Organs At Risk Research Articles

Planning Benchmark Study for Stereotactic Body Radiation Therapy of Pancreas Carcinomas With Simultaneously Integrated Boost and Protection: Results of the DEGRO/DGMP Working Group on Stereotactic Radiation Therapy and Radiosurgery

The proximity or overlap of planning target volume (PTV) and organs-at-risk (OARs) poses a major challenge in stereotactic body radiation therapy (SBRT) of pancreatic cancer (PACA). This international treatment planning benchmark study investigates whether simultaneous integrated boost (SIB) and simultaneous integrated protection (SIP) concepts in PACA SBRT can lead to improved and harmonized plan quality. A multiparametric specification of desired target doses (gross target volume [GTV]D50%, GTVD99%, PTVD95%, and PTV0.5cc) with 2 prescription doses of GTVD50% = 5 × 9.2Gy (46 Gy) and GTVD50% = 8 × 8.25 Gy (66 Gy) and OAR limits were distributed with planning computed tomography and contours from 3 PACA patients. In phase 1, plans were ranked using a scoring system for comparison of trade-offs between GTV/PTV and OAR. In phase 2, replanning was performed for the most challenging case and prescription with dedicated SIB and SIP contours provided for optimization after group discussion. For all 3 cases and both phases combined, 292 plans were generated from 42 institutions in 5 countries using commonly available treatment planning systems. The GTVD50% prescription was performed by only 76% and 74% of planners within 2% for 5 and 8 fractions, respectively. The GTVD99% goal was mostly reached, while the balance between OAR and target dose showed initial SIB/SIP-like optimization strategies in about 50% of plans. For plan ranking, 149 and 217 score penalties were given for 5 and 8 fractions, pointing to improvement possibilities. For phase 2, the GTVD50% prescription was performed by 95% of planners within 2%, and GTVD99% as well as OAR doses were better harmonized with notable less score penalties. Fourteen of 19 planners improved their plan rank, 9 of them by at least 2 ranks. Dedicated SIB/SIP concepts in combination with multiparametric prescriptions and constraints can lead to overall harmonized and high treatment plan quality for PACA SBRT. Standardized SIB/SIP treatment planning in multicenter clinical trials appears feasible after group consensus and training.

Dose prediction for cervical cancer in radiotherapy based on the beam channel generative adversarial network

BackgroundExisting deep learning methods, such as generative adversarial network (GAN) technology, face challenges when dealing with mixed datasets, which involve a combination of Intensity Modulated Radiotherapy (IMRT) and Volumetric Modulated Arc Therapy (VMAT). This issue significantly complicates the application of dose prediction in the field of radiotherapy. In this study, we propose a novel approach called beam channel GAN (Bc-GAN) to address the task of radiation dose prediction for mixed datasets. Bc-GAN introduces a dose prediction calculation method that requires less precision. By defining an approximate range for dose prediction, Bc-GAN limits the physical range of GAN prediction, resulting in more reasonable dose distribution predictions. MethodsWe adopt a beam angle weighting method to determine the beam angle in the dose calculation. The dose of the beam with the highest weight is calculated using medical images and is then inputted into the artificial intelligence dose prediction model as the input channel. Additionally, we collect data from a total of 346 patients with Cervical Cancer (CC) for dataset. After cleaning the data, we exclude 51 cases with incomplete organ delineation, leaving us with 295 cases (IMRT: VMAT = 137:158) randomly divided into three sets: the training set, the validation set, and the test set, with proportions of 205:60:30, respectively. The assessment of model predictions was conducted via an analysis of dose distributions on the tomographic plane, dose volume histogram (DVH), and dosimetric parameters within the target zones and organs at risk (OAR). ResultsAfter DVH analysis, minimal discrepancy was found between predicted and actual dose distributions in PTV and OAR. The predicted distribution aligned with clinical standards. Dosimetric parameters for PTV were generally lower in the predicted model, except for homogeneity index (HI) (0.238 ± 0.024, P = 0.017) and Dmax (53.599 ± 0.710 Gy, P = 1.8e-05). The prediction model varied in estimating doses for six organs. Specifically, small intestine showed higher V20 (67.92 ± 51.64 %, P = 0.019) and V30 (57.171 ± 1.213 %, P = 0.024) than manual planning. A similar trend was seen in colon's V30 (37.13 ± 61.14 %, P = 0.016). However, predicted bladder V30 (87.51 ± 41.44 %, P = 2.03e-16) was lower, indicating significant dosimetric differences. ConclusionOverall, this study presents an innovative prediction method for CC in radiotherapy using the Bc-GAN model, addressing the challenges posed by different radiotherapy techniques. The proposed approach allows IMRT and VMAT in radiotherapy to be used as training sets, enabling the potential for large-scale engineering and commercialization applications of artificial intelligence (AI). The Bc-GAN-based prediction method for CC in radiotherapy not only reduces the amount of data needed for the training set but also expedites the model generation process. This approach can be applied to guide the development of clinical radiation therapy plans. Furthermore, future studies should consider extending the dose prediction method to encompass other types of tumors.

