In silico evaluation and feasibility of near margin-less head and neck daily adaptive radiotherapy.

OBJECTIVE: We explore the potential dosimetric benefits of reducing treatment volumes through daily adaptive radiation therapy for head and neck cancer (HNC) patients using the Ethos system/Intelligent Optimizer Engine (IOE). We hypothesize reducing treatment volumes afforded by daily adaption will significantly reduce the dose to adjacent organs at risk. We also explore the capability of the Ethos IOE to accommodate this highly conformal approach in HNC radiation therapy. METHODS: Ten HNC patients from a phase II trial were chosen, and their cone-beam CT (CBCT) scans were uploaded to the adaptive RT (ART) emulator. A new initial reference plan was generated using both a 1 mm and 5 mm planning target volume (PTV) expansion. Daily adaptive ART plans (1 mm) were simulated from the clinical CBCT taken every fifth fraction. Additionally, using physician-modified ART contours the larger 5 mm plan was recalculated on this recontoured on daily anatomy. Changes in target and OAR contours were measured using Dice coefficients as a surrogate of clinician effort. PTV coverage and organ-at-risk (OAR) doses were statistically compared, and the robustness of each ART plan was evaluated at fractions 5 and 35 to observe if OAR doses were within 3 Gy of pre-plan. RESULTS: This study involved six patients with oropharynx and four with larynx cancer, totaling 70 adaptive fractions. The primary and nodal gross tumor volumes (GTV) required the most adjustments, with median Dice scores of 0.88 (range: 0.80-0.93) and 0.83 (range: 0.66-0.91), respectively. For the 5th and 35th fraction plans, 80 % of structures met robustness criteria (quartile 1-3: 67-100 % and 70-90 %). Adaptive planning improved median PTV V100% coverage for doses of 70 Gy (96 % vs. 95.6 %), 66.5 Gy (98.5 % vs. 76.5 %), and 63 Gy (98.9 % vs. 74.9 %) (p < 0.03). Implementing ART with total volume reduction yielded median dose reductions of 7-12 Gy to key organs-at-risk (OARs) like submandibular glands, parotids, oral cavity, and constrictors (p < 0.05). CONCLUSIONS: The IOE enables feasible daily ART treatments with reduced margins while enhancing target coverage and reducing OAR doses for HNC patients. A phase II trial recently finished accrual and forthcoming analysis will determine if these dosimetric improvements correlate with improved patient-reported outcomes.

In Silico Analysis of Adjuvant Head and Neck Online Adaptive Radiation Therapy.

Purpose: Recently developed online adaptive radiation therapy (OnART) systems enable frequent treatment plan adaptation, but data supporting a dosimetric benefit in postoperative head and neck radiation therapy (RT) are sparse. We performed an in silico dosimetric study to assess the potential benefits of a single versus weekly OnART in the treatment of patients with head and neck squamous cell carcinoma in the adjuvant setting. Methods and Materials: Twelve patients receiving conventionally fractionated RT over 6 weeks and 12 patients receiving hypofractionated RT over 3 weeks on a clinical trial were analyzed. The OnART emulator was used to virtually adapt either once midtreatment or weekly based on the patient's routinely performed cone beam computed tomography. The planning target volume (PTV) coverage, dose heterogeneity, and cumulative dose to the organs at risk for these 2 adaptive approaches were compared with the nonadapted plan. Results: In total, 13, 8, and 3 patients had oral cavity, oropharynx, and larynx primaries, respectively. In the conventionally fractionated RT cohort, weekly OnART led to a significant improvement in PTV V100% coverage (6.2%), hot spot (-1.2 Gy), and maximum cord dose (-3.1 Gy), whereas the mean ipsilateral parotid dose increased modestly (1.8 Gy) versus the nonadapted plan. When adapting once midtreatment, PTV coverage improved with a smaller magnitude (0.2%-2.5%), whereas dose increased to the ipsilateral parotid (1.0-1.1 Gy) and mandible (0.2-0.7 Gy). For the hypofractionated RT cohort, similar benefit was observed with weekly OnART, including significant improvement in PTV coverage, hot spot, and maximum cord dose, whereas no consistent dosimetric advantage was seen when adapting once midtreatment. Conclusions: For head and neck squamous cell carcinoma adjuvant RT, there was a limited benefit of single OnART, but weekly adaptations meaningfully improved the dosimetric criteria, predominantly PTV coverage and dose heterogeneity. A prospective study is ongoing to determine the clinical benefit of OnART in this setting.

A high-resolution cone beam computed tomography (HRCBCT) reconstruction framework for CBCT-guided online adaptive therapy.

