Improving intracranial aneurysms image quality and diagnostic confidence with deep learning reconstruction in craniocervical CT angiography.

BACKGROUND: The diagnostic impact of deep learning computed tomography (CT) reconstruction on intracranial aneurysm (IA) remains unclear. PURPOSE: To quantify the image quality and diagnostic confidence on IA in craniocervical CT angiography (CTA) reconstructed with DEep Learning Trained Algorithm (DELTA) compared to the routine hybrid iterative reconstruction (HIR). MATERIAL AND METHODS: A total of 60 patients who underwent craniocervical CTA and were diagnosed with IA were retrospectively enrolled. Images were reconstructed with DELTA and HIR, where the image quality was first compared in noise, signal-to-noise ratio (SNR), and contrast-to-noise ratio (CNR). Next, two radiologists independently graded the noise appearance, arterial sharpness, small vessel visibility, conspicuity of calcifications that may present in arteries, and overall image quality, each with a 5-point Likert scale. The diagnostic confidence on IAs of various sizes was also graded. RESULTS: Significantly lower noise and higher SNR and CNR were found on DELTA than on HIR images (all P < 0.05). All five subjective metrics were scored higher by both readers on the DELTA images (all P < 0.05), with good to excellent inter-observer agreement (κ = 0.77-0.93). DELTA images were rated with higher diagnostic confidence on IAs compared to HIR (P < 0.001), particularly for those with size ≤3 mm, which were scored 4.5 ± 0.6 versus 3.4 ± 0.8 and 4.4 ± 0.7 versus 3.5 ± 0.8 by two readers, respectively. CONCLUSION: The DELTA shows potential for improving the image quality and the associated confidence in diagnosing IA that may be worth consideration for routine craniocervical CTA applications.

Use of diffusion-weighted magnetic resonance imaging (DW-MRI) to predict early response to anti-tumor therapy in advanced non-small cell lung cancer (NSCLC): a comparison of intravoxel incoherent motion-derived parameters and apparent diffusion coefficient.

BACKGROUND: The intravoxel incoherent motion (IVIM) method of magnetic resonance imaging (MRI) analysis can provide information regarding many physiological and pathological processes. This study aimed to investigate whether IVIM-derived parameters and the apparent diffusion coefficient (ADC) can act as imaging biomarkers for predicting non-small cell lung cancer (NSCLC) response to anti-tumor therapy and compare their performances. METHODS: This prospective study included 45 patients with NSCLC treated with chemotherapy (29 men and 16 women, mean age 57.9±9.7 years). Diffusion-weighted imaging was performed with 13 b-values before and 2-4 weeks after treatment. The IVIM parameter pseudo-diffusion coefficient (D*), perfusion fraction (f), diffusion coefficient (D), and ADC from a mono-exponential model were obtained. Responses 2 months after chemotherapy were assessed. The diagnostic performance was evaluated, and optimal cut-off values were determined by receiver operating characteristic (ROC) curve analysis, and the differences of progression-free survival (PFS) in groups of responders and non-responders were tested by Cox regression and Kaplan-Meier survival analyses. RESULTS: Of 45 patients, 30 (66.7%) were categorized as responders, and 15 as non-responders. Differences in the diffusion coefficient D and ADC between responders and non-responders were statistically significant (all P<0.05). Conversely, differences in f and D* between responders and non-responders were both not statistically significance (all P>0.05). The ROC analyses showed the change in D value (ΔD) was the best predictor of early response to anti-tumor therapy [area under the ROC curve (AUC), 0.764]. The Cox-regression model showed that all ADC and D parameters were independent predictors of PFS, with a range of reduction in risk from 56.2% to 82.7%, and ΔD criteria responders had the highest reduction (82.7%). CONCLUSIONS: ADC and D derived from IVIM are potentially useful for the prediction of NSCLC treatment response to anti-tumor therapy. Although ΔD is best at predicting response to treatment, ΔADC measurement may simplify manual efforts and reduce the workload.

Pre-Immunotherapy Contrast-Enhanced CT Texture-Based Classification: A Useful Approach to Non-Small Cell Lung Cancer Immunotherapy Efficacy Prediction.

Objective: To investigate the utility of the pre-immunotherapy contrast-enhanced CT-based texture classification in predicting response to non-small cell lung cancer (NSCLC) immunotherapy treatment. Methods: Sixty-three patients with 72 lesions who received immunotherapy were enrolled in this study. We extracted textures including histogram, absolute gradient, run-length matrix, gray-level co-occurrence matrix, autoregressive model, and wavelet transform from pre-immunotherapy contrast-enhanced CT by using Mazda software. Three different methods, namely, Fisher coefficient, mutual information measure (MI), and minimization of classification error probability combined average correlation coefficients (POE + ACC), were performed to select 10 optimal texture feature sets, respectively. The patients were divided into non-progressive disease (non-PD) and progressive disease (PD) groups. t-test or Mann-Whitney U-test was performed to test the differences in each texture feature set between the above two groups. Each texture feature set was analyzed by principal component analysis (PCA), linear discriminant analysis (LDA), and non-linear discriminant analysis (NDA). The area under the curve (AUC) was used to quantify the predictive accuracy of the above three analysis models for each texture feature set, and the sensitivity, specificity, accuracy, positive predictive value (PPV), and negative predictive value (NPV) were also calculated, respectively. Results: Among the three texture feature sets, the texture parameter differences of kurtosis (2.12 ± 3.92 vs. 0.78 ± 1.10, p = 0.047), "S(2,2)SumEntrp" (1.14 ± 0.31 vs. 1.24 ± 0.12, p = 0.036), and "S(1,0)SumEntrp" (1.18 ± 0.27 vs. 1.28 ± 0.11, p = 0.046) between the non-PD and PD group were statistically significant (all p < 0.05). The classification result of texture feature set selected by POE + ACC and analyzed by NDA was identified as the best model (AUC = 0.812, 95% CI: 0.706-0.919) with a sensitivity, specificity, accuracy, PPV, and NPV of 88.2, 76.3, 81.9, 76.9, and 87.9%, respectively. Conclusion: Pre-immunotherapy contrast-enhanced CT-based texture provides a new method for clinical evaluation of the NSCLC immunotherapy efficacy prediction.