Multimodal Image Confidence: A Novel Method for Tumor and Organ Boundary Representation

BackgroundThe ambiguous boundaries of tumors and organs at risk (OARs) seen in medical images pose challenges in treatment planning and other tasks in radiotherapy. MethodsThis study introduces an innovative analytical algorithm, Multi-Modal Image Confidence (MMC), which exploits the collective strengths of complementary multi-modal medical images to determine a confidence measure for each voxel belonging to the region of interest (ROI). MMC facilitates the creation of modality-specific ROI-enhanced images, enabling a detailed representation of the ROI's boundaries and internal features. By employing an interpretable mathematical model that propagates voxel confidence based on inter-voxel correlations, MMC avoids the need for model training, distinguishing it from deep learning (DL)-based methods. ResultsThe performance of the proposed algorithm was qualitatively and quantitatively evaluated using 156 nasopharyngeal carcinoma cases and 1251 glioma cases. Qualitative assessments underscored the accuracy of MMC and ROI-enhanced images in estimating lesion boundaries and capturing internal tumor characteristics. Quantitative analyses revealed strong agreement between MMC and manual delineations. ConclusionThis paper introduces a novel analytical algorithm to identify and depict ROI boundaries based on complementary multi-modal 3D medical images. The applicability of the proposed method can extend to both targets and OARs at diverse anatomical sites across multiple image modalities, amplifying its potential for augmenting radiotherapy-related tasks.

Evaluation and Comparison of the Dose Received by the Mandible, Maxilla, and Teeth in Two Methods of Three-dimensional Conformal Radiation Therapy and Helical Tomotherapy.

Using three-dimensional conformal radiation treatment (3D-CRT) and helical tomotherapy (HT), this study examines and contrasts the dosage received by the mandible, maxilla, and teeth. Sixteen patients with head-and-neck cancer (H and NC) were the subject of treatment planning at the Seyyed Al-Shohada Hospital in Isfahan, Iran. This study examined target coverage quality, exposure of healthy tissue, and radiation delivery effectiveness. In terms of a number of measures, including D2%, D50%, Dmean, V95%, conformity index (CI), and homogeneity index (HI) for the planning target volume (PTV) and D2%, D98%, Dmean, V95%, CI, and HI for the nodal PTV, HT showed considerable gains over 3D-CRT. The brainstem, D1cc, and D10cc received considerably lower maximum dosages in HT. Measurements of the right and left cochleas (Dmean, V55, and Dmax) revealed decreases in HT, with Dmean revealing the most significant variations. The Dmean and Dmax values for HT significantly decreased in constrictors as well. In terms of several HT-related indicators, the larynx, optic chiasm, optic nerves, oral cavity, mandible, thyroid, and parotid glands all showed considerable decreases. The findings of the comparison of the two treatment approaches revealed that the HT method was more than 50% more effective than the 3D-CRT method in sustaining organs at risk (OARs) and the target volume dose. In general, dosimetric coverage, homogeneity, conformity indices, and the absence of cold and hot patches showed that HT produced targets with greater accuracy than 3D-CRT. In addition, HT outperformed 3D-CRT in protecting important structures (OARs). HT as a result has the potential to be a more effective method of treatment for those with H and NC and involvement of regional lymph nodes.

The Current use of Adaptive Strategies for External Beam Radiotherapy in Cervical Cancer: A Systematic Review

AimsVariability in the target and organs at risk (OARs) in cervical cancer treatment presents challenges for precise radiotherapy. Adaptive radiotherapy (ART) offers the potential to enhance treatment precision and outcomes. However, the increased workload and a lack of consensus on the most suitable ART approach hinder its clinical adoption. This systematic review aims to assess the current use of adaptive strategies for cervical cancer and define the optimal approach. Materials and methodsA systematic review of current literature published between January 2012 and May 2023 was conducted. Searches used PubMed/Medline, Cochrane Library, and Web of Science databases, supplemented with the University of Manchester, Google Scholar, and papers retrieved from reference lists. The review assessed workflows, compared dosimetric benefits, and examined resources for each identified strategy. Excluded were abstracts, conference abstracts, reviews, articles unrelated to ART management, proton therapy, brachytherapy, or qualitative studies. A narrative synthesis involved data tabulation, summarizing selected studies detailing workflow for cervical cancer and dosimetric outcomes for targets and OARs. ResultsSixteen articles met the inclusion criteria; these were mostly retrospective simulation planning studies, except four studies that had been clinically implemented. We identified five approaches for ART radiotherapy for cervical cancer: reactive and scheduled adaptation, internal target volume (ITV)-based approach using library of plans (LOP), fixed-margin approach using LOP, and real-time adaptation, with each approach reducing irradiated volumes without compromising target coverage compared to the non-ART approach. The LOP-based ITV approach is the most used and clinically assessed. ConclusionIdentifying the optimal strategy is challenging due to dosimetric assessment limitations. Implementing cervical cancer ART necessitates strategic optimization of clinical benefits and resources through research, including studies to identify the optimal frequency, and prospective evaluations of toxicity.

