A Randomised Phase II Trial to Evaluate the Feasibility of Radiotherapy Dose Escalation, Facilitated by Intensity-Modulated Arc Radiotherapy Techniques, in High-Risk Neuroblastoma

BACKGROUND AND PURPOSE

For high-risk neuroblastoma, planning target volume coverage is often compromised to respect adjacent kidney tolerance. This trial investigated whether intensity-modulated arc radiotherapy techniques (IMAT) could facilitate dose escalation better than conventional techniques.

MATERIALS AND METHODS

Children with high-risk abdominal neuroblastoma referred for radiotherapy to the primary tumour site and involved regional lymph nodes were randomised to receive either standard dose (21 Gy in 14 fractions) or escalated dose (36 Gy in 24 fractions) radiotherapy. Dual planning with both a conventional anterior-posterior parallel opposed pair radiotherapy technique and an IMAT technique was performed. The quality of target volume and organ-at-risk delineation, and dosimetric plans, were externally reviewed. Dosimetric parameters were used to judge the superior technique for treatment. This feasibility trial was not powered to detect improvement in outcome with dose escalation.

RESULTS

Between 2017 and 2020, 50 patients were randomised and dual-planned. The IMAT technique was judged more favourable in 48 patients. In all patients randomised to receive 36 Gy, IMAT would have permitted delivery of the full dose (median D50% 36.0 Gy, inter-quartile range 36.0-36.1 Gy) to the target volume, whereas dose compromise would have been required with conventional planning (median D50% 35.6 Gy, inter-quartile range 28.7-35.9 Gy).

CONCLUSION

IMAT facilitates safe dose escalation to 36 Gy in patients receiving radiotherapy for neuroblastoma. The value of dose escalation is now being evaluated in a current prospective phase III randomised trial.

Dosimetric impact of contour editing on CT and MRI deep-learning autosegmentation for brain OARs

PURPOSE

To establish the clinical applicability of deep-learning organ-at-risk autocontouring models (DL-AC) for brain radiotherapy. The dosimetric impact of contour editing, prior to model training, on performance was evaluated for both CT and MRI-based models. The correlation between geometric and dosimetric measures was also investigated to establish whether dosimetric assessment is required for clinical validation.

METHOD

CT and MRI-based deep learning autosegmentation models were trained using edited and unedited clinical contours. Autosegmentations were dosimetrically compared to gold standard contours for a test cohort. D1%, D5%, D50%, and maximum dose were used as clinically relevant dosimetric measures. The statistical significance of dosimetric differences between the gold standard and autocontours was established using paired Student's t-tests. Clinically significant cases were identified via dosimetric headroom to the OAR tolerance. Pearson's Correlations were used to investigate the relationship between geometric measures and absolute percentage dose changes for each autosegmentation model.

RESULTS

Except for the right orbit, when delineated using MRI models, the dosimetric statistical analysis revealed no superior model in terms of the dosimetric accuracy between the CT DL-AC models or between the MRI DL-AC for any investigated brain OARs. The number of patients where the clinical significance threshold was exceeded was higher for the optic chiasm D1% than other OARs, for all autosegmentation models. A weak correlation was consistently observed between the outcomes of dosimetric and geometric evaluations.

CONCLUSIONS

Editing contours before training the DL-AC model had no significant impact on dosimetry. The geometric test metrics were inadequate to estimate the impact of contour inaccuracies on dose. Accordingly, dosimetric analysis is needed to evaluate the clinical applicability of DL-AC models in the brain.

Comparative Study of Eclipse and RayStation Multi-Criteria Optimization-Based Prostate Radiotherapy Treatment Planning Quality

Multi-criteria optimization (MCO) function has been available on commercial radiotherapy (RT) treatment planning systems to improve plan quality; however, no study has compared Eclipse and RayStation MCO functions for prostate RT planning. The purpose of this study was to compare prostate RT MCO plan qualities in terms of discrepancies between Pareto optimal and final deliverable plans, and dosimetric impact of final deliverable plans. In total, 25 computed tomography datasets of prostate cancer patients were used for Eclipse (version 16.1) and RayStation (version 12A) MCO-based plannings with doses received by 98% of planning target volume having 76 Gy prescription (PTV76D98%) and 50% of rectum (rectum D50%) selected as trade-off criteria. Pareto optimal and final deliverable plan discrepancies were determined based on PTV76D98% and rectum D50% percentage differences. Their final deliverable plans were compared in terms of doses received by PTV76 and other structures including rectum, and PTV76 homogeneity index (HI) and conformity index (CI), using a t-test. Both systems showed discrepancies between Pareto optimal and final deliverable plans (Eclipse: -0.89% (PTV76D98%) and -2.49% (Rectum D50%); RayStation: 3.56% (PTV76D98%) and -1.96% (Rectum D50%)). Statistically significantly different average values of PTV76D98%,HI and CI, and mean dose received by rectum (Eclipse: 76.07 Gy, 0.06, 1.05 and 39.36 Gy; RayStation: 70.43 Gy, 0.11, 0.87 and 51.65 Gy) are noted, respectively (p < 0.001). Eclipse MCO-based prostate RT plan quality appears better than that of RayStation.

Dosimetric comparison of intra-cavitary brachytherapy technique with free-hand (intra-cavitary + interstitial) technique in cervical cancer

Purpose

The aim of the study was to dosimetrically compare intra-cavitary brachytherapy technique (ICBT) with free-hand (intra-cavitary + interstitial, IC + IS) technique.

Material and methods

Twenty seven locally advanced carcinoma cervix patients were included in the study. Patients with more than medial 1/3rd parametrial residual disease without extending upto lateral pelvic wall were included, following external beam radiotherapy (EBRT), in which cobalt-60 high-dose-rate (60Co HDR) brachytherapy source was used. Dose for both plans were 6.5 Gy × 4 fractions, 2 fractions per day, 6 hours apart, over 2 days. Free-hand brachytherapy technique, consisted of placement of central tandem and 2 ovoids along with needles without using template, was applied. Two plans were generated by activating and deactivating the needles, and compared by normalizing to V100.

Results

A total of 79 needles were applied. Using paired-t test, dosimetric comparison of both the plans was done. Free-hand plan had a significant higher mean V90 (volume receiving 90% of the dose) of 94.2% compared with 87.22% in ICBT plan (p ≤ 0.0001). Free-hand and ICBT plans presented a mean V100 values of 89.06% and 81.51% (p ≤ 0.0001), respectively, favoring free-hand plan. The mean D90 (dose to 90% volume), D98, and D100 of free-hand plan were 6.28 Gray (Gy), 4.91 Gy, and 3.62 Gy, respectively, but equivalent parameters in ICBT plan were 5.26 Gy, 3.72 Gy, and 2.61 Gy, with p value ≤ 0.0001. In both the plans, D2cc of the bladder, rectum, and sigmoid were 4.59 Gy, 3.98 Gy, 2.77 Gy, and 4.46 Gy, 3.90 Gy, 2.67 Gy, respectively, with no statistical significance.

Conclusions

Free-hand brachytherapy (IC + IS) achieves a statistically significant better dose distribution to high-risk clinical target volume (HR-CTV) comparing with ICBT technique with similar dose to organs at risk.

Understanding the Radiation Dose Variability in Nasopharyngeal Cancer: An Organs-at-Risk Approach

Objective This study aims to thoroughly assess the radiation dose distribution to critical organs in patients with nasopharyngeal carcinoma, focusing on the correlation between the radiation dosages for the various organs at risk (OARs) in nasopharyngeal cancer patients. Methods We meticulously analysed a dataset comprising 38 nasopharyngeal carcinoma patients, focusing on radiation dosages measured in Gray (Gy) and volumetric data in cubic centimetres (cc) of critical organs, including the lens, brainstem, spinal cord, optic nerve, optic chiasm, and cochlea. A detailed exploratory data analysis approach encompassed univariate, bivariate, and multivariate techniques. Results Our analysis revealed several key findings. The mean and median values across various dose measurements were closely aligned, indicating symmetrical distributions with minimal skewness. The histograms further corroborated this, showing evenly distributed dose values across different anatomical regions. The correlation matrix highlighted varying degrees of interrelationships between the doses, with some showing strong correlations while others exhibited minimal or no correlation. The 3D scatter plot provided a view of the multi-dimensional dose relationships, with a specific focus on the spinal cord, lens, and brainstem doses. The bivariate scatter plots revealed symmetrical distributions between the right and left lens doses and more complex relationships involving the brainstem and spinal cord, illustrating the intricacies of dose distribution in radiation therapy. Conclusion Our findings reveal distinct radiation exposure patterns to OARs of nasopharyngeal carcinoma. This research emphasises the need for tailored radiation therapy planning to achieve optimal clinical outcomes while safeguarding vital organs.

