Acta radiologica最新文献

BackgroundAccurate differentiation of clear cell renal cell carcinoma (ccRCC), the most aggressive subtype of renal masses, is crucial for guiding management decisions. Magnetic resonance imaging (MRI)-based Clear Cell Likelihood Score (ccLS) has recently emerged as a useful tool in this regard.PurposeTo evaluate the diagnostic performance and inter-observer reliability of the MRI-based ccLS in distinguishing ccRCC from other renal tumors that could not be clearly classified with conventional imaging.Material and MethodsThis single-center, retrospective study included 176 patients with renal masses who underwent preoperative dynamic contrast-enhanced MRI. Two radiologists independently reviewed the images, applying the ccLS scoring system based on T2 signal intensity, corticomedullary phase enhancement, and other imaging features as previously described. The histopathological results were used as the reference standard. The diagnostic performance of ccLS, with varying thresholds, was assessed, and inter-observer agreement was evaluated.ResultsThe study found that the ccLS system demonstrated high sensitivity (93.3%) but low specificity (47.9%) at a threshold of ≥3 and balanced accuracy (sensitivity = 81%, specificity = 70.4%) at a threshold of ≥4. Larger tumors (≥4 cm) showed superior diagnostic performance. MRI features such as T2 hyperintensity and corticomedullary hypervascularity were significantly more frequent in ccRCC compared to non-ccRCC (P <0.001). The inter-observer agreement for ccLS and key MRI features including T2 hyperintensity and corticomedullary hypervascularity were substantial (weighted kappa = 0.71-0.74).ConclusionAlthough highly reproducible, the current ccLS algorithm, should be used cautiously in distinguishing ccRCC from other renal masses that cannot be easily classified with conventional imaging.

BackgroundComputed tomography (CT) fluoroscopy provides high-resolution images and is widely used for safe and accurate procedures, but it exposes operators to high radiation doses.PurposeTo develop and evaluate a tunnel-shaped shielding system to reduce operator exposure to scattered radiation during CT fluoroscopy-guided procedures.Material and MethodsThe shield, designed based on scattered radiation distribution, consists of a semi-cylindrical leaded acrylic part and a bottom plate with a non-lead shielding board surrounding the patient. Radiation doses were measured with and without the shield using patient and operator phantoms. Dosimeters were placed at 10 locations on the operator phantom, including the eye lens, thyroid, chest, abdomen, pelvis, legs, patient-side armpit, and needle-holding hand. Percentage reductions in radiation exposure were calculated.ResultsThe tunnel-shaped shield significantly reduced radiation exposure, with dose reductions of 83%-100% at the eye lens, 88%-96% at the thyroid, 84%-95% at the upper chest, 84%-92% at the lower chest, 88%-94% at the abdomen, 91%-94% at the pelvis, 57%-68% at the upper leg, 44%-83% at the lower leg, 90%-94% at the patient-side armpit, and 73%-86% at the needle-holding hand. All reductions were statistically significant.ConclusionPhantom experiments demonstrated that the tunnel-shaped shielding system effectively reduces operator exposure to scattered radiation during CT fluoroscopy-guided procedures.

BackgroundThe widespread use of high-resolution ultrasonography (US) imaging has led to an increased detection of thyroid nodules, which are common in the general population.PurposeTo evaluate the correlation between ultrasonographic and pathological findings of thyroid nodules undergoing US-guided fine-needle aspiration (FNA) and assess the contribution of US features to malignancy prediction.Material and MethodsA total of 573 patients (137 men, 436 women; age range = 20-88 years) who underwent US-guided FNA were included. Nodule characteristics were recorded using the British Thyroid Association (BTA) U classification, and cytological results were assessed according to the Bethesda system. Logistic regression analysis (LRA) was performed to determine the relationship between US features and malignancy.ResultsThe distribution of nodules in U2, U3, U4, and U5 categories was 212, 171, 84, and 36, respectively, with corresponding Bethesda (2-6) classifications of 287, 159, 18, 27, and 12. Malignancy rates (Bethesda 4-6) were 0%, 10%, 28.6%, and 44.5%, respectively. Hypoechogenicity (relative to muscle), internal vascularization, and microcalcifications were significantly associated with malignancy (P <0.05). LRA achieved an 85.5% accuracy in malignancy prediction.ConclusionUS features in the BTA U classification align with pathological findings. Hypoechoic solid nodules, central vascularization, and microcalcifications should raise suspicion for malignancy in the differential diagnosis of thyroid nodules. These study findings highlight the strong association between vascularity in the BTA classification and malignancy, suggesting its potential role in risk stratification.

