Insights into Imaging最新文献

Objectives: In this multi-center study, we proposed a structured reporting (SR) framework for non-small cell lung cancer (NSCLC) and developed a software-assisted tool to automatically translate image-based findings and annotations into TNM classifications. The aim of this study was to validate the software-assisted SR tool for NSCLC, assess its potential clinical impact in a proof-of-concept study, and evaluate current reporting standards in participating institutions.

Methods: A framework for SR and staging of NSCLC was developed in a multi-center collaboration. SR annotations and descriptions were used to generate semi-automated TNM classification. The SR and TNM classification tools were evaluated by nine radiologists on n = 20 representative [18F]FDG PET/CT studies and compared to the free text reporting (FTR) strategy. Results were compared to a multidisciplinary team reference using a generalized linear mixed model (GLMM). Additionally, participants were surveyed on their experience with SR and TNM classification.

Results: Overall, GLMM analysis revealed that readers using SR were 1.707 (CI: 1.137-2.585) times more likely to correctly classify TNM status compared to FTR strategy (p = 0.01) resulting in increased overall TNM correctness in 71.9% (128/178) of cases compared to 62.8% (113/180) FTR. The primary source of variation in classification accuracy was explained by case complexity. Participants rated the potential impact of SR and semi-automated TNM classification as positive across all categories with improved scores after template validation.

Conclusion: This multi-center study yielded an effective software-assisted SR framework for NSCLC. The SR and semi-automated classification tool improved TNM classification and were perceived as valuable.

Critical relevance statement: Software-assisted SR provides robust input for semi-automated rule-based TNM classification in non-small-cell lung carcinoma (NSCLC), improves TNM correctness compared to FTR, and was perceived as valuable by radiology physicians.

Key points: SR and TNM classification are underutilized across participating centers for NSCLC staging. Software-assisted SR has emerged as a promising strategy for oncologic assessment. Software-assisted SR facilitates semi-automated TNM classification with improved staging accuracy compared to free-text reports in NSCLC.

Objective: To develop a computed tomography (CT) radiomics-based interpretable machine learning (ML) model to preoperatively predict human epidermal growth factor receptor 2 (HER2) status in bladder cancer (BCa) with multicenter validation.

Methods: In this retrospective study, 207 patients with pathologically confirmed BCa were enrolled and divided into the training set (n = 154) and test set (n = 53). Least absolute shrinkage and selection operator (LASSO) regression was used to identify the most discriminative features in the training set. Five radiomics-based ML models, namely logistic regression (LR), support vector machine (SVM), k-nearest neighbors (KNN), eXtreme Gradient Boosting (XGBoost) and random forest (RF), were developed. The predictive performance of established ML models was evaluated by the area under the receiver operating characteristic curve (AUC). The Shapley additive explanation (SHAP) was used to analyze the interpretability of ML models.

Results: A total of 1218 radiomics features were extracted from the nephrographic phase CT images, and 11 features were filtered for constructing ML models. In the test set, the AUCs of LR, SVM, KNN, XGBoost, and RF were 0.803, 0.709, 0.679, 0.794, and 0.815, with corresponding accuracies of 71.7%, 69.8%, 60.4%, 75.5%, and 75.5%, respectively. RF was identified as the optimal classifier. SHAP analysis showed that texture features (gray level size zone matrix and gray level co-occurrence matrix) were significant predictors of HER2 status.

Conclusions: The radiomics-based interpretable ML model provides a noninvasive tool to predict the HER2 status of BCa with satisfactory discriminatory performance.

Critical relevance statement: An interpretable radiomics-based machine learning model can preoperatively predict HER2 status in bladder cancer, potentially aiding in the clinical decision-making process.

Key points: The CT radiomics model could identify HER2 status in bladder cancer. The random forest model showed a more robust and accurate performance. The model demonstrated favorable interpretability through SHAP method.

Objective: To assess the image quality of synthetic double inversion recovery (SyDIR) imaging and enhance the value of T2-weighted imaging (T2WI) in evaluating T stage for rectal cancer patients.

