Imaging Assessment of Radiation Therapy-Related Normal Tissue Injury in Children: A PENTEC Visionary Statement.

The Pediatric Normal Tissue Effects in the Clinic (PENTEC) consortium has made significant contributions to understanding and mitigating the adverse effects of childhood cancer therapy. This review addresses the role of diagnostic imaging in detecting, screening, and comprehending radiation therapy-related late effects in children, drawing insights from individual organ-specific PENTEC reports. We further explore how the development of imaging biomarkers for key organ systems, alongside technical advancements and translational imaging approaches, may enhance the systematic application of imaging evaluations in childhood cancer survivors. Moreover, the review critically examines knowledge gaps and identifies technical and practical limitations of existing imaging modalities in the pediatric population. Addressing these challenges may expand access to, minimize the risk of, and optimize the real-world application of, new imaging techniques. The PENTEC team envisions this document as a roadmap for the future development of imaging strategies in childhood cancer survivors, with the overarching goal of improving long-term health outcomes and quality of life for this vulnerable population.

Clinical evaluation of the efficacy of limbus artificial intelligence software to augment contouring for prostate and nodes radiotherapy.

OBJECTIVES: To determine if Limbus, an artificial intelligence (AI) auto-contouring software, can offer meaningful time savings for prostate radiotherapy treatment planning. METHODS: Three clinical oncologists recorded the time taken to contour prostate and seminal vesicles, lymph nodes, bladder, rectum, bowel, and femoral heads on CT scans for 30 prostate patients (15 prostate, 15 prostate and nodes). Limbus 1.6.0 was used to generate these contours on the 30 CT scans. The time taken by the oncologists to modify individual Limbus contours was noted and compared with manual contouring times. The geometric similarity of Limbus and expert contours was assessed using the Dice Similarity Coefficient (DSC), and the dosimetric impact of using un-edited Limbus organs at risk contours was studied. RESULTS: Limbus reduced the time to produce clinically acceptable contours by 26 minutes for prostate and nodes patients and by 13 minutes for the prostate only patients. DSC values of greater than 0.7 were calculated for all contours, demonstrating good initial agreement. A dosimetric study showed that 5 of the 20 plans optimized using unmodified AI structures required unnecessary compromise of PTV coverage, highlighting the importance of expert review. CONCLUSIONS: Limbus offers significant time saving and has become an essential part of our clinical practice. ADVANCES IN KNOWLEDGE: This article is the first to include bowel and lymph nodes when assessing potential time savings using Limbus software. It demonstrates that Limbus can be used as an aid for prostate and node radiotherapy treatment planning.

Anatomical changes and dosimetric analysis of the neck region based on FBCT for nasopharyngeal carcinoma patients during radiotherapy.

BACKGROUND: The study aimed to investigate anatomical changes in the neck region and evaluate their impact on dose distribution in patients with nasopharyngeal carcinoma (NPC) undergoing intensity modulated radiation therapy (IMRT). Additionally, the study sought to determine the optimal time for replanning during the course of treatment. METHODS: Twenty patients diagnosed with NPC underwent IMRT, with weekly pretreatment kV fan beam computed tomography (FBCT) scans in the treatment room. Metastasized lymph nodes in the neck region and organs at risk (OARs) were redelineation using the images from the FBCT scans. Subsequently, the original treatment plan (PLAN0) was replicated to each FBCT scan to generate new plans labeled as PLAN 1-6. The dose-volume histograms (DVH) of the new plans and the original plan were compared. One-way repeated measure ANOVA was utilized to establish threshold(s) at various time points. The presence of such threshold(s) would signify significant change(s), suggesting the need for replanning. RESULTS: Progressive volume reductions were observed over time in the neck region, the gross target volume for metastatic lymph nodes (GTVnd), as well as the submandibular glands and parotids. Compared to PLAN0, the mean dose (Dmean) of GTVnd-L significantly increased in PLAN5, while the minimum dose covering 95% of the volume (D95%) of PGTVnd-L showed a significant decrease from PLAN3 to PLAN6. Similarly, the Dmean of GTVnd-R significantly increased from PLAN4 to PLAN6, whereas the D95% of PGTVnd-R exhibited a significant decrease during the same period. Furthermore, the dose of bilateral parotid glands, bilateral submandibular glands, brainstem and spinal cord was gradually increased in the middle and late period of treatment. CONCLUSION: Significant anatomical and dosimetric changes were noted in both the target volumes and OARs. Considering the thresholds identified, it is imperative to undertake replanning at approximately 20 fractions. This measure ensures the delivery of adequate doses to target volumes while mitigating the risk of overdosing on OARs.

Auto-segmentation of pelvic organs at risk on 0.35T MRI using 2D and 3D Generative Adversarial Network models.

