Search

Background: Direction Modulated Brachytherapy (DMBT) enables conformal dose distributions. However, clinicians may face challenges in creating viable treatment plans within a fast‐paced clinical setting, especially for a novel technology like DMBT, where cumulative clinical experience is limited. Deep learning‐based dose prediction methods have emerged as effective tools for enhancing efficiency. Purpose: To develop a voxel‐wise dose prediction model using an attention‐gating mechanism and a 3D UNET for cervical cancer high‐dose‐rate (HDR) brachytherapy treatment planning with DMBT six‐groove tandems with ovoids or ring applicators. Methods: A multi‐institutional cohort of 122 retrospective clinical HDR brachytherapy plans treated to a prescription dose in the range of 4.8–7.0 Gy/fraction was used. A DMBT tandem model was constructed and incorporated onto a research version of BrachyVision Treatment Planning System (BV‐TPS) as a 3D solid model applicator and retrospectively re‐planned all cases by seasoned experts. Those plans were randomly divided into 64:16:20 as training, validating, and testing cohorts, respectively. Data augmentation was applied to the training and validation sets to increase the size by a factor of 4. An attention‐gated 3D UNET architecture model was developed to predict full 3D dose distributions based on high‐risk clinical target volume (CTVHR) and organs at risk (OARs) contour information. The model was trained using the mean absolute error loss function, Adam optimization algorithm, a learning rate of 0.001, 250 epochs, and a batch size of eight. In addition, a baseline UNET model was trained similarly for comparison. The model performance was evaluated on the testing dataset by analyzing the outcomes in terms of mean dose values and derived dose‐volume‐histogram indices from 3D dose distributions and comparing the generated dose distributions against the ground‐truth dose distributions using dose statistics and clinically meaningful dosimetric indices. Results: The proposed attention‐gated 3D UNET model showed competitive accuracy in predicting 3D dose distributions that closely resemble the ground‐truth dose distributions. The average values of the mean absolute errors were 1.82 ± 29.09 Gy (vs. 6.41 ± 20.16 Gy for a baseline UNET) in CTVHR, 0.89 ± 1.25 Gy (vs. 0.94 ± 3.96 Gy for a baseline UNET) in the bladder, 0.33 ± 0.67 Gy (vs. 0.53 ± 1.66 Gy for a baseline UNET) in the rectum, and 0.55 ± 1.57 Gy (vs. 0.76 ± 2.89 Gy for a baseline UNET) in the sigmoid. The results showed that the mean absolute error (MAE) for the bladder, rectum, and sigmoid were 0.22 ± 1.22 Gy (3.62%) (p = 0.015), 0.21 ± 1.06 Gy (2.20%) (p = 0.172), and ‐0.03 ± 0.54 Gy (1.13%) (p = 0.774), respectively. The MAE for D90, V100%, and V150% of the CTVHR were 0.46 ± 2.44 Gy (8.14%) (p = 0.018), 0.57 ± 11.25% (5.23%) (p = 0.283), and ‐0.43 ± 19.36% (4.62%) (p = 0.190), respectively. The proposed model needs less than 5 s to predict a full 3D dose distribution of 64 × 64 × 64 voxels for any new patient plan, thus making it sufficient for near real‐time applications and aiding with decision‐making in the clinic. Conclusions: Attention gated 3D‐UNET model demonstrated a capability in predicting voxel‐wise dose prediction, in comparison to 3D UNET, for DMBT intracavitary brachytherapy planning. The proposed model could be used to obtain dose distributions for near real‐time decision‐making before DMBT planning and quality assurance. This will guide future automated planning, making the workflow more efficient and clinically viable. [ABSTRACT FROM AUTHOR]

Abstract Background Biological models are used to relate the outcome of radiation therapy to dose distribution. As use of biological models in treatment planning expands, uncertainties associated with the use of specific models for predicting outcomes should be understood and quantified. In particular, the question to what extent model predictions are data-driven or dependent on the choice of the model has to be explored. Methods Four dose-response models--logistic, log-logistic, Poisson-based and probit--were tested for their ability and consistency in describing dose-response data for radiation-induced optic neuropathy (RION) and retinopathy (RIRP). Dose to the optic nerves was specified as the minimum dose, Dmin , received by any segment of the organ to which the damage was diagnosed by ophthalmologic evaluation. For retinopathy, the dose to the retina was specified as the highest isodose covering at least 1/3 of the retinal surface (D33% ) that geometrically covered the observed retinal damage. Data on both complications were modeled separately for patients treated once daily and twice daily. Model parameters D50 and γ and corresponding confidence intervals were obtained using maximum-likelihood method. Results Model parameters were reasonably consistent for RION data for patients treated once daily, D50 ranging from 94.2 to 104.7 Gy and γ from 0.88 to 1.41. Similar consistency was seen for RIRP data which span a broad range of complication incidence, with D50 from 72.2 to 75.0 Gy and γ from 1.51 to 2.16 for patients treated twice daily; 72.2-74.0 Gy and 0.84-1.20 for patients treated once daily. However, large variations were observed for RION in patients treated twice daily, D50 from 96.3 to 125.2 Gy and γ from 0.80 to 1.56. Complication incidence in this dataset in any dose group did not exceed 20%. Conclusions For the considered data sets, the log-logistic model tends to lead to larger D50 and lower γ compared to other models for all datasets. Statements regarding normal tissue radiosensitivity and steepness of dose-response, based on model parameters, should be made with caution as the latter are not only model-dependent but also sensitive to the range of complication incidence exhibited by clinical data.

