Xiaodong Zhang

Background/Objectives: Stereotactic body radiation therapy (SBRT) for skull base reirradiation is particularly challenging, as patients have already received substantial radiation doses to the region, and nearby normal organs may have approached their tolerance limit from prior treatments. In this study, we reviewed the characteristics and capabilities of four advanced external beam radiation delivery systems and four modern treatment planning systems and evaluated the treatment plan quality of each technique using skull base reirradiation patient cases. Methods: SBRT plans were generated for sixteen skull base reirradiation patients using four modalities: the GK plan for the Elekta Leksell Gamma Knife Perfexion/ICON, the CyberKnife (CK) plan for the Accuray CyberKnife, the intensity-modulated proton therapy (IMPT) plan for the Hitachi ProBeat-FR proton therapy machine, and the volumetric-modulated arc therapy (VMAT) plan for the Varian TrueBeam STx. These plans were evaluated and compared using two novel gradient indices in addition to traditional dosimetry metrics for targets and organs at risk (OARs). The steepest border gradient quantified the percent prescription dose fall-off per millimeter at the boundary between the target and adjacent critical structures. This gradient index highlighted the system’s ability to spare nearby critical OARs. The volume gradient assessed the extent of dose spread outside the target toward the patient’s body. Results: All plans achieved comparable target coverage and conformity, while IMPT and VMAT demonstrated significantly better uniformity. The GK plans exhibited the highest border gradient, up to 20.9%/mm, followed by small-spot-size IMPT plans and CK plans. Additionally, IMPT plans showed the benefit of reduced dose spread in low-dose regions and the lowest maximum and mean doses to the brainstem and carotid artery. Conclusions: The advanced external beam radiotherapy modalities evaluated in this study are well-suited for SBRT in skull base reirradiation, which demands precise targeting of tumors with highly conformal doses and steep dose gradients to protect nearby normal structures.

Background/Objectives: We assessed the influence of local patients and clinical characteristics on the performance of commercial deep learning (DL) segmentation models for head-and-neck (HN), breast, and prostate cancers. Methods: Clinical computed tomography (CT) scans and clinically approved contours of 210 patients (53 HN, 49 left breast, 55 right breast, and 53 prostate cancer) were used to train and validate segmentation models integrated within a vendor-supplied DL training toolkit and to assess the performance of both vendor-pretrained and custom-trained models. Four custom models (HN, left breast, right breast, and prostate) were trained and validated with 30 (training)/5 (validation) HN, 34/5 left breast, 39/5 right breast, and 30/5 prostate patients to auto-segment a total of 24 organs at risk (OARs). Subsequently, both vendor-pretrained and custom-trained models were tested on the remaining patients from each group. Auto-segmented contours were evaluated by comparing them with clinically approved contours via the Dice similarity coefficient (DSC) and mean surface distance (MSD). The performance of the left and right breast models was assessed jointly according to ipsilateral/contralateral locations. Results: The average DSCs for all structures in vendor-pretrained and custom-trained models were as follows: 0.81 ± 0.12 and 0.86 ± 0.11 in HN; 0.67 ± 0.16 and 0.80 ± 0.11 in the breast; and 0.87 ± 0.09 and 0.92 ± 0.06 in the prostate. The corresponding average MSDs were 0.81 ± 0.76 mm and 0.76 ± 0.56 mm (HN), 4.85 ± 2.44 mm and 2.42 ± 1.49 mm (breast), and 2.17 ± 1.39 mm and 1.21 ± 1.00 mm (prostate). Notably, custom-trained models showed significant improvements over vendor-pretrained models for 14 of 24 OARs, reflecting the influence of data/contouring variations in segmentation performance. Conclusions: These findings underscore the substantial impact of institutional preferences and clinical practices on the implementation of vendor-pretrained models. We also found that a relatively small amount of institutional data was sufficient to train customized segmentation models with sufficient accuracy.

Objectives: To compare and evaluate the performance of artificial intelligence (AI) against physicians in classifying benign and malignant pulmonary nodules from computerized tomography (CT) images. Methods: A total of 506 CT images with pulmonary nodules were retrospectively collected. The AI was trained using in-house software. For comparing the diagnostic performance of artificial intelligence and different groups of physicians in pulmonary nodules, statistical methods of receiver operating characteristic (ROC) curve and area under the curve (AUC) were analyzed. The nodules in CT images were analyzed in a case-by-case manner. Results: The diagnostic accuracy of AI surpassed that of all groups of physicians, exhibiting an AUC of 0.88 alongside a sensitivity of 0.80, specificity of 0.84, and accuracy of 0.83. The area under the curve (AUC) of seven groups of physicians varies between 0.63 and 0.84. The sensitivity of the physicians within these groups varies between 0.4 and 0.76. The specificity of different groups ranges from 0.8 to 0.85. Furthermore, the accuracy of the seven groups ranges from 0.7 to 0.82. The professional insights for enhancing deep learning models were obtained through an examination conducted on a per-case basis. Conclusions: AI demonstrated great potential in the benign–malignant classification of pulmonary nodules with higher accuracy. More accurate information will be provided by AI when making clinical decisions.

