Liu, Chenbin

Purpose Automating quality assurance (QA) for contours generated by automatic algorithms is critical in radiotherapy treatment planning. Manual QA is tedious, time-consuming, and prone to subjective experiences. Automatic segmentation reduces physician workload and improves consistency. However, an effective QA process for these automatic contours remains an unmet need in clinical practice. Materials and Methods The patient data used in this study was derived from the AAPM Thoracic Auto-Segmentation Challenge dataset, including left and right lungs, heart, esophagus, and spinal cord. Two groups of organ-at-risk (OAR) were generated. A ResNet-152 network was used as a feature extractor, and a one-class support vector machine (OC-SVM) was employed to classify contours as ‘high’ or ‘low’ quality. To evaluate the generalizability, we generated low-quality contours using translation and resizing techniques and assessed correlations between detection limits and metrics such as volume, Dice similarity coefficient (DSC), 95% Hausdorff distance (HD95), and mean surface distance (MSD). Results The proposed OC-SVM model outperformed binary classifiers n metrics such as balanced accuracy and area under the receiver operating characteristic curve (AUC) . It demonstrated superior performance in detecting various types of contour errors while maintaining high interpretability. Strong correlations were observed between detection limits and contour metrics. Conclusion Our proposed model integrates an attention mechanism with a one-class classification framework to automate QA for OAR delineations. This approach effectively detects diverse types of contour errors with high accuracy, significantly reducing the burden on physicians during radiotherapy planning.

PurposeApproximate dose calculation methods were used in the nominal dose distribution and the perturbed dose distributions due to uncertainties in a commercial treatment planning system (CTPS) for robust optimization in intensity‐modulated proton therapy (IMPT). We aimed to investigate whether the approximations influence plan quality, robustness, and interplay effect of the resulting IMPT plans for the treatment of locally advanced lung cancer patients.Materials and methodsTen consecutively treated locally advanced nonsmall cell lung cancer (NSCLC) patients were selected. Two IMPT plans were created for each patient using our in‐house developed TPS, named “Solo,” and also the CTPS, EclipseTM (Varian Medical Systems, Palo Alto, CA, USA), respectively. The plans were designed to deliver prescription doses to internal target volumes (ITV) drawn by a physician on averaged four‐dimensional computed tomography (4D‐CT). Solo plans were imported back to CTPS, and recalculated in CTPS for fair comparison. Both plans were further verified for each patient by recalculating doses in the inhalation and exhalation phases to ensure that all plans met clinical requirements. Plan robustness was quantified on all phases using dose‐volume‐histograms (DVH) indices in the worst‐case scenario. The interplay effect was evaluated for every plan using an in‐house developed software, which randomized starting phases of each field per fraction and accumulated dose in the exhalation phase based on the patient's breathing motion pattern and the proton spot delivery in a time‐dependent fashion. DVH indices were compared using Wilcoxon rank‐sum test.ResultsCompared to the plans generated using CTPS on the averaged CT, Solo plans had significantly better target dose coverage and homogeneity (normalized by the prescription dose) in the worst‐case scenario [ITV D95%: 98.04% vs 96.28%, Solo vs CTPS, P = 0.020; ITV D5%–D95%: 7.20% vs 9.03%, P = 0.049] while all DVH indices were comparable in the nominal scenario. On the inhalation phase, Solo plans had better target dose coverage and cord Dmax in the nominal scenario [ITV D95%: 99.36% vs 98.45%, Solo vs CTPS, P = 0.014; cord Dmax: 20.07 vs 23.71 Gy(RBE), P = 0.027] with better target coverage and cord Dmax in the worst‐case scenario [ITV D95%: 97.89% vs 96.47%, Solo vs CTPS, P = 0.037; cord Dmax: 24.57 vs 28.14 Gy(RBE), P = 0.037]. On the exhalation phase, similar phenomena were observed in the nominal scenario [ITV D95%: 99.63% vs 98.87%, Solo vs CTPS, P = 0.037; cord Dmax: 19.67 vs 23.66 Gy(RBE), P = 0.039] and in the worst‐case scenario [ITV D95%: 98.20% vs 96.74%, Solo vs CTPS, P = 0.027; cord Dmax: 23.47 vs 27.93 Gy(RBE), P = 0.027]. In terms of interplay effect, plans generated by Solo had significantly better target dose coverage and homogeneity, less hot spots, and lower esophageal Dmean, and cord Dmax [ITV D95%: 101.81% vs 98.68%, Solo vs CTPS, P = 0.002; ITV D5%–D95%: 2.94% vs 7.51%, P = 0.002; cord Dmax: 18.87 vs 22.29 Gy(RBE), P = 0.014].ConclusionsSolo‐generated IMPT plans provide improved cord sparing, better target robustness in all considered phases, and reduced interplay effect compared with CTPS. Consequently, the approximation methods currently used in commercial TPS programs may have space for improvement in generating optimal IMPT plans for patient cases with locally advanced lung cancer.