Comparative Study of Plan Robustness for Breast Radiotherapy: Volumetric Modulated Arc Therapy Plans with Robust Optimization versus Manual Flash Approach

A previous study investigated robustness of manual flash (MF) and robust optimized (RO) volumetric modulated arc therapy plans for breast radiotherapy based on five patients in 2020 and indicated that the RO was more robust than the MF, although the MF is still current standard practice. The purpose of this study was to compare their plan robustness in terms of dose variation to clinical target volume (CTV) and organs at risk (OARs) based on a larger sample size. This was a retrospective study involving 34 female patients. Their plan robustness was evaluated based on measured volume/dose difference between nominal and worst scenarios (ΔV/ΔD) for each CTV and OARs parameter, with a smaller difference representing greater robustness. Paired sample t-test was used to compare their robustness values. All parameters (except CTV ΔD98%) of the RO approach had smaller ΔV/ΔD values than those of the MF. Also, the RO approach had statistically significantly smaller ΔV/ΔD values (p < 0.001-0.012) for all CTV parameters except the CTV ΔV95% and ΔD98% and heart ΔDmean. This study's results confirm that the RO approach was more robust than the MF in general. Although both techniques were able to generate clinically acceptable plans for breast radiotherapy, the RO could potentially improve workflow efficiency due to its simpler planning process.

Consistency in contouring of organs at risk by artificial intelligence vs oncologists in head and neck cancer patients

BACKGROUND

In the Danish Head and Neck Cancer Group (DAHANCA) 35 trial, patients are selected for proton treatment based on simulated reductions of Normal Tissue Complication Probability (NTCP) for proton compared to photon treatment at the referring departments. After inclusion in the trial, immobilization, scanning, contouring and planning are repeated at the national proton centre. The new contours could result in reduced expected NTCP gain of the proton plan, resulting in a loss of validity in the selection process. The present study evaluates if contour consistency can be improved by having access to AI (Artificial Intelligence) based contours.

MATERIALS AND METHODS

The 63 patients in the DAHANCA 35 pilot trial had a CT from the local DAHANCA centre and one from the proton centre. A nationally validated convolutional neural network, based on nnU-Net, was used to contour OARs on both scans for each patient. Using deformable image registration, local AI and oncologist contours were transferred to the proton centre scans for comparison. Consistency was calculated with the Dice Similarity Coefficient (DSC) and Mean Surface Distance (MSD), comparing contours from AI to AI and oncologist to oncologist, respectively. Two NTCP models were applied to calculate NTCP for xerostomia and dysphagia.

RESULTS

The AI contours showed significantly better consistency than the contours by oncologists. The median and interquartile range of DSC was 0.85 [0.78 - 0.90] and 0.68 [0.51 - 0.80] for AI and oncologist contours, respectively. The median and interquartile range of MSD was 0.9 mm [0.7 - 1.1] mm and 1.9 mm [1.5 - 2.6] mm for AI and oncologist contours, respectively. There was no significant difference in Δ NTCP.

CONCLUSIONS

The study showed that OAR contours made by the AI algorithm were more consistent than those made by oncologists. No significant impact on the Δ NTCP calculations could be discerned.

Deep learning-based classification of organs at risk and delineation guideline in pelvic cancer radiation therapy

Deep learning (DL) models for radiation therapy (RT) image segmentation require accurately annotated training data. Multiple organ delineation guidelines exist; however, information on the used guideline is not provided with the delineation. Extraction of training data with coherent guidelines can therefore be challenging. We present a supervised classification method for pelvis structure delineations where bowel cavity, femoral heads, bladder, and rectum data, with two guidelines, were classified. The impact on DL-based segmentation quality using mixed guideline training data was also demonstrated. Bowel cavity was manually delineated on CT images for anal cancer patients (n = 170) according to guidelines Devisetty and RTOG. The DL segmentation quality from using training data with coherent or mixed guidelines was investigated. A supervised 3D squeeze-and-excite SENet-154 model was trained to classify two bowel cavity delineation guidelines. In addition, a pelvis CT dataset with manual delineations from prostate cancer patients (n = 1854) was used where data with an alternative guideline for femoral heads, rectum, and bladder were generated using commercial software. The model was evaluated on internal (n = 200) and external test data (n = 99). By using mixed, compared to coherent, delineation guideline training data mean DICE score decreased 3% units, mean Hausdorff distance (95%) increased 5 mm and mean surface distance (MSD) increased 1 mm. The classification of bowel cavity test data achieved 99.8% unweighted classification accuracy, 99.9% macro average precision, 97.2% macro average recall, and 98.5% macro average F1. Corresponding metrics for the pelvis internal test data were all 99% or above and for the external pelvis test data they were 96.3%, 96.6%, 93.3%, and 94.6%. Impaired segmentation performance was observed for training data with mixed guidelines. The DL delineation classification models achieved excellent results on internal and external test data. This can facilitate automated guideline-specific data extraction while avoiding the need for consistent and correct structure labels.

Geometric evaluations of CT and MRI based deep learning segmentation for brain OARs in radiotherapy

Objective.Deep-learning auto-contouring (DL-AC) promises standardisation of organ-at-risk (OAR) contouring, enhancing quality and improving efficiency in radiotherapy. No commercial models exist for OAR contouring based on brain magnetic resonance imaging (MRI). We trained and evaluated computed tomography (CT) and MRI OAR autosegmentation models in RayStation. To ascertain clinical usability, we investigated the geometric impact of contour editing before training on model quality.Approach.Retrospective glioma cases were randomly selected for training (n= 32, 47) and validation (n= 9, 10) for MRI and CT, respectively. Clinical contours were edited using international consensus (gold standard) based on MRI and CT. MRI models were trained (i) using the original clinical contours based on planning CT and rigidly registered T1-weighted gadolinium-enhanced MRI (MRIu), (ii) as (i), further edited based on CT anatomy, to meet international consensus guidelines (MRIeCT), and (iii) as (i), further edited based on MRI anatomy (MRIeMRI). CT models were trained using: (iv) original clinical contours (CTu) and (v) clinical contours edited based on CT anatomy (CTeCT). Auto-contours were geometrically compared to gold standard validation contours (CTeCT or MRIeMRI) using Dice Similarity Coefficient, sensitivity, and mean distance to agreement. Models' performances were compared using paired Student's t-testing.Main results.The edited autosegmentation models successfully generated more segmentations than the unedited models. Paired t-testing showed editing pituitary, orbits, optic nerves, lenses, and optic chiasm on MRI before training significantly improved at least one geometry metric. MRI-based DL-AC performed worse than CT-based in delineating the lacrimal gland, whereas the CT-based performed worse in delineating the optic chiasm. No significant differences were found between the CTeCT and CTu except for optic chiasm.Significance.T1w-MRI DL-AC could segment all brain OARs except the lacrimal glands, which cannot be easily visualized on T1w-MRI. Editing contours on MRI before model training improved geometric performance. MRI DL-AC in RT may improve consistency, quality and efficiency but requires careful editing of training contours.

Stereotactic body radiation therapy to the spine: contouring the cauda equina instead of the spinal cord is more practical as the organ at risk

Background

Stereotactic body radiotherapy (SBRT) is recognized as a curative treatment for oligometastasis. The spinal cord becomes the cauda equina at the lumbar level, and the nerves are located dorsally. Recently, a consensus has been reached that the cauda equina should be contoured as an organ at risk (OAR). Here, we examined the separate contouring benefits for the spinal canal versus the cauda equina only as the OAR.

Materials and methods

A medical physicist designed a simulation plan for 10 patients with isolated lumbar metastasis. The OAR was set with three contours: the whole spinal canal, cauda equina only, and cauda equina with bilateral nerve roots. The prescribed dose for the planning target volume (PTV) was 30 Gy/3 fx.

Results

For the constrained QAR doses, D90 and D95 were statistically significant due to the different OAR contouring. The maximum dose (Dmax) was increased to the spinal canal when the cauda equina max was set to ≤ 20 Gy, but dose hotspots were observed in most cases in the medullary area. The Dmax and PTV coverage were negatively correlated for the cauda equina and the spinal canal if Dmax was set to ≤ 20 Gy for both.

Conclusions

A portion of the spinal fluid is also included when the spinal canal is set as the OAR. Thus, the PTV coverage rate will be poor if the tumor is in contact with the spinal canal. However, the PTV coverage rate increases if only the cauda equina is set as the OAR.

Applying a novel two-step deep learning network to improve the automatic delineation of esophagus in non-small cell lung cancer radiotherapy

Purpose

To introduce a model for automatic segmentation of thoracic organs at risk (OARs), especially the esophagus, in non-small cell lung cancer radiotherapy, using a novel two-step deep learning network.

Materials and methods

A total of 59 lung cancer patients' CT images were enrolled, of which 39 patients were randomly selected as the training set, 8 patients as the validation set, and 12 patients as the testing set. The automatic segmentations of the six OARs including the esophagus were carried out. In addition, two sets of treatment plans were made on the basis of the manually delineated tumor and OARs (Plan1) as well as the manually delineated tumor and the automatically delineated OARs (Plan2). The Dice similarity coefficient (DSC), 95% Hausdorff distance (HD95), and average surface distance (ASD) of the proposed model were compared with those of U-Net as a benchmark. Next, two groups of plans were also compared according to the dose-volume histogram parameters.

Results

The DSC, HD95, and ASD of the proposed model were better than those of U-Net, while the two groups of plans were almost the same. The highest mean DSC of the proposed method was 0.94 for the left lung, and the lowest HD95 and ASD were 3.78 and 1.16 mm for the trachea, respectively. Moreover, the DSC reached 0.73 for the esophagus.

