Differentiating malignant and benign necrotic lung lesions using kVp-switching dual-energy spectral computed tomography

Conversion of single-energy CT to parametric maps of dual-energy CT using convolutional neural network

OBJECTIVES

We propose a deep learning (DL) multitask learning framework using convolutional neural network for a direct conversion of single-energy CT (SECT) to 3 different parametric maps of dual-energy CT (DECT): virtual-monochromatic image (VMI), effective atomic number (EAN), and relative electron density (RED).

METHODS

We propose VMI-Net for conversion of SECT to 70, 120, and 200 keV VMIs. In addition, EAN-Net and RED-Net were also developed to convert SECT to EAN and RED. We trained and validated our model using 67 patients collected between 2019 and 2020. Single-layer CT images with 120 kVp acquired by the DECT (IQon spectral CT; Philips Healthcare, Amsterdam, Netherlands) were used as input, while the VMIs, EAN, and RED acquired by the same device were used as target. The performance of the DL framework was evaluated by absolute difference (AD) and relative difference (RD).

RESULTS

The VMI-Net converted 120 kVp SECT to the VMIs with AD of 9.02 Hounsfield Unit, and RD of 0.41% compared to the ground truth VMIs. The ADs of the converted EAN and RED were 0.29 and 0.96, respectively, while the RDs were 1.99% and 0.50% for the converted EAN and RED, respectively.

CONCLUSIONS

SECT images were directly converted to the 3 parametric maps of DECT (ie, VMIs, EAN, and RED). By using this model, one can generate the parametric information from SECT images without DECT device. Our model can help investigate the parametric information from SECT retrospectively.

ADVANCES IN KNOWLEDGE

DL framework enables converting SECT to various high-quality parametric maps of DECT.

Differentiation of Hamartomas and Malignant Lung Tumors in Single-Phased Dual-Energy Computed Tomography

This study investigated the efficacy of single-phase dual-energy CT (DECT) in differentiating pulmonary hamartomas from malignant lung lesions using virtual non-contrast (VNC), iodine, and fat quantification. Forty-six patients with 47 pulmonary lesions (mean age: 65.2 ± 12.1 years; hamartomas-to-malignant lesions = 22:25; male: 67%) underwent portal venous DECT using histology, PET-CT and follow-up CTs as a reference. Quantitative parameters such as VNC, fat fraction, iodine density and CT mixed values were statistically analyzed. Significant differences were found in fat fractions (hamartomas: 48.9%; malignancies: 22.9%; p ≤ 0.0001) and VNC HU values (hamartomas: -20.5 HU; malignancies: 17.8 HU; p ≤ 0.0001), with hamartomas having higher fat content and lower VNC HU values than malignancies. CT mixed values also differed significantly (p ≤ 0.0001), but iodine density showed no significant differences. ROC analysis favored the fat fraction (AUC = 96.4%; sensitivity: 100%) over the VNC, CT mixed value and iodine density for differentiation. The study concludes that the DECT-based fat fraction is superior to the single-energy CT in differentiating between incidental pulmonary hamartomas and malignant lesions, while post-contrast iodine density is ineffective for differentiation.

A diagnostic biomarker of acid glycoprotein 1 for distinguishing malignant from benign pulmonary lesions

BACKGROUND

The acid glycoprotein 1 (AGP1) is downregulated in lung cancer. However, the performance of AGP1 in distinguishing benign from malignant lung lesions is still unknown.

METHODS

The expression of AGP1 in benign diseases and lung cancer samples was detected by Western blot. The receiver operating characteristic curves, bivariate correlation, and multivariate analysis was analyzed by SPSS software.

RESULTS

AGP1 expression levels were significantly downregulated in lung cancer and correlated with carcinoembryonic antigen (CEA), CA199, and CA724 tumor biomarkers. The diagnostic performance of AGP1 for distinguishing malignant from benign pulmonary lesions was better than the other four clinical biomarkers including CEA, squamous cell carcinoma-associated antigen, neuron-specific enolase, and cytokeratin 19 fragment 21-1, with an area under the curve value of 0.713 at 88.8% sensitivity. Furthermore, the multivariate analysis indicated that the variates of thrombin time and potassium significantly affected the AGP1 levels in lung cancer.

CONCLUSIONS

Our study indicates that AGP1 expression is decreased in lung cancer compared to benign samples, which helps distinguish benign and malignant pulmonary lesions.

Dual-energy CT for the detection of skull base invasion in nasopharyngeal carcinoma: comparison of simulated single-energy CT and MRI

BACKGROUND

Skull base invasion in nasopharyngeal carcinoma (NPC) was shown to be a poor negative prognostic factor, and dual-energy CT (DECT) has heralded a new approach to detect this condition. The study aims to evaluate the value of DECT for detection of skull base invasion in NPC and compare the diagnostic performance of DECT with those of simulated single-energy CT (SECT) and MRI.

METHODS

The imaging findings of 50 NPC patients and 31 participants in control group which underwent DECT examinations were assessed in this retrospective study. The skull base invasions were evaluated using 5-point scale by two blind observers. ROC analysis, Mcnemar test, paired t test, weighted K statistics and intraclass correlation coefficient were performed to evaluate the diagnostic performance of simulated SECT, MRI and DECT.

