Impact of endoscopic ultrasound-guided fine-needle aspiration and multidisciplinary approach in the management of abdominal or mediastinal mass

Application of machine learning for the differentiation of thymomas and thymic cysts using deep transfer learning: A multi-center comparison of diagnostic performance based on different dimensional models

OBJECTIVE

This study aimed to evaluate the feasibility and performance of deep transfer learning (DTL) networks with different types and dimensions in differentiating thymomas from thymic cysts in a retrospective cohort.

MATERIALS AND METHODS

Based on chest-enhanced computed tomography (CT), the region of interest was delineated, and the maximum cross section of the lesion was selected as the input image. Five convolutional neural networks (CNNs) and Vision Transformer (ViT) were used to construct a 2D DTL model. The 2D model constructed by the maximum section (n) and the upper and lower layers (n - 1, n + 1) of the lesion was used for feature extraction, and the features were selected. The remaining features were pre-fused to construct a 2.5D model. The whole lesion image was selected for input and constructing a 3D model.

RESULTS

In the 2D model, the area under curve (AUC) of Resnet50 was 0.950 in the training cohort and 0.907 in the internal validation cohort. In the 2.5D model, the AUCs of Vgg11 in the internal validation cohort and external validation cohort 1 were 0.937 and 0.965, respectively. The AUCs of Inception_v3 in the training cohort and external validation cohort 2 were 0.981 and 0.950, respectively. The AUC values of 3D_Resnet50 in the four cohorts were 0.987, 0.937, 0.938, and 0.905.

CONCLUSIONS

The DTL model based on multiple different dimensions can be used as a highly sensitive and specific tool for the non-invasive differential diagnosis of thymomas and thymic cysts to assist clinicians in decision-making.

Development and Validation of Contrast-Enhanced CT-Based Deep Transfer Learning and Combined Clinical-Radiomics Model to Discriminate Thymomas and Thymic Cysts: A Multicenter Study

RATIONALE AND OBJECTIVES

This study aims to evaluate the feasibility and effectiveness of deep transfer learning (DTL) and clinical-radiomics in differentiating thymoma from thymic cysts.

MATERIALS AND METHODS

Clinical and imaging data of 196 patients pathologically diagnosed with thymoma and thymic cysts were retrospectively collected from center 1. (training cohort: n = 137; internal validation cohort: n = 59). An independent external validation cohort comprised 68 thymoma and thymic cyst patients from center 2. Region of interest (ROI) delineation was performed on contrast-enhanced chest computed tomography (CT) images, and eight DTL models including Densenet 169, Mobilenet V2, Resnet 101, Resnet 18, Resnet 34, Resnet 50, Vgg 13, Vgg 16 were constructed. Radiomics features were extracted from the ROI on the CT images of thymoma and thymic cyst patients, and feature selection was performed using intra-observer correlation coefficient (ICC), Spearman correlation analysis, and least absolute shrinkage and selection operator (LASSO) algorithm. Univariate analysis and multivariable logistic regression (LR) were used to select clinical-radiological features. Six machine learning classifiers, including LR, support vector machine (SVM), k-nearest neighbors (KNN), Light Gradient Boosting Machine (LightGBM), Adaptive Boosting (AdaBoost), and Multilayer Perceptron (MLP), were used to construct Radiomics and Clinico-radiologic models. The selected features from the Radiomics and Clinico-radiologic models were fused to build a Combined model. Receiver operating characteristic curve (ROC), calibration curve, and decision curve analysis (DCA) were used to evaluate the discrimination, calibration, and clinical utility of the models, respectively. The Delong test was used to compare the AUC between different models. K-means clustering was used to subdivide the lesions of thymomas or thymic cysts into subregions, and traditional radiomics methods were used to extract features and compare the ability of Radiomics and DTL models to reflect intratumoral heterogeneity using correlation analysis.