Conclusions

The two-step segmentation method can accurately segment the OARs of lung cancer. The mean DSC of the esophagus realized preliminary clinical significance (>0.70). Choosing different deep learning networks based on different characteristics of organs offers a new option for automatic segmentation in radiotherapy.

Prediction of Radiation-induced Lymphopenia following Exposure of the Thoracic Region and Associated Risk of Infections and Mortality

AIMS

Large blood volumes are irradiated when the heart is exposed to radiation. The mean heart dose (MHD) may be a good surrogate for circulating lymphocytes exposure. We investigated the association between MHD and radiation-induced lymphopenia and explored the impact of the end-of-radiation-therapy (EoRT) lymphocyte count on clinical outcomes.

MATERIALS AND METHODS

In total, 915 patients were analysed: 303 patients with breast cancer and 612 with intrathoracic tumours: oesophageal cancer (291), non-small cell lung cancer (265) and small cell lung cancer (56). Heart contours were generated using an interactive deep learning delineation process and an individual dose volume histogram for each heart was obtained. A dose volume histogram for the body was extracted from the clinical systems. We compared different models analysing the effect of heart dosimetry on the EoRT lymphocyte count using multivariable linear regression and assessed goodness of fit. We published interactive nomograms for the best models. The association of the degree of EoRT lymphopenia with clinical outcomes (overall survival, cancer treatment failure and infection) was investigated.

RESULTS

An increasing low dose bath to the body and MHD were associated with a low EoRT lymphocyte count. The best models for intrathoracic tumours included dosimetric parameters, age, gender, number of fractions, concomitant chemotherapy and pre-treatment lymphocyte count. Models for patients with breast cancer showed no improvement when adding dosimetric variables to the clinical predictors. EoRT lymphopenia grade ≥3 was associated with decreased survival and increased risk of infections among patients with intrathoracic tumours.

CONCLUSION

Among patients with intrathoracic tumours, radiation exposure to the heart contributes to lymphopenia and low levels of peripheral lymphocytes after radiotherapy are associated with worse clinical outcomes.

Measurements of target volumes and organs at risk using DW‑MRI in patients with central lung cancer accompanied with atelectasis

Accurate imaging-based tumor delineation is crucial for guiding the radiotherapy treatments of various solid tumors. Currently, several imaging procedures, including diffusion-weighted magnetic resonance imaging (DW-MRI), intensified computed tomography and positron emission tomography are routinely used for targeted tumor delineation. However, the performance of these imaging procedures has not yet been comprehensively evaluated. In order to address this matter, the present study was conducted in an aim to assess the use of DW-MRI in guiding radiotherapy treatments, by comparing its performance to that of other imaging procedures. Specifically, the exposure dosages to organs at risk, including the lungs, heart and spinal mencord, were evaluated using various radiotherapy regimes. The findings of the present study demonstrated that DW-MRI is a non-invasive and cost-effective imaging procedure that can be used to reduce lung exposure doses, minimizing the risk of radiation pneumonitis. The data further demonstrate the immense potential of the DW-MRI procedure in the precision radiotherapy of lung cancers.

Clinical target volume and organs at risk segmentation for rectal cancer radiotherapy using the Flex U-Net network

Purpose/Objectives

The aim of this study was to improve the accuracy of the clinical target volume (CTV) and organs at risk (OARs) segmentation for rectal cancer preoperative radiotherapy.

Materials/Methods

Computed tomography (CT) scans from 265 rectal cancer patients treated at our institution were collected to train and validate automatic contouring models. The regions of CTV and OARs were delineated by experienced radiologists as the ground truth. We improved the conventional U-Net and proposed Flex U-Net, which used a register model to correct the noise caused by manual annotation, thus refining the performance of the automatic segmentation model. Then, we compared its performance with that of U-Net and V-Net. The Dice similarity coefficient (DSC), Hausdorff distance (HD), and average symmetric surface distance (ASSD) were calculated for quantitative evaluation purposes. With a Wilcoxon signed-rank test, we found that the differences between our method and the baseline were statistically significant (P< 0.05).

Results

Our proposed framework achieved DSC values of 0.817 ± 0.071, 0.930 ± 0.076, 0.927 ± 0.03, and 0.925 ± 0.03 for CTV, the bladder, Femur head-L and Femur head-R, respectively. Conversely, the baseline results were 0.803 ± 0.082, 0.917 ± 0.105, 0.923 ± 0.03 and 0.917 ± 0.03, respectively.

Conclusion

In conclusion, our proposed Flex U-Net can enable satisfactory CTV and OAR segmentation for rectal cancer and yield superior performance compared to conventional methods. This method provides an automatic, fast and consistent solution for CTV and OAR segmentation and exhibits potential to be widely applied for radiation therapy planning for a variety of cancers.

Prioritizing sufficient dose to gross tumor volume over normal tissue sparing in intensity-modulated radiotherapy treatment of T4 nasopharyngeal carcinoma

BACKGROUND

In intensity-modulated radiation therapy (IMRT) for nasopharyngeal carcinoma (NPC), priority is often given minimize dose to the critical organs at risk (OARs) to avoid potential morbid sequelae. However, in T4 NPC, dosimetric inadequacy enforced by dose constraints on OARs may significantly impact tumor control.

METHODS

This was a single-institute cohort that patients diagnosed between July 2005 and December 2010 with T4 NPC treated with IMRT. All patients were re-classification according to the 7th-AJCC stage.

RESULTS

Overall, the average doses such as Dmax , D1% , D2% and D1cc for various Central nervous system (CNS) OARs including brainstem, optic nerve, chiasm, temporal lobes and spinal cord were found to exceed published guidelines as RTOG0225. However, no clinical toxicities were seen during the follow-up period except for 13% patients with temporal lobe necrosis.

CONCLUSION

Our retrospective review showed that its feasible to maximize gross tumor volume dose coverage while exceeding most CNS OAR constraint standards, with ideal local control and no obvious increase of craniocerebral toxicity.

Dosimetric impact of different multileaf collimators on cardiac and left anterior descending coronary artery dose reduction

Introduction

Radiotherapy (RT) may increase the dose of heart structure like left anterior descending coronary artery (LAD). The purpose of this paper was to evaluate the impact of various multileaf collimators (MLCs) in shielding organ at risks (OARs), especially LAD, of patients with left breast cancer.

Materials and Methods

Forty-five patients with left breast cancer were selected. The treatment plans were created applying three techniques for all patients. In the first plan (uncovered LAD), the treatment plan was made without considering LAD as OARs. In the two other plans, two MLCs with different leaf widths (6.8 mm and 5 mm) were used to shield the LAD. For all plans, MLC was shielded as much of OAR as possible without compromising planning target volume (PTV) coverage. Dosimetric parameters of the heart, LAD, and ipsilateral lung were assessed.

Results

Compared to other plans, the covered LAD plan 1(CL1) obtained lower lung, cardiac, and LAD doses with the same PTV coverage. On average, the mean heart dose decreased from 6.2 Gy to 5.4 Gy by CL1, and the average mean dose to the LAD was reduced from 36.4 Gy to 33.7 Gy, which was statistically significant. The average lung volume receiving >20 Gy was significantly reduced from 24.6% to 23.4%. Moreover, the results show that covered LAD plan 2(CL2) is less useful for shielding OARs compared to CL1.

Conclusion

CL1 plans may reduce OAR dose for patients without compromising the target coverage. Hence, the proper implementation of MLC can decrease the side effects of RT.

Delineating and sparing the ileal conduit in adjuvant radiotherapy for bladder cancer with modulated radiotherapy

Purpose

We undertook a prospective planning study to describe the delineation of ileal conduit (IC) loop on radiotherapy planning computed tomography (RTP CT) scan as an organ at risk (OAR) and its sparing using volumetric modulated arc therapy (VMAT) during adjuvant irradiation of bladder malignancies.

Materials and Methods

Fifteen patients with bladder malignancy needing adjuvant radiotherapy postoperatively and having normal renal function underwent delayed phase RTP CT from June 2020 to March 2021, with certain modifications (Foley's catheter through stoma, additional delayed scans). We identified the course of ureters, external stoma, IC, and uretero-ileal (right and left) anastomotic sites. VMAT plans were generated.

Results

A step-by-step description is given. Genitourinary OARs include kidneys, ureters, uretero-ileal anastomoses, and IC. The contrast on delayed scan opacifies ureters and IC. IC can be seen three-dimensionally as a structure with two fixed ends (blind proximal end anterior to the right sacroiliac joint and the open distal end over the right anterior abdominal wall in parasagittal location) and a 15-20 cm hanging intraabdominal loop that lies adjacent to the right iliac vessels. For prescription doses (PD) of 50.4 gray and 54 gray, respectively, VMAT plan achieved IC dose maximum to less than PD and V50 lower than 10 cc. Stoma sparing traditionally used as a surrogate for IC sparing is insufficient due to the variable intraabdominal location of IC loop.

