Does volume perfusion computed tomography enable differentiation of metastatic and non-metastatic mediastinal lymph nodes in lung cancer patients? A feasibility study

LNAS: a clinically applicable deep-learning system for mediastinal enlarged lymph nodes segmentation and station mapping without regard to the pathogenesis using unenhanced CT images

BACKGROUND

The accurate identification and evaluation of lymph nodes by CT images is of great significance for disease diagnosis, treatment, and prognosis.

PURPOSE

To assess the lymph nodes' segmentation, size, and station by artificial intelligence (AI) for unenhanced chest CT images and evaluate its value in clinical scenarios.

MATERIAL AND METHODS

This retrospective study proposed an end-to-end Lymph Nodes Analysis System (LNAS) consisting of three models: the Lymph Node Segmentation model (LNS), the Mediastinal Organ Segmentation model (MOS), and the Lymph Node Station Registration model (LNR). We selected a healthy chest CT image as the template image and annotated 14 lymph node station masks according to the IASLC to build the lymph node station mapping template. The exact contours and stations of the lymph nodes were annotated by two junior radiologists and reviewed by a senior radiologist. Patients aged 18 and above, who had undergone unenhanced chest CT and had at least one suspicious enlarged mediastinal lymph node in imaging reports, were included. Exclusions were patients who had thoracic surgeries in the past 2 weeks or artifacts on CT images affecting lymph node observation by radiologists. The system was trained on 6725 consecutive chest CTs that from Tianjin Medical University General Hospital, among which 6249 patients had suspicious enlarged mediastinal lymph nodes. A total of 519 consecutive chest CTs from Qilu Hospital of Shandong University (Qingdao) were used for external validation. The gold standard for each CT was determined by two radiologists and reviewed by one senior radiologist.

RESULTS

The patient-level sensitivity of the LNAS system reached of 93.94% and 92.89% in internal and external test dataset, respectively. And the lesion-level sensitivity (recall) reached 89.48% and 85.97% in internal and external test dataset. For man-machine comparison, AI significantly apparently shortened the average reading time (p < 0.001) and had better lesion-level and patient-level sensitivities.

CONCLUSION

AI improved the sensitivity lymph node segmentation by radiologists with an advantage in reading time.

Preoperatively Estimating the Malignant Potential of Mediastinal Lymph Nodes: A Pilot Study Toward Establishing a Robust Radiomics Model Based on Contrast-Enhanced CT Imaging

PURPOSE

To establish and validate a radiomics model to estimate the malignancy of mediastinal lymph nodes (LNs) based on contrast-enhanced CT imaging.

METHOD

In total, 201 pathologically confirmed mediastinal LNs from 129 patients were enrolled and assigned to training and test sets. Radiomics features were extracted from the region of interest (ROI) delineated on venous-phase CT imaging of LN. Feature selection was performed with least absolute shrinkage and selection operator (LASSO) binary logistic regression. Multivariate logistic regression was performed with the backward stepwise elimination. A model was fitted to associate mediastinal LN malignancy with selected features. The performance of the model was assessed and compared to that of five other machine learning algorithms (support vector machine, naive Bayes, random forest, decision tree, K-nearest neighbor) using receiver operating characteristic (ROC) curves. Calibration curves and Hosmer-Lemeshow tests were used to assess the calibration degree. Decision curve analysis (DCA) was used to assess the clinical usefulness of the logistic regression model in both the training and test sets. Stratified analysis was performed for different scanners and slice thicknesses.

RESULT

Among the six machine learning methods, the logistic regression model with the eight strongest features showed a significant association with mediastinal LN status and the satisfactory diagnostic performance for distinguishing malignant LNs from benign LNs. The accuracy, sensitivity, specificity and area under the ROC curve (AUC) were 0.850/0.803, 0.821/0.806, 0.893/0.800, and 0.922/0.850 in the training/test sets, respectively. The Hosmer-Lemeshow test showed that the P value was > 0.05, indicating good calibration, and the calibration curves showed good agreement between the classifications and actual observations. DCA showed that the model would obtain more benefit when the threshold probability was between 30% and 90% in the test set. Stratified analysis showed that the performance was not affected by different scanners or slice thicknesses. There was no significant difference (DeLong test, P > 0.05) between any two subgroups, which showed the generalization of the radiomics score across different factors.

