Radiotherapy Planning Research Articles

Precision dose prediction for breast cancer patients undergoing IMRT: The Swin-UMamba-Channel Model

BackgroundRadiation therapy is one of the crucial treatment modalities for cancer. An excellent radiation therapy plan relies heavily on an outstanding dose distribution map, which is traditionally generated through repeated trials and adjustments by experienced physicists. However, this process is both time-consuming and labor-intensive, and it comes with a degree of subjectivity. Now, with the powerful capabilities of deep learning, we are able to predict dose distribution maps more accurately, effectively overcoming these challenges. MethodsIn this study, we propose a novel Swin-UMamba-Channel prediction model specifically designed for predicting the dose distribution of patients with left breast cancer undergoing radiotherapy after total mastectomy. This model integrates anatomical position information of organs and ray angle information, significantly enhancing prediction accuracy. Through iterative training of the generator (Swin-UMamba) and discriminator, the model can generate images that closely match the actual dose, assisting physicists in quickly creating DVH curves and shortening the treatment planning cycle. Our model exhibits excellent performance in terms of prediction accuracy, computational efficiency, and practicality, and its effectiveness has been further verified through comparative experiments with similar networks. ResultsThe results of the study indicate that our model can accurately predict the clinical dose of breast cancer patients undergoing intensity-modulated radiation therapy (IMRT). The predicted dose range is from 0 to 50 Gy, and compared with actual data, it shows a high accuracy with an average Dice similarity coefficient of 0.86. Specifically, the average dose change rate for the planning target volume ranges from 0.28 % to 1.515 %, while the average dose change rates for the right and left lungs are 2.113 % and 0.508 %, respectively. Notably, due to their small sizes, the heart and spinal cord exhibit relatively higher average dose change rates, reaching 3.208 % and 1.490 %, respectively. In comparison with similar dose studies, our model demonstrates superior performance. Additionally, our model possesses fewer parameters, lower computational complexity, and shorter processing time, further enhancing its practicality and efficiency. These findings provide strong evidence for the accuracy and reliability of our model in predicting doses, offering significant technical support for IMRT in breast cancer patients. ConclusionThis study presents a novel Swin-UMamba-Channel dose prediction model, and its results demonstrate its precise prediction of clinical doses for the target area of left breast cancer patients undergoing total mastectomy and IMRT. These remarkable achievements provide valuable reference data for subsequent plan optimization and quality control, paving a new path for the application of deep learning in the field of radiation therapy.

Overall survival following heterogeneous FDG-guided dose-escalation for locally advanced NSCLC in the international phase III NARLAL2 trial.

LBA8069 Background: The survival and loco-regional control for patients (pts) with locally advanced non-small cell lung cancer (LA_NSCLC) treated with radiotherapy (RT) are dismal despite adjuvant Durvalumab. However, there have been concerns about dose escalation for these pts since the unexpected result of the dose-escalation trial RTOG0617. A novel approach is therefore warranted to escalate the dose to the tumor. A possible approach is to use the principle from stereotactic body radiotherapy (SBRT) with inhomogeneous dose distribution. SBRT has demonstrated excellent local control in early-stage lung cancer. The international multicenter NARLAL2 (novel approach to RT for LA_NSCLC) phase III trial on dose escalation, randomized pts with LA_NSCLC between standard 66 Gy/ 33 fractions (F) versus heterogeneous FDG-PET driven dose escalation, aiming at mean dose to GTV-tumorPET 95 Gy/ 33 F and mean dose to GTV-nodePET 74 Gy/ 33 F while strictly respecting dose to organs at risk. We here present the data on overall survival (OS) 1 year after the end of recruitment. Methods: Pts aged ≥18 years with LA_NSCLC were recruited from seven institutions in Denmark and Norway. Eligibility criteria included ECOG PS 0-1, histological or cytological confirmed NSCLC stage IIB-IIIB, signed informed consent, and a clinically acceptable plan for RT with conventional 66 Gy/ 33 F. PET-CT and brain MR were part of staging. Pts were randomly assigned to either treatment group (1:1, stratified for center and histology). The trial aimed to have iso-lung toxicity within the treatment arms by creating two RT plans (before randomization) for each patient (one for each treatment arm) with matching mean lung dose and lung V20Gy. The follow-up (FU) were scheduled weekly during RT, every 3rd month for 2 years, and every 6th month for another 3 years after randomization. At FU visit a CT-scan and toxicity scoring were performed. All interim analyses were passed without interventions (toxicity and OS). The trial's primary endpoint was time to loco-regional failure from randomization. Secondary endpoints included OS, acute, and late toxicity. The sample size calculations requested 350 pts to be enrolled in the study. Recruitment of the pre-planned number of pts finalized in March 2023. The trial was registered with ClinicalTrials.gov (NCT02354274). Results: From January 2015 to March 2023, 350 pts were randomized: 177 and 173 pts in standard and escalated arms respectively. The two groups were well-balanced regarding age, gender, stage, and PS. The dose to GTV-tumor was 66.5 Gy [66.2, 67.1] (median [IQR]) in the standard arm and 88.1 Gy [84.9, 90.4] in the escalated arm. Median OS were 35.8 months (m) and 51.6 m for pts treated in the standard and escalated arm, respectively ( p = 0.36). Median FU time 50.8 m (reverse Kaplan-Meier). Conclusions: Dose escalation is safe in the NARLAL2 setting with respect to OS. Clinical trial information: NCT02354274 .

