis testing is used for BM statistical distribution analysis.

Results: For spatial analysis, results have shown a statistical increase in the proportions of high-level centrality BMs at the left cerebellum (p<0.01). BMs rapidly form graphs with high clustering rather than those with high centrality. For demographic analysis, the cerebellum and frontal are the top high-frequency areas of BMs with 0-4 and 5-10 radii. Statistical increases in the proportions of BMs at cerebellum (p<0.01).

Conclusion: Results indicate that distributions of both BMs spatial relations and demographics are statistically non-random. This research offers novel insights into the BMs distribution analysis, providing physicians with the BMs demographic to guide screening and early diagnosis.

Radiologists are crucial in the diagnostic workflow. They must maintain an independent perspective, being a "third party" to the patients and referral clinicians. This is important when documenting the absence of relevant abnormalities or providing information that contradicts the self-reported symptoms and/or the impression of the colleagues, as well as in the case of incidental findings that impact patient management. Appropriate communication is the outcome of this professional independence, becoming more and more important in the current era of application of generative artificial intelligence to the radiological world. In fact, while radiological reports could be improved by our smart use of large language models, patients are already using such tools to understand their meaning and practical implications.

Purpose: Evaluate the classification performance and interpretability of the Vision Transformer (ViT) model on acute and chronic vertebral compression fractures using Shapley significance maps.

Materials and methods: This retrospective study utilized medical imaging data from December 2018 to December 2023 from three hospitals in China. The study included 942 patients, with imaging data comprising X-rays, CTs, and MRIs. Patients were divided into training, validation, and test sets with a ratio of 7:2:1. The ViT model variant, SimpleViT, was fine-tuned on the training dataset. Statistical analyses were performed using the PixelMedAI platform, focusing on metrics such as ROC curves, sensitivity, specificity, and AUC values, with statistical significance assessed using the DeLong test.

Results: A total of 942 patients (mean age 69.17 ± 10.61 years) were included, with 1076 vertebral fractures analyzed (705 acute, 371 chronic). In the test set, the ViT model demonstrated superior performance over the ResNet18 model, with an accuracy of 0.880 and an AUC of 0.901 compared to 0.843 and 0.833, respectively. The use of ViT Shapley saliency maps significantly enhanced diagnostic sensitivity and specificity, reaching 0.883 (95% CI: 0.800, 0.963) and 0.950 (95% CI: 0.891, 1.00), respectively.

Conclusion: In vertebral compression fractures classification, Vision Transformer outperformed Convolutional Neural Network, providing more effective Shapley-based saliency maps that were favored by radiologists over GradCAM.

Background: Neoadjuvant chemotherapy (NACT) improves surgical outcomes for breast cancer patients, with pathologic complete response (pCR) correlated with enhanced survival. The role of radiomics, particularly from peritumoral tissue, in predicting pCR remains under investigation.

Methods: This retrospective study analyzed radiomic features from pretreatment dynamic contrast-enhanced breast MRI scans of 150 patients undergoing NACT. A proportional approach was used to define peritumoral zones, assessed both with a 10% and 30% extension, allowing more standardized assessments relative to the tumor size. Radiomic features were evaluated alongside clinical and biological data to predict pCR. The association of clinical/biological and radiomic features with pCR to NACT was evaluated using univariate and multivariate analysis, logistic regression, and a random forest model. A clinical/biological model, a radiomic model, and a combined clinical/biological and 4 radiomic models for predicting the response to NACT were constructed. Area under the curve (AUC) and 95% confidence intervals (CIs) were used to assess the performance of the models.

Results: Ninety-five patients (average age 47 years) were finally included. HER2 + , basal-like molecular subtypes, and a high level of Ki67 (≥ 20%) were associated with a higher likelihood of pCR to NACT. The combined clinical-biological-radiomic model, especially with a 10% peritumoral extension, showed improved predictive accuracy (AUC 0.76, CI 0.65-0.85) compared to models using clinical-biological data alone (AUC 0.73, CI 0.63-0.83).

Conclusions: Integrating peritumoral radiomic features with clinical and biological data enhances the prediction of pCR to NACT, underscoring the potential of a multifaceted approach in treatment personalization.