PURPOSE: Manual recontouring of targets and Organs At Risk (OARs) is a time-consuming and operator-dependent task. We explored the potential of Generative Adversarial Networks (GAN) to auto-segment the rectum, bladder and femoral heads on 0.35T MRIs to accelerate the online MRI-guided-Radiotherapy (MRIgRT) workflow. METHODS: 3D planning MRIs from 60 prostate cancer patients treated with 0.35T MR-Linac were collected. A 3D GAN architecture and its equivalent 2D version were trained, validated and tested on 40, 10 and 10 patients respectively. The volumetric Dice Similarity Coefficient (DSC) and 95th percentile Hausdorff Distance (HD95th) were computed against expert drawn ground-truth delineations. The networks were also validated on an independent external dataset of 16 patients. RESULTS: In the internal test set, the 3D and 2D GANs showed DSC/HD95th of 0.83/9.72 mm and 0.81/10.65 mm for the rectum, 0.92/5.91 mm and 0.85/15.72 mm for the bladder, and 0.94/3.62 mm and 0.90/9.49 mm for the femoral heads. In the external test set, the performance was 0.74/31.13 mm and 0.72/25.07 mm for the rectum, 0.92/9.46 mm and 0.88/11.28 mm for the bladder, and 0.89/7.00 mm and 0.88/10.06 mm for the femoral heads. The 3D and 2D GANs required on average 1.44 s and 6.59 s respectively to generate the OARs' volumetric segmentation for a single patient. CONCLUSIONS: The proposed 3D GAN auto-segments pelvic OARs with high accuracy on 0.35T, in both the internal and the external test sets, outperforming its 2D equivalent in both segmentation robustness and volume generation time.

Multi-organ segmentation of organ-at-risk (OAR's) of head and neck site using ensemble learning technique.

INTRODUCTION: This paper presents a novel approach to automate the segmentation of Organ-at-Risk (OAR) in Head and Neck cancer patients using Deep Learning models combined with Ensemble Learning techniques. The study aims to improve the accuracy and efficiency of OAR segmentation, essential for radiotherapy treatment planning. METHODS: The dataset comprised computed tomography (CT) scans of 182 patients in DICOM format, obtained from an institutional image bank. Experienced Radiation Oncologists manually segmented seven OARs for each scan. Two models, 3D U-Net and 3D DenseNet-FCN, were trained on reduced CT scans (192 × 192 x 128) due to memory limitations. Ensemble Learning techniques were employed to enhance accuracy and segmentation metrics. Testing was conducted on 78 patients from the institutional dataset and an open-source dataset (TCGA-HNSC and Head-Neck Cetuximab) consisting of 31 patient scans. RESULTS: Using the Ensemble Learning technique, the average dice similarity coefficient for OARs ranged from 0.990 to 0.994, indicating high segmentation accuracy. The 95% Hausdorff distance (mm) ranged from 1.3 to 2.1, demonstrating precise segmentation boundaries. CONCLUSION: The proposed automated segmentation method achieved efficient and accurate OAR segmentation, surpassing human expert performance in terms of time and accuracy. IMPLICATIONS FOR PRACTICE: This approach has implications for improving treatment planning and patient care in radiotherapy. By reducing manual segmentation reliance, the proposed method offers significant time savings and potential improvements in treatment planning efficiency and precision for head and neck cancer patients.

Validation of Fully Automated Robust Multicriterial Treatment Planning for Head and Neck Cancer IMPT.

PURPOSE: Our purpose was to compare robust intensity modulated proton therapy (IMPT) plans, automatically generated with wish-list-based multicriterial optimization as implemented in Erasmus-iCycle, with manually created robust clinical IMPT plans for patients with head and neck cancer. METHODS AND MATERIALS: Thirty-three patients with head and neck cancer were retrospectively included. All patients were previously treated with a manually created IMPT plan with 7000 cGy dose prescription to the primary tumor (clinical target volume [CTV]7000) and 5425 cGy dose prescription to the bilateral elective volumes (CTV5425). Plans had a 4-beam field configuration and were generated with scenario-based robust optimization (21 scenarios, 3-mm setup error, and ±3% density uncertainty for the CTVs). Three clinical plans were used to configure the Erasmus-iCycle wish-list for automated generation of robust IMPT plans for the other 30 included patients, in line with clinical planning requirements. Automatically and manually generated IMPT plans were compared for (robust) target coverage, organ-at-risk (OAR) doses, and normal tissue complication probabilities (NTCP). No manual fine-tuning of automatically generated plans was performed. RESULTS: For all automatically generated plans, voxel-wise minimum D98% values for the CTVs were within clinical constraints and similar to manual plans. All investigated OAR parameters were favorable in the automatically generated plans (all P < .001). Median reductions in mean dose to OARs went up to 667 cGy for the inferior pharyngeal constrictor muscle, and median reductions in D0.03cm3 in serial OARs ranged up to 1795 cGy for the spinal cord surface. The observed lower mean dose in parallel OARs resulted in statistically significant lower NTCP for xerostomia (grade ≥2: 34.4% vs 38.0%; grade ≥3: 9.0% vs 10.2%) and dysphagia (grade ≥2: 11.8% vs 15.0%; grade ≥3: 1.8% vs 2.8%). CONCLUSIONS: Erasmus-iCycle was able to produce IMPT dose distributions fully automatically with similar (robust) target coverage and improved OAR doses and NTCPs compared with clinical manual planning, with negligible hands-on planning workload.