Reirradiation of Utracentrally Located Thoracic Tumors Using a 10-Fraction Hypofractionated Stereotactic Body Radiation Therapy Course: A Detailed Dosimetric Analysis

PurposeThere is very little information detailing outcomes and toxicity following re-irradiation for ultracentrally located thoracic tumors, and detailed dosimetric data is non-existent. This data is critical for the safe management of these extremely difficult cases. Materials and MethodsThe records of fifteen individuals undergoing 10-fraction hypofractionated stereotactic body radiotherapy (hfSBRT) for the management of ultracentrally located thoracic tumors between 2009 and 2020 at a single institution were retrospectively reviewed. Treatment outcomes and toxicity were analyzed. A detailed dosimetric analysis of treatment plans and centrally located organs at risk (OARs), from the initial, re-irradiation, and cumulative radiotherapy courses was presented. ResultsAt a median follow up of 10 months, one- and three-year overall survival (OS), progression free survival (PFS) and local control (LC) were 52% and 28%, 33% and 28%, and 76% and 61%, respectively. Treatment related adverse events were low with 5 individuals (33%) developing ≥ grade 2 pneumonitis (Grade 2 = 4, Grade 3 = 1). Dosimetric parameters were not associated with the development of clinically relevant pneumonitis. No adverse events involving central OARs (esophagus, great vessels, primary bronchial tree) were identified. Median cumulative mean lung dose (MLD) was 24 Gy (EQD2) (range: 10-33 Gy), with a V20 of 33% (range: 11-51%). Median esophageal, primary bronchial tree, and great vessel maximum doses (Dmax) were 93.2 Gy (EQD2) (range: 50-148 Gy), 163 Gy (range: 77-204 Gy), and 191 Gy (range: 129-262 Gy), respectively. ConclusionsThe current investigation is the first to provide detailed cumulative dosimetric data from a cohort of patients comprised entirely of ultracentrally located thoracic tumors. Despite unfavorable anatomic tumor location given an intimate association to critical OARs, delivering an ablative dose with a 10-fraction hfSBRT course can serve as a feasible option for these challenging cases.

Treatment plan quality for stereotactic treatment of multiple cranial metastases: Comparison of C-arm and O-ring treatment platforms

C-arm linacs have been used widely to treat multiple cranial metastases using stereotactic radiosurgery (SRS). A new generation of O-ring linacs offer several workflow advantages when compared to C-arm platforms. However, O-ring linacs are not able to employ couch rotations for noncoplanar beams used in SRS treatments. This study was conducted in order to simulate further possible developments of O-ring treatment units by assessing their geometrical efficiency. In this work we compare the plan quality for C-arm versus an O-ring platform including metrics that are relevant to SRS for multiple metastases. The comparison is conducted by incorporating tilted arcs on the O-ring platform therefore introducing noncoplanarity.Total 40 patients previously treated for SRS with 20 Gy single fraction were replanned for C-arm with a standard noncoplanar 5-arc arrangement and O-ring with both coplanar and noncoplanar beams. For the O-ring plans, we considered a default 3-arc coplanar arrangement, as well as 3- and 5-arc arrangements with arcs tipped up to 10 degrees from the axial plane. Target coverage, organ-at-risk (OAR) doses, monitor unit (MU) efficiency, conformity and gradient indices were assessed for all plans.For most metrics the O-ring geometries, even the coplanar arrangement, produced statistically comparable results to the C-arm. Small but significant differences were found for the 3 arc O-ring for PTV: D90%, D2% and MU/Gy and for the 5 arc O-ring at D2% when both were compared to the C-arm. Cumulative dose volume histograms (DVHs) for normal brain showed a cross-over between the C-arm and coplanar O-ring geometry at a low dose (2.3 ± 1.8 Gy), with O-ring associated with higher volumes above this cross-over dose. However, no statistical difference was seen in the brainstem, optic pathway and volumes of normal brain receiving 12 Gy or 20 Gy.This study has found that O-ring geometry linacs can produce SRS plans of comparable quality to those from a C-arm for multiple cranial metastases.

In Silico Study of Simultaneous Integrated Boost Carbon-Ion Radiotherapy for Locally Advanced Pancreatic Cancer.