RESULTS

The Densenet 169 based on DTL performed the best, with AUC of 0.933 (95% CI: 0.875-0.991) in the internal validation cohort and 0.962 (95% CI: 0.923-1.000) in the external validation cohort. The AdaBoost classifier achieved AUC of 0.965 (95% CI: 0.923-1.000) and 0.959 (95% CI: 0.919-1.000) in the internal and external validation cohorts, respectively, for the Radiomics model. The LightGBM classifier achieved AUC of 0.805 (95% CI: 0.690-0.920) and 0.839 (95% CI: 0.736-0.943) in the Clinico-radiologic model. The AUC of the Combined model in the internal and external validation cohorts was 0.933 (95% CI: 0.866-1.000) and 0.945 (95% CI: 0.897-0.994), respectively. The results of the Delong test showed that the Radiomics model, DTL model, and Combined model outperformed the Clinico-radiologic model in both internal and external validation cohorts (p-values were 0.002, 0.004, and 0.033 in the internal validation cohort, while in the external validation cohort, the p-values were 0.014, 0.006, and 0.015, respectively). But there was no statistical difference in performance among the three models (all p-values <0.05). Correlation analysis showed that radiomics performed better than DTL in quantifying intratumoral heterogeneity differences between thymoma and thymic cysts.

CONCLUSION

The developed DTL model and the Combined model based on radiomics and clinical-radiologic features achieved excellent diagnostic performance in differentiating thymic cysts from thymoma. They can serve as potential tools to assist clinical decision-making, particularly when endoscopic biopsy carries a high risk.

Technical Performance, Overall Accuracy and Complications of EUS-Guided Interventional Procedures: A Dynamic Landscape

Endoscopic ultrasound (EUS) gained wide acceptance as the diagnostic and minimally invasive therapeutic approach for intra-luminal and extraluminal gastrointestinal, as well as various non-gastrointestinal lesions. Since its introduction, EUS has undergone substantial technological advances. This multi-centric study is a retrospective analysis of a prospectively maintained database of patients who underwent EUS for the evaluation of lesions located within the gastrointestinal tract and the proximal organs. It aimed to extensively assess in dynamic the dual-center EUS experience over the course of the past 20 years. Hence, we performed a population study and an overall assessment of the EUS procedures. The performance of EUS-FNA/FNB in diagnosing pancreatic neoplasms was evaluated. We also investigated the contribution of associating contrast-enhanced ultrasound imaging (CE-EUS) with EUS-FNA/FNB for differentiating solid pancreatic lesions or cystic pancreatic lesions. A total of 2935 patients undergoing EUS between 2002–2021 were included, out of which 1880 were diagnostic EUS and 1052 EUS-FNA/FNB (80% FNA and 20% FNB). Therapeutic procedures performed included endoscopic transmural drainage of pancreatic fluid collections, celiac plexus block and neurolysis, while diagnostic EUS-like CE-EUS (20%) and real-time elastography (12%) were also conducted. Most complications occurred during the first 7 days after EUS-FNA/FNB or pseudocyst drainage. EUS and the additional tools have high technical success rates and low rates of complications. The EUS methods are safe, cost effective and indispensable for the diagnostic or therapeutic management in gastroenterological everyday practice.

Factors influencing diagnostic accuracy of endoscopic ultrasound-guided fine-needle aspiration (EUS-FNA) in pancreatic and biliary tumors

BACKGROUND AND AIM

Diagnostic accuracy of endoscopic ultrasound-guided fine-needle aspiration (EUS-FNA) is influenced by several factors, primarily operator expertise. Formal training in EUS-FNA, as suggested by the European Society of Gastrointestinal Endoscopy and the American Society for Gastrointestinal Endoscopy guidelines, is not always available and is often expensive and time-consuming. In this study we evaluate factors influencing the diagnostic accuracy of pancreatic EUS-FNA.

METHODS

In a retrospective study, 557 consecutive EUS-FNAs were evaluated. Several variables relating to the procedures were considered to calculate the EUS-FNA performance over eight years.