Extensive clinical testing of Deep Learning Segmentation models for thorax and breast cancer radiotherapy planning.

BACKGROUND: The performance of deep learning segmentation (DLS) models for automatic organ extraction from CT images in the thorax and breast regions was investigated. Furthermore, the readiness and feasibility of integrating DLS into clinical practice were addressed by measuring the potential time savings and dosimetric impact. MATERIAL AND METHODS: Thirty patients referred to radiotherapy for breast cancer were prospectively included. A total of 23 clinically relevant left- and right-sided organs were contoured manually on CT images according to ESTRO guidelines. Next, auto-segmentation was executed, and the geometric agreement between the auto-segmented and manually contoured organs was qualitatively assessed applying a scale in the range [0-not acceptable, 3-no corrections]. A quantitative validation was carried out by calculating Dice coefficients (DSC) and the 95% percentile of Hausdorff distances (HD95). The dosimetric impact of optimizing the treatment plans on the uncorrected DLS contours, was investigated from a dose coverage analysis using DVH values of the manually delineated contours as references. RESULTS: The qualitative analysis showed that 93% of the DLS generated OAR contours did not need corrections, except for the heart where 67% of the contours needed corrections. The majority of DLS generated CTVs needed corrections, whereas a minority were deemed not acceptable. Still, using the DLS-model for CTV and heart delineation is on average 14 minutes faster. An average DSC=0.91 and H95=9.8 mm were found for the left and right breasts, respectively. Likewise, and average DSC in the range [0.66, 0.76]mm and HD95 in the range [7.04, 12.05]mm were found for the lymph nodes. CONCLUSION: The validation showed that the DLS generated OAR contours can be used clinically. Corrections were required to most of the DLS generated CTVs, and therefore warrants more attention before possibly implementing the DLS models clinically.

Can we predict the cardiac benefit of deep inspiration breath hold for left breast and regional nodal irradiation?

PURPOSE: Deep inspiration breath hold (DIBH) is used to decrease the dose of radiotherapy delivered to the heart. There is a need to define criteria to select patients with the potential to derive a real clinical benefit from DIBH treatment. Our study's main goal was to investigate whether two CT-scan cardiac anatomical parameters, cardiac contact distance in the parasagittal plane (CCDps) and lateral heart-to-chest distance (HCD), were predictive of unmet dosimetric cardiac constraints for left breast and regional nodal irradiation (RNI). MATERIALS AND METHODS: This retrospective single-institution dosimetric study included 62 planning CT scans of women with left-sided breast cancer (BC) from 2016 to 2021. Two independent radiation oncologists measured HCD and CCDps twice to assess inter- and intra-observer reproducibility. Dosimetric constraints to be respected were defined, and dosimetric parameters of interest were collected for each patient. RESULTS: Mean heart dose was 7.9Gy. Inter-rater reproducibility between the two readers was considered excellent. The mean heart dose constraint<8Gy was not achieved in 25 patients (40%) and was achieved in 37 patients (60%). There was a significant correlation between mean heart dose and HCD (rs=-0.25, P=0.050) and between mean heart dose and CCDps (rs=0.25, P=0.047). The correlation between HCD and CCDps and unmet cardiac dosimetric constraints was not statistically significant. CONCLUSION: Our dosimetric analysis did not find that the cardiac anatomical parameters HCD and CCDps were predictive of unmet dosimetric cardiac constraints, nor that they were good predictors for cardiac exposure in left-sided BC radiotherapy comprising RNI.

Clinical evaluation of atlas-based auto-segmentation in breast and nodal radiotherapy.

