Search

Simple Summary: Ultrahigh-dose-rate therapy, known as FLASH radiotherapy (RT), is an emerging cancer treatment technique that offers similar tumor control to conventional RT but with the enhanced protection of normal tissue through the FLASH-sparing effect. Preclinical studies on animals and cell lines show promising results. This is significant for patients with recurrent tumors and reirradiation cases, where conventional RT has high toxicity rates. FLASH-RT can potentially improve tumor control while reducing side effects and preserving quality of life. Among the FLASH modalities, proton therapy stands out for its superior dosimetric and delivery characteristics, making it a safe and effective option for human malignancies. Despite its potential, proton Bragg peak FLASH for HN cancer remains underexplored, and this review highlights the novel proton conformal FLASH techniques, which allow for high-quality plans while minimizing radiation exposure to critical organs at risk (OARs) for HN cancer reirradiation. Ultrahigh-dose-rate therapy, also known as FLASH radiotherapy (RT), is an emerging technique that is garnering significant interest in cancer treatment due to its potential to revolutionize therapy. This method can achieve comparable tumor control to conventional-dose-rate RT while offering the enhanced protection of normal tissue through the FLASH-sparing effect. This innovative technique has demonstrated promising results in preclinical studies involving animals and cell lines. Particularly noteworthy is its potential application in treating head and neck (HN) cancers, especially in patients with challenging recurrent tumors and reirradiation cases, where the toxicity rates with conventional radiotherapy are high. Such applications aim to enhance tumor control while minimizing side effects and preserving patients' quality of life. In comparison to electron or photon FLASH modalities, proton therapy has demonstrated superior dosimetric and delivery characteristics and is a safe and effective FLASH treatment for human malignancies. Compared to the transmission proton FLASH, single-energy Bragg peak FLASH is a novel delivery method that allows highly conformal doses to targets and minimal radiation doses to crucial OARs. Proton Bragg peak FLASH for HN cancer has still not been well studied. This review highlights the significance of proton FLASH in enhancing cancer therapy by examining the advantages and challenges of using it for HN cancer reirradiation. [ABSTRACT FROM AUTHOR]

Purpose: Manual delineation of organs‐at‐risk (OARs) in radiotherapy is both time‐consuming and subjective. Automated and more accurate segmentation is of the utmost importance in clinical application. The purpose of this study is to further improve the segmentation accuracy and efficiency with a novel network named convolutional neural networks (CNN) Cascades. Methods: CNN Cascades was a two‐step, coarse‐to‐fine approach that consisted of a simple region detector (SRD) and a fine segmentation unit (FSU). The SRD first used a relative shallow network to define the region of interest (ROI) where the organ was located, and then, the FSU took the smaller ROI as input and adopted a deep network for fine segmentation. The imaging data (14,651 slices) of 100 head‐and‐neck patients with segmentations were used for this study. The performance was compared with the state‐of‐the‐art single CNN in terms of accuracy with metrics of Dice similarity coefficient (DSC) and Hausdorff distance (HD) values. Results: The proposed CNN Cascades outperformed the single CNN on accuracy for each OAR. Similarly, for the average of all OARs, it was also the best with mean DSC of 0.90 (SRD: 0.86, FSU: 0.87, and U‐Net: 0.85) and the mean HD of 3.0 mm (SRD: 4.0, FSU: 3.6, and U‐Net: 4.4). Meanwhile, the CNN Cascades reduced the mean segmentation time per patient by 48% (FSU) and 5% (U‐Net), respectively. Conclusions: The proposed two‐step network demonstrated superior performance by reducing the input region. This potentially can be an effective segmentation method that provides accurate and consistent delineation with reduced clinician interventions for clinical applications as well as for quality assurance of a multicenter clinical trial. [ABSTRACT FROM AUTHOR]

Purpose: Convolutional neural networks (CNN) have greatly improved medical image segmentation. A robust model requires training data can represent the entire dataset. One of the differing characteristics comes from variability in patient positioning (prone or supine) for radiotherapy. In this study, we investigated the effect of position orientation on segmentation using CNN. Methods: Data of 100 patients (50 in supine and 50 in prone) with rectal cancer were collected for this study. We designed three sets of experiments for comparison: (a) segmentation using the model trained with data from the same orientation; (b) segmentation using the model trained with data from the opposite orientation; (c) segmentation using the model trained with data from both orientations. We performed fivefold cross‐validation. The performance was evaluated on segmentation of the clinical target volume (CTV), bladder, and femurs with Dice similarity coefficient (DSC) and Hausdorff distance (HD). Results: Compared with models trained on cases positioned in the same orientation, the models trained with cases positioned in the opposite orientation performed significantly worse (P < 0.05) on CTV and bladder segmentation, but had comparable accuracy for femurs (P > 0.05). The average DSC values were 0.74 vs 0.84, 0.85 vs 0.88, and 0.91 vs 0.91 for CTV, bladder, and femurs, respectively. The corresponding HD values (mm) were 16.6 vs 14.6, 8.4 vs 8.1, and 6.3 vs 6.3, respectively. The models trained with data from both orientations have comparable accuracy (P > 0.05), with average DSC of 0.84, 0.88, and 0.91 and HD of 14.4, 8.1, and 6.3, respectively. Conclusions: Orientation affects the accuracy for CTV and bladder, but has negligible effect on the femurs. The model trained from data combining both orientations performs as well as a model trained with data from the same orientation for all the organs. These observations can offer guidance on the choice of training data for accurate segmentation. [ABSTRACT FROM AUTHOR]

Purpose: We hypothesized that the radiation dose in high-ventilation portions of the lung better predicts radiation pneumonitis (RP) outcome for patients treated with proton radiation therapy (PR) and photon radiation therapy (PH).Methods and Materials: Seventy-four patients (38 protons, 36 photons) with locally advanced non-small cell lung cancer treated with concurrent chemoradiation therapy were identified, of whom 24 exhibited RP (graded using Common Terminology Criteria for Adverse Events v4.0) after PR or PH, and 50 were negative controls. The inhale and exhale simulation computed tomography scans were deformed using Advanced Normalization Tools. The 3-dimensional lung ventilation maps were derived from the deformation matrix and partitioned into low- and high-ventilation zones for dosimetric analysis. Receiver operating curve analysis was used to study the power of relationship between RP and ventilation zones to determine an optimal ventilation cutoff. Univariate logistic regression was used to correlate dose in high- and low-ventilation zones with risk of RP. A nonparametric random forest process was used for multivariate importance assessment.Results: The optimal high-ventilation zone definition was determined to be the higher 45% to 60% of the ventilation values. The parameter vV20Gy_high (high ventilation volume receiving ≥20 Gy) was found to be a significant indicator for RP (PH: P = .002, PR: P = .035) with improved areas under the curve compared with the traditional V20Gy for both photon and proton cohorts. The relationship of RP with dose to the low-ventilation zone of the lung was insignificant (PH: P = .123, PR: P = .661). Similar trends were observed for ventilation mean lung dose and ventilation V5Gy. Multivariate importance assessment determined that vV20Gy_high, vV5_high, and mean lung dose were the most significant parameters for the proton cohort with a combined area under the curve of 0.78.Conclusion: Dose to the high-ventilated regions of the lung can improve predictions of RP for both PH and PR. [ABSTRACT FROM AUTHOR]