BACKGROUND: Kilo-voltage cone-beam computed tomography (CBCT) is a prevalent modality used for adaptive radiotherapy (ART) due to its compatibility with linear accelerators and ability to provide online imaging. However, the widely-used Feldkamp-Davis-Kress (FDK) reconstruction algorithm has several limitations, including potential streak aliasing artifacts and elevated noise levels. Iterative reconstruction (IR) techniques, such as total variation (TV) minimization, dictionary-based methods, and prior information-based methods, have emerged as viable solutions to address these limitations and improve the quality and applicability of CBCT in ART. PURPOSE: One of the primary challenges in IR-based techniques is finding the right balance between minimizing image noise and preserving image resolution. To overcome this challenge, we have developed a new reconstruction technique called high-resolution CBCT (HRCBCT) that specifically focuses on improving image resolution while reducing noise levels. METHODS: The HRCBCT reconstruction technique builds upon the conventional IR approach, incorporating three components: the data fidelity term, the resolution preservation term, and the regularization term. The data fidelity term ensures alignment between reconstructed values and measured projection data, while the resolution preservation term exploits the high resolution of the initial Feldkamp-Davis-Kress (FDK) algorithm. The regularization term mitigates noise during the IR process. To enhance convergence and resolution at each iterative stage, we applied Iterative Filtered Backprojection (IFBP) to the data fidelity minimization process. RESULTS: We evaluated the performance of the proposed HRCBCT algorithm using data from two physical phantoms and one head and neck patient. The HRCBCT algorithm outperformed all four different algorithms; FDK, Iterative Filtered Back Projection (IFBP), Compressed Sensing based Iterative Reconstruction (CSIR), and Prior Image Constrained Compressed Sensing (PICCS) methods in terms of resolution and noise reduction for all data sets. Line profiles across three line pairs of resolution revealed that the HRCBCT algorithm delivered the highest distinguishable line pairs compared to the other algorithms. Similarly, the Modulation Transfer Function (MTF) measurements, obtained from the tungsten wire insert on the CatPhan 600 physical phantom, showed a significant improvement with HRCBCT over traditional algorithms. CONCLUSION: The proposed HRCBCT algorithm offers a promising solution for enhancing CBCT image quality in adaptive radiotherapy settings. By addressing the challenges inherent in traditional IR methods, the algorithm delivers high-definition CBCT images with improved resolution and reduced noise throughout each iterative step. Implementing the HR CBCT algorithm could significantly impact the accuracy of treatment planning during online adaptive therapy.

Technical note: Progressive deep learning: An accelerated training strategy for medical image segmentation.

BACKGROUND: Recent advancements in Deep Learning (DL) methodologies have led to state-of-the-art performance in a wide range of applications especially in object recognition, classification, and segmentation of medical images. However, training modern DL models requires a large amount of computation and long training times due to the complex nature of network structures and the large number of training datasets involved. Moreover, it is an intensive, repetitive manual process to select the optimized configuration of hyperparameters for a given DL network. PURPOSE: In this study, we present a novel approach to accelerate the training time of DL models via the progressive feeding of training datasets based on similarity measures for medical image segmentation. We term this approach Progressive Deep Learning (PDL). METHODS: The two-stage PDL approach was tested on the auto-segmentation task for two imaging modalities: CT and MRI. The training datasets were ranked according to similarity measures between each sample based on Mean Square Error (MSE), Peak Signal-to-Noise Ratio (PSNR), Structural Similarity Index (SSIM), and the Universal Quality Image Index (UQI) values. At the start of the training process, a relatively coarse sampling of training datasets with higher ranks was used to optimize the hyperparameters of the DL network. Following this, the samples with higher ranks were used in step 1 to yield accelerated loss minimization in early training epochs and the total dataset was added in step 2 for the remainder of training. RESULTS: Our results demonstrate that the PDL approach can reduce the training time by nearly half (∼49%) and can predict segmentations (CT U-net/DenseNet dice coefficient: 0.9506/0.9508, MR U-net/DenseNet dice coefficient: 0.9508/0.9510) without major statistical difference (Wilcoxon signed-rank test) compared to the conventional DL approach. The total training times with a fixed cutoff at 0.95 DSC for the CT dataset using DenseNet and U-Net architectures, respectively, were 17 h, 20 min and 4 h, 45 min in the conventional case compared to 8 h, 45 min and 2 h, 20 min with PDL. For the MRI dataset, the total training times using the same architectures were 2 h, 54 min and 52 min in the conventional case and 1 h, 14 min and 25 min with PDL. CONCLUSION: The proposed PDL training approach offers the ability to substantially reduce the training time for medical image segmentation while maintaining the performance achieved in the conventional case.

Spare the Bowel, Don't Spoil the Target: Optimal Margin Assessment for Online Cone Beam Adaptive Radiation Therapy (OnC-ART) of the Cervix.

PURPOSE: The standard treatment for locally advanced cervical cancer involves pelvic chemoradiation. Intensity modulated radiation therapy planning requires expansion of the cervix and uterus clinical target volume (CTV) by 1.5 to 2 cm to account for motion. With online cone beam adaptive radiation therapy (OnC-ART), interfractional movement is accounted for, which can potentially lead to smaller CTV to planned target volume (PTV) margins. In this study, we attempted to determine the optimal CTV-to-PTV margin for adequate coverage with OnC-ART and factors that can affect CTV coverage. METHODS AND MATERIALS: A retrospective cohort of 21 patients with cervical cancer treated with definitive chemoradiation was included. Nine patients treated with nonadaptive radiation had the uterocervix contoured on pretreatment cone beam computed tomography (CBCT) and end-treatment CBCTs. Anterior-posterior, lateral, and superior-inferior shifts and the average shift in all directions were calculated. A CTV-to-PTV expansion was determined and verified on a validation cohort of 12 patients treated with OnC-ART. RESULTS: The average anterior-posterior, lateral, and superior-inferior shifts with standard deviation were 0.32 ± 1.55 cm, 0.12 ± 2.31 cm, and 1.67 ± 3.41 cm, respectively. A uniform 5-mm expansion around the pretreatment CTV covered 98.85% ± 1.23% of the end-treatment CTV. This 5-mm expansion was applied to our validation cohort treated with OnC-ART, and 98.39% ± 3.0% of the end-treatment CTV was covered. Time between CBCTs >30 minutes and change in bladder volume were significantly correlated to CTV coverage. CONCLUSIONS: Based on our analysis, a CTV-to-PTV margin of 5 mm is adequate to encompass 98% of the CTV. A significantly reduced margin could potentially decrease the toxicities associated with radiation for patients with cervical cancer and lead to improved patient reported toxicity outcomes. We recommend physicians begin with a 5-mm margin and assess adequate coverage with image guidance during daily adaptation.