OBJECTIVES: Accurate contouring of anatomical structures allows for high-precision radiotherapy planning, targeting the dose at treatment volumes and avoiding organs at risk. Manual contouring is time-consuming with significant user variability, whereas auto-segmentation (AS) has proven efficiency benefits but requires editing before treatment planning. This study investigated whether atlas-based AS (ABAS) accuracy improves with template atlas group size and character-specific atlas and test case selection. METHODS AND MATERIALS: One clinician retrospectively contoured the breast, nodes, lung, heart, and brachial plexus on 100 CT scans, adhering to peer-reviewed guidelines. Atlases were clustered in group sizes, treatment positions, chest wall separations, and ASs created with Mirada software. The similarity of ASs compared to reference contours was described by the Jaccard similarity coefficient (JSC) and centroid distance variance (CDV). RESULTS: Across group sizes, for all structures combined, the mean JSC was 0.6 (SD 0.3, p = .999). Across atlas-specific groups, 0.6 (SD 0.3, p = 1.000). The correlation between JSC and structure volume was weak in both scenarios (adjusted R2-0.007 and 0.185).Mean CDV was similar across groups but varied up to 1.2 cm for specific structures. CONCLUSIONS: Character-specific atlas groups and test case selection did not improve accuracy outcomes. High-quality ASs were obtained from groups containing as few as ten atlases, subsequently simplifying the application of ABAS. CDV measures indicating auto-segmentation variations on the x, y, and z axes can be utilised to decide on the clinical relevance of variations and reduce AS editing. ADVANCES IN KNOWLEDGE: High-quality ABASs can be obtained from as few as ten template atlases.Atlas and test case selection do not improve AS accuracy.Unlike well-known quantitative similarity indices, volume displacement metrics provide information on the location of segmentation variations, helping assessment of the clinical relevance of variations and reducing clinician editing. Volume displacement metrics combined with the qualitative measure of clinician assessment could reduce user variability.

Progressively refined deep joint registration segmentation (ProRSeg) of gastrointestinal organs at risk: Application to MRI and cone-beam CT.

BACKGROUND: Adaptive radiation treatment (ART) for locally advanced pancreatic cancer (LAPC) requires consistently accurate segmentation of the extremely mobile gastrointestinal (GI) organs at risk (OAR) including the stomach, duodenum, large and small bowel. Also, due to lack of sufficiently accurate and fast deformable image registration (DIR), accumulated dose to the GI OARs is currently only approximated, further limiting the ability to more precisely adapt treatments. PURPOSE: Develop a 3-D Progressively refined joint Registration-Segmentation (ProRSeg) deep network to deformably align and segment treatment fraction magnetic resonance images (MRI)s, then evaluate segmentation accuracy, registration consistency, and feasibility for OAR dose accumulation. METHOD: ProRSeg was trained using five-fold cross-validation with 110 T2-weighted MRI acquired at five treatment fractions from 10 different patients, taking care that same patient scans were not placed in training and testing folds. Segmentation accuracy was measured using Dice similarity coefficient (DSC) and Hausdorff distance at 95th percentile (HD95). Registration consistency was measured using coefficient of variation (CV) in displacement of OARs. Statistical comparison to other deep learning and iterative registration methods were done using the Kruskal-Wallis test, followed by pair-wise comparisons with Bonferroni correction applied for multiple testing. Ablation tests and accuracy comparisons against multiple methods were done. Finally, applicability of ProRSeg to segment cone-beam CT (CBCT) scans was evaluated on a publicly available dataset of 80 scans using five-fold cross-validation. RESULTS: ProRSeg processed 3D volumes (128 × 192 × 128) in 3 s on a NVIDIA Tesla V100 GPU. It's segmentations were significantly more accurate ( p < 0.001 $p<0.001$ ) than compared methods, achieving a DSC of 0.94 ±0.02 for liver, 0.88±0.04 for large bowel, 0.78±0.03 for small bowel and 0.82±0.04 for stomach-duodenum from MRI. ProRSeg achieved a DSC of 0.72±0.01 for small bowel and 0.76±0.03 for stomach-duodenum from public CBCT dataset. ProRSeg registrations resulted in the lowest CV in displacement (stomach-duodenum C V x $CV_{x}$ : 0.75%, C V y $CV_{y}$ : 0.73%, and C V z $CV_{z}$ : 0.81%; small bowel C V x $CV_{x}$ : 0.80%, C V y $CV_{y}$ : 0.80%, and C V z $CV_{z}$ : 0.68%; large bowel C V x $CV_{x}$ : 0.71%, C V y $CV_{y}$ : 0.81%, and C V z $CV_{z}$ : 0.75%). ProRSeg based dose accumulation accounting for intra-fraction (pre-treatment to post-treatment MRI scan) and inter-fraction motion showed that the organ dose constraints were violated in four patients for stomach-duodenum and for three patients for small bowel. Study limitations include lack of independent testing and ground truth phantom datasets to measure dose accumulation accuracy. CONCLUSIONS: ProRSeg produced more accurate and consistent GI OARs segmentation and DIR of MRI and CBCTs compared to multiple methods. Preliminary results indicates feasibility for OAR dose accumulation using ProRSeg.