BackgroundEsophageal carcinoma is the eighth most common cancer in the world. Volumetric‐modulated arc therapy (VMAT) is widely used to treat distal esophageal carcinoma due to high conformality to the target and good sparing of organs at risk (OAR). It is not clear if small‐spot intensity‐modulated proton therapy (IMPT) demonstrates a dosimetric advantage over VMAT. In this study, we compared dosimetric performance of VMAT and small‐spot IMPT for distal esophageal carcinoma in terms of plan quality, plan robustness, and interplay effects.Methods35 distal esophageal carcinoma patients were retrospectively reviewed; 19 patients received small‐spot IMPT and the remaining 16 of them received VMAT. Both plans were generated by delivering prescription doses to clinical target volumes (CTVs) on phase‐averaged 4D‐CT's. The dose‐volume‐histogram (DVH) band method was used to quantify plan robustness. Software was developed to evaluate interplay effects with randomized starting phases for each field per fraction. DVH indices were compared using Wilcoxon rank‐sum test. For fair comparison, all the treatment plans were normalized to have the same CTVhigh D95% in the nominal scenario relative to the prescription dose.ResultsIn the nominal scenario, small‐spot IMPT delivered statistically significantly lower liver Dmean and V30Gy[RBE], lung Dmean, heart Dmean compared with VMAT. CTVhigh dose homogeneity and protection of other OARs were comparable between the two treatments. In terms of plan robustness, the IMPT and VMAT plans were comparable for kidney V18Gy[RBE], liver V30Gy[RBE], stomach V45Gy[RBE], lung Dmean, V5Gy[RBE], and V20Gy[RBE], cord Dmax and , liver Dmean, heart V20Gy[RBE], and V30Gy[RBE], but IMPT was significantly worse for CTVhigh D95%, , and D5%‐D95%, CTVlow D95%, heart Dmean, and V40Gy[RBE], requiring careful and experienced adjustments during the planning process and robustness considerations. The small‐spot IMPT plans still met the standard clinical requirements after interplay effects were considered.ConclusionsSmall‐spot IMPT decreases doses to heart, liver, and total lung compared to VMAT as well as achieves clinically acceptable plan robustness. Our study supports the use of small‐spot IMPT for the treatment of distal esophageal carcinoma.

159 Background: Intensity-modulated proton therapy (IMPT) with small spot size has the potential to reduce dose to normal tissues but also introduces new confounding factors such as setup uncertainty, range uncertainty, and interplay effects due to breathing motion. We investigated plan quality and robustness of IMPT with small spot size for distal esophageal adenocarcinoma (DEA). Methods: 19 patients with DEA treated by IMPT were retrospectively evaluated. Spot sizes ranged from 2 to 6mm, with spot spacing of 5mm. All plans were generated using a commercial treatment planning system. In-house-developed dose-evaluation software modeled time-dependent spot delivery to incorporate interplay effects. Dose-volume-histogram (DVH) indices were used to evaluate plan quality and robustness was evaluated using the DVH band method. Results: For plan quality, median values of clinical target volume D95% and D5%-D95% (normalized to the prescribed doses), total lung mean dose, heart mean dose, and cord Dmax were 1.014, 0.035, 3.82Gy[RBE], 7.73Gy[RBE], 39.16Gy[RBE], respectively. For plan robustness, median band widths of the aforementioned DVH indices were 0.018, 0.048, 0.60Gy[RBE], 4.17Gy[RBE], and 2.36Gy[RBE], respectively. For interplay effects, median values of the aforementioned DVH indices were 0.99, 0.061, 4.07Gy[RBE], 7.87Gy[RBE], and 39.66Gy[RBE], respectively. Seven patients underwent esophagectomy after neoadjuvant chemoradiation, and five, three, and one of them achieved downstaging, near complete response, and pathologic complete response, respectively; R0 resection was achieved in all cases. For all patients, acute side effects were mostly limited to grades 1-2 only. The only grade 3 adverse events were related to feeding tube placement (8 patients); there were no RT-induced pneumonitis or other lung-related toxicities. Conclusions: IMPT plans with small spot size for DEA have good target dose coverage, homogeneity and normal tissue protection. Treatment plans are also robust to uncertainties and interplay effects. Early clinical results demonstrate low acute toxicity and encouraging clinical and pathologic response.

