European Radiology最新文献

Purpose: To determine whether color-rendered 3D MR neurography (MRN) images (heatmaps) improve diagnostic accuracy, reader confidence levels, and time savings to assess LS plexus lesions compared to the conventional grayscale images.

Materials and methods: A cross-sectional study included adults of all genders with randomly chosen MRNs of LS plexus and known reference standards of normal or neuropathy (plexopathy and radiculopathy). Heatmaps were constructed using 3D MRN STIR images and color rendered with higher intensity to yellow and lower intensity to darker-red colors in 1-2 min on average and were available on PACS for the readers. 2D plus 3D grayscale MIP images and 2D plus 3D MIP heatmaps were analyzed by four musculoskeletal radiologists (two faculty and two fellows) in two separate rounds blinded to the final diagnosis. Readers evaluated: neuropathy and number of nerves affected (neuropathy score: 0-normal; 1-one nerve affected; and 2-two or more nerves affected); final diagnosis; confidence levels; and time taken to evaluate the studies. Conger's kappa and paired t-test were used for analysis.

Results: Among 70 MRNs from 70 patients, there were 32 males and 38 females with average age ± SD of 54.8 ± 20.1 years and 49.9 ± 16.6 years, respectively. There were 30 normal and 40 LS plexus lesion scans. Interreader agreements for neuropathy scores were substantial to moderate on conventional imaging and heat maps (Conger's kappa: 0.65; 95% CI: 0.55, 0.73, and 0.59; 95% CI: 0.47, 0.69), respectively. The mean neuropathy score and final diagnosis accuracies were similar in both rounds 85.7% ± 0.1% vs 83.2% ± 0.1% (p = 0.13), and 83.6% ± 0.1% vs 80.0% ± 0.1%; p = 0.16), respectively. Time savings were significant when using heatmaps for all readers (p < 0.001). Time savings using heatmaps ranged from 57.7% to 74.6% and 56.3% to 75% of the original time for the fellows and faculty, respectively. Average confidence levels for neuropathy score significantly increased using heatmaps for one fellow and one faculty (p < 0.05), while average confidence levels for final diagnosis improved for both fellows and one faculty (p < 0.05).

Conclusion: 3D color-rendered MRN heatmaps show comparable diagnostic accuracy to conventional MRN imaging but with significant time savings to identify LS plexus lesions.

Key points: Question Do color-rendered 3D MRN images (heatmaps) improve accuracy, and confidence, and save time when assessing lumbosacral (LS) plexus lesions compared to conventional grayscale images? Findings 3D-rendered heatmaps showed comparable diagnostic accuracy with time savings ranging from 56.3% to 75%. Clinical relevance 3D color-rendered heatmaps increase time efficiency in evaluating MRNs of LS plexus, allowing for improved radiologist productivity and diagnostic confidence.

Objectives: To assess the correlation between the use of artificial intelligence (AI) software and burnout in the radiology departments of hospitals in China.

Methods: This study employed a cross-sectional research design. From February to July 2024, an online survey was conducted among radiologists and technicians at 68 public hospitals in China. The survey utilized general information questionnaires, the Maslach Burnout Inventory-Human Services Survey (MBI-HSS) scale, and a custom-designed AI usage questionnaire. This study analyzed the correlation between AI software usage and occupational burnout, and general information was included as a control variable in a multiple linear regression analysis.

Results: The analysis of survey data from 522 radiology staff revealed that 389 (74.5%) had used AI and that 252 (48.3%) had used it for more than 12 months. Only 133 (25.5%) had not yet adopted AI. Among the respondents, radiologists had a higher AI usage rate (82.0%) than technicians (only 59.9%). Furthermore, 344 (65.9%) of the respondents exhibited signs of burnout. The duration of AI software usage was significantly negatively correlated with overall burnout, yielding a Pearson correlation coefficient of -0.112 (p < 0.05). Multiple stepwise regression analysis revealed that salary satisfaction, night shifts, duration of AI usage, weekly working hours, having children, and professional rank were the main factors influencing occupational burnout (all p < 0.05).