Comparison of magnetic resonance imaging and CT scan-based delineation of target volumes and organs at risk in the radiation treatment planning of head and neck malignancies.

INTRODUCTION: Accuracy of target definition is paramount in radiation treatment planning. The optimal choice of imaging modality to define the tumor volume in head and neck tumors is debatable. The study compared MRI and CT scan-based delineation of target volume and Organs At Risk in head and neck cancers. MATERIALS AND METHODS: 54 head and neck carcinoma patients underwent rigid image registration of planning CT images with MRI images. The gross tumor volume of the primary tumor, node, and organs at risk were delineated on both CT and MRI images. A volumetric evaluation was done for gross tumors, nodes, and organs at risk. Dice Similarity coefficient (DSC), Conformity index(CI), Sensitivity index(SI), and Inclusion index(II) were calculated for gross tumor, node, brainstem, and bilateral parotids. RESULTS: The mean volume of the tumor in CT and MRI obtained were 41 .94 cc and 34.76 ccs, mean DSC, CI, SI, and II of the tumor were 0.71, 0.56, 67.37, and 79.80. The mean volume of the node in CT and MRI were 12.16 cc and 10.24 cc, mean DSC, CI, SI, and II of the node were 0.61, 0.45, 62.47, and 64. The mean volume of the brainstem in CT and MRI was 24.13 cc and 21.21 cc. The mean volume of the right parotid in CT and MRI was 24.39 cc, 26.04 ccs. The mean volume of left parotid in CT and MRI, respectively, were 23.95 ccs and 25.04 ccs. CONCLUSIONS: The study shows that MRI may be used in combination with CT for better delineation of target volume and organs at risk for head and neck malignancies.

Evaluation of Dosimetry Formalisms in Intraoperative Radiation Therapy of Glioblastoma.

PURPOSE: The intraoperative radiotherapy in newly diagnosed glioblastoma multiforme (INTRAGO) clinical trial assesses survival in patients with glioblastoma treated with intraoperative radiation therapy (IORT) using the INTRABEAM. Treatment planning for INTRABEAM relies on vendor-provided in-water depth dose curves obtained according to the TARGeted Intraoperative radioTherapy (TARGIT) dosimetry protocol. However, recent studies have shown discrepancies between the estimated TARGIT and delivered doses. This work evaluates the effect of the choice of dosimetry formalism on organs at risk (OAR) doses. METHODS AND MATERIALS: A treatment planning framework for INTRABEAM was developed to retrospectively calculate the IORT dose in 8 INTRAGO patients. These patients received an IORT prescription dose of 20 to 30 Gy in addition to external beam radiation therapy. The IORT dose was obtained using (1) the TARGIT method; (2) the manufacturer's V4.0 method; (3) the CQ method, which uses an ionization chamber Monte Carlo (MC) calculated factor; (4) MC dose-to-water; and (5) MC dose-to-tissue. The IORT dose was converted to 2 Gy fractions equivalent dose. RESULTS: According to the TARGIT method, the OAR dose constraints were respected in all cases. However, the other formalisms estimated a higher mean dose to OARs and revealed 1 case where the constraint for the brain stem was exceeded. The addition of the external beam radiation therapy and TARGIT IORT doses resulted in 10 cases of OARs exceeding the dose constraints. The more accurate MC calculation of dose-to-tissue led to the highest dosimetric differences, with 3, 3, 2, and 2 cases (out of 8) exceeding the dose constraint to the brain stem, optic chiasm, optic nerves, and lenses, respectively. Moreover, the mean cumulative dose to brain stem exceeded its constraint of 66 Gy with the MC dose-to-tissue method, which was not evident with the current INTRAGO clinical practice. CONCLUSIONS: The current clinical approach of calculating the IORT dose with the TARGIT method may considerably underestimate doses to nearby OARs. In practice, OAR dose constraints may have been exceeded, as revealed by more accurate methods.

Patient-Specific Auto-segmentation on Daily kVCT Images for Adaptive Radiation Therapy.