Conclusions

Delineation of IC as an OAR is feasible with slight modifications in the RTP protocols. VMAT (or other forms of intensity modulated radiation therapy) can help IC sparing and should be considered when it lies in close proximity to target volumes and the risk of additional morbidity is considerable.

Dose-volume constraints for head-and-neck cancer in carbon ion radiotherapy: A literature review

BACKGROUND

Carbon ion radiotherapy (CIRT) has been applied in cancer treatment for over 25 years. However, guidelines for dose-volume constraints have not been established yet. The aim of this review is to summarize the dose-volume constraints in CIRT for head-and-neck (HN) cancer that were determined through previous clinical studies based on the Japanese models for relative biological effectiveness (RBE).

METHODS

A literature review was conducted to identify all constraints determined for HN cancer CIRT that are based on the Japanese RBE models.

RESULTS

Dose-volume constraints are reported for 17 organs at risk (OARs), including the brainstem, ocular structures, masticatory muscles, and skin. Various treatment planning strategies are also presented for reducing the dose delivered to OARs.

CONCLUSIONS

The reported constraints will provide assistance during treatment planning to ensure that radiation to OARs is minimized, and thus adverse effects are reduced. Although the constraints are given based on the Japanese RBE models, applying the necessary conversion factors will potentially enable their application by institutions worldwide that use the local effect model for RBE.

Auto-segmentation of important centers of growth in the pediatric skeleton to consider during radiation therapy based on deep learning

BACKGROUND

Routinely delineating of important skeletal growth centers is imperative to mitigate radiation-induced growth abnormalities for pediatric cancer patients treated with radiotherapy. However, it is hindered by several practical problems, including difficult identification, time consumption, and inter-practitioner variability.

PURPOSE

The goal of this study was to construct and evaluate a novel Triplet-Attention U-Net (TAU-Net)-based auto-segmentation model for important skeletal growth centers in childhood cancer radiotherapy, concentrating on the accuracy and time efficiency.

METHODS

A total of 107 childhood cancer patients fulfilled the eligibility criteria were enrolled in the training cohort (N = 80) and test cohort (N = 27). The craniofacial growth plates, shoulder growth centers, and pelvic ossification centers, with a total of 19 structures in the three groups, were manually delineated by two experienced radiation oncologists on axial, coronal, and sagittal computed tomography images. Modified from U-Net, the proposed TAU-Net has one main branch and two bypass branches, receiving semantic information of three adjacent slices to predict the target structure. With supervised deep learning, the skeletal growth centers contouring of each group was generated by three different auto-segmentation models: U-Net, V-Net, and the proposed TAU-Net. Dice similarity coefficient (DSC) and Hausdorff distance 95% (HD95) were used to evaluate the accuracy of three auto-segmentation models. The time spent on performing manual tasks and manually correcting auto-contouring generated by TAU-Net was recorded. The paired t-test was used to compare the statistical differences in delineation quality and time efficiency.

RESULTS

Among the three groups, including craniofacial growth plates, shoulder growth centers, and pelvic ossification centers groups, TAU-Net had demonstrated highly acceptable performance (the average DSC = 0.77, 0.87, and 0.83 for each group; the average HD95 = 2.28, 2.07, and 2.86 mm for each group). In the overall evaluation of 19 regions of interest (ROIs) in the test cohort, TAU-Net had an overwhelming advantage over U-Net (63.2% ROIs in DSC and 31.6% ROIs in HD95, p = 0.001-0.042) and V-Net (94.7% ROIs in DSC and 36.8% ROIs in HD95, p = 0.001-0.040). With an average time of 52.2 min for manual delineation, the average time saved to adjust TAU-Net-generated contours was 37.6 min (p < 0.001), a 72% reduction.

CONCLUSIONS

Deep learning-based models have presented enormous potential for the auto-segmentation of important growth centers in pediatric skeleton, where the proposed TAU-Net outperformed the U-Net and V-Net in geometrical precision for the majority status.

Deep learning-based two-step organs at risk auto-segmentation model for brachytherapy planning in parotid gland carcinoma

Purpose

Delineation of organs at risk (OARs) represents a crucial step for both tailored delivery of radiation doses and prevention of radiation-induced toxicity in brachytherapy. Due to lack of studies on auto-segmentation methods in head and neck cancers, our study proposed a deep learning-based two-step approach for auto-segmentation of organs at risk in parotid carcinoma brachytherapy.

Material and methods

Computed tomography images of 200 patients with parotid gland carcinoma were used to train and evaluate our in-house developed two-step 3D nnU-Net-based model for OARs auto-segmentation. OARs during brachytherapy were defined as the auricula, condyle process, skin, mastoid process, external auditory canal, and mandibular ramus. Auto-segmentation results were compared to those of manual segmentation by expert oncologists. Accuracy was quantitatively evaluated in terms of dice similarity coefficient (DSC), Jaccard index, 95^th-percentile Hausdorff distance (95HD), and precision and recall. Qualitative evaluation of auto-segmentation results was also performed.

Results

The mean DSC values of each OAR were 0.88, 0.91, 0.75, 0.89, 0.74, and 0.93, respectively, indicating close resemblance of auto-segmentation results to those of manual contouring. In addition, auto-segmentation could be completed within a minute, as compared with manual segmentation, which required over 20 minutes. All generated results were deemed clinically acceptable.

Conclusions

Our proposed deep learning-based two-step OARs auto-segmentation model demonstrated high efficiency and good agreement with gold standard manual contours. Thereby, this novel approach carries the potential in expediting the treatment planning process of brachytherapy for parotid gland cancers, while allowing for more accurate radiation delivery to minimize toxicity.

Reporting of Inter Fraction Dose Variations of Organs at Risk in Computed Tomography-Guided High Dose Rate Intracavitary Brachytherapy in Carcinoma Cervix

Assess the interfraction dose variations of the organs at risk (OARs) in carcinoma cervix high dose rate (HDR) computed tomography (CT)-guided intra cavitary brachytherapy (ICBT). 120 CT scans of 40 patients who had undergone three fractions of ICBT (7 Gy/fr) were analyzed. Dose to Point A and the minimum doses to the volumes of 2, 1, and 0.1cc of bladder, rectum and sigmoid colon were recorded. Revised plans were generated in 20 patients. Paired t-test was used to compare the difference in the means. Point "A" mean dose difference was statistically significant between the treated and revised plans. For bladder, the difference in means of dosage to all volumes, whilst for the rectum and sigmoid colon, the low volume dosage (0.1cc) was statistically significant. Absence of individualized planning would have resulted in underdosage of tumor and increased dosage of up to 30% to OARs. CT-guided ICBT should be implemented for each HDR fraction treatment.

Dose-Volume Constraints fOr oRganS At risk In Radiotherapy (CORSAIR): An "All-in-One" Multicenter-Multidisciplinary Practical Summary

BACKGROUND

The safe use of radiotherapy (RT) requires compliance with dose/volume constraints (DVCs) for organs at risk (OaRs). However, the available recommendations are sometimes conflicting and scattered across a number of different documents. Therefore, the aim of this work is to provide, in a single document, practical indications on DVCs for OaRs in external beam RT available in the literature.

MATERIAL AND METHODS

A multidisciplinary team collected bibliographic information on the anatomical definition of OaRs, on the imaging methods needed for their definition, and on DVCs in general and in specific settings (curative RT of Hodgkin's lymphomas, postoperative RT of breast tumors, curative RT of pediatric cancers, stereotactic ablative RT of ventricular arrythmia). The information provided in terms of DVCs was graded based on levels of evidence.

RESULTS

Over 650 papers/documents/websites were examined. The search results, together with the levels of evidence, are presented in tabular form.

CONCLUSIONS

A working tool, based on collected guidelines on DVCs in different settings, is provided to help in daily clinical practice of RT departments. This could be a first step for further optimizations.

Clinical evaluation of deep learning and atlas-based auto-segmentation for critical organs at risk in radiation therapy

INTRODUCTION

Contouring organs at risk (OARs) is a time-intensive task that is a critical part of radiation therapy. Atlas-based automatic segmentation has shown some success at reducing this time burden on practitioners; however, this method often requires significant manual editing to reach a clinically accurate standard. Deep learning (DL) auto-segmentation has recently emerged as a promising solution. This study compares the accuracy of DL and atlas-based auto-segmentation in relation to clinical 'gold standard' reference contours.

METHODS

Ninety CT datasets (30 head and neck, 30 thoracic, 30 pelvic) were automatically contoured using both atlas and DL segmentation techniques. Sixteen critical OARs were then quantitatively measured for accuracy using the Dice similarity coefficient (DSC) and Hausdorff distance (HD). Qualitative analysis was performed to visually classify the accuracy of each structure into one of four explicitly defined categories. Additionally, the time to edit atlas and DL contours to a clinically acceptable level was recorded for a subset of 9 OARs.

RESULTS

Of the 16 OARs analysed, DL delivered statistically significant improvements over atlas segmentation in 13 OARs measured with DSC, 12 OARs measured with HD, and 12 OARs measured qualitatively. The mean editing time for the subset of DL contours was 50%, 23% and 61% faster (all P < 0.05) than that of atlas segmentation for the head and neck, thorax, and pelvis respectively.

