Anterior mediastinal lesions: CT and MRI features and differential diagnosis

Therapeutic Decision Making in Prevascular Mediastinal Tumors Using CT Radiomics and Clinical Features: Upfront Surgery or Pretreatment Needle Biopsy?

The study aimed to develop machine learning (ML) classification models for differentiating patients who needed direct surgery from patients who needed core needle biopsy among patients with prevascular mediastinal tumor (PMT). Patients with PMT who received a contrast-enhanced computed tomography (CECT) scan and initial management for PMT between January 2010 and December 2020 were included in this retrospective study. Fourteen ML algorithms were used to construct candidate classification models via the voting ensemble approach, based on preoperative clinical data and radiomic features extracted from the CECT. The classification accuracy of clinical diagnosis was 86.1%. The first ensemble learning model was built by randomly choosing seven ML models from a set of fourteen ML models and had a classification accuracy of 88.0% (95% CI = 85.8 to 90.3%). The second ensemble learning model was the combination of five ML models, including NeuralNetFastAI, NeuralNetTorch, RandomForest with Entropy, RandomForest with Gini, and XGBoost, and had a classification accuracy of 90.4% (95% CI = 87.9 to 93.0%), which significantly outperformed clinical diagnosis (p < 0.05). Due to the superior performance, the voting ensemble learning clinical-radiomic classification model may be used as a clinical decision support system to facilitate the selection of the initial management of PMT.

Approach to Imaging of Mediastinal Masses

Mediastinal masses present a diagnostic challenge due to their diverse etiologies. Accurate localization and internal characteristics of the mass are the two most important factors to narrow the differential diagnosis or provide a specific diagnosis. The International Thymic Malignancy Interest Group (ITMIG) classification is the standard classification system used to localize mediastinal masses. Computed tomography (CT) and magnetic resonance imaging (MRI) are the two most commonly used imaging modalities for characterization of the mediastinal masses.

MRI Findings and Differential Diagnosis of Anterior Mediastinal Solid Tumors

The anterior mediastinum is the most common location of mediastinal tumors, and thymic epithelial tumors are the most common mediastinal tumors. It is important to differentiate thymic epithelial tumors from malignant lymphomas and malignant germ cell tumors because of the different treatment strategies. Dynamic contrast-enhanced MRI and diffusion-weighted imaging can provide additional information on the differential diagnosis. Chemical shift imaging can detect tiny fat tissues in the lesion and is useful in differentiating thymic hyperplasia from other solid tumors such as thymomas. MRI findings reflect histopathological features of mediastinal tumors, and a comprehensive evaluation of MRI sequences is important for estimation of the histopathological features of the tumor. In this manuscript, we describe the MRI findings of anterior mediastinal solid tumors and the role of MRI in the differential diagnosis.

Pan-mediastinal neoplasm diagnosis via nationwide federated learning: a multicentre cohort study

BACKGROUND

Mediastinal neoplasms are typical thoracic diseases with increasing incidence in the general global population and can lead to poor prognosis. In clinical practice, the mediastinum's complex anatomic structures and intertype confusion among different mediastinal neoplasm pathologies severely hinder accurate diagnosis. To solve these difficulties, we organised a multicentre national collaboration on the basis of privacy-secured federated learning and developed CAIMEN, an efficient chest CT-based artificial intelligence (AI) mediastinal neoplasm diagnosis system.

METHODS

In this multicentre cohort study, 7825 mediastinal neoplasm cases and 796 normal controls were collected from 24 centres in China to develop CAIMEN. We further enhanced CAIMEN with several novel algorithms in a multiview, knowledge-transferred, multilevel decision-making pattern. CAIMEN was tested by internal (929 cases at 15 centres), external (1216 cases at five centres and a real-world cohort of 11 162 cases), and human-AI (60 positive cases from four centres and radiologists from 15 institutions) test sets to evaluate its detection, segmentation, and classification performance.