Deep learning promoted target volumes delineation of total marrow and total lymphoid irradiation for accelerated radiotherapy: A multi-institutional study

Background and purposeOne of the current roadblocks to the widespread use of Total Marrow Irradiation (TMI) and Total Marrow and Lymphoid Irradiation (TMLI) is the challenging difficulties in tumor target contouring workflow. This study aims to develop a hybrid neural network model that promotes accurate, automatic, and rapid segmentation of multi-class clinical target volumes. Materials and methodsPatients who underwent TMI and TMLI from January 2018 to May 2022 were included. Two independent oncologists manually contoured eight target volumes for patients on CT images. A novel Dual-Encoder Alignment Network (DEA-Net) was developed and trained using 46 patients from one internal institution and independently evaluated on a total of 39 internal and external patients. Performance was evaluated on accuracy metrics and delineation time. ResultsThe DEA-Net achieved a mean dice similarity coefficient of 90.1 % ± 1.8 % for internal testing dataset (23 patients) and 91.1 % ± 2.5 % for external testing dataset (16 patients). The 95 % Hausdorff distance and average symmetric surface distance were 2.04 ± 0.62 mm and 0.57 ± 0.11 mm for internal testing dataset, and 2.17 ± 0.68 mm, and 0.57 ± 0.20 mm for external testing dataset, respectively, outperforming most of existing state-of-the-art methods. In addition, the automatic segmentation workflow reduced delineation time by 98 % compared to the conventional manual contouring process (mean 173 ± 29 s vs. 12168 ± 1690 s; P < 0.001). Ablation study validate the effectiveness of hybrid structures. ConclusionThe proposed deep learning framework achieved comparable or superior target volume delineation accuracy, significantly accelerating the radiotherapy planning process.

Predictive power of PTV volume for choosing manual or automatic planning in lung stereotactic body radiotherapy

PurposeThis study investigated the role of Planning Target Volume (PTV) in determining the suitability of manual and automatic Stereotactic Body Radiation Therapy (SBRT) planning for lung cancer patients. MethodsWe retrospectively created manual and automatic lung SBRT plans for ninety-eight patients using the Pinnacle 16.2 Treatment Planning System (TPS). The superior plan, whether manual or automatic, was selected for each patient through a combined index. Receiver Operating Characteristic (ROC) analysis was used to assess the predictive potential of the PTV volume in determining the superior plan and to establish a cutoff value. Patients were then stratified into two groups based on this value, and dosimetric variances were evaluated. ResultsThe ROC analysis highlighted the PTV volume's proficiency in predicting the superior choice between manual and automatic lung SBRT plans (Area Under Curve (AUC): 0.918, p = 0.005). The delineated cutoff value was set at 22.675 cc. For PTV volumes below this threshold, automatic plans surpassed manual plans in the Conformity Index (CI), Gradient Index (GI), and lung doses. Conversely, for PTV volumes exceeding 22.675 cc, manual plans exhibited improved results in the Heterogeneity Index (HI), GI, and dosimetric metric of heart and lung. ConclusionThe PTV volume is a significant determinant in guiding the optimal selection between manual and automatic lung SBRT plans with the Pinnacle TPS. Automatic plans are recommended for patients with PTV volumes below 22.675 cc, and manual plans for those above this threshold.

Current Applications of PET/MR: Part II: Clinical Applications II.

Due to the major improvements in the hardware and image reconstruction algorithms, positron emission tomography/magnetic resonance imaging (PET/MR) is now a reliable state-of-the-art hybrid modality in medical practice. Currently, it can provide a broad range of advantages in preclinical and clinical imaging compared to single-modality imaging. In the second part of this review, we discussed the further clinical applications of PET/MR. In the chest, PET/MR has particular potential in the oncology setting, especially when utilizing ultrashort/zero echo time MR sequences. Furthermore, cardiac PET/MR can provide reliable information in evaluating myocardial inflammation, cardiac amyloidosis, myocardial perfusion, myocardial viability, atherosclerotic plaque, and cardiac masses. In gastrointestinal and hepato-pancreato-biliary malignancies, PET/MR is able to precisely detect metastases to the liver, being superior over the other imaging modalities. In genitourinary and gynaecology applications, PET/MR is a comprehensive diagnostic method, especially in prostate, endometrial, and cervical cancers. Its simultaneous acquisition has been shown to outperform other imaging techniques for the detection of pelvic nodal metastases and is also a reliable modality in radiation planning. Lastly, in haematologic malignancies, PET/MR can significantly enhance lymphoma diagnosis, particularly in detecting extra-nodal involvement. It can also comprehensively assess treatment-induced changes. Furthermore, PET/MR may soon become a routine in multiple myeloma management, being a one-stop shop for evaluating bone, bone marrow, and soft tissues.