Carbon-ion radiotherapy (CiRT) has been used for the treatment of locally advanced pancreatic cancer (LAPC) with uniform dose plan. The aim of the present study is to investigate the effectiveness of a simultaneous integrated boost (SIB) technique with scanned CiRT against LAPC. Data of 21 patients with LAPC were used to compare two treatment planning approaches: a conventional uniform dose approach and a SIB approach. A relative biological effectiveness (RBE)-weighted dose (DRBE) of 55.2 Gy (RBE) in 12 fractions was prescribed to the planning target volume (PTV) in the conventional approach. In the SIB approach, DRBE of 67.2 Gy (RBE) and 43.2 Gy (RBE) in 12 fractions were prescribed to a high-risk PTV (HR-PTV) and low-risk PTV (LR-PTV), respectively. The DRBE and dose-averaged linear energy transfer (LETd) of targets and gastrointestinal tracts as organs at risk (OARs) were evaluated. The HR-PTV D90% and LR-PTV D90% were 64.4±0.6 and 42.5±0.1 Gy (RBE) in SIB approach compared to the PTV D90% of 54.1±0.4 Gy (RBE) in the conventional approach. All SIB plans achieved the D2cc lower than 46 Gy (RBE) and V30 lower than 4 cm3 within OARs. The SIB approach increased the minimum LETd within the GTV to 44 keV/μm or higher for 20 out of 21 patients as compared to 16 out of 21 patients in the conventional approach. The SIB approach effectively increased the RBE-weighted dose and LETd within the HR-PTV and GTV by accumulating the high-LET stopping carbon-ions into the HR-PTV in addition to the decreased RBE-weighted dose to OARs.

Artificial intelligence-based motion tracking in cancer radiotherapy: A review.

Radiotherapy aims to deliver a prescribed dose to the tumor while sparing neighboring organs at risk (OARs). Increasingly complex treatment techniques such as volumetric modulated arc therapy (VMAT), stereotactic radiosurgery (SRS), stereotactic body radiotherapy (SBRT), and proton therapy have been developed to deliver doses more precisely to the target. While such technologies have improved dose delivery, the implementation of intra-fraction motion management to verify tumor position at the time of treatment has become increasingly relevant. Artificial intelligence (AI) has recently demonstrated great potential for real-time tracking of tumors during treatment. However, AI-based motion management faces several challenges, including bias in training data, poor transparency, difficult data collection, complex workflows and quality assurance, and limited sample sizes. This review presents the AI algorithms used for chest, abdomen, and pelvic tumor motion management/tracking for radiotherapy and provides a literature summary on the topic. We will also discuss the limitations of these AI-based studies and propose potential improvements.

Comparison of two different VMAT radiotherapy TPSs for pancreatic cancer using flattening filter free photon beam energy

BackgroundPancreatic cancer is a devastating disease with a poor prognosis, and radiation therapy plays a crucial role in its treatment and management. Conventional radiation therapy (RT) techniques have limitations in delivering adequate doses to the tumor while sparing surrounding normal tissues. However, modern RT techniques such as intensity-modulated radiation therapy (IMRT), volumetric modulated arc therapy (VMAT), and stereotactic body radiation therapy (SBRT) have led to the development of novel approaches that can reduce toxicity. The incorporation of advanced imaging modalities, like four-dimensional computed tomography (4D-CT) and magnetic resonance imaging (MRI), enables enhancement of tumor control and improves conformality and treatment outcomes. Additionally, using flattening filter-free (FFF) beams can further enhance treatment efficiency and efficacy. PurposeThis study aims to compare two different VMAT techniques using two different treatment planning systems (TPSs), Monaco and Eclipse, in the treatment of pancreatic cancer II stage infiltrating duct carcinoma patients using an FFF photon beam. Materials and methods20 pancreatic cancer II stage infiltrating duct carcinoma patients were retrospectively analyzed, and each patient's plans were designed using the two TPSs. The dose distribution of the target using 6 MV FFF for TrueBeam-Varian and organs at risk (OARs) were compared. The monitor unit (MU), treatment time, conformity (CI), and homogeneity (HI) indices were also evaluated. ResultsFor pancreatic cancer patients, the mean dose of the planning target volume (PTV) in the Monaco plan was lower than the Eclipse plan. The plan evaluation parameters in Monaco and Eclipse were similar without significant differences (p-value = 0.152). The Monaco plan was better than the Eclipse plan regarding mean dose and V15Gy of the kidneys; the spinal cord was lowest in the Monaco plan, and the maximum dose and V45Gy of the spinal cord were 592.1 cGy and 1.37% lower than the Eclipse plan, respectively. ConclusionThe VMAT Monaco plan is a favorable TPS for pancreatic cancer patients, providing improved sparing of critical organs while maintaining adequate target coverage.