CONCLUSIONS

Deep learning segmentation comprehensively outperformed atlas-based contouring for the majority of evaluated OARs. Improvements were observed in geometric accuracy and visual acceptability, while editing time was reduced leading to increased workflow efficiency.

Automatic delineation of organ at risk in cervical cancer radiotherapy based on ensemble learning

OBJECTIVES

The automatic delineation of organs at risk (OARs) can help doctors make radiotherapy plans efficiently and accurately, and effectively improve the accuracy of radiotherapy and the therapeutic effect. Therefore, this study aims to propose an automatic delineation method for OARs in cervical cancer scenarios of both after-loading and external irradiation. At the same time, the similarity of OARs structure between different scenes is used to improve the segmentation accuracy of OARs in difficult segmentations.

METHODS

Our ensemble model adopted the strategy of ensemble learning. The model obtained from the pre-training based on the after-loading and external irradiation was introduced into the integrated model as a feature extraction module. The data in different scenes were trained alternately, and the personalized features of the OARs within the model and the common features of the OARs between scenes were introduced. Computer tomography (CT) images for 84 cases of after-loading and 46 cases of external irradiation were collected as the train data set. Five-fold cross-validation was adopted to split training sets and test sets. The five-fold average dice similarity coefficient (DSC) served as the figure-of-merit in evaluating the segmentation model.

RESULTS

The DSCs of the OARs (the rectum and bladder in the after-loading images and the bladder in the external irradiation images) were higher than 0.7. Compared with using an independent residual U-net (convolutional networks for biomedical image segmentation) model [residual U-net (Res-Unet)] delineate OARs, the proposed model can effectively improve the segmentation performance of difficult OARs (the sigmoid in the after-loading CT images and the rectum in the external irradiation images), and the DSCs were increased by more than 3%.

CONCLUSIONS

Comparing to the dedicated models, our ensemble model achieves the comparable result in segmentation of OARs for different treatment options in cervical cancer radiotherapy, which may be shorten time for doctors to sketch OARs and improve doctor's work efficiency.

Impact of Denoising on Deep-Learning-Based Automatic Segmentation Framework for Breast Cancer Radiotherapy Planning

Objective: This study aimed to investigate the segmentation accuracy of organs at risk (OARs) when denoised computed tomography (CT) images are used as input data for a deep-learning-based auto-segmentation framework. Methods: We used non-contrast enhanced planning CT scans from 40 patients with breast cancer. The heart, lungs, esophagus, spinal cord, and liver were manually delineated by two experienced radiation oncologists in a double-blind manner. The denoised CT images were used as input data for the AccuContourTM segmentation software to increase the signal difference between structures of interest and unwanted noise in non-contrast CT. The accuracy of the segmentation was assessed using the Dice similarity coefficient (DSC), and the results were compared with those of conventional deep-learning-based auto-segmentation without denoising. Results: The average DSC outcomes were higher than 0.80 for all OARs except for the esophagus. AccuContourTM-based and denoising-based auto-segmentation demonstrated comparable performance for the lungs and spinal cord but showed limited performance for the esophagus. Denoising-based auto-segmentation for the liver was minimal but had statistically significantly better DSC than AccuContourTM-based auto-segmentation (p < 0.05). Conclusions: Denoising-based auto-segmentation demonstrated satisfactory performance in automatic liver segmentation from non-contrast enhanced CT scans. Further external validation studies with larger cohorts are needed to verify the usefulness of denoising-based auto-segmentation.

Quality assurance based on deep learning for pelvic OARs delineation in radiotherapy

BACKGROUND

Correct delineation of organs at risk (OARs) is an important step for radiotherapy and it is also a time-consuming process that depends on many factors.

OBJECTIVE

An automatic quality assurance (QA) method based on deep learning (DL) was proposed to improve efficiency for detecting contouring errors of OARs.

MATERIALS AND METHODS

A total of 180 planning CT scan sets at the pelvic site and the corresponding OARs contours from clinics were enrolled in this study. Among them, 140 cases were randomly chosen as the training datasets, 20 cases were used as the validation datasets, and the remaining 20 cases were used as the test datasets. DL-based models were trained through data curation for data cleaning based on the Dice similarity coefficient and the 95th percentile Hausdorff distance between the original contours and the predicted contours. All contouring errors could be classified into two types：minor modification required and major modification required. The pass criteria were established using Bias-Corrected and Accelerated bootstrap on 20 manually reviewed validation datasets. The performance of the QA method was evaluated with the metrics of sensitivity, specificity, the area under the receiving operator characteristic curve (AUC) and detection rate sensitivity on the 20 test datasets.

RESULTS

For all OARs, segmentation results after data curation were superior to those without. The sensitivity of the QA method was greater than 0.890 and the specificity was higher than 0.975. The AUCs were 0.948, 0.966, 0.965 and 0.932 for the bladder, right femoral head, left femoral head and rectum, respectively. Almost all major errors could be detected by the automatic QA method, and the lowest detection rate sensitivity of minor errors was 0.863 for the rectum.

CONCLUSIONS

QA of OARs is an important step for the correct implementation of radiotherapy. The DL-based QA method proposed in this study showed a high potential to automatically detect contouring errors with high precision. The method can be integrated into the existing radiotherapy procedures to improve the efficiency of delineating the OARs.

Association between radiation dose to organs at risk and acute patient reported outcome during radiation treatment for head and neck cancers

BACKGROUND

Associations between patient-reported outcomes and dose to organs at risk (OARs) may promote management and guide future investigations.

METHODS

We retrospectively evaluated PROs and OAR dose in head and neck (H&N) cancer.

RESULTS

In 169 patients, we identified weak associations between: "Difficulty swallowing/chewing" and increased mean RT dose to the oral cavity, larynx, pharyngeal constrictor muscles (PCM) and contralateral parotid; "choking/coughing" and larynx mean dose; "problems with mucus in mouth and throat" and oral cavity, contralateral parotid mean dose and parotid V30, contralateral submandibular gland and PCM mean dose; "difficulty with voice/speech" and oral cavity, contralateral parotid, contralateral submandibular gland and larynx mean dose; and "dry mouth" and ipsilateral submandibular gland, oral cavity and PCM mean dose.

CONCLUSION

We identified weak associations between PRO and dose to OARs-these data can guide on treatment management, patient counseling, and serve as a baseline for future investigations.

RefineNet-based 2D and 3D automatic segmentations for clinical target volume and organs at risks for patients with cervical cancer in postoperative radiotherapy

PURPOSE

An accurate and reliable target volume delineation is critical for the safe and successful radiotherapy. The purpose of this study is to develop new 2D and 3D automatic segmentation models based on RefineNet for clinical target volume (CTV) and organs at risk (OARs) for postoperative cervical cancer based on computed tomography (CT) images.

METHODS

A 2D RefineNet and 3D RefineNetPlus3D were adapted and built to automatically segment CTVs and OARs on a total of 44 222 CT slices of 313 patients with stage I-III cervical cancer. Fully convolutional networks (FCNs), U-Net, context encoder network (CE-Net), UNet3D, and ResUNet3D were also trained and tested with randomly divided training and validation sets, respectively. The performances of these automatic segmentation models were evaluated by Dice similarity coefficient (DSC), Jaccard similarity coefficient, and average symmetric surface distance when comparing them with manual segmentations with the test data.

RESULTS

The DSC for RefineNet, FCN, U-Net, CE-Net, UNet3D, ResUNet3D, and RefineNet3D were 0.82, 0.80, 0.82, 0.81, 0.80, 0.81, and 0.82 with a mean contouring time of 3.2, 3.4, 8.2, 3.9, 9.8, 11.4, and 6.4 s, respectively. The generated RefineNetPlus3D demonstrated a good performance in the automatic segmentation of bladder, small intestine, rectum, right and left femoral heads with a DSC of 0.97, 0.95, 091, 0.98, and 0.98, respectively, with a mean computation time of 6.6 s.

CONCLUSIONS

The newly adapted RefineNet and developed RefineNetPlus3D were promising automatic segmentation models with accurate and clinically acceptable CTV and OARs for cervical cancer patients in postoperative radiotherapy.

Geometric and Dosimetric Evaluation of the Automatic Delineation of Organs at Risk (OARs) in Non-Small-Cell Lung Cancer Radiotherapy Based on a Modified DenseNet Deep Learning Network

Purpose

To introduce an end-to-end automatic segmentation model for organs at risk (OARs) in thoracic CT images based on modified DenseNet, and reduce the workload of radiation oncologists.

Materials and Methods

The computed tomography (CT) images of 36 lung cancer patients were included in this study, of which 27 patients’ images were randomly selected as the training set, 9 patients’ as the testing set. The validation set was generated by cross validation and 6 patients’ images were randomly selected from the training set during each epoch as the validation set. The autosegmentation task of the left and right lungs, spinal cord, heart, trachea and esophagus was implemented, and the whole training time was approximately 5 hours. Geometric evaluation metrics including the Dice similarity coefficient (DSC), 95% Hausdorff distance (HD95) and average surface distance (ASD), were used to assess the autosegmentation performance of OARs based on the proposed model and were compared with those based on U-Net as benchmarks. Then, two sets of treatment plans were optimized based on the manually contoured targets and OARs (Plan1), as well as the manually contours targets and the automatically contoured OARs (Plan2). Dosimetric parameters, including Dmax, Dmean and Vx, of OARs were obtained and compared.