The Evolving Role of Novel Imaging Techniques for Radiotherapy Planning

The ability to visualise cancer with imaging has been crucial to the evolution of modern radiotherapy (RT) planning and delivery. And as evolving RT technologies deliver increasingly precise treatment, the importance of accurate identification and delineation of disease assumes ever greater significance. However, innovation in imaging technology has matched that seen with RT delivery platforms, and novel imaging techniques are a focus of much research activity. How these imaging modalities may alter and improve the diagnosis and staging of cancer is an important question, but already well served by the literature. What is less clear is how novel imaging techniques may influence and improve practical and technical aspects of RT planning and delivery. In this review, current gold standard approaches to integration of imaging, and potential future applications of bleeding-edge imaging technology into RT planning pathways are explored.

Establishing a 4D-CT lung function related volumetric dose model to reduce radiation pneumonia

In order to study how to use pulmonary functional imaging obtained through 4D-CT fusion for radiotherapy planning, and transform traditional dose volume parameters into functional dose volume parameters, a functional dose volume parameter model that may reduce level 2 and above radiation pneumonia was obtained. 41 pulmonary tumor patients who underwent 4D-CT in our department from 2020 to 2023 were included. MIM Software (MIM 7.0.7; MIM Software Inc., Cleveland, OH, USA) was used to register adjacent phase CT images in the 4D-CT series. The three-dimensional displacement vector of CT pixels was obtained when changing from one respiratory state to another respiratory state, and this three-dimensional vector was quantitatively analyzed. Thus, a color schematic diagram reflecting the degree of changes in lung CT pixels during the breathing process, namely the distribution of ventilation function strength, is obtained. Finally, this diagram is fused with the localization CT image. Select areas with Jacobi > 1.2 as high lung function areas and outline them as fLung. Import the patient's DVH image again, fuse the lung ventilation image with the localization CT image, and obtain the volume of fLung different doses (V60, V55, V50, V45, V40, V35, V30, V25, V20, V15, V10, V5). Analyze the functional dose volume parameters related to the risk of level 2 and above radiation pneumonia using R language and create a predictive model. By using stepwise regression and optimal subset method to screen for independent variables V35, V30, V25, V20, V15, and V10, the prediction formula was obtained as follows: Risk = 0.23656–0.13784 * V35 + 0.37445 * V30-0.38317 * V25 + 0.21341 * V20-0.10209 * V15 + 0.03815 * V10. These six independent variables were analyzed using a column chart, and a calibration curve was drawn using the calibrate function. It was found that the Bias corrected line and the Apparent line were very close to the Ideal line, The consistency between the predicted value and the actual value is very good. By using the ROC function to plot the ROC curve and calculating the area under the curve: 0.8475, 95% CI 0.7237–0.9713, it can also be determined that the accuracy of the model is very high. In addition, we also used Lasso method and random forest method to filter out independent variables with different results, but the calibration curve drawn by the calibration function confirmed poor prediction performance. The function dose volume parameters V35, V30, V25, V20, V15, and V10 obtained through 4D-CT are key factors affecting radiation pneumonia. Establishing a predictive model can provide more accurate lung restriction basis for clinical radiotherapy planning.

Phase I study of copaiba aqueous mouthwash in patients with head and neck cancer undergoing radiotherapy.