FINDINGS

In the external test experiments, the area under the receiver operating characteristic curve for detecting mediastinal neoplasms of CAIMEN was 0·973 (95% CI 0·969-0·977). In the real-world cohort, CAIMEN detected 13 false-negative cases confirmed by radiologists. The dice score for segmenting mediastinal neoplasms of CAIMEN was 0·765 (0·738-0·792). The mediastinal neoplasm classification top-1 and top-3 accuracy of CAIMEN were 0·523 (0·497-0·554) and 0·799 (0·778-0·822), respectively. In the human-AI test experiments, CAIMEN outperformed clinicians with top-1 and top-3 accuracy of 0·500 (0·383-0·633) and 0·800 (0·700-0·900), respectively. Meanwhile, with assistance from the computer aided diagnosis software based on CAIMEN, the 46 clinicians improved their average top-1 accuracy by 19·1% (0·345-0·411) and top-3 accuracy by 13·0% (0·545-0·616).

INTERPRETATION

For mediastinal neoplasms, CAIMEN can produce high diagnostic accuracy and assist the diagnosis of human experts, showing its potential for clinical practice.

FUNDING

National Key R&D Program of China, National Natural Science Foundation of China, and Beijing Natural Science Foundation.

Tips and Tricks in Thoracic Radiology for Beginners: A Findings-Based Approach

This review has the purpose of illustrating schematically and comprehensively the key concepts for the beginner who approaches chest radiology for the first time. The approach to thoracic imaging may be challenging for the beginner due to the wide spectrum of diseases, their overlap, and the complexity of radiological findings. The first step consists of the proper assessment of the basic imaging findings. This review is divided into three main districts (mediastinum, pleura, focal and diffuse diseases of the lung parenchyma): the main findings will be discussed in a clinical scenario. Radiological tips and tricks, and relative clinical background, will be provided to orient the beginner toward the differential diagnoses of the main thoracic diseases.

Extracellular volume fraction derived from equilibrium contrast-enhanced CT as a diagnostic parameter in anterior mediastinal tumors

PURPOSE

To assess the usefulness of extracellular volume (ECV) fraction derived from equilibrium contrast-enhanced CT (CECT) for diagnosing anterior mediastinal tumors.

METHOD

This study included 161 histologically confirmed anterior mediastinal tumors (55 low-risk thymomas, 57 high-risk thymomas, 32 thymic carcinomas, and 17 malignant lymphomas) that were assessed by pretreatment CECT. ECV fraction was calculated using measurements obtained within the lesion and the aorta on unenhanced and equilibrium phase CECT. ECV fraction was compared among anterior mediastinal tumors using one-way ANOVA or t-test. Receiver-operating characteristic (ROC) curve analysis was performed to evaluate the ability of ECV fraction to differentiate thymic carcinomas/lymphomas from thymomas.

RESULTS

ECV fraction differed significantly among the anterior mediastinal tumors (p < 0.001). ECV fraction of thymic carcinomas was significantly higher than those of low-risk thymomas, high-risk thymomas, and lymphomas (p < 0.001, p < 0.001, and p = 0.006, respectively). ECV fraction of lymphomas was significantly higher than that of low-risk thymomas (p < 0.001). ECV fraction was significantly higher in thymic carcinomas/lymphomas than in thymomas (40.1 % vs. 27.7 %, p < 0.001). The optimal cutoff value to differentiate thymic carcinomas/lymphomas from thymomas was 38.5 % (AUC, 0.805; 95 %CI, 0.736-0.863).

CONCLUSIONS

ECV fraction derived from equilibrium CECT is helpful in diagnosing anterior mediastinal tumors. High ECV fraction is indicative of thymic carcinomas/lymphomas, particularly thymic carcinomas.

Clinical radiomics-based machine learning versus three-dimension convolutional neural network analysis for differentiation of thymic epithelial tumors from other prevascular mediastinal tumors on chest computed tomography scan

Purpose

To compare the diagnostic performance of radiomic analysis with machine learning (ML) model with a convolutional neural network (CNN) in differentiating thymic epithelial tumors (TETs) from other prevascular mediastinal tumors (PMTs).