Hippocampal-Sparing Radiation Therapy in Primary Sinonasal and Cutaneous Tumors of the Head and Neck

Patients with primary sinonasal and cutaneous head and neck (H&N) malignancies often receive meaningful radiation dose to their hippocampi, but this not a classic avoidance structure in radiation planning. We aimed to characterize the feasibility and tradeoffs of hippocampal-sparing radiation therapy (HSRT) for patients with primary sinonasal and cutaneous H&N malignancies. We retrospectively selected patients who were treated definitively for primary sinonasal or cutaneous malignancies of the H&N at an academic medical center. All received (chemo)radiation alone or adjuvantly and substantial radiation dose to 1 or both hippocampi. We created new HSRT plans for each patient with intensity modulated radiation therapy using the original target and organ-at-risk (OAR) volumes. Hippocampi were contoured based on Radiation Therapy Oncology Group guidelines and reviewed by a neuroradiologist. Absolute and relative differences in radiation dose to the hippocampi, planning target volumes (PTVs), and OARs were recorded and compared. There were 18 sinonasal and 12 cutaneous H&N primary tumors (30 patients in total). Median prescription dose was 6600 cGy (range, 5000-7440 cGy), and 14 of the 30 patients received 120 cGy/fraction twice daily, 13 of the 30 patients received 200 cGy/fraction once daily, whereas others received 180-275 cGy/fraction once daily. The relative decrease in ipsilateral hippocampal Dmax and D100% using HSRT was 44% (median, 2009 cGy from 3586 cGy) and 65% (median 434 cGy from 1257 cGy), respectively. There were no statistically significant or clinically meaningful differences in PTV V100%, PTV D1%, or radiation dose to other OARs between HSRT and non-HSRT plans. HSRT is feasible and results in meaningful dose reduction to the hippocampi without reducing PTV coverage or increasing dose to other OARs. We suggest target hippocampal constraints of Dmax < 1600 cGy and D100% < 500 cGy when feasible (without compromising PTV coverage or impacting other critical OARs). The clinical significance of HSRT in patients with primary H&N tumors should be investigated prospectively.

A novel x-Ray and γ-Ray combination strategy for radiotherapy after breast-conserving surgery in patients with right breast cancer.

Radiotherapy is a primary therapeutic approach for breast cancer following breast-conserving surgery. The TaiChiB dual-modality radiotherapy system combining X-ray and focused γ-ray, offers a new approach to reduce the radiation dose of organs at risk (OARs) and has the potential to mitigate the adverse effects of radiotherapy. Currently, there are few studies on the dosimetric characteristics of the TaiChiB dual-modality system for actual treatment plans for specific diseases. The purpose of this work is to study the dosimetric advantages of dual-modal systems for right breast patients after breast-conserving surgery. Treatment plans for 20 patients with right breast cancer were generated for a linear accelerator (LINAC) based system and the TaiChiB dual-modality system, respectively. Volumetric modulated arc therapy plans with simultaneous integrated boost (VMAT-SIB) were made for the LINAC. Focused γ-ray was used to deliver the boost dose with the dual-modality system. The dosimetric parameters of the target and OARs were evaluated and compared between the treatment plans generated for the two systems. The TaiChiB dual-modality plans exhibit a higher conformal index (CI) and lower gradient index (GI) for the PGTV and PTV compared with the LINAC-based VMAT-SIB plans. Compared to VMAT-SIB plans, the PTV Dmax, PTV Dmean, PTV V110, PGTV Dmax, and PGTV Dmean of the TaiChiB dual-modality plans are significantly lower. Meanwhile, the dose to OARs, such as the Dmean of the heart, the V5 of liver, the Dmean of ipsilateral lung, the V30 of ipsilateral lung, the V20 of ipsilateral lung, the V5 of ipsilateral lung, the Dmean of contralateral lung, Dmax of contralateral breast and the Dmean of contralateral breast are significantly reduced. Our study demonstrates the dosimetric advantages of the novel TaiChiB dual-modality radiotherapy system for the treatment of right-sided breast cancer. Overall, for the TaiChiB dual-modality radiotherapy system, the radiation dose outside the target region decreases rapidly, thereby minimizing radiation exposure to neighboring organs and ensuring the conformity of the target area. Our research confirms the potential of the TaiChiB dual-modality system for future radiotherapy.