e24103 Background: Due to the contraindication of low-power laser therapy in the tumor region, the use of copaiba for the management of oral mucositis was proposed, given its anti-inflammatory, antimicrobial and healing properties. This study aimed to evaluate the dose-limiting toxicity/maximum tolerated dose of copaiba aqueous mouthwash solution. Methods: This is a phase I study including patients with cavity or oropharynx cancer (CID-10 C00-C06,10), undergoing radiotherapy alone or associated with chemotherapy. Six successive cohorts were proposed, with a minimum of 3 patients each. The copaiba aqueous mouthwash was used daily starting on the first day of radiotherapy and up to 37 days, associated with Low Power Laser applications (100Mw, 660nm, beam area 0.09842 cm²,1J) in non-tumoral areas. In cohorts 1, 2, and 3, a 10% solution was used, and in cohorts 4, 5, and 6, 15%, 2, 3 and 4 times a day, respectively. Daily assessment was carried out evaluating the presence of oral mucositis lesions (World Health Organization and Oral Mucositis Assessment Scale) and complaints of pain (CTCAE v5.0 and Visual Analogue Pain Scale) and xerostomia (presence or absence). Sialometry was carried out through the collection of unstimulated saliva (by Davies (2002) criteria), once a week. Results: Twenty patients were included (cohort 1 = 5, cohort 2 = 3, cohort 3 = 3, cohort 4 = 3, cohort 5 = 3, cohort 6 = 3) - 1 patient was excluded and 1 discontinued from cohort 1 (due to changes in radiotherapy planning and non-adherence to dentistry appointments). A total of 19 participants used the mouthwash. Most of the participants were women (57.9%), with a median age of 63.2 years, and performance status 1 (84.2%). Most tumors were squamous cell carcinomas (84.2%), 47.4% of them in the palate; 57.9% were staged as IVA. Themedian total radiotherapy dose was 68.0 (60.0-70.0) Gy delivered in 33.0 (30.0-34.5) fractions. Pain in the oral cavity (73.7%) and oropharynx (52.6%) were referred, graded respectively as 4.5 (0.75-7) and 1.5 (0-6). Oral mucositis was classified as grade 3 at most; none of the patients developed grade 4 or had to have radiotherapy interrupted due to toxicity. Ulcerated lesions of oral mucositis developed in the tumor area in 68.4% of patients and non-tumor areas in 84.2%. Patients complained of xerostomia in 73.7% of cases and the median unstimulated sialometry was 0.17mL/min. None of the patients experienced dose-limiting toxicity related to the copaiba solution. Conclusions: Copaiba mouthwash did not trigger dose-limiting toxicity in any of the patients throughout the study, leading to amaximum tolerated dose of 15%, 4 times/day. None of the patients complained of pain or burning related to the use of mouthwash in the absence of oral mucositis lesions, suggesting that it is safe and non-toxic for this use. In this sense, considering the obtained results, the development of a phase II study becomes the next logical step in this research area. Clinical trial information: ID - 34635020.5.0000.5274.

Comparative Analysis of Recurrent Glioblastoma Target Contours via 11C-Methionine, 68Ga-Prostate-Specific Membrane Antigen Positron Emission Tomography, and Magnetic Resonance Imaging: Implications for Precision Radiotherapy Planning

PurposeGlioblastoma (GBM) recurrence poses challenges in radiotherapy treatment planning as reirradiation has limited leeway needing for precise target delineation. Though effective radiotracers are emerging for treatment planning, comparisons of 11C-methionine positron emission tomography (MET-PET), 68Ga-prostate-specific membrane antigen PET (PSMA-PET), and magnetic resonance imaging (MRI) for contouring recurrent GBMs are lacking in the literature. This case study aims to highlight the differences and similarities in target contours delineated from three examinations, aiming to raise doubts about the adequacy of current radiotherapy planning practices. Methods and MaterialsA 37-year-old female patient with recurrent IDH1/2 wild-type GBM underwent MRI, MET-PET, and PSMA-PET scans. Target delineations were performed, and volumes were compared using the Dice Similarity Coefficient (DSC), Conformity Index (CI), and Overlap Volume (OV), considering different planning target volume (PTV) margins. ResultsWe found that MET-PET and MRI volumes showed superior agreement compared to PSMA-PET across all similarity parameters, indicating a more marked discrepancy between PSMA-PET and other modalities. Increasing PTV margins demonstrated progressive convergence in inter-volume discrepancies. Notably, PSMA-PET delineated larger volumes extending beyond MRI-based volumes. ConclusionsThus, MRI alone may not suffice for target delineation in recurrent GBMs. PET imaging modalities offer complementary insights. Combined PET-MRI guidance could improve tumor boundary detection in target delineation for reirradiation. Prospective trials are necessary to ascertain its impact on patient outcomes.

Rapid Selection of Patients Suitable for Deep Inspiration Breath-Hold Using an Automatic Delineating System and RapidPlan Model in Patients With Left Breast Cancer Undergoing Adjuvant Radiation Therapy With IMRT

