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.

Objective: We quantify liver perfusion using quantitative transport mapping (QTM) method that is free of arterial input function (AIF). QTM method is validated in a vasculature computational fluid dynamics (CFD) simulation and is applied for processing dynamic contrast enhanced (DCE) MRI images in differentiating liver with nonalcoholic fatty liver disease (NAFLD) from healthy controls using pathology reference in a preclinical rabbit model. Methods: QTM method was validated on a liver perfusion simulation based on fluid dynamics using a rat liver vasculature model and the mass transport equation. In the NAFLD grading task, DCE MRI images of 7 adult rabbits with methionine choline-deficient diet-induced nonalcoholic steatohepatitis (NASH), 8 adult rabbits with simple steatosis (SS) were acquired and processed using QTM method and dual-input two compartment Kety's method respectively. Statistical analysis was performed on six perfusion parameters: velocity magnitude $| {\boldsymbol{u}} |$ derived from QTM, liver arterial blood flow ${\boldsymbol{LB}}{{\boldsymbol{F}}}_{\boldsymbol{a}}$ , liver venous blood flow ${\boldsymbol{LB}}{{\boldsymbol{F}}}_{\boldsymbol{v}}$ , permeability ${{\boldsymbol{K}}}^{{\boldsymbol{trans}}}$ , blood volume ${{\boldsymbol{V}}}_{\boldsymbol{p}}$ and extravascular space volume ${{\boldsymbol{V}}}_{\boldsymbol{e}}$ averaged in liver ROI. Results: In the simulation, QTM method successfully reconstructed blood flow, reduced error by 48% compared to Kety's method. In the preclinical study, only QTM |u| showed significant difference between high grade NAFLD group and low grade NAFLD group. Conclusion: QTM postprocesses DCE-MRI automatically through deconvolution in space and time to solve the inverse problem of the transport equation. Comparing with Kety's method, QTM method showed higher accuracy and better differentiation in NAFLD classification task. Significance: We propose to apply QTM method in liver DCE MRI perfusion quantification.

Zhang Q, et al. Korean J Radiol. 2023 Mar;24:e22. https://doi.org/10.3348/kjr.2022.0652