Conclusion: AI has the potential to significantly help mitigate occupational burnout among radiology staff. This study reveals the key role that AI plays in assisting radiology staff in their work.

Key points: Questions Although we are aware that radiology staff burnout is intensifying, there is no quantitative research assessing whether artificial intelligence software can mitigate this occupational burnout. Findings The longer staff use deep learning-based artificial intelligence imaging software, the less severe their occupational burnout tends to be. This result is particularly evident among radiologists. Clinical relevance In China, radiologists and technicians experience high burnout rates. Even if there is an artificial intelligence usage controversy, encouraging the use of artificial intelligence software in radiology helps prevent and alleviate this occupational burnout.

Objectives: Screening for obstructive coronary artery disease (CAD) with coronary computed tomography angiography (CCTA) could prevent unnecessary invasive coronary angiography (ICA) procedures during work-up for trans-catheter aortic valve implantation (TAVI). CT-derived fractional flow reserve (CT-FFR) improves CCTA accuracy in chest pain patients. However, its reliability in the TAVI population is unknown. This systematic review and meta-analysis assesses CCTA and CT-FFR in TAVI candidates.

Methods: PubMed, Embase and Web of Science were searched for studies regarding CCTA and/or CT-FFR in TAVI candidates. Primary endpoint was correct identification and rule-out of obstructive CAD. Results were pooled in a meta-analysis.

Results: Thirty-four articles were part of the meta-analysis, reporting results for CCTA and CT-FFR in 7235 and 1269 patients, respectively. Reference standard was mostly anatomical severity of CAD. At patient level, pooled CCTA sensitivity was 94.0% and specificity 72.4%. CT-FFR sensitivity was 93.2% and specificity 70.3% with substantial variation between studies. However, in studies that compared both, CT-FFR performed better than CCTA. Sensitivity of CCTA versus CT-FFR was 74.9% versus 83.9%, and specificity was 65.5% versus 89.8%.

Conclusions: Negative CCTA accurately rules out CAD in the TAVI population. CCTA could lead to significant reduction in pre-TAVI ICA, but false positives remain high. Diagnostic accuracy of CT-FFR was comparable to that of CCTA in our meta-analyses, but in studies performing a direct comparison, CT-FFR performed better than CCTA. However, as most studies were small and used CT-FFR software exclusively available for research, a large study on CT-FFR in TAVI work-up using commercially available CT-FFR software would be appropriate before considering routine implementation.

Key points: Question Coronary artery disease (CAD) screening with invasive coronary angiography before trans-catheter aortic valve implantation (TAVI) is often retrospectively unnecessary, revealing no obstructive CAD. Findings Coronary CTA ruled out CAD in approximately half of TAVI candidates. CT-derived fractional flow reserve (CT-FFR) performed similarly overall but better than coronary CTA in direct comparison. Clinical relevance Addition of coronary CTA to TAVI planning-CT to screen for obstructive CAD could reduce negative invasive coronary angiographies in TAVI work-up. CT-FFR could reduce false-positive coronary CTA results, improving its gatekeeper function in this population, but more data is necessary.

Objectives: Tumor collagen is vital in chemotherapy resistance of pancreatic cancer (PC), but its non-invasive evaluation remains challenging. This study aims to investigate the association of variables derived from dual-energy CT with the collagen ratio (CR) of PC and to determine the prognostic value of CR in unresectable diseases.

Materials and methods: A total of 83 patients with resected PC and 71 patients with unresectable PC were enrolled. In the resected group, the correlation between the tumor CR and variables of dual-energy CT was analyzed. In the unresectable group, Cox regression analyses were conducted to investigate the prognostic value of dual-energy CT-predicted CR and other clinicoradiological indicators.

