Effect of synthetic CT on dose-derived toxicity predictors for MR-only prostate radiotherapy

Abstract

Objectives: Toxicity-driven adaptive radiotherapy (RT) is enhanced by the superior soft tissue contrast of magnetic resonance (MR) imaging compared with conventional computed tomography (CT). However, in an MR-only RT pathway synthetic CTs (sCT) are required for dose calculation. This study evaluates 3 sCT approaches for accurate rectal toxicity prediction in prostate RT.

Methods: Thirty-six patients had MR (T2-weighted acquisition optimized for anatomical delineation, and T1-Dixon) with same day standard-of-care planning CT for prostate RT. Multiple sCT were created per patient using bulk density (BD), tissue stratification (TS, from T1-Dixon) and deep-learning (DL) artificial intelligence (AI) (from T2-weighted) approaches for dose distribution calculation and creation of rectal dose volume histograms (DVH) and dose surface maps (DSM) to assess grade-2 (G2) rectal bleeding risk.

Results: Maximum absolute errors using sCT for DVH-based G2 rectal bleeding risk (risk range 1.6% to 6.1%) were 0.6% (BD), 0.3% (TS) and 0.1% (DL). DSM-derived risk prediction errors followed a similar pattern. DL sCT has voxel-wise density generated from T2-weighted MR and improved accuracy for both risk-prediction methods.

Conclusions: DL improves dosimetric and predicted risk calculation accuracy. Both TS and DL methods are clinically suitable for sCT generation in toxicity-guided RT, however, DL offers increased accuracy and offers efficiencies by removing the need for T1-Dixon MR.

Advances in knowledge: This study demonstrates novel insights regarding the effect of sCT on predictive toxicity metrics, demonstrating clear accuracy improvement with increased sCT resolution. Accuracy of toxicity calculation in MR-only RT should be assessed for all treatment sites where dose to critical structures will guide adaptive-RT strategies.

Clinical trial registration number: Patient data were taken from an ethically approved (UK Health Research Authority) clinical trial run at Guy's and St Thomas' NHS Foundation Trust. Study Name: MR-simulation in Radiotherapy for Prostate Cancer. ClinicalTrials.gov Identifier: NCT03238170.

Keywords: artificial intelligence; deep learning; prostate; rectal toxicity; synthetic CT.

Figure 1.

CNN (U-Net) design.

Figure 2.

Axial slice from representative patient showing (A) planning CT, (B) T2tse, (C) sCT_BDw, (D) sCT_TS, and (E) sCT_AI.

Figure 3.

Left: Range of ground truth G2 LRB risk predictions for the 12 test patients, Right: Error in risk prediction due to sCT method. Boxes represent the interquartile range (IQR). Whiskers represent the largest value within 1.5 times the IQR above and below the box. Mean value is shown as a cross. Statistical significance (paired t-test, P < .05) indicated by asterisk, after normal distribution was confirmed by Shapiro-Wilk test.

Figure 4.

DSM methodology and results for representative patient. (A) Surface dose wash displayed on 3D render of rectum [grey (online version only)] adjacent to clinical target volumes [yellow (online version only)] and bladder [blue (online version only)], (B) EQD2-corrected rectal DSM, (C) binary map of EQD2 dose > 51 Gy, (D) binary map of EQD2 dose > 61 Gy with superimposed ellipse [green (online version only)].

Figure 5.

Left: test cohort range of 51 Gy relative area on DSM with 37.4% tolerance indicated as thick horizontal line. Right: absolute errors introduced by sCT. Boxes represent the IQR. Whiskers represent the largest value within 1.5 times the IQR above and below the box. Mean (cross) and median (line) are also shown. Statistical significance (paired t-test, P < .05) indicated by asterisk, after normal distribution was confirmed by Shapiro-Wilk test.

Figure 6.

Left: test cohort range of 61 Gy relative lateral extent on DSM with 59.1% tolerance indicated as thick horizontal line. Right: absolute errors introduced by sCT. Boxes represent the IQR. Whiskers represent the largest value within 1.5 times the IQR above and below the box. Mean (cross) and median (line) are also shown. Statistical significance (paired t-test, P < .05) indicated by asterisk, after normal distribution was confirmed by Shapiro-Wilk test.