BackgroundIntraductal papillary mucinous neoplasms (IPMNs) of the pancreas are cystic lesions with varying malignant potential requiring long-term surveillance. However, optimal surveillance strategies remain debated.PurposeTo evaluate imaging and demographic characteristics of IPMN patients referred to our multidisciplinary team (MDT) conference over a 5-year period, and to determine the frequency and histopathological outcomes of surgical resections.Material and MethodsWe assessed a cohort of all patients referred to the weekly IPMN MDT conference between 1 January 2019 and 31 December 2023. Using electronic health records, we linked information from imaging records with clinical characteristics. Outcomes included imaging features, presence and development of worrisome features (WFs), and surgical interventions.ResultsDuring the study period, 1082 patients were eligible for inclusion in the study cohort. The majority were female (57.1%) and mean age at entry was 69.8 years. Branch duct IPMN was the most common subtype (95.3%). At baseline, WFs were present in 207 (19.1%) patients and an additional 47 (4.1%) patients developed WFs during follow-up. Rapid cyst growth was observed in 6.8% using the Fukuoka criteria and 10.3% using the updated Kyoto 2024 criteria. Surgical resection was performed in 62 (5.7%) patients, of whom 31 (2.9%) had malignant transformation or high-grade dysplasia.ConclusionMalignant transformation was uncommon among our IPMN patients. WFs and rapid cyst growth were not consistent predictors. These findings support more individualized and less intensive surveillance.

BackgroundManual data curation was necessary to extract radiology reports due to the ambiguities of natural language.PurposeTo develop a fine-tuned large language model that classifies computed tomography (CT)-guided interventional radiology reports into technique categories and to compare its performance with that of the readers.Material and MethodsThis retrospective study included patients who underwent CT-guided interventional radiology between August 2008 and November 2024. Patients were chronologically assigned to the training (n = 1142; 646 men; mean age = 64.1 ± 15.7 years), validation (n = 131; 83 men; mean age = 66.1 ± 16.1 years), and test (n = 332; 196 men; mean age = 66.1 ± 14.8 years) datasets. In establishing a reference standard, reports were manually classified into categories 1 (drainage), 2 (lesion biopsy within fat or soft tissue density tissues), 3 (lung biopsy), and 4 (bone biopsy). The bi-directional encoder representation from the transformers model was fine-tuned with the training dataset, and the model with the best performance in the validation dataset was selected. The performance and required time for classification in the test dataset were compared between the best-performing model and the two readers.ResultsCategories 1/2/3/4 included 309/367/270/196, 30/42/40/19, and 75/124/78/55 patients for the training, validation, and test datasets, respectively. The model demonstrated an accuracy of 0.979 in the test dataset, which was significantly better than that of the readers (0.922-0.940) (P ≤0.012). The model classified reports within a 49.8-53.5-fold shorter time compared to readers.ConclusionThe fine-tuned large language model classified CT-guided interventional radiology reports into four categories demonstrating high accuracy within a remarkably short time.

BackgroundLimited data exist comparing the detection of microscopic fat in adrenal adenomas on two-dimensional chemical shift dual-echo (2D CSI) magnetic resonance imaging (MRI) and three-dimensional two-point Dixon techniques (3D Dixon).PurposeTo compare the sensitivity of 2D CSI versus 3D Dixon techniques for the diagnosis of adrenal adenomas.Material and MethodsA retrospective analysis was conducted of 33 patients with adrenal masses who underwent both 2D CSI and 3D Dixon sequences on a 1.5-T scanner. Two blinded radiologists measured and calculated signal intensity (SI) index (SII) (100×(SI in phase - SI out of phase)/SI in phase) of nodules on each technique. Reference standard diagnosis of 30 adrenal adenomas was established. Sensitivity for adrenal adenoma diagnosis was determined using a SII >16.5%.ResultsIn total, 33 nodules were investigated (mean size=22 mm, range=11-55 mm). Of the 30 adenomas, the mean SII on 2D CSI was 48% for reader 1 and 44% for reader 2, compared to 34% on 3D Dixon for both readers (P < 0.001). Sensitivity for the diagnosis of adenoma with 2D CSI was 90% (95% confidence interval [CI]=82-98) for both readers, while 3D Dixon demonstrated a sensitivity of 73% (95% CI=65-82) for reader 1 and 63% (95% CI=55-72) for reader 2.Conclusion2D dual gradient-echo CSI demonstrated a higher sensitivity for the diagnosis of adrenal adenoma than the 3D Dixon technique. Adrenal MRI evaluation of the adrenal glands at 1.5 T should include 2D dual gradient-echo CSI and not rely solely on 3D two-point Dixon techniques for the diagnosis of adrenal adenomas.

BackgroundThe use of artificial intelligence (AI) in screen-reading of mammograms has shown promising results for cancer detection. However, less attention has been paid to the false positives generated by AI.PurposeTo investigate mammographic features in screening mammograms with high AI scores but a true-negative screening result.Material and MethodsIn this retrospective study, 54,662 screening examinations from BreastScreen Norway 2010-2022 were analyzed with a commercially available AI system (Transpara v. 2.0.0). An AI score of 1-10 indicated the suspiciousness of malignancy. We selected examinations with an AI score of 10, with a true-negative screening result, followed by two consecutive true-negative screening examinations. Of the 2,124 examinations matching these criteria, 382 random examinations underwent blinded consensus review by three experienced breast radiologists. The examinations were classified according to mammographic features, radiologist interpretation score (1-5), and mammographic breast density (BI-RADS 5th ed. a-d).ResultsThe reviews classified 91.1% (348/382) of the examinations as negative (interpretation score 1). All examinations (26/26) categorized as BI-RADS d were given an interpretation score of 1. Classification of mammographic features: asymmetry = 30.6% (117/382); calcifications = 30.1% (115/382); asymmetry with calcifications = 29.3% (112/382); mass = 8.9% (34/382); distortion = 0.8% (3/382); spiculated mass = 0.3% (1/382). For examinations with calcifications, 79.1% (91/115) were classified with benign morphology.ConclusionThe majority of false-positive screening examinations generated by AI were classified as non-suspicious in a retrospective blinded consensus review and would likely not have been recalled for further assessment in a real screening setting using AI as a decision support.