The advances in artificial intelligence (AI) technology in recent years have been remarkable, and the field of radiology is at the forefront of applying and implementing these technologies in daily clinical practice. Radiologists must keep up with this trend and continually update their knowledge. This narrative review discusses the application of artificial intelligence in the field of musculoskeletal imaging. For image generation, we focused on the clinical application of deep learning reconstruction and the recently emerging MRI-based cortical bone imaging. For automated diagnostic support, we provided an overview of qualitative diagnosis, including classifications essential for daily practice, and quantitative diagnosis, which can serve as imaging biomarkers for treatment decision making and prognosis prediction. Finally, we discussed current issues in the use of AI, the application of AI in the diagnosis of rare diseases, and the role of AI-based diagnostic imaging in preventive medicine as part of our outlook for the future.

Purpose: To investigate pancreatic changes associated with visceral fat obesity (VFO) and their clinical relevance using contrast-enhanced dual-energy CT (DE-CT) with automated 3D volumetry.

Methods: This retrospective study included patients who underwent triple-phase contrast-enhanced dynamic abdominal DE-CT. The patients were divided into two groups based on the measured visceral fat area: the VFO group (≥ 100 cm²) and the non-VFO group (< 100 cm²). Pancreatic changes in 3D CT volumetric measurement parameters were evaluated.

Results: In total, 119 patients were evaluated (mean age, 67.6 ± 12.9 years old; 80 men). The extracellular volume fraction calculated from iodine maps (ECV-ID) (r = -0.683, p < 0.001) was most strongly associated with the visceral fat area, followed by the fat volume fraction (FVF) of the pancreas (r = 0.582, p < 0.001) with a statistically moderate correlation. The pancreatic volume and FVF of the pancreas were significantly higher in the VFO group than in the non-VFO group (volume: 84.9 ± 22.9 vs. 76.5 ± 25.8, p = 0.025, FVF: 15.5 ± 7.7 vs. 8.7 ± 9.5, p < 0.001). Conversely, the pancreatic CT attenuation value on unenhanced CT (19.9 ± 12.0 vs. 29.6 ± 13.8, p < 0.001), pancreatic iodine concentration in the equilibrium phase (EP) (18.4 ± 5.7 vs. 19.8 ± 4.7, p = 0.003), contrast enhancement (CE) value of pancreas (32.2 ± 5.3 vs. 34.5 ± 8.5, p = 0.005), and ECV-ID (26.7 ± 5.4 vs. 34.1 ± 7.4, p < 0.001) in the VFO group were significantly lower than those in the non-VFO group.

Conclusion: An increase in the pancreatic volume and FVF of the pancreas, as well as a reduction in the ECV fraction and the CE value in EP of the pancreas measured by automated 3D DE-CT volumetry, were the characteristic pancreatic changes in patients with VFO.

Purpose: To investigate metabolic parameters from baseline ¹⁸F-FDG PET/CT as predictors of pathological complete response (pCR) to neoadjuvant chemotherapy (NAC) and disease recurrence in locally advanced breast cancer (LABC) patients.

Materials and methods: From 142 LABC in 137 patients (bilateral-synchronous BC: 5/137), the following parameters from baseline (pre-treatment) ¹⁸F-FDG PET/CT were retrospectively analyzed, along with clinic-histological data: primary tumor activity (SUVmax, SUVmean, SUVpeak, tumor-to-liver ratio-TLR-, MTV, TLG); lymphoid organs activity (spleen and bone marrow SUVmax and SUVmean, spleen-to-liver ratio-SLR-, bone marrow-to-liver ratio-BLR); and PET-positive lymph-nodes' number. Predictors of pCR and recurrence-free survival (RFS) were assessed by univariable logistic regression and Cox regression (significant or suggestive association: p < 0.05; p < 0.10).

