Target Re-Delineation in Daily Online Adaptive Radiotherapy of Bladder Cancer: AI vs. Adapters

PURPOSE/OBJECTIVE(S)

The purpose was to assess the quality of artificial intelligence (AI) generated targets in cone-beam CT (CBCT) guided online adaptive radiotherapy (oART) of bladder cancer and compare it to corresponding contours edited by adapters (radiotherapy technicians performing oART routinely). Furthermore, to assess the inter-observer delineation variation in daily target re-delineation in oART of bladder cancer.

MATERIALS/METHODS

Ten consecutive patients treated with oART for muscle-invasive bladder cancer from Feb 2020 to Feb 2021 were retrospectively included. One CBCT randomly selected from each of the 10 clinical treatment courses was exported to an emulator, where delineations and oART simulations were carried out. The bladder was automatically segmented (clinical target volume (CTV)) using AI. Seven adapters independently reviewed and, if necessary, manually edited the AI-generated structure. A ground truth structure was first delineated blindly by a senior oncologist, then reviewed by an oART experienced medical physicist, and finally edited to a consensus structure. Planning CT and MR images with reference delineations were available during all simulations and delineations. The AI-generated and adapter-edited CTVs were compared to ground truth using dice similarity coefficient (DSC) and volume difference. The inter-observer variation in adapter-edited CTVs was assessed using coefficient of variation (CV) and the generalized conformity index (CIgen). Cigen was calculated as the ratio of the sum of all overlapping volumes between pairs of observers and the sum of all overlapping and non-overlapping volumes between the same pairs.

RESULTS

Nine CTVs (7 adapter-edited, 1 AI-generated, 1 ground truth) were generated per patient. Patient cases included three male and seven females; three had catheter. The ground truth volume ranged from 51.5 to 221.6 cc. The median volume difference compared to ground truth was -4.5 (range, -17.8 - 42.4) cc and -15.5 (range, -54.2 - 4.3) cc for adapter-edited and AI-generated structures, respectively. Corresponding DSC values were 0.87 (range, 0.71 - 0.95) and 0.84 (range, 0.64 - 0.95). The AI-generated CTV was smaller than ground truth for all patients except one and smaller than all adapter-edited CTVs. The largest differences among adapter-edited CTVs were observed in cranial, caudal and posterior directions. The median CV was 0.08 (range, 0.05-0.11) and Cigen was 0.78 (range, 0.71-0.88).

CONCLUSION

Target re-delineations in daily CBCT-based oART of bladder cancer demonstrated small inter-observer variation. Manual adjustment of AI-generated structures resulted in improved accuracy in target delineation compared to ground truth. Efforts to reduce the inter-observer variation, e.g., physician support during the initial fractions and review by a second adapter, have been implemented clinically.

Accumulated dose implications from systematic dose-rate transients in gated treatments with Viewray MRIdian accelerators

The combination of magnetic resonance (MR) imaging and linear accelerators (linacs) into MR-Linacs enables continuous MR imaging and advanced gated treatments of patients. Previously, a dose-rate transient (∼8% reduced dose rate during the initial 0.5 s of each beam) was identified for a Viewray MRIdian MR-Linac (Klavsenet al2022Radiation Measurement106759). Here, the dose-rate transient is studied in more detail at four linacs of the same type at different hospitals. The implications of dose-rate transients were examined for gated treatments. The dose-rate transients were investigated using dose-per pulse measurements with organic plastic scintillators in three experiments: (i) A gated treatment with the scintillator placed in a moving target in a dynamic phantom, (ii) a gated treatment with the same dynamic conditions but with the scintillator placed in a stationary target, and (iii) measurements in a water-equivalent material to examine beam quality deviations at a dose-per-pulse basis. Gated treatments (i) compared with non-gated treatments with a static target in the same setup showed a broadening of accumulated dose profiles due to motion (dose smearing). The linac with the largest dose-rate transient had a reduced accumulated dose of up to (3.1 ± 0.65) % in the center of the PTV due to the combined dose smearing and dose-rate transient effect. Dose-rate transients were found to vary between different machines. Two MR-Linacs showed initial dose-rate transients that could not be identified from conventional linearity tests. The source of the transients includes an initial change in photon fluence rate and an initial change in x-ray beam quality. For gated treatments, this caused a reduction of more than 1% dose delivered at the central part of the beam for the studied, cyclic-motion treatment plan. Quality assurance of this effect should be considered when gated treatment with the Viewray MRIdian is implemented clinically.

Interfractional dose accumulation for MR-guided liver SBRT: Variation among algorithms is highly patient- and fraction-dependent

BACKGROUND AND PURPOSE

Daily plan adaptations could take the dose delivered in previous fractions into account. Due to high dose delivered per fraction, low number of fractions, steep dose gradients, and large interfractional organ deformations, this might be particularly important for liver SBRT. This study investigates inter-algorithm variation of interfractional dose accumulation for MR-guided liver SBRT.

MATERIALS AND METHODS

We assessed 27 consecutive MR-guided liver SBRT treatments of 67.5 Gy in three (n = 15) or 50 Gy in five fractions (n = 12), both prescribed to the GTV. We calculated fraction doses on daily patient anatomy, warped these doses to the simulation MRI using seven different algorithms, and accumulated the warped doses. Thus, we obtained differences in planned doses and warped or accumulated doses for each algorithm. This enabled us to calculate the inter-algorithm variations in warped doses per fraction and in accumulated doses per treatment course.

RESULTS

The four intensity-based algorithms were more consistent with planned PTV dose than affine or contour-based algorithms. The mean (range) variation of the dose difference for PTV D_95% due to dose warping by these intensity-based algorithms was 10.4 percentage points (0.3 to 43.7) between fractions and 8.6 (0.3 to 24.9) between accumulated treatment doses. As seen by these ranges, the variation was very dependent on the patient and the fraction being analyzed. Nevertheless, no correlations between patient or plan characteristics on the one hand and inter-algorithm dose warping variation on the other hand was found.

CONCLUSION

Inter-algorithm dose accumulation variation is highly patient- and fraction-dependent for MR-guided liver SBRT. We advise against trusting a single algorithm for dose accumulation in liver SBRT.