Survival rate prediction of nasopharyngeal carcinoma patients based on MRI and gene expression using a deep neural network.

To achieve a better treatment regimen and follow-up assessment design for intensity-modulated radiotherapy (IMRT)-treated nasopharyngeal carcinoma (NPC) patients, an accurate progression-free survival (PFS) time prediction algorithm is needed. We propose developing a PFS prediction model of NPC patients after IMRT treatment using a deep learning method and comparing that with the traditional texture analysis method. One hundred and fifty-one NPC patients were included in this retrospective study. T1-weighted, proton density and dynamic contrast-enhanced magnetic resonance (MR) images were acquired. The expression level of five genes (HIF-1α, EGFR, PTEN, Ki-67, and VEGF) and infection of Epstein-Barr (EB) virus were tested. A residual network was trained to predict PFS from MR images. The output as well as patient characteristics were combined using a linear regression model to provide a final PFS prediction. The prediction accuracy was compared with that of the traditional texture analysis method. A regression model combining the deep learning output with HIF-1α expression and Epstein-Barr infection provides the best PFS prediction accuracy (Spearman correlation R2  = 0.53; Harrell's C-index = 0.82; receiver operative curve [ROC] analysis area under the curve [AUC] = 0.88; log-rank test hazard ratio [HR] = 8.45), higher than a regression model combining texture analysis with HIF-1α expression (Spearman correlation R2  = 0.14; Harrell's C-index =0.68; ROC analysis AUC = 0.76; log-rank test HR = 2.85). The deep learning method does not require a manually drawn tumor region of interest. MR image processing using deep learning combined with patient characteristics can provide accurate PFS prediction for nasopharyngeal carcinoma patients and does not rely on specific kernels or tumor regions of interest, which is needed for the texture analysis method.

Hippocampal subfield morphology in regular hemodialysis patients.

BACKGROUND: Hippocampal alterations have been implicated in the pathophysiology of cognitive impairment in hemodialysis patients. The hippocampus consists of several distinct subfields, and the molecular mechanisms underlying cognition might be associated with specific hippocampal subfield volume changes. However, this has not yet been investigated in hemodialysis patients. This study aimed to explore volumetric abnormalities in hippocampal subfields in regular hemodialysis patients. METHODS: High-resolution T1-weighted structural images were collected in 61 subjects including 36 hemodialysis patients and 25 healthy controls. A state-of-the-art hippocampal segmentation approach was adopted to segment the hippocampal subfields. Group differences in hippocampal subfield volumes were assessed in Python with a statsmodels module using an ordinary least squares regression with age and sex as nuisance effects. RESULTS: Hemodialysis patients had significantly smaller volumes in the bilateral hippocampus (P < .05/2, Bonferroni corrected), cornu ammonis 1 (CA1), CA4, granule cell and molecular layer of the dentate gyrus, hippocampus-amygdala transition area and molecular layer of the hippocampus than healthy controls (P < .05/24, Bonferroni corrected). Hemodialysis patients also had lower volumes in the left hippocampal tail and right fimbria than healthy controls (P < .05/24, Bonferroni corrected). Hippocampal subfield volumes were associated with neuropsychological test scores, the duration of disease and hemoglobin levels. CONCLUSIONS: We found smaller hippocampal subfield volumes in hemodialysis patients, which were associated with impaired cognition, supporting their role in memory disturbance in the hemodialysis population. However, multiple clinical factors may have confounded the results, and therefore, the interpretation of these results needs to be cautious.

Intravoxel incoherent motion radiomics nomogram for predicting tumor treatment responses in nasopharyngeal carcinoma.

BACKGROUND: Intravoxel incoherent motion (IVIM) plays an important role in predicting treatment responses in patient with nasopharyngeal carcinoma (NPC). The goal of this study was to develop and validate a radiomics nomogram based on IVIM parametric maps and clinical data for the prediction of treatment responses in NPC patients. METHODS: Eighty patients with biopsy-proven NPC were enrolled in this study. Sixty-two patients had complete responses and 18 patients had incomplete responses to treatment. Each patient received a multiple b-value diffusion-weighted imaging (DWI) examination before treatment. Radiomics features were extracted from IVIM parametric maps derived from DWI image. Feature selection was performed by the least absolute shrinkage and selection operator method. Radiomics signature was generated by support vector machine based on the selected features. Receiver operating characteristic (ROC) curves and area under the ROC curve (AUC) values were used to evaluate the diagnostic performance of radiomics signature. A radiomics nomogram was established by integrating the radiomics signature and clinical data. RESULTS: The radiomics signature showed good prognostic performance to predict treatment response in both training (AUC = 0.906, P<0.001) and testing (AUC = 0.850, P<0.001) cohorts. The radiomic nomogram established by integrating the radiomic signature with clinical data significantly outperformed clinical data alone (C-index, 0.929 vs 0.724; P<0.0001). CONCLUSIONS: The IVIM-based radiomics nomogram provided high prognostic ability to treatment responses in patients with NPC. The IVIM-based radiomics signature has the potential to be a new biomarker in prediction of the treatment responses and may affect treatment strategies in patients with NPC.