Methods: A total of 112 pathologically confirmed rectal cancer patients were retrospectively selected after undergoing MRI, including synthetic MRI. The image quality of T2WI and SyDIR imaging was compared based on signal-to-noise ratio (SNR), contrast-to-noise ratio (CNR), overall picture quality, presence of motion artifacts, lesion edge sharpness, and conspicuity. The concordance between MRI and pathological staging results, using T2WI alone and the combination of T2WI and SyDIR for junior and senior radiologists, was assessed using the Kappa test. The area under the receiver operating characteristic curve (AUC) was used to assess the diagnostic efficacy of extramural infiltration in rectal cancer patients.

Results: No significant differences in imaging quality were observed between conventional T2WI and SyDIR (p = 0.07-0.53). The combination of T2WI and SyDIR notably improved the staging concordance between MRI and pathology for both junior (kappa value from 0.547 to 0.780) and senior radiologists (kappa value from 0.738 to 0.834). In addition, the integration of T2WI and SyDIR increased the AUC for diagnosing extramural infiltration for both junior (from 0.842 to 0.918) and senior radiologists (from 0.917 to 0.938).

Conclusion: The combination of T2WI and SyDIR increased the consistency of T staging between MRI and pathology, as well as the diagnostic performance of extramural infiltration, which would benefit treatment selection.

Critical relevance statement: SyDIR sequence provides additional diagnostic value for T2WI in the T staging of rectal cancer, improving the agreement of T staging between MRI and pathology, as well as the diagnostic performance of extramural infiltration.

Key points: Synthetic double inversion recovery (SyDIR) and T2WI have comparable image quality. SyDIR provides rectal cancer anatomical features for extramural infiltration detections. The combination of T2WI and SyDIR improves the accuracy of T staging in rectal cancer.

Over the last few years, radiation therapy (RT) techniques have evolved very rapidly, with the aim of conforming high-dose volume tightly to a target. Although to date CT is still considered the imaging modality for target delineation, it has some known limited capabilities in properly identifying pathologic processes occurring, for instance, in soft tissues. This limitation, along with other advantages such as dose reduction, can be overcome using magnetic resonance imaging (MRI), which is increasingly being recognized as a useful tool in RT clinical practice. This review has a two-fold aim of providing a basic introduction to the physics of MRI in a narrative way and illustrating the current knowledge on its application "from head to toe" (i.e., different body sites), in order to highlight the numerous advantages in using MRI to ensure the best therapeutic response. We provided a basic introduction for residents and non-radiologist on the physics of MR and reported evidence of the advantages and future improvements of MRI in planning a tailored radiotherapy treatment "from head to toe". CRITICAL RELEVANCE STATEMENT: This review aims to help understand how MRI has become indispensable, not only to better characterize and evaluate lesions, but also to predict the evolution of the disease and, consequently, to ensure the best therapeutic response. KEY POINTS: MRI is increasingly gaining interest and applications in RT planning. MRI provides high soft tissue contrast resolution and accurate delineation of the target volume. MRI will increasingly become indispensable for characterizing and evaluating lesions, and to predict the evolution of disease.

Purpose: Steatotic liver disease (SLD) has become the most common cause of chronic liver disease. Nevertheless, the non-invasive quantitative diagnosis of steatosis is still lacking in clinical practice. This study aimed to evaluate the reproducibility of the new parameter for steatosis quantification named ultrasound-derived fat fraction (UDFF).

Materials and methods: The UDFF values were independently executed by two operators in two periods. In the process, repeated measurements of the same patient were performed by the same operator under different conditions (liver segments, respiration, positions, and dietary). Finally, the results of some subjects (28) were compared with the MRI-derived proton density fat fraction (PDFF). The concordance analysis was mainly achieved by the intraclass correlation coefficient (ICC) and Bland-Altman.

Results: One hundred-five participants were included in the study. UDFF had good reliability in measuring the adult liver (ICC_{intra-observer} = 0.96, ICC_{inter-observer} = 0.94). Meanwhile, the ICC of the two operators increased over time. The variable measurement states did not influence the UDFF values on the surface, but they affected the coefficient of variation (Cov) of the results. Segment 8 (S8), end-expiratory, supine, and fasting images had the most minor variability. On the other hand, the UDFF value of S8 displayed satisfied consistency with PDFF (mean difference, -0.24 ± 1.44), and the results of both S5 (mean difference: -0.56 ± 3.95) and S8 (mean difference: 0.73 ± 1.87) agreed well with the whole-liver PDFF.

Conclusion: UDFF measurements had good reproducibility. Furthermore, the state of S8, end-expiration, supine, and fasting might be the more stable measurement approach.