PURPOSE: This study explored deep-learning-based patient-specific auto-segmentation using transfer learning on daily RefleXion kilovoltage computed tomography (kVCT) images to facilitate adaptive radiation therapy, based on data from the first group of patients treated with the innovative RefleXion system. METHODS AND MATERIALS: For head and neck (HaN) and pelvic cancers, a deep convolutional segmentation network was initially trained on a population data set that contained 67 and 56 patient cases, respectively. Then the pretrained population network was adapted to the specific RefleXion patient by fine-tuning the network weights with a transfer learning method. For each of the 6 collected RefleXion HaN cases and 4 pelvic cases, initial planning computed tomography (CT) scans and 5 to 26 sets of daily kVCT images were used for the patient-specific learning and evaluation separately. The performance of the patient-specific network was compared with the population network and the clinical rigid registration method and evaluated by the Dice similarity coefficient (DSC) with manual contours being the reference. The corresponding dosimetric effects resulting from different auto-segmentation and registration methods were also investigated. RESULTS: The proposed patient-specific network achieved mean DSC results of 0.88 for 3 HaN organs at risk (OARs) of interest and 0.90 for 8 pelvic target and OARs, outperforming the population network (0.70 and 0.63) and the registration method (0.72 and 0.72). The DSC of the patient-specific network gradually increased with the increment of longitudinal training cases and approached saturation with more than 6 training cases. Compared with using the registration contour, the target and OAR mean doses and dose-volume histograms obtained using the patient-specific auto-segmentation were closer to the results using the manual contour. CONCLUSIONS: Auto-segmentation of RefleXion kVCT images based on the patient-specific transfer learning could achieve higher accuracy, outperforming a common population network and clinical registration-based method. This approach shows promise in improving dose evaluation accuracy in RefleXion adaptive radiation therapy.

Automatic segmentation of kidneys in computed tomography images using U-Net.

PURPOSE: Accurate segmentation of target volumes and organs at risk from computed tomography (CT) images is essential for treatment planning in radiation therapy. The segmentation task is often done manually making it time-consuming. Besides, it is biased to the clinician experience and subject to inter-observer variability. Therefore, and due to the development of artificial intelligence tools and particularly deep learning (DL) algorithms, automatic segmentation has been proposed as an alternative. The purpose of this work is to use a DL-based method to segment the kidneys on CT images for radiotherapy treatment planning. MATERIALS AND METHODS: In this contribution, we used the CT scans of 20 patients. Segmentation of the kidneys was performed using the U-Net model. The Dice similarity coefficient (DSC), the Matthews correlation coefficient (MCC), the Hausdorff distance (HD), the sensitivity and the specificity were used to quantitatively evaluate this delineation. RESULTS: This model was able to segment the organs with a good accuracy. The obtained values of the used metrics for the kidneys segmentation, were presented. Our results were also compared to those obtained recently by other authors. CONCLUSION: Fully automated DL-based segmentation of CT images has the potential to improve both the speed and the accuracy of radiotherapy organs contouring.

HaN-Seg: The head and neck organ-at-risk CT and MR segmentation dataset.

PURPOSE: For the cancer in the head and neck (HaN), radiotherapy (RT) represents an important treatment modality. Segmentation of organs-at-risk (OARs) is the starting point of RT planning, however, existing approaches are focused on either computed tomography (CT) or magnetic resonance (MR) images, while multimodal segmentation has not been thoroughly explored yet. We present a dataset of CT and MR images of the same patients with curated reference HaN OAR segmentations for an objective evaluation of segmentation methods. ACQUISITION AND VALIDATION METHODS: The cohort consists of HaN images of 56 patients that underwent both CT and T1-weighted MR imaging for image-guided RT. For each patient, reference segmentations of up to 30 OARs were obtained by experts performing manual pixel-wise image annotation. By maintaining the distribution of patient age and gender, and annotation type, the patients were randomly split into training Set 1 (42 cases or 75%) and test Set 2 (14 cases or 25%). Baseline auto-segmentation results are also provided by training the publicly available deep nnU-Net architecture on Set 1, and evaluating its performance on Set 2. DATA FORMAT AND USAGE NOTES: The data are publicly available through an open-access repository under the name HaN-Seg: The Head and Neck Organ-at-Risk CT & MR Segmentation Dataset. Images and reference segmentations are stored in the NRRD file format, where the OAR filenames correspond to the nomenclature recommended by the American Association of Physicists in Medicine, and OAR and demographics information is stored in separate comma-separated value  files. POTENTIAL APPLICATIONS: The HaN-Seg: The Head and Neck Organ-at-Risk CT & MR Segmentation Challenge is launched in parallel with the dataset release to promote the development of automated techniques for OAR segmentation in the HaN. Other potential applications include out-of-challenge algorithm development and benchmarking, as well as external validation of the developed algorithms.

Pencil-beam Delivery Pattern Optimization Increases Dose Rate for Stereotactic FLASH Proton Therapy.