Dynamic contrast-enhanced magnetic resonance imaging-based radiomics for the prediction of progression-free survival in advanced nasopharyngeal carcinoma.

To establish a multidimensional nomogram model for predicting progression-free survival (PFS) and risk stratification in patients with advanced nasopharyngeal carcinoma (NPC). This retrospective cross-sectional study included 156 patients with advanced NPC who underwent dynamic contrast-enhanced magnetic resonance imaging (DCE-MRI). Radiomic features were extracted from the efflux rate constant (Ktrans ) and extracellular extravascular volume (Ve ) mapping derived from DCE-MRI. Least absolute shrinkage and selection operator (LASSO) Cox regression analysis was applied for feature selection. The Radscore was constructed using the selected features with their respective weights in the LASSO Cox regression analysis. A nomogram model combining the Radscore and clinical factors was built using multivariate Cox regression analysis. The C-index was used to assess the discrimination power of the Radscore and nomogram. The Kaplan-Meier method was used for survival analysis. Of the 360 radiomic features, 28 were selected (7, 6, and 15 features extracted from Ktrans , Ve, and Ktrans +Ve images, respectively). The combined Radscore k trans +Ve (C-index, 0.703, 95% confidence interval [CI]: 0.571-0.836) showed higher efficacy in predicting the prognosis of advanced NPC than Radscore k trans (C-index, 0.693; 95% CI, 0.560-0.826) and Radscore Ve (C-index, 0.614; 95% CI, 0.481-0.746) did. Multivariable Cox regression analysis revealed clinical stage, T stage, and treatment with nimotuzumab as risk factors for PFS. The nomogram established by Radscore k trans +Ve and risk factors (C-index, 0.732; 95% CI: 0.599-0.864) was better than Radscore k trans +Ve in predicting PFS in patients with advanced NPC. A lower Radscore k trans +Ve (HR 3.5584, 95% CI 2.1341-5.933), lower clinical stage (hazard ratio [HR] 1.5982, 95% CI 0.5262-4.854), lower T stage (HR 1.4365, 95% CI 0.6745-3.060), and nimotuzumab (NTZ) treatment (HR 0.7879, 95% CI 0.4899-1.267) were associated with longer PFS. Kaplan-Meier analysis showed a lower PFS in the high-risk group than in the low-risk group (p<0.0001). The nomogram based on combined pretreatment DCE-MRI radiomics features, NTZ, and clinicopathological risk factors may be considered as a noninvasive imaging marker for predicting individual PFS in patients with advanced NPC.

Early Stage Markers of Late Delayed Neurocognitive Decline Using Diffusion Kurtosis Imaging of Temporal Lobe in Nasopharyngeal Carcinoma Patients.

Purpose: To determine whether the early assessment of temporal lobe microstructural changes using diffusion kurtosis imaging (DKI) can predict late delayed neurocognitive decline after radiotherapy in nasopharyngeal carcinoma (NPC) patients. Methods and Materials: Fifty-four NPC patients undergoing intensity-modulated radiotherapy (IMRT) participated in a prospective DKI magnetic resonance (MR) imaging study. MR imaging was acquired prior to IMRT (-0), 1 month (-1), and 3 (-3) months after IMRT. Kurtosis (Kmean, Kax, Krad) and Diffusivity (Dmean, Dax, Drad) variables in the temporal lobe gray and white matter were computed. Neurocognitive function tests (MoCA) were administered pre-radiotherapy and at 2 years post-IMRT follow-up. All the patients were divided into neurocognitive function decline (NFD group) and neurocognitive function non-decline groups (NFND group) according to whether the MoCA score declined ≥3 2 years after IMRT. All the DKI metrics were compared between the two groups, and the best imaging marker was chosen for predicting a late delayed neurocognitive decline. Results: Kurtosis (Kmean-1, Kmean-3, Kax-1, Kax-3, Krad-1, and Krad-3) and Diffusivity (Dmean-1 and Dmean-3) of white matter were significantly different between the two groups (p<0.05). Axial Kurtosis (Kax-1, Kax-3) of gray matter was significantly different between the two groups (p<0.05). By receiver operating characteristic (ROC) curves, Kmean-1 of white matter performed best in predicting of MoCA scores delayed decline (p<0.05). The radiation dose was also significantly different between NFD and NFND group (p=0.031). Conclusions: Temporal lobe white matter is more vulnerable to microstructural changes and injury following IMRT in NPC. Metrics derived from DKI should be considered as imaging markers for predicting a late delayed neurocognitive decline. Both temporal lobe white and gray matter show microstructural changes detectable by DKI. The Kmean early after radiotherapy has the best prediction performance.