CONCLUSION

The model we built could help assist the preoperative estimation of mediastinal LN malignancy based on contrast-enhanced CT imaging, with stability for different scanners and slice thicknesses.

Spectral CT and its specific values in the staging of patients with non-small cell lung cancer: technical possibilities and clinical impact

AIM

To investigate how spectral computed tomography (SCT) values impact the staging of non-small cell lung cancer (NSCLC) patients.

MATERIALS AND METHODS

One hundred and thirteen patients with confirmed NSCLC were included in a prospective cohort study. All patients underwent single-phase contrast-enhanced SCT (using the fast tube voltage switching technique, 80-140 kV). SCT values (iodine content [IC], spectral slope pitch, and radiodensity increase) of malignant tissue (primary and metastases) and lymph nodes (LNs) were measured. Adrenal masses were evaluated in a virtual non-contrast series (VNS). If pulmonary embolism was present, pulmonary perfusion was analysed as an additional finding.

RESULTS

Fifty-two untreated primary NSCLC lesions were evaluable. Lung adenocarcinoma had significantly higher normalised IC (NIC: 19.37) than squamous cell carcinoma (NIC: 12.03; p=0.035). Pulmonary metastases were not significantly different from benign lung nodules. A total of 126 LNs were analysed and histologically proven metastatic LNs (2.08 mg/ml) had significantly lower IC than benign LNs (2.58 mg/ml; p=0.023). Among 34 adrenal masses, VNS identified adenomas with high sensitivity (91%) and specificity (100%). In two patients, a perfusion defect due to pulmonary embolism was detected in the iodine images.

CONCLUSION

SCT may contribute to the differentiation of histological NSCLC subtypes and improve the identification of LN metastases. VNS differentiates adrenal adenoma from metastasis. In case of pulmonary embolism, iodine imaging can visualise associated pulmonary perfusion defects.

Intravoxel incoherent motion diffusion-weighted imaging of resectable oesophageal squamous cell carcinoma: association with tumour stage

OBJECTIVE

To determine whether intravoxel incoherent motion (IVIM) diffusion-weighted imaging (DWI) derived parameters can be associated with tumour stage of oesophageal squamous cell carcinoma (SCC).

METHODS

60 patients with resectable oesophageal SCC and 20 healthy individuals underwent oesophageal DWI-using multi b-values with a 3.0 T MR system. Pure diffusion coefficient (D), perfusion-related incoherent microcirculation (D*), microvascular volume fraction (f) and apparent diffusion coefficient (ADC) were measured on DWI. Statistical analyses were performed to determine associations of DWI-derived parameters with T-stage.

RESULTS

ADC (r = -0.842), D (r = -0.729), D* (r = -0.301) and f (r = -0.817) were negatively correlated with T-stage of oesophageal SCC (all p < 0.01), and the multinominal regression analyses revealed that IVIM-derived parameters including D (p = 0.038; odds ratio <1) and f (p < 0.001; odds ratio <1) were associated with T-stage. The Mann-Whitney U tests with Bonferroni correction showed that D, f and ADC could discriminate oesophageal SCC, especially T₁-staged tumour, from normal oesophagus (all p < 0.05) while D* could not (p > 0.05). By receiver operating characteristic analyses, f could be the best indicator for detecting oesophageal SCC with an area under receiver operating characteristic (AUC) of 0.964, especially T₁-staged cancer with an AUC of 0.984, and for discriminating T₁-stages between T_0-1 and T_2-3 with an AUC of 0.957, and between T_0-2 and T₃ with an AUC of 0.945 in comparison with any other DWI-derived parameter.