Results

The DSC, HD95 and ASD of the proposed model were better than those of U-Net. The differences in the DSC of the spinal cord and esophagus, differences in the HD95 of the spinal cord, heart, trachea and esophagus, as well as differences in the ASD of the spinal cord were statistically significant between the two models (P<0.05). The differences in the dose-volume parameters of the two sets of plans were not statistically significant (P>0.05). Moreover, compared with manual segmentation, autosegmentation significantly reduced the contouring time by nearly 40.7% (P<0.05).

Conclusions

The bilateral lungs, spinal cord, heart and trachea could be accurately delineated using the proposed model in this study; however, the automatic segmentation effect of the esophagus must still be further improved. The concept of feature map reuse provides a new idea for automatic medical image segmentation.

Knowledge-based quality control of organ delineations in radiation therapy

PURPOSE

To reduce the likelihood of errors in organ delineations used for radiotherapy treatment planning, a knowledge-based quality control (KBQC) system, which discriminates between valid and anomalous delineations is developed.

METHOD AND MATERIALS

The KBQC is comprised of a group-wise inference system and anomaly detection modules trained using historical priors from 296 locally advanced lung and prostate cancer patient computational tomographies (CTs). The inference system discriminates different organs based on shape, relational, and intensity features. For a given delineated image set, the inference system solves a combinatorial optimization problem that results in an organ group whose relational features follow those of the training set considering the posterior probabilities obtained from support vector machine (SVM), discriminant subspace ensemble (DSE), and artificial neural network (ANN) classifiers. These classifiers are trained on nonrelational features with a 10-fold cross-validation scheme. The anomaly detection module is a bank of ANN autoencoders, each corresponding with an organ, trained on nonrelational features. A heuristic rule detects anomalous organs that exceed predefined organ-specific tolerances for the feature reconstruction error and the classifier's posterior probabilities. Independent data sets with anomalous delineations were used to test the overall performance of the KBQC system. The anomalous delineations were manually manipulated, computer-generated, or propagated based on a transformation obtained by imperfect registrations. Both peer-review-based scoring system and shape similarity coefficient (DSC) were used to label regions of interest (ROIs) as normal or anomalous in two independent test cohorts.

RESULTS

The accuracy of the classifiers was ≥ $\ge$ 99.8%, and the minimum per-class F1-scores were 0.99, 0.99, and 0.98 for SVM, DSE, and ANN, respectively. The group-wise inference system reduced the miss-classification likelihood for the test data set with anomalous delineations compared to each individual classifier and a fused classifier that used the average posterior probability of all classifiers. For 15 independent locally advanced lung patients, the system detected > $>$ 79% of the anomalous ROIs. For 1320 auto-segmented abdominopelvic organs, the anomaly detection system identified anomalous delineations, which also had low Dice similarity coefficient values with respect to manually delineated organs in the training data set.

CONCLUSION

The KBQC system detected anomalous delineations with superior accuracy compared to classification methods that judge only based on posterior probabilities.

Dosimetric comparison between intensity-modulated radiotherapy and volumetric-modulated arc therapy in patients of left-sided breast cancer treated with modified radical mastectomy: CONSORT

Volumetric-modulated arc therapy (VMAT) is a novel treatment strategy that protects normal tissues and enhances target volume coverage during radiotherapy.This study aimed to clarify whether VMAT is superior to intensity-modulated radiotherapy (IMRT) in treatment planning for left-sided breast cancer patients after modified radical mastectomy.Left-sided breast cancer patients treated with modified radical mastectomy were eligible for analysis. The dose distribution of both planning target volume and organs at risk were analyzed by using dose volume histograms.Twenty-four patients were eligible for analysis. Both VMAT and IMRT plans were sufficient in planning target volume coverage. In terms of conformity, VMAT was superior to IMRT (P = .034). Dmean, V5, and V10 of the heart were significantly decreased in VMAT plans when compared with IMRT plans. VMAT was as effective as IMRT plans in sparing of other normal tissues. In addition, both the mean number of monitor units and treatment time were significantly reduced when VMAT was compared with IMRT.VMAT plans was equivalent or superior to IMRT plans in dose distribution, and was associated with slightly advantage in sparing of the heart and coronary arteries. Our analyses suggested VMAT as a preferred option in left-sided breast cancer patients treated with modified radical mastectomy.

Cascaded deep learning-based auto-segmentation for head and neck cancer patients: Organs at risk on T2-weighted magnetic resonance imaging

PURPOSE

To investigate multiple deep learning methods for automated segmentation (auto-segmentation) of the parotid glands, submandibular glands, and level II and level III lymph nodes on magnetic resonance imaging (MRI). Outlining radiosensitive organs on images used to assist radiation therapy (radiotherapy) of patients with head and neck cancer (HNC) is a time-consuming task, in which variability between observers may directly impact on patient treatment outcomes. Auto-segmentation on computed tomography imaging has been shown to result in significant time reductions and more consistent outlines of the organs at risk.

METHODS

Three convolutional neural network (CNN)-based auto-segmentation architectures were developed using manual segmentations and T2-weighted MRI images provided from the American Association of Physicists in Medicine (AAPM) radiotherapy MRI auto-contouring (RT-MAC) challenge dataset (n = 31). Auto-segmentation performance was evaluated with segmentation similarity and surface distance metrics on the RT-MAC dataset with institutional manual segmentations (n = 10). The generalizability of the auto-segmentation methods was assessed on an institutional MRI dataset (n = 10).

RESULTS

Auto-segmentation performance on the RT-MAC images with institutional segmentations was higher than previously reported MRI methods for the parotid glands (Dice: 0.860 ± 0.067, mean surface distance [MSD]: 1.33 ± 0.40 mm) and the first report of MRI performance for submandibular glands (Dice: 0.830 ± 0.032, MSD: 1.16 ± 0.47 mm). We demonstrate that high-resolution auto-segmentations with improved geometric accuracy can be generated for the parotid and submandibular glands by cascading a localizer CNN and a cropped high-resolution CNN. Improved MSDs were observed between automatic and manual segmentations of the submandibular glands when a low-resolution auto-segmentation was used as prior knowledge in the second-stage CNN. Reduced auto-segmentation performance was observed on our institutional MRI dataset when trained on external RT-MAC images; only the parotid gland auto-segmentations were considered clinically feasible for manual correction (Dice: 0.775 ± 0.105, MSD: 1.20 ± 0.60 mm).

CONCLUSIONS

This work demonstrates that CNNs are a suitable method to auto-segment the parotid and submandibular glands on MRI images of patients with HNC, and that cascaded CNNs can generate high-resolution segmentations with improved geometric accuracy. Deep learning methods may be suitable for auto-segmentation of the parotid glands on T2-weighted MRI images from different scanners, but further work is required to improve the performance and generalizability of these methods for auto-segmentation of the submandibular glands and lymph nodes.

Automatic segmentation of organs-at-risks of nasopharynx cancer and lung cancer by cross-layer attention fusion network with TELD-Loss

PURPOSE

Radiotherapy is one of the main treatments of nasopharyngeal cancer (NPC) and lung cancer. Accurate segmentation of organs at risks (OARs) in CT images is a key step in radiotherapy planning for NPC and lung cancer. However, the segmentation of OARs is influenced by the highly imbalanced size of organs, which often results in very poor segmentation results for small and difficult-to-segment organs. In addition, the complex morphological changes and fuzzy boundaries of OARs also pose great challenges to the segmentation task. In this paper, we propose a cross-layer attention fusion network (CLAF-CNN) to solve the problem of accurately segmenting OARs.

METHODS

In CLAF-CNN, we integrate the spatial attention maps of the adjacent spatial attention modules to make the segmentation targets more accurately focused, so that the network can capture more target-related features. In this way, the spatial attention modules in the network can be learned and optimized together. In addition, we introduce a new Top-K exponential logarithmic Dice loss (TELD-Loss) to solve the imbalance problem in OAR segmentation. The TELD-Loss further introduces a Top-K optimization mechanism based on Dice loss and exponential logarithmic loss, which makes the network pay more attention to small organs and difficult-to-segment organs, so as to enhance the overall performance of the segmentation model.

RESULTS

We validated our framework on the OAR segmentation datasets of the head and neck and lung CT images in the StructSeg 2019 challenge. Experiments show that the CLAF-CNN outperforms the state-of-the-art attention-based segmentation methods in the OAR segmentation task with average Dice coefficient of 79.65% for head and neck OARs and 88.39% for lung OARs.

CONCLUSIONS

This work provides a new network named CLAF-CNN which contains cross-layer spatial attention map fusion architecture and TELD-Loss for OAR segmentation. Results demonstrated that the proposed method could obtain accurate segmentation results for OARs, which has a potential of improving the efficiency of radiotherapy planning for nasopharynx cancer and lung cancer.