Critical relevance statement: UDFF is the quantitative ultrasound parameter of hepatic steatosis and has good reproducibility. It can show more robust performance under specific measurement conditions (S8, end-expiratory, supine, and fasting).

Trial registration: The research protocol was registered at the Chinese Clinical Trial Registry on October 9, 2023 ( http://www.chictr.org.cn/ ). The registration number is ChiCTR 2300076457.

Key points: There is a lack of non-invasive quantitative measurement options for hepatic steatosis. UDFF demonstrated excellent reproducibility in measuring hepatic steatosis. S8, end-expiratory, supine, and fasting may be the more stable measuring condition. Training could improve the operators' measurement stability. Variable measurement state affects the repeatability of the UDFF values (Cov).

The Strengthening the Screening of Lung Cancer in Europe (SOLACE) initiative, supported by Europe's Beating Cancer Plan, is dedicated to advancing lung cancer screening. This initiative brings together the most extensive pan-European network of respiratory and radiology experts, involving 37 partners from 15 countries. SOLACE aims to enhance equitable access to lung cancer screening by developing targeted recruitment strategies for underrepresented and high-risk populations. Through comprehensive work packages, SOLACE integrates scientific research, pilot studies, and sustainability efforts to bolster regional and national screening efforts across EU member states. CRITICAL RELEVANCE STATEMENT: The SOLACE project aims to facilitate the optimization and implementation of equitable lung cancer screening programs across the heterogeneous healthcare landscape in EU member states. KEY POINTS: The effectiveness of lung cancer screening is supported by both scientific evidence and now increasing legislative support. SOLACE aims to develop, test, and disseminate tools to facilitate the realization of lung cancer screening at both a national and regional level. Previously underrepresented populations in lung cancer screening will be targeted by tailored recruitment strategies. SOLACE forms the first pan-European network of experts poised to drive real-world implementation of lung cancer screening.

Objectives: To develop and validate nomograms combining radiomics and semantic features to identify the invasiveness and histopathological risk stratification of thymic epithelial tumors (TET) using contrast-enhanced CT.

Methods: This retrospective multi-center study included 224 consecutive cases. For each case, 6764 intratumor and peritumor radiomics features and 31 semantic features were collected. Multi-feature selections and decision tree models were performed on radiomics features and semantic features separately to select the most important features for Masaoka-Koga staging and WHO classification. The selected features were then combined to create nomograms for the two systems. The performance of the radiomics model, semantic model, and combined model was evaluated using the area under the receiver operating characteristic curves (AUCs).

Results: One hundred eighty-seven cases (56.5 years ± 12.3, 101 men) were included, with 62 cases as the external test set. For Masaoka-Koga staging, the combined model, which incorporated five peritumor radiomics features and four semantic features, showed an AUC of 0.958 (95% CI: 0.912-1.000) in distinguishing between early-stage (stage I/II) and advanced-stage (III/IV) TET in the external test set. For WHO classification, the combined model incorporating five peritumor radiomics features and two semantic features showed an AUC of 0.857 (0.760-0.955) in differentiating low-risk (type A/AB/B1) and high-risk (B2/B3/C) TET. The combined models showed the most effective predictive performance, while the semantic models exhibited comparable performance to the radiomics models in both systems (p > 0.05).

Conclusion: The nomograms combining peritumor radiomics features and semantic features could help in increasing the accuracy of grading invasiveness and risk stratification of TET.

Critical relevance statement: Peripheral invasion and histopathological type are major determinants of treatment and prognosis of TET. The integration of peritumoral radiomics features and semantic features into nomograms may enhance the accuracy of grading invasiveness and risk stratification of TET.

Key points: Peritumor region of TET may suggest histopathological and invasive risk. Peritumor radiomic and semantic features allow classification by Masaoka-Koga staging (AUC: 0.958). Peritumor radiomic and semantic features enable the classification of histopathological risk (AUC: 0.857).

Objectives: To develop and evaluate a multi-task deep-learning (DL) model for automated segment-level coronary artery calcium (CAC) scoring on non-contrast computed tomography (CT) for precise localization and quantification of calcifications in the coronary artery tree.