Factors Affecting the Effectiveness of DIBH (Deep Inspiratory Breath Hold) in Patients with Left Breast Cancer: A Narrative Review

Deep Inspiratory Breath Hold (DIBH) has become a valuable technique in left-breast cancer radiotherapy, offering the possibility to reduce radiation exposure to organs at risks (OARs) and minimize the risk of cardiac complications. This treatment method involves stopping the breathing of patients during irradiation in order to temporarily distance the heart from the radiation field, which reduces potential cardiac risks and other complications. To identify factors that may affect the effectiveness of DIBH treatment, we analyzed the most important 5-year studies published in the PubMed database. Research shows that DIBH reduces the radiation dose to the heart and lungs. However, the effectiveness of DIBH is determined by a variety of factors, including the patient’s training, cooperation, anatomical features, age, and choice of radiotherapy technique. Additionally, cardiovascular risk factors, such as diabetes, smoking, and hypertension, can be impactful to the effectiveness and potential complications of DIBH. Moreover, if a patient has a substantial level of depression or anxiety, then they may be potentially disqualified from the DIBH treatment method. In addition to this, a lack of consent and/or fear may also disqualify a patient from DIBH treatment. Careful patient selection, comprehensive training, and optimization of treatment parameters are essential to maximize the benefits of DIBH whilst minimizing any potential side effects. DIBH enhancement techniques, such as IMRT and VMAT, also have an important role to play. The purpose of this narrative review article is to summarize the factors affecting the efficacy and side effects of DIBH in radiation therapy for left-breast cancer, with the aim of optimizing its clinical application while minimizing side effects. Patients who are likely to benefit most from DIBH are young women in good medical condition, able to cooperate with the procedure, and with smaller breasts. The increase in the estimated 10-year patient survival is significantly influenced by cardiovascular problems, so patients without diabetes and metabolic syndrome, and non-smokers, will benefit the most. An estimated 50–70% of breast cancer patients are likely to benefit from DIBH, and in the best case, it can result in a 50% reduction in the risk of cardiac problems after photodynamic therapy (PDT).

FA-Net: A hierarchical feature fusion and interactive attention-based network for dose prediction in liver cancer patients

Dose prediction is a crucial step in automated radiotherapy planning for liver cancer. Several deep learning-based approaches for dose prediction have been proposed to enhance the design efficiency and quality of radiotherapy plan. However, these approaches usually take CT images and contours of organs at risk (OARs) and planning target volume (PTV) as a multi-channel input and is thus difficult to extract sufficient feature information from each input, which results in unsatisfactory dose distribution. In this paper, we propose a novel dose prediction network for liver cancer based on hierarchical feature fusion and interactive attention. A feature extraction module is first constructed to extract multi-scale features from different inputs, and a hierarchical feature fusion module is then built to fuse these multi-scale features hierarchically. A decoder based on attention mechanism is designed to gradually reconstruct the fused features into dose distribution. Additionally, we design an autoencoder network to generate a perceptual loss during training stage, which is used to improve the accuracy of dose prediction. The proposed method is tested on private clinical dataset and obtains HI and CI of 0.31 and 0.87, respectively. The experimental results are better than those by several existing methods, indicating that the dose distribution generated by the proposed method is close to that approved in clinics. The codes are available at https://github.com/hired-ld/FA-Net.

Evaluation of the conformity of intensity-modulated radiation therapy and volumetric modulated arc therapy using AAPM TG 119 protocol.

The aim of this work was to evaluate the conformity of intensity-modulated radiation therapy (IMRT) and volumetric modulated arc therapy (VMAT), and verify the accuracy of the planning and delivery system used in this work based on the AAPM TG-119 protocol. The Eclipse 13.6 treatment planning system (TPS) was used to plan the TG-119 test suite, which included four test cases: MultiTarget, Prostate, Head/Neck, and C-Shape for IMRT and VMAT techniques with 6 MV and 10 MV acceleration voltages. The results were assessed and discussed in terms of the TG-119 protocol and the results of previous studies. In addition, point dose and planar dose measurements were done using a semiflex ion chamber and an electronic portal imaging device (EPID), respectively. The planned doses of all test cases met the criteria of the TG-119 protocol, except those for the spinal cord of the C-Shape hard case. There were no significant differences between the treatment planning doses and the doses given in the TG-119 report, with p-values ranging from 0.974 to 1 (p > 0.05). Doses to the target volumes were similar in the IMRT and VMAT plans, but the organs at risk (OARs) doses were different depending on the test case. The planning results showed that IMRT is more conformal than VMAT in certain cases. For the point dose measurements, the confidence limit (CLpoint) of 0.030 and 0.021 were better than the corresponding values of 0.045 and 0.047 given in the TG-119 report for high-dose and low-dose areas, respectively. Regarding the planar dose measurements, the CLplanar value of 0.38 obtained in this work was lower than that given in the TG-119 report (12.4). It is concluded that the dosimetry measurements performed in this study showed better confidence limits than those provided in the TG 119 report. IMRT remains more conformal in certain circumstances than the more progressive VMAT. When selecting the method of delivering a dose to the patient, several factors must be considered, including the radiotherapy technique, energy, treatment site, and tumour geometry.