PurposeIntensity‐modulated proton therapy (IMPT) is known to be sensitive to patient setup and range uncertainty issues. Multiple robust optimization methods have been developed to mitigate the impact of these uncertainties. Here, we propose a new robust optimization method, which provides an alternative way of robust optimization in IMPT, and is clinically practical, which will enable users to control the balance between nominal plan quality and plan robustness in a user‐defined fashion.MethodWe calculated nine individual dose distributions which corresponded to one nominal and eight extreme scenarios caused by patient setup and proton beam's range uncertainties. For each voxel, the normalized dose interval (NDI) is defined as the full dose range variation divided by the maximum dose in all uncertainty scenarios (NDI = [max – min dose]/max dose), which was then used to calculate the normalized dose interval volume histogram (NDIVH) curves. The areas under the NDIVH curves were used to quantify plan robustness. A normalized dose interval volume constraint (NDIVC) applied to the target was incorporated to specify the desired robustness which was user‐defined. Users could then explore the trade‐off between nominal plan quality and plan robustness by adjusting the position of the NDIVCs on the NDIVH curves freely. We benchmarked our method using one lung, five head and neck (H&N), and three prostate cases by comparing our results to those derived using the voxel‐wise worst‐case robust optimization.ResultsUsing the benchmark cases, our new method achieved quality IMPT plans comparable to those derived from the voxel‐wise worst‐case robust optimization for both nominal plan quality and plan robustness in general; even more conformal and more homogeneous target dose distributions in some cases, if proper NDIVCs were applied. The AUC under NDIVH, as a precise quantitative index of plan robustness, was consistent with DVH bandwidths. Additionally, we demonstrated the feasibility of adjusting the position of NDIVCs in the NDIVH curves which allowed users to explore the trade‐off between nominal plan quality and plan robustness.ConclusionsThe NDIVH‐based robust optimization method provided a novel and individualized way of robust optimization in IMPT, and enables users to adjust the balance between nominal plan quality and plan robustness in a user‐defined fashion. This method is applicable for continued improvement and developing the next generation of IMPT planning algorithms in the future.

AbstractPurposeTo compare dosimetric performance of volumetric‐modulated arc therapy (VMAT) and small‐spot intensity‐modulated proton therapy for stage III non‐small‐cell lung cancer (NSCLC).Methods and MaterialsA total of 24 NSCLC patients were retrospectively reviewed; 12 patients received intensity‐modulated proton therapy (IMPT) and the remaining 12 received VMAT. Both plans were generated by delivering prescription doses to clinical target volumes (CTV) on averaged 4D‐CTs. The dose‐volume‐histograms (DVH) band method was used to quantify plan robustness. Software was developed to evaluate interplay effects with randomized starting phases of each field per fraction. DVH indices were compared using Wilcoxon rank sum test.ResultsCompared with VMAT, IMPT delivered significantly lower cord Dmax, heart Dmean, and lung V5 Gy[RBE] with comparable CTV dose homogeneity, and protection of other OARs. In terms of plan robustness, the IMPT plans were statistically better than VMAT plans in heart Dmean, but were statistically worse in CTV dose coverage, cord Dmax, lung Dmean, and V5 Gy[RBE]. Other DVH indices were comparable. The IMPT plans still met the standard clinical requirements with interplay effects considered.ConclusionsSmall‐spot IMPT improves cord, heart, and lung sparing compared to VMAT and achieves clinically acceptable plan robustness at least for the patients included in this study with motion amplitude less than 11 mm. Our study supports the usage of IMPT to treat some lung cancer patients.