PurposeThis study aimed to determine whether radiotherapy plans created using an automatic delineating system and a RapidPlan (RP) module could rapidly and accurately predict heart doses and benefit from deep inspiratory breath-hold (DIBH)in left breast cancer patients. Methods and MaterialsOne hundred thirty-six clinically approved free breathing (FB) plans for patients with left breast cancer were included, defined as manual delineation–manual plan (MD–MP). A total of 104/136 plans were selected for RP model training. A total of 32/136 patients were automatically delineated by software, after which the RP generated plans, defined as automatic delineation–RapidPlan (AD–RP). In addition, 40 patients who used DIBH were included to analyze differences in heart benefits from DIBH. ResultsTwo RP models were established for post breast-conserving surgery (BCS) and post modified radical mastectomy (MRM). There were no significant differences in most of the dosimetric parameters between the MD–MP and AD–RP. The heart doses of the two plans were strongly correlated in patients after BCS (0.80 ≤ r ≤ 0.88, P < 0.05) and moderately correlated in patients after MRM (0.46 ≤ r ≤ 0.58, P < 0.05). The RP model predicted the mean heart dose (MHD) within ± 59.67 cGy and ± 63.32 cGy for patients who underwent the two surgeries described above. The heart benefits from DIBH were significantly greater in patients with FB-MHD ≥ 4 Gy than in those with FB-MHD < 4 Gy. ConclusionsThe combined automatic delineation RP model allows for the rapid and accurate prediction of heart dose under FB in patients with left breast cancer. FB-MHD ≥ 4 Gy can be used as a dose threshold to select patients suitable for DIBH.

Cardiac substructure radiation dose study of conventional radiotherapy for stage N2-3 non-small cell lung cancer.

e20071 Background: There has been widespread reporting on predictive dose parameters for cardiac substructures in radiotherapy for non-small cell lung cancer (NSCLC). However, most advanced NSCLC patients are staged as N2-3, and there is a lack of research on the dose distribution, dose contribution and prognosis of the heart in conventional radiotherapy for N2-3 stage NSCLC. Methods: Retrospective analysis of 274 patients of stage N2-3 NSCLC treated with radiotherapy (RT) of prescription dose from 60Gy to 70Gy. Experienced radiation oncologists delineated the cardiac substructures. All patients were categorized according to different lymph node irradiation and tumor spatial locations. Spearman and linear regression were used for variation of dose-volume parameters, as well as the impact of different primary tumor locations and irradiated lymph nodes on the parameters of the entire heart and substructures. Receiver operating characteristic (ROC) curves, Kaplan-Meier, and Cox regression were performed on the influencing factors of adverse cardiac events after radiotherapy and prognosis analysis. Results: There are significant differences in the dose-volume parameters of the whole heart and its substructures. Mean heart doses (MHD),and the mean doses (Dmean) for the left atrium, right atrium, right ventricle, left ventricle and the left anterior descending coronary artery (LAD) were 15.7Gy (range 0.2-30.0Gy), 19.7Gy (range 0.3-55.0Gy), 9.7Gy (range 0.3-59.8Gy), 7.9Gy (range 0.1-48.2Gy), 6.4Gy (range 0.1-52.6Gy) and 5.2Gy (range 0.1-45.0Gy), respectively. The left atrium Dmean has the most significant impact on MHD compared to other substructures (B = 0.418, P &lt; 0.05). Dose-volume parameters of the whole heart and the left atrium were positively correlated with the irradiation of the 7th lymph node region (P &lt; 0.05). MHD and left atrium Dmean for tumors located in the lower region were significantly higher than those in the upper region (P &lt; 0.001). Patients with LAD V30 ≥ 26.9% had a significantly higher risk of mortality compared to those with LAD V30 &lt; 26.9% (P = 0.003, HR = 2.883, 95% CI = 1.436-5.788). Conclusions: With the dose distribution differences among the whole heart and its substructures. We observed the base of the heart received the highest dose, the dose to the left atrium is particularly required attention. The irradiation of different lymph nodes and different primary lesions has an impact on the dose variations of different cardiac structures. LAD V30 is an independent influencing factor of overall survival (OS) for N2-3 stage NSCLC. This study provides considerable information for the dose optimization of cardiac substructure in radiotherapy planning for N2-3 stage NSCLC.

Impact of joint peer review with a specialist radiologist in head and neck cancer radiotherapy planning.