Use of a Biodegradable, Contrast-Filled Rectal Spacer Balloon in Intensity-Modulated Radiotherapy for Intermediate-Risk Prostate Cancer Patients: Dosimetric Gains in the BioPro-RCMI-1505 Study

Background/purpose

Dose-escalated external beam radiotherapy (RT) is effective in the control of prostate cancer but is associated with a greater incidence of rectal adverse events. We assessed the dosimetric gain and safety profile associated with implantation of a new biodegradable rectal spacer balloon.

Materials/methods

Patients scheduled for image-guided, intensity-modulated RT for intermediate-risk prostate cancer were prospectively included in the French multicenter BioPro-RCMI-1505 study (NCT02478112). We evaluated the dosimetric gain, implantation feasibility, adverse events (AEs), and prostate-cancer-specific quality of life associated with use of the balloon spacer.

Results

After a scheduled review of the initial recruitment target of 50 patients by the study's independent data monitoring committee (IDMC), a total of 24 patients (including 22 with dosimetry data) were included by a single center between November 2016 and May 2018. The interventional radiologist who implanted the balloons considered that 86% of the procedures were easy. 20 of the 24 patients (83.3%) received IMRT and 4 (16.7%) received volumetric modulated arc therapy (78-80 Gy delivered in 39 fractions). The dosimetric gains associated with spacer implantation were highly significant (p<0.001) for most variables. For the rectum, the median (range) relative gain ranged from 15.4% (-9.2-47.5) for D20cc to 91.4% (36.8-100.0) for V70 Gy (%). 15 patients (62%) experienced an acute grade 1 AE, 8 (33%) experienced a late grade 1 AE, 1 (4.2%) experienced an acute grade 2 AE, and 3 experienced a late grade 2 AE. No grade 3 AEs were reported. Quality of life was good at baseline (except for sexual activity) and did not markedly worsen during RT and up to 24 months afterwards.

Conclusion

The use of a biodegradable rectal spacer balloon is safe, effective and associated with dosimetric gains in modern RT for intermediate-risk prostate cancer.

Role of MRI-Based Functional Imaging in Improving the Therapeutic Index of Radiotherapy in Cancer Treatment

Advances in radiation technology, such as intensity-modulated radiation therapy (IMRT), have largely enabled a biological dose escalation of the target volume (TV) and reduce the dose to adjacent tissues or organs at risk (OARs). However, the risk of radiation-induced injury increases as more radiation dose utilized during radiation therapy (RT), which predominantly limits further increases in TV dose distribution and reduces the local control rate. Thus, the accurate target delineation is crucial. Recently, technological improvements for precise target delineation have obtained more attention in the field of RT. The addition of functional imaging to RT can provide a more accurate anatomy of the tumor and normal tissues (such as location and size), along with biological information that aids to optimize the therapeutic index (TI) of RT. In this review, we discuss the application of some common MRI-based functional imaging techniques in clinical practice. In addition, we summarize the main challenges and prospects of these imaging technologies, expecting more inspiring developments and more productive research paths in the near future.

Clinical characteristics and outcomes of Langerhans cell histiocytosis at a single institution in Thailand: a 20-year retrospective study

Background

Langerhans cell histiocytosis (LCH) is a rare disease characterized by the various systems involved and clinical manifestations with a wide range of symptoms.

Objectives

To describe clinical characteristics, imaging, treatment, and outcomes of pediatric LCH at Phramongkutklao Hospital, Bangkok, Thailand.

Methods

We conducted a 20-year retrospective review of the medical records of patients diagnosed with LCH from birth to 21 years old from January 1, 1997, to December 31, 2016.

Results

In all, 14 patients with median age of 2.5 years were studied. Six (43%) patients had single-system (SS) LCH. Five patients (63%) with multisystem (MS) LCH (n = 8. 57%) had risk-organ involvement (RO+). All patients had plain X-ray imaging of their skull with 11 (79%) showing abnormal findings. Tc-99m bone imaging and fluorodeoxyglucose F18 (FDG) positron emission tomography (PET)-computed tomography (CT) demonstrated abnormal findings in 8 (89%) and 4 (29%) patients, respectively. The 5-year event-free survival (EFS) for patients with RO+ MS-LCH was less than that for those without risk-organ involvement (RO-) MS-LCH and SS-LCH (20% vs. 100%, P = 0.005). Hematological dysfunction, hypoalbuminemia, and conjugated hyperbilirubinemia may be worse prognostic factors for RO+ MS-LCH.

Conclusion

FDG-PET-CT might have a greater accuracy to detect LCH disease than conventional plain X-ray and Tc-99m bone imaging. RO+ MS-LCH has been encountered with relapse and poor outcomes. Hematopoietic involvement, hypoalbuminemia, and conjugated hyperbilirubinemia may be worse prognostic factors for RO+ MS-LCH.

Support Vector Machine Model Predicts Dose for Organs at Risk in High-Dose Rate Brachytherapy of Cervical Cancer

Introduction

This study aimed to establish a support vector machine (SVM) model to predict the dose for organs at risk (OARs) in intracavitary brachytherapy planning for cervical cancer with tandem and ovoid treatments.

Methods

Fifty patients with loco-regionally advanced cervical cancer treated with 200 CT-based tandem and ovoid brachytherapy plans were included. The brachytherapy plans were randomly divided into the training (N = 160) and verification groups (N = 40). The bladder, rectum, sigmoid colon, and small intestine were divided into sub-OARs. The SVM model was established using MATLAB software based on the sub-OAR volume to predict the bladder, rectum, sigmoid colon, and small intestine D 2 c m 3 . Model performance was quantified by mean squared error (MSE) and δ ( δ = | D 2 c m 3 / D prescription ( actual ) - D 2 c m 3 / D prescription ( predicted ) | ) . The goodness of fit of the model was quantified by the coefficient of determination (R²). The accuracy and validity of the SVM model were verified using the validation group.

Results

The D 2 c m 3 value of the bladder, rectum, sigmoid colon, and small intestine correlated with the volume of the corresponding sub-OARs in the training group. The mean squared error (MSE) in the SVM model training group was <0.05; the R² of each OAR was >0.9. There was no significant difference between the D 2 c m 3 -predicted and actual values in the validation group (all P > 0.05): bladder δ = 0.024 ± 0.022, rectum δ = 0.026 ± 0.014, sigmoid colon δ = 0.035 ± 0.023, and small intestine δ = 0.032 ± 0.025.

Conclusion

The SVM model established in this study can effectively predict the D 2 c m 3 for the bladder, rectum, sigmoid colon, and small intestine in cervical cancer brachytherapy.

Re-Irradiation for Head and Neck Cancer: Cumulative Dose to Organs at Risk and Late Side Effects

Simple Summary

Local recurrences of head and neck cancer are unfortunately common and can be difficult to treat. The treatment is challenging, partly due to the location, with several important organs in the head and neck area, but also because recurrence often occurs in an area already treated with radiotherapy. It has been shown that repeat radiotherapy, re-irradiation, can offer long-lasting tumor control and sometimes even cure in selected patients. However, there is a risk of normal tissue close to the tumor being damaged by high cumulative doses of radiotherapy. In this study, we aim to establish levels of cumulative dose to specific organs that could be considered reasonably safe to deliver at re-irradiation without causing high rates of severe side effects. Increased knowledge in dose–response relationships in re-irradiation for head and neck cancer will facilitate a tailored treatment for the individual patient.

Abstract

Re-irradiation in head and neck cancer is challenging, and cumulative dose constraints and dose/volume data are scarce. In this study, we present dose/volume data for patients re-irradiated for head and neck cancer and explore the correlations of cumulative dose to organs at risk and severe side effects. We analyzed 54 patients re-irradiated for head and neck cancer between 2011 and 2017. Organs at risk were delineated and dose/volume data were collected from cumulative treatment plans of all included patients. Receiver–operator characteristics (ROC) analysis assessed the association between dose/volume parameters and the risk of toxicity. The ROC-curve for a logistic model of carotid blowout vs. maximum doses to the carotid arteries showed AUC = 0.92 (95% CI 0.83 to 1.00) and a cut-off value of 119 Gy (sensitivity 1.00/specificity 0.89). The near-maximum dose to bones showed an association with the risk of osteoradionecrosis: AUC = 0.74 (95% CI 0.52 to 0.95) and a cut-off value of 119 Gy (sensitivity 1.00/specificity 0.52). Our analysis showed an association between cumulative dose to organs at risk and the risk of developing osteoradionecrosis and carotid blowout, and our results support the existing dose constraint for the carotid arteries of 120 Gy. The confirmation of these dose–response relationships will contribute to further improvements of re-irradiation strategies.

Evaluation of Three-Dimensional Conformal Radiotherapy and Intensity Modulated Radiotherapy Techniques for Left Breast Post-Mastectomy Patients: Our Experience in Nigerian Sovereign Investment Authority-Lagos University Teaching Hospital Cancer Center, South-West Nigeria

Objective

This study aimed to evaluate the dosimetric properties of treatment plans obtained from three-dimensional conformal radiotherapy (3D-CRT) and intensity-modulated radiotherapy techniques (IMRT) plans for left chest wall breast cancer patients.

