Purpose: To develop a machine learning-derived radiomics approach to simultaneously discriminate epidermal growth factor receptor (EGFR), Kirsten rat sarcoma viral oncogene (KRAS), Erb-B2 receptor tyrosine kinase 2 (ERBB2), and tumor protein 53 (TP53) genetic mutations in patients with non-small cell lung cancer (NSCLC). Methods: This study included consecutive patients from April 2018 to June 2020 who had histologically confirmed NSCLC, and underwent pre-surgical contrast-enhanced CT and post-surgical next-generation sequencing (NGS) tests to determine the presence of EGFR, KRAS, ERBB2, and TP53 mutations. A dedicated radiomics analysis package extracted 1672 radiomic features in three dimensions. Discriminative models were established using the least absolute shrinkage and selection operator to determine the presence of EGFR, KRAS, ERBB2, and TP53 mutations, based on radiomic features and relevant clinical factors. Results: In 134 patients (63.6 ± 8.9 years), the 20 most relevant radiomic features (13 for KRAS) to mutations were selected to construct models. The areas under the curve (AUCs) of the combined model (radiomic features and relevant clinical factors) for discriminating EGFR, KRAS, ERBB2, and TP53 mutations were 0.78 (95% CI: 0.70–0.86), 0.81 (0.69–0.93), 0.87 (0.78–0.95), and 0.84 (0.78–0.91), respectively. In particular, the specificity to exclude EGFR mutations was 0.96 (0.87–0.99). The sensitivity to determine KRAS, ERBB2, and TP53 mutations ranged from 0.82 (0.69–90) to 0.92 (0.62–0.99). Conclusions: Machine learning-derived 3D radiomics can simultaneously discriminate the presence of EGFR, KRAS, ERBB2, and TP53 mutations in patients with NSCLC. This noninvasive and low-cost approach may be helpful in screening patients before invasive sampling and NGS testing.

This study validated the use of photon-counting detector CT for accurate, protocol-independent liver fat quantification in metabolic dysfunction–associated steatotic liver disease across various imaging settings.

Objective: The purpose is to establish and validate a machine-learning-derived radiomics approach to determine the existence of atrial fibrillation (AF) by analyzing epicardial adipose tissue (EAT) in CT images. Methods: Patients with AF based on electrocardiographic tracing who underwent contrast-enhanced (n = 200) or non-enhanced (n = 300) chest CT scans were analyzed retrospectively. After EAT segmentation and radiomics feature extraction, the segmented EAT yielded 1691 radiomics features. The most contributive features to AF were selected by the Boruta algorithm and machine-learning-based random forest algorithm, and combined to construct a radiomics signature (EAT-score). Multivariate logistic regression was used to build clinical factor and nested models. Results: In the test cohort of contrast-enhanced scanning (n = 60/200), the AUC of EAT-score for identifying patients with AF was 0.92 (95%CI: 0.84–1.00), higher than 0.71 (0.58–0.85) of the clinical factor model (total cholesterol and body mass index) (DeLong’s p = 0.01), and higher than 0.73 (0.61–0.86) of the EAT volume model (p = 0.01). In the test cohort of non-enhanced scanning (n = 100/300), the AUC of EAT-score was 0.85 (0.77–0.92), higher than that of the CT attenuation model (p < 0.001). The two nested models (EAT-score+volume and EAT-score+volume+clinical factors) for contrast-enhanced scan and one (EAT-score+CT attenuation) for non-enhanced scan showed similar AUCs with that of EAT-score (all p > 0.05). Conclusion: EAT-score generated by machine-learning-based radiomics achieved high performance in identifying patients with AF. Advances in knowledge: A radiomics analysis based on machine learning allows for the identification of AF on the EAT in contrast-enhanced and non-enhanced chest CT.