RESULTS

Quantitative analysis of DECT parameters showed higher normalized iodine concentration and effective atomic number values in sclerosis and lower values in erosion than those in normal bones (both p < 0.05). Compared with simulated SECT and MRI, the diagnostic sensitivity for DECT was significantly improved from 75% (simulated SECT) and 84.26% (MRI) to 90.74% (DECT) (both p < 0.001), specificity from 93.23% and 93.75% to 95.31 (both p < 0.001), accuracy from 86.67% and 90.33% to 93.67%, and AUC from 0.927 and 0.955 to 0.972 (both p < 0.05), respectively.

CONCLUSIONS

DECT demonstrates better diagnostic performance than simulated SECT and MRI for detecting skull base invasions in NPC, even those slight bone invasions in early stage, with higher sensitivity, specificity and accuracy.

Nondiagnostic, radial-probe endobronchial ultrasound-guided biopsy for peripheral lung lesions: The added value of radiomics from ultrasound imaging for predicting malignancy

OBJECTIVES

This study investigated whether radiomic features extracted from radial-probe endobronchial ultrasound (radial EBUS) images can assist in decision-making for subsequent clinical management in cases with indeterminate pathologic results.

METHODS

A total of 494 patients who underwent radial EBUS biopsy for lung nodules between January 2017 and December 2018 were allocated to our training set. For the validation set, 229 patients with radial EBUS biopsy results from January 2019 to April 2020 were used. A multivariate logistic regression analysis was used for feature selection and prediction modeling.

RESULTS

In the training set, 157 (67 benign and 90 malignant) of 212 patients pathologically diagnosed as indeterminate were analyzed. In the validation set, 213 patients were diagnosed as indeterminate, and 158 patients (63 benign and 95 malignant) were included in the analysis. The performance of the radiomics-added model, which considered satellite nodules, linear arc, shape, patency of vessels and bronchi, echogenicity, spiculation, C-reactive protein, and minimum histogram, was 0.929 for the training set and 0.877 for the validation set, whereas the performance of the model without radiomics was 0.910 and 0.891, respectively.

CONCLUSION

Although the next diagnostic step for indeterminate lung biopsy results remains controversial, integrating various factors, including radiomic features from radial EBUS, might facilitate decision-making for subsequent clinical management.

Differential diagnosis of localized pneumonic-type lung adenocarcinoma and pulmonary inflammatory lesion

BACKGROUND

In clinical practice, a number of delayed diagnoses of localized pneumonic-type lung adenocarcinoma (L-PLADC) mimicking pneumonia have been identified due to the lack of knowledge regarding the radiological findings associated with this condition. Here, we defined L-PLADC as a special type of lung adenocarcinoma that presents as a focal consolidation involving < 50% of the area of a lobe and aimed to investigate the differential clinical and imaging features between L-PLADC and localized pulmonary inflammatory lesion (L-PIL).

RESULTS

The data of 120 patients with L-PLADC and 125 patients with L-PIL who underwent contrast-enhanced chest computed tomography (CT) scan were retrospectively analyzed. For clinical characteristics, older age, women, nonsmokers, and no symptom were more common in L-PLADC (all p < 0.001). With regard to CT features, air bronchogram, irregular air bronchogram, ground-glass opacity (GGO) component, and pleural retraction were more frequently observed in L-PLADC, while necrosis, satellite lesions, halo sign, bronchial wall thickening, interlobular septa thickening, pleural attachment, and pleural thickening were more commonly seen in L-PIL (all p < 0.001). Multivariate analysis showed age ≥ 58 years, female sex, GGO component, irregular air bronchogram, pleural retraction, and the absence of necrosis and pleural attachment were the most effective variations associated with L-PLADC with an AUC of 0.979. Furthermore, an external validation cohort containing 62 patients obtained an AUC of 0.929.

CONCLUSIONS

L-PLADC and L-PIL have different clinical and imaging characteristics. An adequate understanding of these differential features can contribute to the early diagnosis of L-PLADC and the subsequent therapeutic strategy.

Deep learning radiomics of dual-energy computed tomography for predicting lymph node metastases of pancreatic ductal adenocarcinoma

PURPOSE

Diagnosis of lymph node metastasis (LNM) is critical for patients with pancreatic ductal adenocarcinoma (PDAC). We aimed to build deep learning radiomics (DLR) models of dual-energy computed tomography (DECT) to classify LNM status of PDAC and to stratify the overall survival before treatment.

METHODS

From August 2016 to October 2020, 148 PDAC patients underwent regional lymph node dissection and scanned preoperatively DECT were enrolled. The virtual monoenergetic image at 40 keV was reconstructed from 100 and 150 keV of DECT. By setting January 1, 2021, as the cut-off date, 113 patients were assigned into the primary set, and 35 were in the test set. DLR models using VMI 40 keV, 100 keV, 150 keV, and 100 + 150 keV images were developed and compared. The best model was integrated with key clinical features selected by multivariate Cox regression analysis to achieve the most accurate prediction.

RESULTS

DLR based on 100 + 150 keV DECT yields the best performance in predicting LNM status with the AUC of 0.87 (95% confidence interval [CI]: 0.85-0.89) in the test cohort. After integrating key clinical features (CT-reported T stage, LN status, glutamyl transpeptadase, and glucose), the AUC was improved to 0.92 (95% CI: 0.91-0.94). Patients at high risk of LNM portended significantly worse overall survival than those at low risk after surgery (P = 0.012).

CONCLUSIONS

The DLR model showed outstanding performance for predicting LNM in PADC and hold promise of improving clinical decision-making.