Objective: To determine the effect of dose calculation accuracy on inverse linear energy transfer (LET) optimization for intensity‐modulated proton therapy, and to determine whether adding more beams would improve the plan robustness to different dose calculation engines.Methods: Two sets of intensity‐modulated proton therapy plans using two, four, six, and nine beams were created for 10 prostate cancer patients: one set was optimized with dose constraints (DoseOpt) using the pencil beam (PB) algorithm, and the other set was optimized with additional LET constraints (LETOpt) using the Monte Carlo (MC) algorithm. Dose distributions of DoseOpt plans were then recalculated using the MC algorithm, and the LETOpt plans were recalculated using the PB algorithm. Dosimetric indices of targets and critical organs were compared between the PB and MC algorithms for both sets of plans.Results: For DoseOpt plans, dose differences between the PB and MC algorithms were minimal. However, the maximum dose differences in LETOpt plans were 11.11% and 15.85% in the dose covering 98% and 2% (D2) of the clinical target volume, respectively. Furthermore, the dose to 1 cc of the bladder differed by 11.42 Gy (relative biological effectiveness). Adding more beams reduced the discrepancy in target coverage, but the errors in D2 of the structure were increased with the number of beams.Conclusion: High modulation of LET requires high dose calculation accuracy during the optimization and final dose calculation in the inverse treatment planning for intensity‐modulated proton therapy, and adding more beams did not improve the plan robustness to different dose calculation algorithms.

This study aimed to compare the predictive performance of different modeling methods in developing normal tissue complication probability (NTCP) models for predicting radiation-induced esophagitis (RE) in non–small cell lung cancer (NSCLC) patients receiving proton radiotherapy. The dataset was composed of 328 NSCLC patients receiving passive-scattering proton therapy and 41.6% of the patients experienced ≥ grade 2 RE. Five modeling methods were used to build NTCP models: standard Lyman–Kutcher–Burman (sLKB), generalized LKB (gLKB), multivariable logistic regression using two variable selection procedures-stepwise forward selection (Stepwise-MLR), and least absolute shrinkage and selection operator (LASSO-MLR), and support vector machines (SVM). Predictive performance was internally validated by a bootstrap approach for each modeling method. The overall performance, discriminative ability, and calibration were assessed using the Negelkerke R², area under the receiver operator curve (AUC), and Hosmer–Lemeshow test, respectively. The LASSO-MLR model showed the best discriminative ability with an AUC value of 0.799 (95% confidence interval (CI): 0.763–0.854), and the best overall performance with a Negelkerke R² value of 0.332 (95% CI: 0.266–0.486). Both of the optimism-corrected Negelkerke R² values of the SVM and sLKB models were 0.301. The optimism-corrected AUC of the gLKB model (0.796) was higher than that of the SVM model (0.784). The sLKB model had the smallest optimism in the model variation and discriminative ability. In the context of classification and probability estimation for predicting the NTCP for radiation-induced esophagitis, the MLR model developed with LASSO provided the best predictive results. The simplest LKB modeling had similar or even better predictive performance than the most complex SVM modeling, and it was least likely to overfit the training data. The advanced machine learning approach might have limited applicability in clinical settings with a relatively small amount of data.

Opinion statement: The rise in the incidence of human papillomavirus (HPV)-associated oropharyngeal squamous cell carcinoma (OPC), the relatively young age at which it is diagnosed, and its favorable prognosis necessitate the use of treatment techniques that reduce the likelihood of side effects during and after curative treatment. Intensity-modulated proton therapy (IMPT) is a form of radiotherapy that de-intensifies treatment through dose de-escalation to normal tissues without compromising dose to the primary tumor and involved, regional lymph nodes. Preclinical studies have demonstrated that HPV-positive squamous cell carcinoma is more sensitive to proton radiation than is HPV-negative squamous cell carcinoma. Retrospective studies comparing intensity-modulated photon (X-ray) radiotherapy to IMPT for OPC suggest comparable rates of disease control and lower rates of pain, xerostomia, dysphagia, dysgeusia, gastrostomy tube dependence, and osteoradionecrosis with IMPT—all of which meaningfully affect the quality of life of patients treated for HPV-associated OPC. Two phase III trials currently underway—the “Randomized Trial of IMPT versus IMRT for the Treatment of Oropharyngeal Cancer of the Head and Neck” and the “TOxicity Reduction using Proton bEam therapy for Oropharyngeal cancer (TORPEdO)” trial—are expected to provide prospective, level I evidence regarding the effectiveness of IMPT for such patients.

In intensity-modulated proton therapy, robust optimization processes have been developed to manage uncertainties associated with (1) range, (2) setup, (3) anatomic changes, (4) dose calculation, and (5) biological effects. Here we review our experience using a robust optimization technique that directly incorporates range and setup uncertainties into the optimization process to manage those sources of uncertainty. We also review procedures for implementing adaptive planning to manage the anatomic uncertainties. Finally, we share some early experiences regarding the impact of uncertainties in dose calculation and biological effects, along with techniques to manage and potentially reduce these uncertainties.