Methods

A retrospective study was performed in patients with PMTs and undergoing surgical resection or biopsy in National Cheng Kung University Hospital, Tainan, Taiwan, E-Da Hospital, Kaohsiung, Taiwan, and Kaohsiung Veterans General Hospital, Kaohsiung, Taiwan between January 2010 and December 2019. Clinical data including age, sex, myasthenia gravis (MG) symptoms and pathologic diagnosis were collected. The datasets were divided into UECT (unenhanced computed tomography) and CECT (enhanced computed tomography) for analysis and modelling. Radiomics model and 3D CNN model were used to differentiate TETs from non-TET PMTs (including cyst, malignant germ cell tumor, lymphoma and teratoma). The macro F1-score and receiver operating characteristic (ROC) analysis were performed to evaluate the prediction models.

Result

In the UECT dataset, there were 297 patients with TETs and 79 patients with other PMTs. The performance of radiomic analysis with machine learning model using LightGBM with Extra Tree (macro F1-Score = 83.95%, ROC-AUC = 0.9117) had better performance than the 3D CNN model (macro F1-score = 75.54%, ROC-AUC = 0.9015). In the CECT dataset, there were 296 patients with TETs and 77 patients with other PMTs. The performance of radiomic analysis with machine learning model using LightGBM with Extra Tree (macro F1-Score = 85.65%, ROC-AUC = 0.9464) had better performance than the 3D CNN model (macro F1-score = 81.01%, ROC-AUC = 0.9275).

Conclusion

Our study revealed that the individualized prediction model integrating clinical information and radiomic features using machine learning demonstrated better predictive performance in the differentiation of TETs from other PMTs at chest CT scan than 3D CNN model.

Thoracoscopic approach for massive thymic hyperplasia in an infant: Case report and literature review

Introduction

Massive thymic hyperplasia (MTH) is a very rare entity, with fewer than 20 cases reported in the literature in infancy. Most patients have respiratory symptoms and the enlarged thymus gland occupies one side of the thoracic cavity. Posterolateral thoracotomy or median sternotomy is the main treatment for MTH in infants. We report a case of an infant with MTH in which the enlarged thymus occupied his bilateral thoracic cavity and he underwent video-assisted thoracoscopic surgery (VATS). In addition, we reviewed and summarized the relevant literature.

Case Report

A 4-month-old boy was admitted to the hospital with no apparent cause of dyspnea for 18 days, with cough and sputum. On examination, the patient was found to have cyanotic lips, diminished breath sounds in both lungs, and a positive three concave sign. There was no fever or ptosis. Preoperative imaging showed large soft tissue shadows in the bilateral thoracic cavity, with basic symmetry between the right and left sides. Tumor markers were within the normal range. Ultrasound-guided fine needle biopsy showed normal thymic structures with no evidence of malignancy. As his symptoms worsened, he eventually underwent unilateral thoracic approach video-assisted thoracoscopic exploratory surgery, during which a large mass occupying the bilateral thoracic cavity was removed in a separate block and part of the thymus in the left lobe was preserved. Pathological examination confirmed true thymic hyperplasia (TTH). No relevant complications occurred at the 2-month postoperative follow-up.

Conclusion

In infants, MTH occupying the bilateral thoracic cavity can produce severe respiratory and circulatory symptoms due to occupying effects. Although a definitive preoperative diagnosis is sometimes difficult, after combining computed tomography (CT) and fine needle biopsy to exclude evidence of other malignancies, the enlarged thymus occupying the bilateral thoracic cavity can be resected via VATS. Whether the enlarged thymus occupies the bilateral thoracic cavity and the size of the thymus are not absolute contraindications to thoracoscopic surgery. The method is safe, feasible, and minimally invasive to the patient.

Multiparameter diagnostic model based on 18F-FDG PET and clinical characteristics can differentiate thymic epithelial tumors from thymic lymphomas

OBJECTIVE

To evaluate the diagnostic performance of combined multiparametric ¹⁸F-fluorodeoxyglucose positron emission tomography (¹⁸FDG PET) with clinical characteristics in differentiating thymic epithelial tumors (TETs) from thymic lymphomas.