CONCLUSIONS

IVIM derived parameters can be associated with T-stage of oesophageal SCC. Advances in knowledge (1) IVIM-derived parameters are negatively correlated with stage of oesophageal SCC. (2) Among IVIM-derived parameters, microvascular volume fraction helps detect and stage oesophageal SCC.

Imaging of Tumor Angiogenesis for Radiologists--Part 2: Clinical Utility

Angiogenesis is a key cancer hallmark involved in tumor growth and metastasis development. Angiogenesis and tumor microenvironment significantly influence the response of tumors to therapies. Imaging techniques have changed our understanding of the process of angiogenesis, the resulting vascular performance, and the tumor microenvironment. This article reviews the status and potential clinical value of the imaging modalities used to assess the status of tumor vasculature in vivo, before, during, and after treatment.

Quantification of heterogeneity as a biomarker in tumor imaging: a systematic review

BACKGROUND

Many techniques are proposed for the quantification of tumor heterogeneity as an imaging biomarker for differentiation between tumor types, tumor grading, response monitoring and outcome prediction. However, in clinical practice these methods are barely used. This study evaluates the reported performance of the described methods and identifies barriers to their implementation in clinical practice.

METHODOLOGY

The Ovid, Embase, and Cochrane Central databases were searched up to 20 September 2013. Heterogeneity analysis methods were classified into four categories, i.e., non-spatial methods (NSM), spatial grey level methods (SGLM), fractal analysis (FA) methods, and filters and transforms (F&T). The performance of the different methods was compared.

PRINCIPAL FINDINGS

Of the 7351 potentially relevant publications, 209 were included. Of these studies, 58% reported the use of NSM, 49% SGLM, 10% FA, and 28% F&T. Differentiation between tumor types, tumor grading and/or outcome prediction was the goal in 87% of the studies. Overall, the reported area under the curve (AUC) ranged from 0.5 to 1 (median 0.87). No relation was found between the performance and the quantification methods used, or between the performance and the imaging modality. A negative correlation was found between the tumor-feature ratio and the AUC, which is presumably caused by overfitting in small datasets. Cross-validation was reported in 63% of the classification studies. Retrospective analyses were conducted in 57% of the studies without a clear description.

CONCLUSIONS

In a research setting, heterogeneity quantification methods can differentiate between tumor types, grade tumors, and predict outcome and monitor treatment effects. To translate these methods to clinical practice, more prospective studies are required that use external datasets for validation: these datasets should be made available to the community to facilitate the development of new and improved methods.

Quantitative CT texture and shape analysis: can it differentiate benign and malignant mediastinal lymph nodes in patients with primary lung cancer?

OBJECTIVE

To assess the accuracy of CT texture and shape analysis in the differentiation of benign and malignant mediastinal nodes in lung cancer.

METHODS

Forty-three patients with biopsy-proven primary lung malignancy with pathological mediastinal nodal staging and unenhanced CT of the thorax were studied retrospectively. Grey-level co-occurrence and run-length matrix textural features, as well as morphological features, were extracted from 72 nodes. Differences between benign and malignant features were assessed using Mann-Whitney U tests. Receiver operating characteristic (ROC) curves for each were constructed and the area under the curve (AUC) calculated with histopathology diagnosis as outcome. Combinations of features were also entered as predictors in logistic regression models and optimal threshold criteria were used to estimate sensitivity and specificity.

RESULTS

Using optimum-threshold criteria, the combined textural and shape features identified malignant mediastinal nodes with 81% sensitivity and 80% specificity (AUC = 0.87, P < 0.0001). Using this combination, 84% malignant and 71% benign nodes were correctly classified.

CONCLUSIONS

Quantitative CT texture and shape analysis has the potential to accurately differentiate malignant and benign mediastinal nodes in lung cancer.

KEY POINTS

• Mediastinal nodal staging is crucial in the management of lung cancer • Mediastinal nodal metastasis affects prognosis and suitability for surgical treatment • Computed tomography (CT) is limited for mediastinal nodal staging • Texture analysis measures tissue heterogeneity not perceptible to human vision • CT texture analysis may accurately differentiate malignant and benign mediastinal nodes.