PURPOSE: FLASH dose rates >40 Gy/s are readily available in proton therapy (PT) with cyclotron-accelerated beams and pencil-beam scanning (PBS). The PBS delivery pattern will affect the local dose rate, as quantified by the PBS dose rate (PBS-DR), and therefore needs to be accounted for in FLASH-PT with PBS, but it is not yet clear how. Our aim was to optimize patient-specific scan patterns for stereotactic FLASH-PT of early-stage lung cancer and lung metastases, maximizing the volume irradiated with PBS-DR >40 Gy/s of the organs at risk voxels irradiated to >8 Gy (FLASH coverage). METHODS AND MATERIALS: Plans to 54 Gy/3 fractions with 3 equiangular coplanar 244 MeV proton shoot-through transmission beams for 20 patients were optimized with in-house developed software. Planning target volume-based planning with a 5 mm margin was used. Planning target volume ranged from 4.4 to 84 cc. Scan-pattern optimization was performed with a Genetic Algorithm, run in parallel for 20 independent populations (islands). Mapped crossover, inversion, swap, and shift operators were applied to achieve (local) optimality on each island, with migration between them for global optimality. The cost function was chosen to maximize the FLASH coverage per beam at >8 Gy, >40 Gy/s, and 40 nA beam current. The optimized patterns were evaluated on FLASH coverage, PBS-DR distribution, and population PBS-DR-volume histograms, compared with standard line-by-line scanning. Robustness against beam current variation was investigated. RESULTS: The optimized patterns have a snowflake-like structure, combined with outward swirling for larger targets. A population median FLASH coverage of 29.0% was obtained for optimized patterns compared with 6.9% for standard patterns, illustrating a significant increase in FLASH coverage for optimized patterns. For beam current variations of 5 nA, FLASH coverage varied between -6.1%-point and 2.2%-point for optimized patterns. CONCLUSIONS: Significant improvements on the PBS-DR and, hence, on FLASH coverage and potential healthy-tissue sparing are obtained by sequential scan-pattern optimization. The optimizer is flexible and may be further fine-tuned, based on the exact conditions for FLASH.

Automated Robust Planning for IMPT in Oropharyngeal Cancer Patients Using Machine Learning.

PURPOSE: The aim of this study was to evaluate an automated treatment planning method for robustly optimized intensity modulated proton therapy (IMPT) plans for oropharyngeal carcinoma patients and to compare the results with manually optimized robust IMPT plans. METHODS AND MATERIALS: An atlas regression forest-based machine learning (ML) model for dose prediction was trained on CT scans, contours, and dose distributions of robust IMPT plans of 88 oropharyngeal cancer (OPC) patients. The ML model was combined with a robust voxel and dose volume histogram-based dose mimicking optimization algorithm for 21 perturbed scenarios to generate a machine-deliverable plan from the predicted dose distribution. Machine learning optimization (MLO) configuration was performed using a cross-validation approach with 3 × 8 tuning patients and comprised of adjustments to the mimicking optimization, to generate higher-quality MLO plans. Independent testing of the MLO algorithm was performed with another 25 patients. Plan quality of clinical and MLO plans was evaluated by the clinical target volume (D98% voxel-wise minimum dose >94%), organ at risk (OAR) doses, and the normal tissue complication probability (NTCP) (sum (Σ) of grade-2 and grade-3 dysphagia and xerostomia). RESULTS: Adequate robust target coverage was achieved in 24/25 clinical plans and in 23/25 MLO plans in the primary clinical target volume (CTV). In the elective CTV, 22/25 clinical plans and 24/25 MLO plans passed the robust target coverage evaluation threshold. The MLO average Σgrade 2 and Σgrade 3 NTCPs were comparable to the clinical plans (Σgrade 2 NTCPs: clinical 47.5% vs MLO 48.4%, Σgrade 3 NTCPs: clinical 11.9% vs MLO 12.3%). Significant increases in OAR average doses in MLO plans were found in the pharynx constrictor muscles (163 cGy, P = .002) and cervical esophagus (265 cGy, P = .002). The MLO plans were created within 45 minutes. CONCLUSION: This study showed that automated MLO planning can generate robustly optimized MLO plans with quality comparable to clinical plans in OPC patients.

Male pelvic multi-organ segmentation using token-based transformer Vnet.