PATIENTS AND METHODS

A total of 173 patients with 80 TETs and 93 thymic lymphomas who underwent ¹⁸F-FDG PET/CT before treatment were enrolled in this retrospective study. All patients were confirmed by pathology, and baseline characteristics and clinical data were also collected. The semi-parameters of ¹⁸F-FDG PET/CT, including lesion size, SUVmax (maximum standard uptake value), SUVmean (mean standard uptake value), TLG (total lesion glycolysis), MTV (metabolic tumor volume) and SUVR (tumor-to-normal liver standard uptake value ratio) were evaluated. The differential diagnostic efficacy was evaluated using the receiver operating characteristic (ROC) curve. Integrated discriminatory improvement (IDI) and net reclassification improvement (NRI), and Delong test were used to evaluate the improvement in diagnostic efficacy. The clinical efficacy was evaluated by decision curve analysis (DCA).

RESULTS

Age, clinical symptoms, and metabolic parameters differed significantly between patients with TETs and thymic lymphomas. The ROC curve analysis of SUVR showed the highest differentiating diagnostic value (sensitivity = 0.763; specificity = 0.888; area under the curve [AUC] = 0.881). The combined diagnostics model of age, clinical symptoms and SUVR resulted in the highest AUC of 0.964 (sensitivity = 0.882, specificity = 0.963). Compared with SUVR, the diagnostic efficiency of the model was improved significantly. The DCA also confirmed the clinical efficacy of the model.

CONCLUSIONS

The multiparameter diagnosis model based on ¹⁸F-FDG PET and clinical characteristics had excellent value in the differential diagnosis of TETs and thymic lymphomas.

Efficacy of contrast-enhanced ultrasound-guided percutaneous core needle biopsy in anterior mediastinal masses

Objective

To evaluate the efficacy and safety of percutaneous core needle biopsy (PCNB) using ultrasound (US)-guided and contrast-enhanced ultrasound (CEUS)-guided procedures for anterior mediastinal masses (AMMs).

Methods

In total, 284 consecutive patients (166 men, 118 women; mean age, 43.0 ​± ​18.4 years) who underwent PCNB for AMMs were enrolled. Patients were divided into the US-guided group (n ​= ​133) and the CEUS-guided group (n ​= ​151). PCNB was performed using a core needle (16-gauge or 18-gauge). Internal necrosis, diagnostic yield, and diagnostic accuracy were compared between the two groups.

Results

The predominant final diagnosis of the cases in this study was thymoma (29.7%), lymphoma (20.5%), thymic carcinoma (13.3%), and germ cell tumour (13.3%), respectively. There was no significant difference in patient age, sex, number of percutaneous biopsies, or display rate of internal necrosis on conventional US between the two groups. The rate of internal necrosis of the lesions was significantly higher after contrast agent injection (72.2% vs. 41.7%; P ​< ​0.001). The CEUS-guided group had a higher diagnostic yield than the US-guided group (100% vs. 89.5%, P ​< ​0.001). There was no significant difference between the diagnostic accuracy of the CEUS-guided and US-guided groups (97.3% vs. 97.4%; P ​= ​1.000). None of the patients experienced adverse reactions or complications after US-guided or CEUS-guided PCNB.

Conclusions

CEUS-guided PCNB can improve the diagnostic yield by optimizing the biopsy procedure.

Development and Validation of a CT-Based Radiomics Nomogram in Patients With Anterior Mediastinal Mass: Individualized Options for Preoperative Patients

Background

To improve the preoperative diagnostic accuracy and reduce the non-therapeutic thymectomy rate, we established a comprehensive predictive nomogram based on radiomics data and computed tomography (CT) features and further explored its potential use in clinical decision-making for anterior mediastinal masses (AMMs).

Methods

A total of 280 patients, including 280 with unenhanced CT (UECT) and 241 with contrast-enhanced CT (CECT) scans, all of whom had undergone thymectomy for AMM with confirmed histopathology, were enrolled in this study. A total of 1,288 radiomics features were extracted from each labeled mass. The least absolute shrinkage and selection operator model was used to select the optimal radiomics features in the training set to construct the radscore. Multivariate logistic regression analysis was conducted to establish a combined clinical radiographic radscore model, and an individualized prediction nomogram was developed.