Results: The patients with resected PC were divided into low and high-CR sets with a threshold of 55%. In the resected group, the extracellular volume fraction calculated by the iodine concentration (ECV_IC) was the only predictor of tumor CR according to univariate and multivariate analysis (hazard ratio [HR] (95% confidence interval [CI]):1.19 [1.03-1.37]). The correlation coefficient r was 0.26 (p = 0.02) between ECV_IC and specific CR values. In the training set of unresectable PC group, ECV_IC (HR (95% CI): 0.94 (0.89-0.99), p = 0.03) and contrast-enhanced pattern (CEP) (HR (95% CI): 3.20 (1.41-7.27), p = 0.01) were independent prognostic factors for overall survival. The nomogram model was constructed and showed a good performance.

Conclusion: The ECV_IC is a non-invasive indicator of tumor CR in PC. The ECV_IC and CEP have the potential to predict the prognosis of unresectable PC.

Key points: Question Non-invasive evaluation of tumor collagen, a vital determinant of chemotherapy resistance of pancreatic cancer, remains challenging. Findings Tumor collagen ratio can be noninvasively predicted by extracellular volume fraction based on iodine concentration. Clinical relevance The nomogram model composed of extracellular volume fraction and contrast-enhanced pattern can serve as an effective and convenient tool for stratifying the prognosis of patients with unresectable pancreatic cancer.

Objectives: The aim is to assess the feasibility and accuracy of a novel quantitative ultrasound (US) method based on global speed-of-sound (g-SoS) measurement using conventional US machines, for breast density assessment in comparison to mammographic ACR (m-ACR) categories.

Materials and methods: In a prospective study, g-SoS was assessed in the upper-outer breast quadrant of 100 women, with 92 of them also having m-ACR assessed by two radiologists across the entire breast. For g-SoS, ultrasonic waves were transmitted from varying transducer locations and the image misalignments between these were then related analytically to breast SoS. To test reproducibility, two consecutive g-SoS acquisitions each were taken at two similar breast locations by the same operator.

Results: Measurements were found highly repeatable, with a mean absolute difference ± standard deviation of 3.16 ± 3.79 m/s. Multiple measurements were combined yielding a single g-SoS estimate per each patient, which strongly correlated to m-ACR categories (Spearman's = 0.773). The g-SoS values for categories A-D were 1459.6 ± 0.74, 1475.6 ± 15.92, 1515.6 ± 27.10, and 1545.7 ± 20.62, with all groups (except A-B) being significantly different from each other. Dense breasts (m-ACR C&D) were classified with 100% specificity at 78% sensitivity, with an area under the curve (AUC) of 0.931. Extremely dense breasts (m-ACR D) were classified with 100% sensitivity at 77.5% specificity (AUC = 0.906).

Conclusion: Quantitative g-SoS measurement of the breast was shown feasible and repeatable using conventional US machines, with values correlating strongly with m-ACR assessments.

Key points: Question Breast density is a strong predictor of risk for breast cancer, which frequently develops in dense tissue regions. Therefore, density assessment calls for refined non-ionizing methods. Findings Quantitative global speed-of-sound (g-SoS) measurement of the breast is shown to be feasible using conventional US machines, repeatable, and able to classify breast density with high accuracy. Clinical relevance Being effective in classifying dense breasts, where mammography has reduced sensitivity, g-SoS can help stratify patients for alternative modalities. Ideal day for mammography or MRI can be determined by monitoring g-SoS. Furthermore, g-SoS can be integrated into personalized risk assessment.

Purpose: To train and validate machine learning-derived clinical decision algorithm (_MLCDA) for the diagnosis of hyperfunctioning parathyroid glands using preoperative variables to facilitate surgical planning.

Methods: This retrospective study included 458 consecutive primary hyperparathyroidism (PHPT) patients who underwent combined 4D-CT and sestamibi SPECT/CT (MIBI) with subsequent parathyroidectomy from February 2013 to September 2016. The study cohort was divided into training (first 400 patients) and validation sets (remaining 58 patients). Sixteen clinical, laboratory, and imaging variables were evaluated. A random forest algorithm selected the best predictor variables and generated a clinical decision algorithm with the highest performance (_MLCDA). The _MLCDA was trained to predict the probability of a hyperfunctioning vs normal gland for each of the four parathyroid glands in a patient. The reference standard was a four-quadrant location on operative reports and pathology. The accuracy of _MLCDA was prospectively validated.