Objective. This work aims to develop an automated segmentation method for the prostate and its surrounding organs-at-risk in pelvic computed tomography to facilitate prostate radiation treatment planning.Approach. In this work, we propose a novel deep learning algorithm combining a U-shaped convolutional neural network (CNN) and vision transformer (VIT) for multi-organ (i.e. bladder, prostate, rectum, left and right femoral heads) segmentation in male pelvic CT images. The U-shaped model consists of three components: a CNN-based encoder for local feature extraction, a token-based VIT for capturing global dependencies from the CNN features, and a CNN-based decoder for predicting the segmentation outcome from the VIT's output. The novelty of our network is a token-based multi-head self-attention mechanism used in the transformer, which encourages long-range dependencies and forwards informative high-resolution feature maps from the encoder to the decoder. In addition, a knowledge distillation strategy is deployed to further enhance the learning capability of the proposed network.Main results. We evaluated the network using: (1) a dataset collected from 94 patients with prostate cancer; (2) and a public dataset CT-ORG. A quantitative evaluation of the proposed network's performance was performed on each organ based on (1) volume similarity between the segmented contours and ground truth using Dice score, segmentation sensitivity, and precision, (2) surface similarity evaluated by Hausdorff distance (HD), mean surface distance (MSD) and residual mean square distance (RMS), (3) and percentage volume difference (PVD). The performance was then compared against other state-of-art methods. Average volume similarity measures obtained by the network overall organs were Dice score = 0.91, sensitivity = 0.90, precision = 0.92, average surface similarities were HD = 3.78 mm, MSD = 1.24 mm, RMS = 2.03 mm; average percentage volume difference was PVD = 9.9% on the first dataset. The network also obtained Dice score = 0.93, sensitivity = 0.93, precision = 0.93, average surface similarities were HD = 5.82 mm, MSD = 1.16 mm, RMS = 1.24 mm; average percentage volume difference was PVD = 6.6% on the CT-ORG dataset.Significance. In summary, we propose a token-based transformer network with knowledge distillation for multi-organ segmentation using CT images. This method provides accurate and reliable segmentation results for each organ using CT imaging, facilitating the prostate radiation clinical workflow.

Machine learning-based detection of aberrant deep learning segmentations of target and organs at risk for prostate radiotherapy using a secondary segmentation algorithm.

Objective.The output of a deep learning (DL) auto-segmentation application should be reviewed, corrected if needed and approved before being used clinically. This verification procedure is labour-intensive, time-consuming and user-dependent, which potentially leads to significant errors with impact on the overall treatment quality. Additionally, when the time needed to correct auto-segmentations approaches the time to delineate target and organs at risk from scratch, the usability of the DL model can be questioned. Therefore, an automated quality assurance framework was developed with the aim to detect in advance aberrant auto-segmentations.Approach. Five organs (prostate, bladder, anorectum, femoral head left and right) were auto-delineated on CT acquisitions for 48 prostate patients by an in-house trained primary DL model. An experienced radiation oncologist assessed the correctness of the model output and categorised the auto-segmentations into two classes whether minor or major adaptations were needed. Subsequently, an independent, secondary DL model was implemented to delineate the same structures as the primary model. Quantitative comparison metrics were calculated using both models' segmentations and used as input features for a machine learning classification model to predict the output quality of the primary model.Main results. For every organ, the approach of independent validation by the secondary model was able to detect primary auto-segmentations that needed major adaptation with high sensitivity (recall = 1) based on the calculated quantitative metrics. The surface DSC and APL were found to be the most indicated parameters in comparison to standard quantitative metrics for the time needed to adapt auto-segmentations.Significance. This proposed method includes a proof of concept for the use of an independent DL segmentation model in combination with a ML classifier to improve time saving during QA of auto-segmentations. The integration of such system into current automatic segmentation pipelines can increase the efficiency of the radiotherapy contouring workflow.

ThoraxNet: a 3D U-Net based two-stage framework for OAR segmentation on thoracic CT images.

An important phase of radiation treatment planning is the accurate contouring of the organs at risk (OAR), which is necessary for the dose distribution calculation. The manual contouring approach currently used in clinical practice is tedious, time-consuming, and prone to inter and intra-observer variation. Therefore, a deep learning-based auto contouring tool can solve these issues by accurately delineating OARs on the computed tomography (CT) images. This paper proposes a two-stage deep learning-based segmentation model with an attention mechanism that automatically delineates OARs in thoracic CT images. After preprocessing the input CT volume, a 3D U-Net architecture will locate each organ to generate cropped images for the segmentation network. Next, two differently configured U-Net-based networks will perform the segmentation of large organs-left lung, right lung, heart, and small organs-esophagus and spinal cord, respectively. A post-processing step integrates all the individually-segmented organs to generate the final result. The suggested model outperformed the state-of-the-art approaches in terms of dice similarity coefficient (DSC) values for the lungs and the heart. It is worth mentioning that the proposed model achieved a dice score of 0.941, which is 1.1% higher than the best previous dice score, in the case of the heart, an important organ in the human body. Moreover, the clinical acceptance of the results is verified using dosimetric analysis. To delineate all five organs on a CT scan of size [Formula: see text], our model takes only 8.61 s. The proposed open-source automatic contouring tool can generate accurate contours in minimal time, consequently speeding up the treatment time and reducing the treatment cost.