CNN-based multi-modal radiomics analysis of pseudo-CT utilization in MRI-only brain stereotactic radiotherapy: a feasibility study

Abstract

Background: Pseudo-computed tomography (pCT) quality is a crucial issue in magnetic resonance image (MRI)-only brain stereotactic radiotherapy (SRT), so this study systematically evaluated it from the multi-modal radiomics perspective.

Methods: 34 cases (< 30 cm³) were retrospectively included (2021.9-2022.10). For each case, both CT and MRI scans were performed at simulation, and pCT was generated by a convolutional neural network (CNN) from planning MRI. Conformal arc or volumetric modulated arc technique was used to optimize the dose distribution. The SRT dose was compared between pCT and planning CT with dose volume histogram (DVH) metrics and gamma index. Wilcoxon test and Spearman analysis were used to identify key factors associated with dose deviations. Additionally, original image features were extracted for radiomic analysis. Tumor control probability (TCP) and normal tissue complication probability (NTCP) were employed for efficacy evaluation.

Results: There was no significant difference between pCT and planning CT except for radiomics. The mean value of Hounsfield unit of the planning CT was slightly higher than that of pCT. The Gadolinium-based agents in planning MRI could increase DVH metrics deviation slightly. The median local gamma passing rates (1%/1 mm) between planning CTs and pCTs (non-contrast) was 92.6% (range 63.5-99.6%). Also, differences were observed in more than 85% of original radiomic features. The mean absolute deviation in TCP was 0.03%, and the NTCP difference was below 0.02%, except for the normal brain, which had a 0.16% difference. In addition, the number of SRT fractions and lesions, and lesion morphology could influence dose deviation.

Conclusions: This is the first multi-modal radiomics analysis of CNN-based pCT from planning MRI for SRT of small brain lesions, covering dosiomics and radiomics. The findings suggest the potential of pCT in SRT plan design and efficacy prediction, but caution needs to be taken for radiomic analysis.

Keywords: MRI-only radiotherapy; Multi-modal radiomics analysis; Pseudo-CT.

Fig. 1

Overall workflow of multi-omics feasibility analysis performed in this study. SRT = stereotactic radiotherapy, T1W = T1-Weighted, T1W-CE = contrast-enhancing T1W, HU = Hounsfield unit, PTV = planning target volume, OARs = organs at risk, DVH = dose-volume histogram, TCP = tumor control probability, NTCP = normal tissue complication probability

Fig. 2

The box distribution of 3D gamma passing rates. (A) single lesion; (B) multiple lesions; (C) 1 fraction SRT; (D) 3 fractions SRT; (E) 5 fractions SRT. “-G” = global gamma, “-L” = Local gamma

Fig. 3

Correlation analysis map: (A) inter-group analysis of factors associated with dose deviation of PTV; (B) intra-group between factors related to dose deviation and radiomic features of PTV. The correlation coefficient matrix values range from − 1 to 1, representing a perfectly negative and positive correlation, respectively. The values close to 0, the smaller the correlation. The color, value, and circle size in the figure indicate the value of the correlation coefficient. “*” is used as the Wilcoxon-test significance label, < 0.05 is indicated by “*”, < 0.01 is indicated by “**”, and < 0.001 is indicated by “***”. And “ × ” indicates that the result did not pass the significance test. “-G” = global gamma, “-L” = Local gamma, der-V(PTV) = PTV volume deviation between pCT and planned CT, Lesions = number of lesions, Fractions = number of fractions, Type = planning MRI sequence (T1W or T1W-CE)