Results

In the UECT dataset, radscore and the UECT ratio were selected for the nomogram. The combined model achieved higher accuracy (AUC: 0.870) than the clinical model (AUC: 0.752) for the prediction of therapeutic thymectomy probability. In the CECT dataset, the clinical and combined models achieved higher accuracy (AUC: 0.851 and 0.836, respectively) than the radscore model (AUC: 0.618) for the prediction of therapeutic thymectomy probability.

Conclusions

In patients who underwent UECT only, a nomogram integrating the radscore and the UECT ratio achieved good accuracy in predicting therapeutic thymectomy in AMMs. However, the use of radiomics in patients with CECT scans did not improve prediction performance; therefore, a clinical model is recommended.

An MRI-Based Clinical-Perfusion Model Predicts Pathological Subtypes of Prevascular Mediastinal Tumors

This study aimed to build machine learning prediction models for predicting pathological subtypes of prevascular mediastinal tumors (PMTs). The candidate predictors were clinical variables and dynamic contrast–enhanced MRI (DCE-MRI)–derived perfusion parameters. The clinical data and preoperative DCE–MRI images of 62 PMT patients, including 17 patients with lymphoma, 31 with thymoma, and 14 with thymic carcinoma, were retrospectively analyzed. Six perfusion parameters were calculated as candidate predictors. Univariate receiver-operating-characteristic curve analysis was performed to evaluate the performance of the prediction models. A predictive model was built based on multi-class classification, which detected lymphoma, thymoma, and thymic carcinoma with sensitivity of 52.9%, 74.2%, and 92.8%, respectively. In addition, two predictive models were built based on binary classification for distinguishing Hodgkin from non-Hodgkin lymphoma and for distinguishing invasive from noninvasive thymoma, with sensitivity of 75% and 71.4%, respectively. In addition to two perfusion parameters (efflux rate constant from tissue extravascular extracellular space into the blood plasma, and extravascular extracellular space volume per unit volume of tissue), age and tumor volume were also essential parameters for predicting PMT subtypes. In conclusion, our machine learning–based predictive model, constructed with clinical data and perfusion parameters, may represent a useful tool for differential diagnosis of PMT subtypes.

Artificial Intelligence and COVID-19 Using Chest CT Scan and Chest X-ray Images: Machine Learning and Deep Learning Approaches for Diagnosis and Treatment

OBJECTIVE

To report an overview and update on Artificial Intelligence (AI) and COVID-19 using chest Computed Tomography (CT) scan and chest X-ray images (CXR). Machine Learning and Deep Learning Approaches for Diagnosis and Treatment were identified.

METHODS

Several electronic datasets were analyzed. The search covered the years from January 2019 to June 2021. The inclusion criteria were studied evaluating the use of AI methods in COVID-19 disease reporting performance results in terms of accuracy or precision or area under Receiver Operating Characteristic (ROC) curve (AUC).

RESULTS

Twenty-two studies met the inclusion criteria: 13 papers were based on AI in CXR and 10 based on AI in CT. The summarized mean value of the accuracy and precision of CXR in COVID-19 disease were 93.7% ± 10.0% of standard deviation (range 68.4-99.9%) and 95.7% ± 7.1% of standard deviation (range 83.0-100.0%), respectively. The summarized mean value of the accuracy and specificity of CT in COVID-19 disease were 89.1% ± 7.3% of standard deviation (range 78.0-99.9%) and 94.5 ± 6.4% of standard deviation (range 86.0-100.0%), respectively. No statistically significant difference in summarized accuracy mean value between CXR and CT was observed using the Chi square test (p value > 0.05).

CONCLUSIONS

Summarized accuracy of the selected papers is high but there was an important variability; however, less in CT studies compared to CXR studies. Nonetheless, AI approaches could be used in the identification of disease clusters, monitoring of cases, prediction of the future outbreaks, mortality risk, COVID-19 diagnosis, and disease management.