RESULTS

A total of 308 out of 557 EUS-FNAs were selected. Overall sensitivity of EUS-FNA was 66% (95% CI: 60.8-71.8), specificity 100%, and diagnostic accuracy 69% (95% CI: 64.0-74.4). An increase in diagnostic accuracy was observed to >90% using a new fine-needle biopsy (FNB) needle and in the case of simultaneous sampling of primary and metastatic lesions. Diagnostic accuracy >80% was observed after 250 procedures, in the absence of rapid on-site cytopathological examination (ROSE). Multivariate logistic regression analysis confirmed that the FNB needle, operator skill, and double EUS-FNA sampling are associated with high diagnostic accuracy.

CONCLUSIONS

The learning curve for EUS-FNA may be longer and a considerable number of procedures are needed to achieve high diagnostic accuracy in the absence of ROSE. However, the use of FNB needles and the simultaneous sampling of primary and metastatic lesions can rapidly improve the diagnostic accuracy of the procedure.

Can computed tomography-based radiomics potentially discriminate between anterior mediastinal cysts and type B1 and B2 thymomas?

Background

Anterior mediastinal cysts (AMC) are often misdiagnosed as thymomas and undergo surgical resection, which caused unnecessary treatment and medical resource waste. The purpose of this study is to explore potential possibility of computed tomography (CT)-based radiomics for the diagnosis of AMC and type B1 and B2 thymomas.

Methods

A group of 188 patients with pathologically confirmed AMC (106 cases misdiagnosed as thymomas in CT) and thymomas (82 cases) and underwent routine chest CT from January 2010 to December 2018 were retrospectively analyzed. The lesions were manually delineated using ITK-SNAP software, and radiomics features were performed using the artificial intelligence kit (AK) software. A total of 180 tumour texture features were extracted from enhanced CT and unenhanced CT, respectively. The general test, correlation analysis, and LASSO were used to features selection and then the radiomics signature (radscore) was obtained. The combined model including radscore and independent clinical factors was developed. The model performances were evaluated on discrimination, calibration curve.

Results

Two radscore models were constructed from the unenhanced and enhanced phases based on the selected four and three features, respectively. The AUC, sensitivity, and specificity of the enhanced radscore model were 0.928, 89.3%, and 83.8% in the training dataset and 0.899, 84.6%, and 87.5% in the test dataset (higher than the unenhanced radscore model). The combined model of enhanced CT including radiomics features and independent clinical factors yielded an AUC, sensitivity and specificity of 0.941, 82.1%, and 94.6% in the training dataset and 0.938, 92.3%, and 87.5% in the test dataset (higher than the unenhanced combined model and enhanced radscore model).

Conclusions

The study suggested the possibility that the combined model in enhanced CT provided a potential tool to facilitate the differential diagnosis of AMC and type B1 and B2 thymomas.

Contrast-Enhanced Ultrasound Guided Biopsy of Undetermined Abdominal Lesions: A Multidisciplinary Decision-Making Approach

Aim. To investigate the value of contrast-enhanced ultrasound (CEUS) guided biopsy of undetermined abdominal lesions in multidisciplinary treatment (MDT) decision-making approach. Methods. Between Jan 2012 and Dec 2015, 60 consecutive patients (male, 37; female, 23; mean age, 51.3 years ± 14.6) who presented with undetermined abdominal lesions were included. CEUS and core needle percutaneous biopsy was performed under real-time CEUS guidance in all lesions. Data were recorded and compared with conventional ultrasound (US) guidance group (n = 75). All CEUS findings and clinical data were evaluated in MDT. Results. CEUS enabled the delimitation of more (88.3% versus 41.3%) and larger (14.1 ± 10.7 mm versus 32.3 ± 18.5 mm) nonenhanced necrotic areas. More inner (20.0% versus 6.7%) and surrounding (18.3% versus 2.7%) major vessels were visualized and avoided during biopsies. CEUS-guided biopsy increased the diagnostic accuracy from 93.3% to 98.3%, with correct diagnosis in 57 of 60 lesions (95.0%). The therapeutic plan was influenced by CEUS guided biopsies findings in the majority of patients (98.3%). Conclusion. The combination of CEUS guided biopsy and MDT decision-making approach is useful in the diagnostic work-up and therapeutic management.