Methods: This study included 1514 patients (mean age, 60.0 ± 10.2 years; 56.0% female) with stable chest pain from 26 centers participating in the multicenter DISCHARGE trial (NCT02400229). The patients were randomly assigned to a training/validation set (1059) and a test set (455). We developed a multi-task neural network for performing the segmentation of calcifications on the segment level as the main task and the segmentation of coronary artery segment regions with weak annotations as an auxiliary task. Model performance was evaluated using (micro-average) sensitivity, specificity, F1-score, and weighted Cohen's κ for segment-level agreement based on the Agatston score and performing interobserver variability analysis.

Results: In the test set of 455 patients with 1797 calcifications, the model assigned 73.2% (1316/1797) to the correct coronary artery segment. The model achieved a micro-average sensitivity of 0.732 (95% CI: 0.710-0.754), a micro-average specificity of 0.978 (95% CI: 0.976-0.980), and a micro-average F1-score of 0.717 (95% CI: 0.695-0.739). The segment-level agreement was good with a weighted Cohen's κ of 0.808 (95% CI: 0.790-0.824), which was only slightly lower than the agreement between the first and second observer (0.809 (95% CI: 0.798-0.845)).

Conclusion: Automated segment-level CAC scoring using a multi-task neural network approach showed good agreement on the segment level, indicating that DL has the potential for automated coronary artery calcification classification.

Critical relevance statement: Multi-task deep learning can perform automated coronary calcium scoring on the segment level with good agreement and may contribute to the development of new and improved calcium scoring methods.

Key points: Segment-level coronary artery calcium scoring is a tedious and error-prone task. The proposed multi-task model achieved good agreement with a human observer on the segment level. Deep learning can contribute to the automation of segment-level coronary artery calcium scoring.

Objectives: To quantitatively investigate the anatomy of the anterior talofibular ligament (ATFL) and calcaneofibular ligament (CFL) for surgical reconstruction procedures in chronic ankle instability (CAI).

Methods: 3D MRI was performed on five fresh-frozen cadaveric ankles using six different spatial resolutions (0.3 × 0.3 × 0.3 mm³, 0.45 × 0.45 × 0.45 mm³, 0.6 × 0.6 × 0.6 mm³, 0.75 × 0.75 × 0.75 mm³, 0.9 × 0.9 × 0.9 mm³, 1.05 × 1.05 × 1.05 mm³). After comparing the MRI results with cadaver dissection, a resolution of 0.45 × 0.45 × 0.45 mm³ was selected for bilateral ankles MRI on 24 volunteers. Classification of the ATFL and four distances of surgically relevant bony landmarkers were analyzed (distance 1 and 3, the fibular origin of the ATFL and CFL to the tip of fibula, respectively; distance 2, the talar insertion of the ATFL to the bare zone of talus; distance 4, the calcaneal insertion of the CFL to the peroneal tubercle).

Results: In subjective evaluation, the interobserver ICC was 0.95 (95% confidence interval (CI): 0.94-0.97) between two readers. The spatial resolution of 0.3 × 0.3 × 0.3 mm³ and 0.45 × 0.45 × 0.45 mm³ received highest subjective score on average and demonstrated highest consistency with autopsy measurements in objective evaluation. Measurements on the 48 volunteer ankles, distance 1 in type I and II were 12.65 ± 2.08 mm, 13.43 ± 2.06 mm (superior-banded in Type II) and 7.69 ± 2.56 mm (inferior-banded in Type II) (means ± SD), respectively. Distance 2 in type I and II were 10.90 ± 2.24 mm, 11.07 ± 2.66 mm (superior-banded in Type II), and 18.44 ± 3.28 mm (inferior-banded in Type II), respectively. Distance 3 and 4 were 4.71 ± 1.04 mm and 14.35 ± 2.22 mm, respectively.

Conclusion: We demonstrated the feasibility of quantifying the distances between bony landmarkers for surgical reconstruction surgery in CAI using high-resolution 3D MRI.

Critical relevance statement: High-resolution 3D MRI examination may have a guiding effect on the preoperative evaluation of chronic ankle instability patients.

Key points: Spatial resolutions of 0.3 × 0.3 × 0.3 mm³ and 0.45 × 0.45 × 0.45 mm³ demonstrated highest consistency with autopsy measurements. The spatial resolution of 0.45 × 0.45 × 0.45 mm³ was conformed more to clinical needs. 3D MRI can assist surgeons in developing preoperative plans for chronic ankle instability.