BackgroundA timely assessment of local recurrence (LoR) risk in extremity high-grade osteosarcoma is crucial for optimizing treatment strategies and improving patient outcomes.PurposeTo explore the potential of machine-learning algorithms in predicting LoR in patients with osteosarcoma.Material and MethodsData from patients with high-grade osteosarcoma who underwent preoperative radiograph and multiparametric magnetic resonance imaging (MRI) were collected. Machine-learning models were developed and trained on this dataset to predict LoR. The study involved selecting relevant features, training the models, and evaluating their performance using the receiver operating characteristic (ROC) curve and the area under the ROC curve (AUC). DeLong's test was utilized for comparing the AUCs.ResultsThe performance (AUC, sensitivity, specificity, and accuracy) of four classifiers (random forest [RF], support vector machine, logistic regression, and extreme gradient boosting) using radiograph-MRI as image inputs were stable (all Hosmer-Lemeshow index >0.05) with the fair to good prognosis efficacy. The RF classifier using radiograph-MRI features as training inputs exhibited better performance (AUC = 0.806, 0.868) than that using MRI only (AUC = 0.774, 0.771) and radiograph only (AUC = 0.613 and 0.627) in the training and testing sets (P <0.05) while the other three classifiers showed no difference between MRI-only and radiograph-MRI models.ConclusionThis study provides valuable insights into the use of machine learning for predicting LoR in osteosarcoma patients. These findings emphasize the potential of integrating radiomics data with algorithms to improve prognostic assessments.

BackgroundArtificial intelligence (AI)-based systems have the potential to increase the efficiency and effectiveness of breast cancer screening programs but need to be carefully validated before clinical implementation.PurposeTo retrospectively evaluate an AI system to safely reduce the workload of a double-reading breast cancer screening program.Material and MethodsAll digital mammography (DM) screening examinations of women aged 40-74 years between August 2021 and January 2022 in Östergötland, Sweden were included. Analysis of the interval cancers (ICs) was performed in 2024. Each examination was double-read by two breast radiologists and processed by the AI system, which assigned a score of 1-10 to each examination based on increasing likelihood of cancer. In a retrospective simulation, the AI system was used for triaging; low-risk examinations (score 1-7) were selected for single reading and high-risk examinations (score 8-10) for double reading.ResultsA total of 15,468 DMs were included. Using an AI triaging strategy, 10,473 (67.7%) examinations received scores of 1-7, resulting in a 34% workload reduction. Overall, 52/53 screen-detected cancers were assigned a score of 8-10 by the AI system. One cancer was missed by the AI system (score 4) but was detected by the radiologists. In total, 11 cases of IC were found in the 2024 analysis.ConclusionReplacing one reader in breast cancer screening with an AI system for low-risk cases could safely reduce workload by 34%. In total, 11 cases of IC were found in the 2024 analysis; of them, three were identified correctly by the AI system at the 2021-2022 examination.

BackgroundComputed tomography (CT)-derived acetabular angles are commonly used in the diagnosis of hip dysplasia, but the measurements are labor-intensive, with higher inter- and intra-operator variation, necessitating an automated method.PurposeTo develop and validate an automatic method for segmenting the acetabular lunate surface and measure diagnostic angles using CT images to improve diagnosis and preoperative planning for patients with hip dysplasia.Material and MethodsWe developed a method to segment the acetabular lunate surface, automatically identify five landmark points (center, anterior, posterior, lateral, and medial) and calculate diagnostic angles for center-edge (CE), anterior-sector (AASA), posterior-sector (PASA), acetabular anteversion (AcAV), and acetabular-index (AI). The method was validated against repeated manual measurements by three raters on a dataset of 18 patients (36 hips).ResultsNo differences between raters and the automatic method for the center (P = 0.18), anterior (P = 0.55), posterior (P = 0.18), lateral (P = 0.13), and medial (P = 0.12) landmarks. No statistically significant differences were observed between raters and the automatic method for the AASA (P = 0.01) and PASA (P = 0.08) angles. Statistically significant differences were found between the automatic method and rater 3 for the CE and AI angles, and between the automatic method and rater 2 for the AcAV angle. The ICC for all angle measurements by raters and the automated method was in the range of 0.90-0.99.ConclusionWith similar agreement between manual and automatic measurements, the automatic method provides important information that may be used for both diagnosis and surgical planning, with the potential to greatly reduce the time used for analysis per patient.