Characterizing Compromised Target Coverage With Hypofractionated Radiation Therapy for Pancreatic Cancer.

Introduction Proximity of organs at risk (OAR) hinders radiation dose escalation for the treatment of pancreatic cancer. To address this limitation, there is interest in protracted-fractionation (PF: 15 to 25 fractions) courses employing moderate hypofractionation (MHF: 3-4 Gy/fraction). However, there persists underdosing where tumor interfaces with OAR. The significance of compromised tumor coverage and dose heterogeneity on tumor control remains unknown. Here, we report our initial planning experience with PF-MHF in pancreatic cancer. Methods We retrospectively reviewed radiation courses for locally advanced or recurrent pancreatic cancer with a PF-MHF approach: 45 Gy in 25 fractions (1.8 Gy/fraction) to PTV with 75 Gy (3 Gy/fraction) as an integrated boost to the GTV. We reviewed dosimetric parameters for the GTV: percentage overlap with planning OAR volume (PRV-GTV overlap), D99.9%, D0.1cc, Dmean, V75Gy, and V60Gy. We also calculated the GTV's generalized equivalent uniform dose (gEUD) valueusing two differentavalues (-5 and -15). Lastly, we reoptimized two plans with two approaches: increasing gEUD or relaxing the maximum dose constraint. Results A total of 26 plans were included in our analysis: 14 locally advanced and 12 locally recurrent pancreatic cancer cases. While the D0.1cc median value was 81.7 Gy, target volume coverage was relatively low (V75Gy median 71%). Median gEUD were 71 Gy (a = -5) and 62.8 Gy (a = -15) and inversely correlated with PRV-GTV overlap. On reoptimized plans, both approaches yielded similar results, but an increase in target coverage and gEUD were seen only when there was limited PRV-GTV overlap. Conclusion Although radiation dose can be escalated within the GTV, there continues to be low coverage by the prescription dose, especially with high PRV-GTV overlap. Relaxing the maximum dose constraint in planning allows for meaningful improvement in tumor coverage in limited PRV overlap scenarios. Continued refinement of the PF-MHF approach is needed.

TEAM: Triangular-mEsh Adaptive and Multiscale proton spot generation method.

Proton therapy is preferred for its dose conformality to spare normal tissues and organs-at-risk (OAR) via Bragg peaks with negligible exit dose. However, proton dose conformality can be further optimized: (1) the spot placement is based on the structured (e.g., Cartesian) grid, which may not offer conformal shaping to complex tumor targets; (2) the spot sampling pattern is uniform, which may be insufficient at the tumor boundary to provide the sharp dose falloff, and at the same time may be redundant at the tumor interior to provide the uniform dose coverage, for example, due to multiple Coulomb scattering (MCS); and (3) the lateral spot penumbra increases with respect to the depth due to MCS, which blurs the lateral dose falloff. On the other hand, while (1) the deliverable spots are subject to the minimum-monitor-unit (MMU) constraint, and (2) the dose rate is proportional to the MMU threshold, the current spot sampling method is sensitive to the MMU threshold and can fail to provide satisfactory plan quality for a large MMU threshold (i.e., high-dose-rate delivery). This work will develop a novel Triangular-mEsh-based Adaptive and Multiscale (TEAM) proton spot generation method to address these issues for optimizing proton dose conformality and plan delivery efficiency. Compared to the standard clinically-used spot placement method, three key elements of TEAM are as follows: (1) a triangular mesh instead of a structured grid: the triangular mesh is geometrically more conformal to complex target shapes and therefore more efficient and accurate for dose shaping inside and around the target; (2) adaptive sampling instead of uniform sampling: the adaptive sampling consists of relatively dense sampling at the tumor boundary to create the sharp dose falloff, which is more accurate, and coarse sampling at the tumor interior to uniformly cover the target, which is more efficient; and (3) depth-dependent sampling instead of depth-independent sampling: the depth-dependent sampling is used to compensate for MCS, that is, with increasingly dense sampling at the tumor boundary to improve dose shaping accuracy, and increasingly coarse sampling at the tumor interior to improve dose shaping efficiency, as the depth increases. In the TEAM method the spot locations are generated for each energy layer and layer-by-layer in the multiscale fashion; and then the spot weights are derived by solving the IMPT problem of dose-volume planning objectives, MMU constraints, and robustness optimization with respect to range and setup uncertainties. Compared to the standard clinically-used spot placement method UNIFORM, TEAM achieved (1) better plan quality using <60% number of spots of UNIFORM; (2) better robustness to the number of spots; (3) better robustness to a large MMU threshold. Furthermore, TEAM provided better plan quality with fewer spots than other adaptive methods (Cartesian-grid or triangular-mesh). A novel triangular-mesh-based proton spot placement method called TEAM is proposed, and it is demonstrated to improve plan quality, robustness to the number of spots, and robustness to the MMU threshold, compared to the clinically-used spot placement method and other adaptive methods.