This study aimed to investigate the potential benefit of ultra-high-resolution (UHR) photon-counting detector CT (PCD-CT) angiography in visualization of abdominal arteries in comparison to standard-reconstruction (SR) images of virtual monoenergetic images (VMI) at low kiloelectron volt (keV). We prospectively included 47 and 47 participants to undergo contrast-enhanced abdominal CT scans within UHR mode on a PCD-CT system using full-dose (FD) and low-dose (LD) protocols, respectively. The data were reconstructed into six series of images: FD_UHR_Br48, FD_UHR_Bv56, FD_UHR_Bv60, FD_SR_Bv40, LD_UHR_Bv48, and LD_SR_Bv40. The UHR reconstructions were performed with three kernels (Bv48, Bv56, and Bv60) within 0.2 mm. The SR were virtual monoenergetic imaging reconstruction with Bv40 kernel at 40-keV within 1 mm. Each series of axial images were reconstructed into coronal and volume-rendered images. The signal-to-noise ratio (SNR) and contrast-to-noise ratio (CNR) of seven arteries were measured. Three radiologists assessed the image quality, and visibility of nine arteries on all the images. SNR and CNR values of SR images were significantly higher than those of UHR images (P < 0.001). The SR images have higher ratings in image noise (P < 0.001), but the FD_UHR_Bv56 and FD_UHR_Bv60 images has higher rating in vessel sharpness (P < 0.001). The overall quality was not significantly different among FD_VMI_40keV, LD_VMI_40keV, FD_UHR_Bv48, and LD_UHR_Bv48 images (P > 0.05) but higher than those of FD_UHR_Bv56 and FD_UHR_Bv60 images (P < 0.001). There is no significant difference of nine abdominal arteries among six series of images of axial, coronal and volume-rendered images (P > 0.05). To conclude, 1-mm SR image of VMI at 40-keV is superior to 0.2-mm UHR regardless of which kernel is used to visualize abdominal arteries, while 0.2-mm UHR image using a relatively smooth kernel may allow similar image quality and artery visibility when thinner slice image is warranted.

Background: Coronary computed tomography (CT) angiography imaging is useful for the preprocedural evaluation of chronic total occlusion (CTO). However, the predictive value of CT radiomics model for successful percutaneous coronary intervention (PCI) has not been studied. We aimed to develop and validate a CT radiomics model for predicting PCI success of CTOs. Methods: In this retrospective study, a radiomics-based model for predicting PCI success was developed on the training and internal validation sets of 202 and 98 patients with CTO, collected from 1 tertiary hospital. The proposed model was validated on an external test set of 75 CTO patients enrolled from another tertiary hospital. CT radiomics features of each CTO lesion were manually labeled and extracted. Other anatomical parameters, including occlusion length, entry morphology, tortuosity, and calcification burden, were also measured. Fifteen radiomics features, 2 quantitative plaque features, and CT-derived Multicenter CTO Registry of Japan score were used to train different models. The predictive values of each model were evaluated for predicting revascularization success. Results: In the external test set, 75 patients (60 men; 65 years [58.5, 71.5]) with 83 CTO lesions were assessed. Occlusion length was shorter (13.00 mm versus 29.30 mm, P =0.007) in PCI success group whereas the presence of tortuous course was more commonly presented in PCI failure group (1.49% versus 25.00%, P =0.004). The radiomics score was significantly smaller in PCI success group (0.10 versus 0.55, P <0.001). The area under the curve of CT radiomics-based model was significantly higher than that of CT-derived Multicenter CTO Registry of Japan score for predicting PCI success (area under the curve=0.920 versus 0.752, P =0.008). The proposed radiomics model accurately identified 89.16% (74/83) CTO lesions with procedure success. Conclusions: CT radiomics-based model outperformed CT-derived Multicenter CTO Registry of Japan score for predicting PCI success. The proposed model is more accurate than the conventional anatomical parameters to identify CTO lesions with PCI success.

Objective: The objective was to evaluate the normal value of left ventricular myocardial strain using the computed tomography feature-tracking technique and to explore the correlation between myocardial strains and cardiac function parameters. Methods: Participants suspected of coronary heart disease were selected from 17 August 2020 to 5 November 2020 to undergo coronary computed tomography angiography using a third-generation dual-source CT scanner. Data were imported into a commercial software (Medis) after multiphase reconstruction. The cardiac function parameters, radial (Err), circumferential (Ecc), and longitudinal strain (Ell) of the left ventricle were recorded. Results: A total of 87 normal subjects were enrolled, including 41 males and 46 females. For healthy subjects, the global radial strain (GRS), circumferential strain (GCS), and longitudinal strain (GLS) of the left ventricle were 74.5 ± 15.2%, −22.7 ± 3.0%, and −26.6 ± 3.2%, respectively. The Err and Ecc absolute values (|Ecc|) were the largest at the apex, and the |Ell| gradually increased from the base to the apex. The Err and |Ecc| were the largest in the lateral and inferior wall, respectively. |Ell| showed a clockwise decrease from the lateral wall in the short axis. Meanwhile, the GRS and |GLS| in females were higher than that in males. Multiple linear regression analysis showed that both SV and LVEF were the independent determinants of GRS, GCS, and GLS. BMI and CO were the independent determined factors of GCS. Conclusions: At a reasonable radiation dose, CT feature-tracking is a feasible and reproducible method to analyze left ventricular myocardial strain. Left ventricular myocardial strain in normal subjects varies in gender, segments, levels, and regions.