Results: Of 16 variables, the algorithm selected 3 variables for optimal prediction: combined 4D-CT and MIBI using (1) sensitive reading, (2) specific reading, and (3) cross-product of serum calcium and parathyroid hormone levels and outputted an _MLCDA using five probability categories for hyperfunctioning glands. The _MLCDA demonstrated excellent accuracy for correct classification in the training (4D-CT + MIBI: 0.91 [95% CI: 0.89-0.92]) and validation sets (4D-CT + MIBI: 0.90 [95% CI: 0.86-0.94].

Conclusion: Machine learning generated a clinical decision algorithm that accurately diagnosed hyperfunctioning parathyroid glands through classification into probability categories, which can be implemented for improved preoperative planning and convey diagnostic certainty.

Key points: Question Can an _MLCDA use preoperative variables for the diagnosis of hyperfunctioning parathyroid glands to facilitate surgical planning? Findings The developed _MLCDA demonstrated excellent accuracy for correct classification in the training (0.91 [95% CI: 0.89-0.92]) and validation sets (0.90 [95% CI: 0.86-0.94]). Clinical relevance Using standard preoperative variables, an _MLCDA for diagnosing hyperfunctioning parathyroid glands can be implemented to improve preoperative parathyroid localization and included in radiology reports for surgical planning.

Objective: To investigate imaging biomarkers of tumour response by describing changes in imaging and pathology findings after neoadjuvant radiotherapy (nRT) and exploring their correlations.

Materials and methods: Tumour diameter, volume, and tumour-to-muscle signal intensity (SI) ratio were collected before and after radiotherapy in a cohort of 107 patients with intermediate/high-grade STS and were correlated with post-radiotherapy pathology findings (percentage of necrosis, viable cells, and fibrosis) using Spearman Rank test. Pathological complete response (pCR) was defined as no residual viable cells present, whereas the presence of < 10% viable cells was defined as near-complete pathologic response (near-pCR).

Results: Median amount of necrosis, viable cells, and fibrosis after nRT were 10%, 30%, and 25%, respectively. 7% of patients achieved pCR and 22% near-pCR. No changes in tumour volume were found except for subtypes myxoid liposarcoma (mLPS) -Δ54.47%, undifferentiated pleomorphic sarcoma (UPS) +Δ24.22% and dedifferentiated liposarcoma (dLPS) +Δ35.91%. The median change of tumour-to-muscle SI ratio was -19.7% for the entire population, whereas it was -19.55% and -36.26% for UPS and mLPS, respectively. Correlations (positive and negative) were found between change in volume and the presence of necrosis or fibrosis (r_s = 0.44; r_s = -0.44), as well as between tumour-to-muscle SI ratio and viable cells (r_s = 0.33) or fibrosis (r_s = -0.28).

Conclusion: STS displays extensive heterogeneity in response patterns after nRT. In some subgroups, particularly UPS and mLPS, tumour size changes or tumour-to-muscle SI ratio are significantly linked with the percentage of viable cells, fibrosis, or necrosis.

Key points: Question How do primary soft tissue sarcomas (STS) respond to neoadjuvant therapy, and what correlations exist between pathological findings and imaging characteristics in assessing treatment response? Findings mLPS shrank post-nRT; undifferentiated pleomorphic and dLPSs enlarged. Volume increase correlated with higher necrosis and lower fibrosis; tumour-to-muscle intensity ratio correlated with viable cells. Clinical relevance These findings emphasise the extensive heterogeneity in STS response to nRT across different subtypes. Preoperative correlations between tumour volume and SI changes with necrosis, fibrosis, and viable cells can aid in more precise treatment assessment and prognostication.