Results: 74/142 tumors were "Luminal A/B HER2-", 44/142 "Luminal B HER2+/HER2+", 24/142 TNBC; pCR after NAC occurred in 26/142 tumors (18.3%) and disease recurrence at follow-up (45 ± 18.1 months) in 25/127 assessable patients (19.7%). Significant or suggestive predictors of NAC response, in Luminal A/B HER2-: lower spleen SUVmax and patients' age (OR 0.06; 0.93) for pCR; lower TLRmax, TLRmean and BLRmax (OR 1.33; 1.22; and 26.42) for residual disease. Significant negative RFS predictors: higher SUVmax, SUVmean, SUVpeak (HR 1.10; 1.15; 1.11), TLRmax and TLRmean (HR 1.02; 1.00), MTV and TLG (HR 1.32; 1.26) in Luminal A/B HER2-; higher spleen SUVmax, PET-positive nodes' number and patients' age (HR 6.24; 1.20; 1.08) in Luminal B HER2+/HER2+.

Conclusion: Primary tumor and lymphoid organs parameters at baseline ¹⁸F-FDG PET/CT resulted as predictors of NAC response and prognosis in LABC patients, respectively, reflecting the BC cells' proliferative activity and metabolic burden, and the role of tumor-induced immune-system activation on tumors' behavior and treatment responsiveness. In LABC candidates to NAC, baseline PET information could improve treatment planning and prognostic stratification.

Purpose: To determine how automation bias (inclination of humans to overly trust-automated decision-making systems) can affect radiologists when interpreting AI-detected cerebral aneurysm findings in time-of-flight magnetic resonance angiography (TOF-MRA) studies.

Material and methods: Nine radiologists with varying levels of experience evaluated twenty TOF-MRA examinations for the presence of cerebral aneurysms. Every case was evaluated with and without assistance by the AI software © mdbrain, with a washout period of at least four weeks in-between. Half of the cases included at least one false-positive AI finding. Aneurysm ratings, follow-up recommendations, and reading times were assessed using the Wilcoxon signed-rank test.

Results: False-positive AI results led to significantly higher suspicion of aneurysm findings (p = 0.01). Inexperienced readers further recommended significantly more intense follow-up examinations when presented with false-positive AI findings (p = 0.005). Reading times were significantly shorter with AI assistance in inexperienced (164.1 vs 228.2 s; p < 0.001), moderately experienced (126.2 vs 156.5 s; p < 0.009), and very experienced (117.9 vs 153.5 s; p < 0.001) readers alike.

Conclusion: Our results demonstrate the susceptibility of radiology readers to automation bias in detecting cerebral aneurysms in TOF-MRA studies when encountering false-positive AI findings. While AI systems for cerebral aneurysm detection can provide benefits, challenges in human-AI interaction need to be mitigated to ensure safe and effective adoption.

Purpose: To evaluate the value of a computed tomography (CT) protocol, including ECG-gated cardiac angiographic and venous phase, in patients with infective endocarditis (IE).

Material and methods: From January 2019 to October 2022, consecutive patients with IE submitted to total-body CT, including ECG-gated cardiac acquisition in angiographic and venous phase, were enrolled. Transesophageal echocardiography was performed in all cases. Rate of local complications including vegetation, pseudoaneurysm, abscess, fistula and valve dehiscence was compared in CT and echocardiography. Systemic embolization was identified through CT scans.

Results: Seventy-six adults (median age 69 [IQR 55-77] years old; males 54/76, 71%] were enrolled. Most patients underwent surgery (51/76, 67%), and the in-hospital mortality rate was 8% (6/76). CT showed higher detection rate of valve vegetation compared to echocardiography (67/76, 88% vs 58/76, 76%; p = 0.008), including vegetation smaller than 10 mm (24/76, 36% vs 16/76, 28%; p = 0.013) and higher detection rate of pseudoaneurysm and abscess (p = 0.004 and p = 0.009, respectively). Abscess showed higher contrast-to-noise ratio (CNR) in the venous scan compared to angiographic scan (2.75 [IQR 2.27; 5.17] vs 1.97 [IQR 1.21; 3.32], p = 0.039) and higher density of perivalvular and epicardial fat compared to pseudoaneurysm (35 [IQR 31; 52]HU and - 50 [IQR - 62; - 35]HU versus 52 [IQR - 60; - 18]HU; p = 0.001, and - 91 [IQR - 95; - 81]HU; p = 0.007, respectively), for greater inflammation. CT overestimated valve dehiscence when compared to echocardiography and surgery.

Conclusion: A comprehensive CT study enhances the diagnostic assessment of patients with IE, not only by detecting distant sites of embolization, but also increasing sensitivity for valve vegetation and local complications.