First implementation of artificial intelligence empowered all-in-one radiotherapy workflow for nasopharyngeal carcinoma.

134 Background: To establish an artificial intelligence (AI)-empowered All-In-One (AIO) workflow for providing one-stop radiotherapy to patients with nasopharyngeal carcinoma (NPC), and evaluate its feasibility and performance. Methods: The NPC-specific AIO workflow operates on a CT-integrated linac and integrates AI contouring and AI planning modules. A 3D U-net was employed for contours generation and 3D dose distribution. Knowledge-based planning approach and a protocol-based approach were used for plan optimization. MRI datasets with contours of primary gross tumors, CT datasets with contours of targets and organs at risk, and radiotherapy treatment planning datasets were collected from 877, 139, and 243 patients, respectively, for the training, validation, and testing of AI contouring and planning models. The NPC-specific AIO workflow underwent real-world clinical testing with an end-to-end evaluation involving 120 patients with NPC. The technical characteristics, implementation procedures and performance of AIO workflow were described and evaluated. Results: From March 2022 to October 2023, 120 patients with newly-diagnosed, non-metastatic NPC underwent AIO workflow, and 117 patients completed it in a median time of 23.2 min (range: 16.3 to 45.8 min). Median translation motions were 0.2 mm (CT scan to planning approval) and 0.1 mm (during beam delivery). AI-generated contours required little revision for clinical target volume (CTV1) and organs at risk (OARs), minor revision for cervical lymph nodes (GTVn) and clinical target volume (CTV2), with median Dice similarity coefficients (DSCs) of 0.98 and 0.94, respectively; more revision for GTVp, with a median DSC of 0.84. Of the 117 AI-generated plannings, 108 (92.3%) passed after initial auto-optimization. Volumes receiving ≥ 100% of the prescribed dose for all planning target volumes was ≥ 97.8%. Mean dosimetric parameters met dose constraints for all OARs except the thyroid and submandibulars. One patient died from acute renal failure after 10 fractions of radiotherapy. At week 12 after radiotherapy completion, 115 patients achieved complete response;1 had stable disease. Grade 3-4 acute effects were reported by 54 of 115 patients (36%). Conclusions: We successfully established an AI-empowered AIO workflow for initial radiotherapy of NPC, confirming its feasibility and safety for clinical application.

Potential anatomical triggers for plan adaptation of cervical cancer external beam radiotherapy.

This study aimed to identify potential anatomical variation triggers using magnetic resonance imaging for plan adaption of cervical cancer patients to ensure dose requirements were met over an external beam radiotherapy course. Magnetic resonance images (MRIs) acquired before and during treatment were rigidly registered to a pre-treatment computerised tomography (CT) image for 11 retrospective cervix cancer datasets. Target volumes (TVs) and organs at risk (OARs) were delineated on both MRIs and propagated onto the CT. Treatment plans were generated based on the pre-treatment contours and applied to the mid-treatment contours. Anatomical and dosimetric changes between each timepoint were assessed. The anatomical changes included the change in centroid position and volume size. Dosimetric changes included the V30Gy and V40Gy for the OARs, and V95%, V100%, D95% and D98% for the TVs. Correlation with dosimetric and anatomical changes were assessed to determine potential replan triggers. Changes in the bowel volume and position in the superior-inferior direction, and the high-risk CTV anterior posterior position were highly correlated with a change in dose to the bowel and target, respectively. Hence changes in bowel and high-risk CTV could be used as a potential replan triggers.

Deep learning for autosegmentation for radiotherapy treatment planning: State-of-the-art and novel perspectives.

The rapid development of artificial intelligence (AI) has gained importance, with many tools already entering our daily lives. The medical field of radiation oncology is also subject to this development, with AI entering all steps of the patient journey. In this review article, we summarize contemporary AI techniques and explore the clinical applications of AI-based automated segmentation models in radiotherapy planning, focusing on delineation of organs at risk (OARs), the gross tumor volume (GTV), and the clinical target volume (CTV). Emphasizing the need for precise and individualized plans, we review various commercial and freeware segmentation tools and also state-of-the-art approaches. Through our own findings and based on the literature, we demonstrate improved efficiency and consistency as well as time savings in different clinical scenarios. Despite challenges in clinical implementation such as domain shifts, the potential benefits for personalized treatment planning are substantial. The integration of mathematical tumor growth models and AI-based tumor detection further enhances the possibilities for refining target volumes. As advancements continue, the prospect of one-stop-shop segmentation and radiotherapy planning represents an exciting frontier in radiotherapy, potentially enabling fast treatment with enhanced precision and individualization.