e18059 Background: Head and neck oncology is heavily dependent on interpretation of radiology. This raises the question whether input from radiology should be formally scheduled as part of the radiotherapy contouring processes. Our aim was to assess the impact of this practice through qualitative and quantitative analysis. Methods: H &amp; N patients treated with radiotherapy between May-2022 and August-2023 were reviewed by a specialist HN radiologist. Incidence of changes in T, N, M and TNM-stage, change as defined by The RCR guidance: 'major' (change in gross tumour volume and/or high-dose clinical target volume, dose/fractionation) or 'minor' (change in intermediate or elective dose clinical target volumes or organs at risk), was recorded. We evaluated whether any of these changes were time dependent (Time interval between MDT to RT Peer Review). Other clinical variables: age, gender, primary diagnosis, tumour site, significant incidental findings, post-operative pTNM, post-operative disease status in adjuvant setting on planning imaging (NIRADS), need for additional imaging. We also recorded number of scans reviewed per patient, types of imaging studies reviewed, time taken for review and number of radiologist PA’s required. Retrospective analysis of a prospective database was performed. Results: 410 patients (252-definitive, 137-adjuvant, 21-palliative) were reviewed of which 51.5%-oropharynx followed by 26.8%-Larynx &amp; Hypopharynx. Mean age was 66.14 yrs (SD 11.46) and M:F was 4:1. Baseline and Therapy planning imaging was reviewed for 100% patients of which baseline included: MR (91.7%), CT (96.1%), US (34.1%), PETCT (31%) and therapy planning (62%-CECT, 19%-MR&amp;CT, 15%-CT, 4%-PETCT). In all patients (n=410), T/N/M/TNM-stage percentage upstage was 27/36.8/8.3/42.2% and in definitive cohort (n=252), it was 41.7/56.7/7.1/59.5%. Reviewing RT-planning Imaging in adjuvant cohort (n=137), 76.6% were NIRADS-1, 11.7% NIRADS-3/4/loco-regional disease and 11.7% distant metastasis. T/N/M/TNM-stage upstage was time dependent and the mean time interval between MDT to RT was higher in upstaged patients (p &lt;0.001). Overall percentage change in treatment plan: no/minor/major/palliative was 40.5/33.9/17.3/8.3% and in definitive cohort 30.2/42.1/20.6/7.1%. Change in plan was not dependent on mean time interval between MDT to RT. Average 10 patients (4 imaging studies/patient) were reviewed by radiologist in 1PA (time to review and peer review meeting time). Conclusions: Routine head and neck radiologist input in radiotherapy peer review is feasible and resulted in a number of major and minor changes to treatment. Inputs not only eased the contouring for oncologists but also lead to updating of current disease stage just prior to treatment. Overall, our results suggest that this is a practice changing step in the radiotherapy workflow which has a direct impact on patient management.

Human-like intelligent automatic treatment planning of head and neck cancer radiation therapy

Objective. Automatic treatment planning of radiation therapy (RT) is desired to ensure plan quality, improve planning efficiency, and reduce human errors. We have proposed an Intelligent Automatic Treatment Planning framework with a virtual treatment planner (VTP), an artificial intelligence robot built using deep reinforcement learning, autonomously operating a treatment planning system (TPS). This study extends our previous successes in relatively simple prostate cancer RT planning to head-and-neck (H&N) cancer, a more challenging context even for human planners due to multiple prescription levels, proximity of targets to critical organs, and tight dosimetric constraints. Approach. We integrated VTP with a real clinical TPS to establish a fully automated planning workflow guided by VTP. This integration allowed direct model training and evaluation using the clinical TPS. We designed the VTP network structure to approach the decision-making process in RT planning in a hierarchical manner that mirrors human planners. The VTP network was trained via the Q-learning framework. To assess the effectiveness of VTP, we conducted a prospective evaluation in the 2023 Planning Challenge organized by the American Association of Medical Dosimetrists (AAMD). We extended our evaluation to include 20 clinical H&N cancer patients, comparing the plans generated by VTP against their clinical plans. Main results. In the prospective evaluation for the AAMD Planning Challenge, VTP achieved a plan score of 139.08 in the initial phase evaluating plan quality, and 15 min of planning time with the first place ranking in the adaptive phase competing for planning efficiency while meeting all plan quality requirements. For clinical cases, VTP-generated plans achieved an average VTP score of 125.33±11.12 , which outperformed the corresponding clinical plans with an average score of 117.76±13.56 . Significance. We successfully integrated VTP with the clinical TPS to achieve a fully automated treatment planning workflow. The compelling performance of VTP demonstrated its potential in automating H&N cancer RT planning.

Deep learning based linear energy transfer calculation for proton therapy

Objective. This study aims to address the limitations of traditional methods for calculating linear energy transfer (LET), a critical component in assessing relative biological effectiveness (RBE). Currently, Monte Carlo (MC) simulation, the gold-standard for accuracy, is resource-intensive and slow for dose optimization, while the speedier analytical approximation has compromised accuracy. Our objective was to prototype a deep-learning-based model for calculating dose-averaged LET (LETd) using patient anatomy and dose-to-water (DW) data, facilitating real-time biological dose evaluation and LET optimization within proton treatment planning systems. Approach. 275 4-field prostate proton Stereotactic Body Radiotherapy plans were analyzed, rendering a total of 1100 fields. Those were randomly split into 880, 110, and 110 fields for training, validation, and testing. A 3D Cascaded UNet model, along with data processing and inference pipelines, was developed to generate patient-specific LETd distributions from CT images and DW. The accuracy of the LETd of the test dataset was evaluated against MC-generated ground truth through voxel-based mean absolute error (MAE) and gamma analysis. Main results. The proposed model accurately inferred LETd distributions for each proton field in the test dataset. A single-field LETd calculation took around 100 ms with trained models running on a NVidia A100 GPU. The selected model yielded an average MAE of 0.94 ± 0.14 MeV cm−1 and a gamma passing rate of 97.4% ± 1.3% when applied to the test dataset, with the largest discrepancy at the edge of fields where the dose gradient was the largest and counting statistics was the lowest. Significance. This study demonstrates that deep-learning-based models can efficiently calculate LETd with high accuracy as a fast-forward approach. The model shows great potential to be utilized for optimizing the RBE of proton treatment plans. Future efforts will focus on enhancing the model’s performance and evaluating its adaptability to different clinical scenarios.