The objective was to compare intensity-modulated radiation therapy (IMRT) with 3D conformal proton therapy (3DCPT) in the treatment of cervical cancer. In particular, each technique's ability to spare pelvic bone marrow (PBM) was of primary interest in this study. A total of six cervical cancer patients (3 postoperative and 3 intact) were planned and analyzed. All plans had uniform 1.0 cm CTV-PTV margin and satisfied the 95% PTV with 100% isodose (prescription dose = 45 Gy) coverage. Dose-volume histograms (DVH) were analyzed for comparison. The overall PTV and PBM volumes were 1035.9 ± 192.2 cc and 1151.4 ± 198.3 cc, respectively. In terms of PTV dose conformity index (DCI) and dose homogeneity index (DHI), 3DCPT was slightly superior to IMRT with 1.00 ± 0.001, 1.01 ± 0.02, and 1.10 ± 0.02, 1.13 ± 0.01, respectively. In addition, 3DCPT demonstrated superiority in reducing lower doses (i.e., V30 or less) to PBM, small bowel and bladder. Particularly in PBM, average V10 and V20 reductions of 10.8% and 7.4% (p = 0.001 and 0.04), respectively, were observed. However, in the higher dose range, IMRT provided better sparing (> V30). For example, in small bowel and PBM, average reductions in V45 of 4.9% and 10.0% (p = 0.048 and 0.008), respectively, were observed. Due to its physical characteristics such as low entrance dose, spread-out Bragg peak and finite particle range of protons, 3DCPT illustrated superior target coverage uniformity and sparing of the lower doses in PBM and other organs. Further studies are, however, needed to fully exploit the benefits of protons for general use in cervical cancer.

Purpose: To analytically assess the heterogeneity effect of vaginal cylinders (VC) made of high‐density plastics on dose calculations, considering the prescription point (surface or 5 mm beyond the surface), and benchmark the accuracy of a commercial model‐based dose calculation (MBDC) algorithm using Monte Carlo (MC) simulations. Methods and materials: The GEANT4 MC code was used to simulate a commercial 192Ir HDR source and VC, with diameters ranging from 20 to 35 mm, inside a virtual water phantom. Standard plans were generated from a commercial treatment planning system [TPS—BrachyVision ACUROS (BV)] optimized for a treatment length of 5 cm through two dose calculation approaches: (1) assuming all the environment as water (i.e., Dw,w‐MC & Dw,w‐TG43) and (2) accounting for the heterogeneity of VC applicators (i.e., Dw,w‐App‐MC & Dw,w‐App‐MBDC). The compared isodose lines, and dose & energy difference maps were extracted for analysis. In addition, the dose difference on the peripheral surface, along the applicator and at middle of treatment length, as well as apical tip was evaluated. Results: The Dw,w‐App‐MC results indicated that the VC heterogeneity can cause a dose reduction of (up to) % 6.8 on average (for all sizes) on the peripheral surface, translating to 1 mm shrinkage of the isodose lines compared to Dw,w‐MC. In addition, the results denoted that BV overestimates the dose on the peripheral surface and apical tip of about 3.7% and 17.9%, respectively, (i.e., Dw,w‐App‐MBDC vs Dw,w‐App‐MC) when prescribing to the surface. However, the difference between the two were negligible at the prescription point when prescribing to 5 mm beyond the surface. Conclusion: The VCs' heterogeneity could cause dose reduction when prescribing dose to the surface of the applicator, and hence increases the level of uncertainty. Thus, reviewing the TG43 results, in addition to ACUROS, becomes prudent, when evaluating the surface coverage at the apex. [ABSTRACT FROM AUTHOR]

Abstract Background Biological models are used to relate the outcome of radiation therapy to dose distribution. As use of biological models in treatment planning expands, uncertainties associated with the use of specific models for predicting outcomes should be understood and quantified. In particular, the question to what extent model predictions are data-driven or dependent on the choice of the model has to be explored. Methods Four dose-response models--logistic, log-logistic, Poisson-based and probit--were tested for their ability and consistency in describing dose-response data for radiation-induced optic neuropathy (RION) and retinopathy (RIRP). Dose to the optic nerves was specified as the minimum dose, Dmin, received by any segment of the organ to which the damage was diagnosed by ophthalmologic evaluation. For retinopathy, the dose to the retina was specified as the highest isodose covering at least 1/3 of the retinal surface (D33%) that geometrically covered the observed retinal damage. Data on both complications were modeled separately for patients treated once daily and twice daily. Model parameters D50 and γ and corresponding confidence intervals were obtained using maximum-likelihood method. Results Model parameters were reasonably consistent for RION data for patients treated once daily, D50 ranging from 94.2 to 104.7 Gy and γ from 0.88 to 1.41. Similar consistency was seen for RIRP data which span a broad range of complication incidence, with D50 from 72.2 to 75.0 Gy and γ from 1.51 to 2.16 for patients treated twice daily; 72.2-74.0 Gy and 0.84-1.20 for patients treated once daily. However, large variations were observed for RION in patients treated twice daily, D50 from 96.3 to 125.2 Gy and γ from 0.80 to 1.56. Complication incidence in this dataset in any dose group did not exceed 20%. Conclusions For the considered data sets, the log-logistic model tends to lead to larger D50 and lower γ compared to other models for all datasets. Statements regarding normal tissue radiosensitivity and steepness of dose-response, based on model parameters, should be made with caution as the latter are not only model-dependent but also sensitive to the range of complication incidence exhibited by clinical data.