Increased Dose to Organs in Urinary Tract Associates With Measures of Genitourinary Toxicity in Pooled Voxel-Based Analysis of 3 Randomized Phase III Trials

Abstract

Purpose: Dose information from organ sub-regions has been shown to be more predictive of genitourinary toxicity than whole organ dose volume histogram information. This study aimed to identify anatomically-localized regions where 3D dose is associated with genitourinary toxicities in healthy tissues throughout the pelvic anatomy. Methods and Materials: Dose distributions for up to 656 patients of the Trans-Tasman Radiation Oncology Group 03.04 RADAR trial were deformably registered onto a single exemplar CT dataset. Voxel- based multiple comparison permutation dose difference testing, Cox regression modeling and LASSO feature selection were used to identify regions where 3D dose-increase was associated with late grade ≥ 2 genitourinary dysuria, incontinence and frequency, and late grade ≥ 1 haematuria. This was externally validated by registering dose distributions from the RT01 (up to n = 388) and CHHiP (up to n = 247) trials onto the same exemplar and repeating the voxel-based tests on each of these data sets. All three datasets were then combined, and the tests repeated. Results: Voxel-based Cox regression and multiple comparison permutation dose difference testing revealed regions where increased dose was correlated with genitourinary toxicity. Increased dose in the vicinity of the membranous and spongy urethra was associated with dysuria for all datasets. Haematuria was similarly correlated with increased dose at the membranous and spongy urethra, for the RADAR, CHHiP, and combined datasets. Some evidence was found for the association between incontinence and increased dose at the internal and external urethral sphincter for RADAR and the internal sphincter alone for the combined dataset. Incontinence was also strongly correlated with dose from posterior oblique beams. Patients with fields extending inferiorly and posteriorly to the CTV, adjacent to the membranous and spongy urethra, were found to experience increased frequency. Conclusions: Anatomically-localized dose-toxicity relationships were determined for late genitourinary symptoms in the urethra and urinary sphincters. Low-intermediate doses to the extraprostatic urethra were associated with risk of late dysuria and haematuria, while dose to the urinary sphincters was associated with incontinence.

Keywords: dose-toxicity relationships; external beam radiotherapy; prostate cancer; urinary toxicity; voxel-based analysis.

Figure 1

Visual representation of the (A) Voxel-Based Dose Difference Permutation Test, (B) Uni-Voxel Cox Regression test and (C) Multi-Voxel Cox Regression Test with LASSO Feature Selection.

Figure 2

(A) slices of the T1 registration template CT image with the penile shaft (containing the spongy urethra) visible despite not being delineated, outlined in yellow dots. Mean dose difference maps between patients with and without (B) grade ≥ 2 dysuria and (C) grade ≥ 1 haematuria, on approximately the same urethral slice as the image in (A) for comparison. It is evident that maximum dose difference is most likely occurring at the urethra.

Figure 3

Results for dysuria. Corresponding axial, coronal and sagittal slices (top to bottom) of (A) mean dose difference maps, (B) uni-voxel Cox regression HR and p-value maps and (C) multi-voxel Cox regression LASSO HR maps (with uni-voxel p-values for comparison), for respective data sets. “No Voxels Selected” implies the LASSO selected no voxels of significant correlation with the endpoint within the patient region. The slices chosen for display are those which coincide with the most dominant emergent dose-endpoint patterns, indicated in corresponding planes with dashed lines. Tones of red correspond to regions where increased dose is associated with incidence of dysuria (HR > 1), while tones of blues correspond to regions where reduced dose is associated with incidence of dysuria (HR < 1). The CTV is delineated in orange while the bladder and rectum are delineated in yellow. Anatomical directions left (L), right (R), superior (S), inferior (I), anterior (A), and posterior (P) are also indicated.

Figure 4

Results for haematuria. Corresponding axial, coronal and sagittal slices (top to bottom) of (A) mean dose difference maps, (B) uni-voxel Cox regression HR and p-value maps and (C) multi-voxel Cox regression LASSO HR maps (with uni-voxel p-values for comparison), for respective data sets. “No Voxels Selected” implies the LASSO selected no voxels of significant correlation with the endpoint within the patient region. The slices chosen for display are those which coincide with the most dominant emergent dose-endpoint patterns, indicated in corresponding planes with dashed lines. Tones of red correspond to regions where increased dose is associated with incidence of haematuria (HR > 1), while tones of blues correspond to regions where reduced dose is associated with incidence of haematuria (HR < 1). The CTV is delineated in orange while the bladder and rectum are delineated in yellow. Anatomical directions left (L), right (R), superior (S), inferior (I), anterior (A), and posterior (P) are also indicated.

Figure 5

Results for incontinence. Corresponding axial, coronal and sagittal slices (top to bottom) of (A) mean dose difference maps, (B) uni-voxel Cox regression HR and p-value maps and (C) multi-voxel Cox regression LASSO HR maps (with uni-voxel p-values for comparison), for respective data sets. “No Voxels Selected” implies the LASSO selected no voxels of significant correlation with the endpoint within the patient region. The slices chosen for display are those which coincide with the most dominant emergent dose-endpoint patterns, indicated in corresponding planes with dashed lines. Tones of red correspond to regions where increased dose is associated with incidence of incontinence (HR > 1), while tones of blues correspond to regions where reduced dose is associated with incidence of incontinence (HR < 1). The CTV is delineated in orange while the bladder and rectum are delineated in yellow. Anatomical directions left (L), right (R), superior (S), inferior (I), anterior (A), and posterior (P) are also indicated.

Figure 6

Results for frequency. Corresponding axial, coronal and sagittal slices (top to bottom) of (A) mean dose difference maps and regions of significant dose difference determined by permutation test, (B) uni-voxel Cox regression HR and p-value maps and (C) multi-voxel Cox regression LASSO HR maps (with uni-voxel or permutation test p-values for comparison), for respective data sets. The slices chosen for display are those which coincide with the most dominant emergent dose-endpoint patterns, indicated in corresponding planes with dashed lines. Tones of red correspond to regions where increased dose is associated with incidence of frequency (HR > 1), while tones of blues correspond to regions where reduced dose is associated with incidence of frequency (HR < 1). The CTV is delineated in orange while the bladder and rectum are delineated in yellow. Anatomical directions left (L), right (R), superior (S), inferior (I), anterior (A), and posterior (P) are also indicated.

Figure 7

(A) Mean dose distributions for patients with the given toxicity in the combined cohort, (B) mean dose distributions for patients without the given toxicity in the combined cohort, and (C) standard deviation dose distributions maps for patients in the combined cohort dataset for the given toxicity. Each map displays the dose value at a point in the vicinity of the distal spongy urethra (above) and membranous urethra (below). The top row represents the grade ≥2 dysuria dataset and the bottom row the grade ≥1 haematuria dataset.