Prompt-gamma track-length estimator with time tagging from proton tracking

The design of prompt-gamma detectors necessitates numerous Monte Carlo simulations to precisely develop and optimize the detection stages in proton therapy. Alongside the advancement of MC simulations, various variance reduction methods have been explored to speed-up calculations. Among these techniques, track-length estimators are interesting scoring methods for achieving both speed and accuracy in Monte Carlo simulations of rare events. This paper introduces an extension of the GATE vpgTLE module that incorporates the prompt-gamma emission time, which is tagged from the proton tracking, enhancing its utility for studies focused on detector design and optimization that rely on time measurements. The results obtained from a clinical radiotherapy plan are presented. We demonstrate that the new vpgTLE tally with time tagging is accurate, except for certain prompt-gamma lines corresponding to long mean-life nuclei.

Modulated Arc Therapy for hippocampal-avoidance whole brain radiation therapy: planning comparison with intensity modulated Radiation Therapy.

This study aimed to evaluate the modulated arc therapy (mARC) technique as a planning and treatment option for hippocampal sparing whole brain radiotherapy (HS-WBRT) following the Radiation Therapy Oncology Group (RTOG) 0933 dosimetric criteria. Computed tomography (CT) and magnetic resonance imaging (MRI) were selected retrospectively for 15 patients. Two types of plans were created for each patient, namely an intensity-modulated radiation therapy (IMRT) and a mARC plan. IMRT and mARC plans were compared in terms of plan quality indices, absorbed dose to organs at risk (OARs), number of monitor units (MUs), and treatment time. All plans in both techniques were considered clinically acceptable for treatment. However, IMRT plans presented a higher conformity (p = 0.01) as well as a higher homogeneity as compared to mARC plans, but this difference was not statistically significant (p > 0.05). In terms of the preservation of the hippocampus, it was observed that the IMRT plans achieved significantly lower doses for both 100% of its volume and for its maximum dose (p < 0.001). The evaluation of the remaining OARs showed that the IMRT technique resulted in lower doses, and significant differences were observed for the following organs: left cochlea (p < 0.001), left eye (p < 0.001), right eye (p = 0.03), both lenses of the eye (p < 0.001), and right optic nerve (p = 0.02). Despite these differences, the absolute differences in all dosimetric parameters were low enough to bear any clinical relevance. A drastic (close to 65%) and significant (p < 0.001) decrease was observed in the number of MUs for the mARC plans. This resulted in a substantial decrease in treatment time (60.45%, p < 0.001). It is concluded that the mARC technique is a feasible planning and treatment solution for HS-WBRT that meets the RTOG 0933 criteria. The main advantage of using mARC over IMRT for HS-WBRT is the considerable reduction in MUs and treatment time.

Factors associated with acute esophagitis during radiation therapy for lung cancer

IntroductionLimiting acute esophagitis remains a clinical challenge during the treatment of locally advanced non-small cell lung cancer (NSCLC). MethodsDemographic, dosimetric, and acute toxicity data were prospectively collected for patients undergoing definitive radiation therapy +/- chemotherapy for stage II-III NSCLC from 2012 to 2022 across a statewide consortium. Logistic regression models were used to characterize the risk of grade 2 + and 3 + esophagitis as a function of dosimetric and clinical covariates. Multivariate regression models were fitted to predict the 50 % risk of grade 2 esophagitis and 3 % risk of grade 3 esophagitis. ResultsOf 1760 patients, 84.2 % had stage III disease and 85.3 % received concurrent chemotherapy. 79.2 % of patients had an ECOG performance status ≤ 1. Overall rates of acute grade 2 + and 3 + esophagitis were 48.4 % and 2.2 %, respectively. On multivariate analyses, performance status, mean esophageal dose (MED) and minimum dose to the 2 cc of esophagus receiving the highest dose (D2cc) were significantly associated with grade 2 + and 3 + esophagitis. Concurrent chemotherapy was associated with grade 2 + but not grade 3 + esophagitis. For all patients, MED of 29 Gy and D2cc of 61 Gy corresponded to a 3 % risk of acute grade 3 + esophagitis. For patients receiving chemotherapy, MED of 22 Gy and D2cc of 50 Gy corresponded to a 50 % risk of acute grade 2 + esophagitis. ConclusionsPerformance status, concurrent chemotherapy, MED and D2cc are associated with acute esophagitis during definitive treatment of NSCLC. Models that quantitatively account for these factors can be useful in individualizing radiation plans.

Radiotherapy Plan Quality Assurance in NRG Oncology Trials for Brain and Head/Neck Cancers: An AI-Enhanced Knowledge-Based Approach.

The quality of radiation therapy (RT) treatment plans directly affects the outcomes of clinical trials. KBP solutions have been utilized in RT plan quality assurance (QA). In this study, we evaluated the quality of RT plans for brain and head/neck cancers enrolled in multi-institutional clinical trials utilizing a KBP approach. The evaluation was conducted on 203 glioblastoma (GBM) patients enrolled in NRG-BN001 and 70 nasopharyngeal carcinoma (NPC) patients enrolled in NRG-HN001. For each trial, fifty high-quality photon plans were utilized to build a KBP photon model. A KBP proton model was generated using intensity-modulated proton therapy (IMPT) plans generated on 50 patients originally treated with photon RT. These models were then applied to generate KBP plans for the remaining patients, which were compared against the submitted plans for quality evaluation, including in terms of protocol compliance, target coverage, and organ-at-risk (OAR) doses. RT plans generated by the KBP models were demonstrated to have superior quality compared to the submitted plans. KBP IMPT plans can decrease the variation of proton plan quality and could possibly be used as a tool for developing improved plans in the future. Additionally, the KBP tool proved to be an effective instrument for RT plan QA in multi-center clinical trials.

Dynamic CBCT imaging using prior model-free spatiotemporal implicit neural representation (PMF-STINR)

Objective. Dynamic cone-beam computed tomography (CBCT) can capture high-spatial-resolution, time-varying images for motion monitoring, patient setup, and adaptive planning of radiotherapy. However, dynamic CBCT reconstruction is an extremely ill-posed spatiotemporal inverse problem, as each CBCT volume in the dynamic sequence is only captured by one or a few x-ray projections, due to the slow gantry rotation speed and the fast anatomical motion (e.g. breathing). Approach. We developed a machine learning-based technique, prior-model-free spatiotemporal implicit neural representation (PMF-STINR), to reconstruct dynamic CBCTs from sequentially acquired x-ray projections. PMF-STINR employs a joint image reconstruction and registration approach to address the under-sampling challenge, enabling dynamic CBCT reconstruction from singular x-ray projections. Specifically, PMF-STINR uses spatial implicit neural representations to reconstruct a reference CBCT volume, and it applies temporal INR to represent the intra-scan dynamic motion of the reference CBCT to yield dynamic CBCTs. PMF-STINR couples the temporal INR with a learning-based B-spline motion model to capture time-varying deformable motion during the reconstruction. Compared with the previous methods, the spatial INR, the temporal INR, and the B-spline model of PMF-STINR are all learned on the fly during reconstruction in a one-shot fashion, without using any patient-specific prior knowledge or motion sorting/binning. Main results. PMF-STINR was evaluated via digital phantom simulations, physical phantom measurements, and a multi-institutional patient dataset featuring various imaging protocols (half-fan/full-fan, full sampling/sparse sampling, different energy and mAs settings, etc). The results showed that the one-shot learning-based PMF-STINR can accurately and robustly reconstruct dynamic CBCTs and capture highly irregular motion with high temporal (∼ 0.1 s) resolution and sub-millimeter accuracy. Significance. PMF-STINR can reconstruct dynamic CBCTs and solve the intra-scan motion from conventional 3D CBCT scans without using any prior anatomical/motion model or motion sorting/binning. It can be a promising tool for motion management by offering richer motion information than traditional 4D-CBCTs.

Nomogram for radiation-induced lymphopenia in patients receiving intensity-modulated radiotherapy based-chemoradiation therapy for newly diagnosed glioblastoma: A multi-institutional study

PurposeSevere lymphopenia (SLP) has emerged as a significant prognostic factor in glioblastoma. Intensity-modulated radiation therapy (IMRT)-based radiation therapy (RT) is suggested to minimize the risk of SLP. This study aimed to evaluate SLP incidence based on multi-institutional database in patients with GBM treated with IMRT and develop a predictive nomogram. Patients and methodsThis retrospective study reviewed data from 348 patients treated with IMRT-based concurrent chemoradiation therapy (CCRT) at two major hospitals from 2016 to 2021. After multivariate regression analysis, a nomogram was developed and internally validated to predict SLP risk. ResultsDuring treatment course, 21.0% of patients developed SLP and SLP was associated with poor overall survival outcomes in patients with GBM. A newly developed nomogram, incorporating gender, pre-CCRT absolute lymphocyte count, and brain mean dose, demonstrated fair predictive accuracy (AUC 0.723). ConclusionsThis study provides the first nomogram for predicting SLP in patients with GBM treated with IMRT-based CCRT, with acceptable predictive accuracy. The findings underscore the need for dose optimization and radiation planning to minimize SLP risk. Further external validation is crucial for adopting this nomogram in clinical practice.