Materials and Methods

A total of 20 patients with left-sided chest wall radiotherapy were randomly selected with the dose prescriptions: 42 Gy and 45 Gy in 15 and 18 fractions, respectively. Treatment plans were obtained using 3D-CRT and IMRT for each patient. Five to seven beams were used for IMRT, while tangential beams were used for 3D-CRT. Planning target volume, D_near-max (D₂ ), D_near-min (D₉₈ ), D_mean, Homogeneity and Conformity Indices (HI and CI) were obtained. Similarly, mean doses to organs at risk (OAR), V₅, V₁₀, V₂₀, V₂₅ were generated from the dose-volume histogram and compared.

Results

IMRT showed a significant improvement in HI compared to 3D-CRT (p<0.0001). Although there was no significant difference in sparing of the left lung between both plans for high-dose volumes (V20: 18.2 vs 30.55, p<0.0001), (V25: 11.17 vs 28.12, p<0.0001). IMRT however showed supremacy to 3D-CRT with high-dose volumes for the heart, including V20 (4.44 vs 10.29, p = 0.02), V25 (2.08 vs 8.94, p = 0.002). 3D-CRT was better than IMRT in low-dose volumes for left lung (V5: 92.23 vs 56.60, p<0.001; V10: 60.98 vs 47.20, p = 0.04) and heart (V5: 57.45 vs 30.39, p = 0.004).

Conclusion

IMRT showed better homogeneity and sparing of high-dose volumes to OAR than 3D-CRT. On the other hand, 3D-CRT showed a reduction of low-dose volumes to OARs than IMRT.

Photon Versus Proton Beam Therapy for T1-3 Squamous Cell Carcinoma of the Thoracic Esophagus Without Lymph Node Metastasis

Background and Purpose

We compared treatment outcomes and toxicities of photon radiotherapy versus proton beam therapy (PBT) and evaluated radiation field effects for T1–3 squamous cell carcinoma of the thoracic esophagus (EC) without lymph node metastasis.

Methods

Medical records of 77 patients with T1–3N0M0 thoracic EC treated with radiotherapy between 2011 and 2019 were retrospectively analyzed. Among these patients, 61 (79.2%) individuals had T1 EC. The initial clinical target volume encompassed the whole esophagus with or without supraclavicular and/or abdominal lymph nodes (extended-field radiotherapy; 67 patients, 87.0%) or the area 3–5 cm craniocaudally and 1–2 cm radially from the gross tumor volume (involved-field radiotherapy; 10 patients, 13.0%). The final clinical target volume included margins of at least 1 cm from the gross tumor volume, with total radiation doses of 50–66 (median, 66) cobalt gray equivalent. Three-dimensional conformal radiotherapy, intensity-modulated radiotherapy, and PBT were used in twenty-four, five, and forty-eight patients, respectively. Concurrent chemotherapy was administered to 17 (22.0%) patients overall and only five (8.0%) T1 patients.

Results

PBT showed significantly lower lung and heart radiation exposure in mean dose, V5, V10, V20, and V30 than photon radiotherapy. The median follow-up for all patients was 46 (interquartile range, 22–72) months. The 5-year progression-free survival and overall survival rates were 56.5 and 64.9%, respectively, with no significant survival difference between photon radiotherapy and PBT. In patients with T1 EC, 5-year progression-free survival and overall survival rates were 62.6 and 73.5%, respectively.

Conclusions

Extended-field radiotherapy using modern radiotherapy techniques without chemotherapy showed satisfactory clinical outcomes for lymph node-negative T1 EC.

Dosimetric Comparison of Whole Breast Radiotherapy Using Field-in-Field and Volumetric Modulated Arc Therapy Techniques in Left-Sided Breast Cancer Patients

Introduction

The radiotherapy of left-sided breast cancers is challenging because of neighboring critical organs, posing an increased risk of complications. Various radiation delivery techniques have been used to deliver the desired dose of radiation to the target area while keeping the doses to nearby structures within constraints.

The main aim of this study is to quantify doses delivered to the organs at risk (OARs) including heart, left lung, spinal cord, and contralateral breast, and to the planning target volume (PTV) using Field-in-Field (FIF) and Volumetric Modulated Arc Therapy (VMAT).

Patients and methods

A retrospective review of 15 left-sided breast cancer patients was done. All the patients underwent breast-conserving surgery and adjuvant radiation. For every patient, two different radiation treatment plans were formulated and compared for the PTV coverage and doses to OARs, including heart, ipsilateral lung, spinal cord, and contralateral breast.

The radiation treatment techniques utilized for this purpose were FIF and VMAT. The homogeneity index (HI), and conformity index (CI) required for the treatment planning were also calculated. Data was analyzed using Statistical Package for the Social Sciences (IBM Corp., Armonk, USA). An Independent T-test was used for statistical analysis.

Results

The mean age was 41 years and the majority of them were stage II. Total nine patients were given 4005centi Gray (cGy) in 15 fractions (fr) followed by 10Gy boost, hence receiving a total dose of 5005cGy in 20fr. While remaining six patients were given a total dose 4005cGy in 15fr without any boost.

All patients were hypofractionated and the dose was delivered at a rate of 267cGy per fr. The FIF technique utilized in breast cancer radiation significantly reduced the mean doses to OARs: mean heart dose (3.81cGy), ipsilateral lung dose (V16- 15cGy), mean contralateral breast dose (0.03cGy), and maximum spinal cord dose (0.18cGy); as compared to VMAT technique which delivered comparatively higher doses: mean heart dose (8.85cGy), ipsilateral lung dose (V16- 19.82cGy), mean contralateral breast dose (4.59cGy), and maximum spinal cord dose (7.14cGy).

There was a significant mean difference between doses of OARs and all p-values were statistically significant (p<0.005). Moreover, the FIF technique also improves the dose distribution of PTV in terms of dose homogeneity. However, the conformity index is more enhanced with VMAT as opposed to FIF.

Conclusion

The FIF technique is more advantageous than the VMAT planning technique because it provides better dose distribution in terms of PTV coverage and significantly lower doses to OARs in radiotherapy to left-sided breast cancer.

The effect of imaging modality (magnetic resonance imaging vs. computed tomography) and patient position (supine vs. prone) on target and organ at risk doses in partial breast irradiation

INTRODUCTION

Conventionally computed tomography (CT) has been used to delineate target volumes in radiotherapy; however, magnetic resonance imaging (MRI) is being continually integrated into clinical practice; therefore, the investigation into targets derived from MRI is warranted. The purpose of this study was to evaluate the impact of imaging modality (MRI vs. CT) and patient positioning (supine vs. prone) on planning target volumes (PTVs) and organs at risk (OARs) for partial breast irradiation (PBI).

METHODS

A retrospective data set, of 35 patients, was accessed where each patient had undergone MRI and CT imaging for tangential whole breast radiotherapy in both the supine and prone position. PTVs were defined from seroma cavity (SC) volumes delineated on each respective image, resulting in 4 PTVs per patient. PBI plans were generated with 6MV external beam radiotherapy (EBRT) using the TROG 06.02 protocol guidelines. A prescription of 38.5Gy in 10 fractions was used for all cases. The impact analysis of imaging modality and patient positioning included dose to PTVs, and OARs based on agreed criteria. Statistical analysis was conducted though Mann-Whitey U, Fisher's exact and chi-squared testing (P < 0.005).

RESULTS

Twenty-four patients were eligible for imaging analysis. However, positioning analysis could only be investigated on 19 of these data sets. No statistically significant difference was found in OAR doses based on imaging modality. Supine patient position resulted in lower contralateral breast dose (0.10Gy ± 0.35 vs. 0.33Gy ± 0.78, p = 0.011). Prone positioning resulted in a lower dose to ipsilateral lung volumes (10.85Gy ± 11.37 vs. 3.41Gy ± 3.93, P = <0.001).

CONCLUSIONS

PBI plans with PTVs derived from MRI exhibited no clinically significant differences when compared to plans created from CT in relation to plan compliance and OAR dose. Patient position requires careful consideration regardless of imaging modality chosen. Although there was no proven superiority of MRI derived target volumes, it indicates that MRI could be considered for PBI target delineation.

Potential gains: Comparison of a mono-isocentric three-dimensional conformal radiotherapy (3D-CRT) planning technique to hybrid intensity-modulated radiotherapy (hIMRT) to the whole breast and supraclavicular fossa (SCF) region

Introduction

Until late 2018, standard of practice at the Northern Sydney Cancer Centre (NSCC) for breast and nodal treatment was a conformal mono‐isocentric technique. A planning study comparing an existing mono‐isocentric three‐dimensional conformal radiotherapy (3D‐CRT) planning technique to a hybrid intensity‐modulated radiotherapy (hIMRT) approach for the whole breast and supraclavicular fossa (SCF) region was undertaken with the aim to improve plan quality by improving dose conformity/homogeneity across target volumes and reducing hotspots outside the target.

Methods

A cohort of 17 patients was retrospectively planned using the proposed hIMRT technique, keeping the same planning constraints as the original treated breast and SCF 3D‐CRT plan and normalising the 3D‐CRT plans to achieve minimum breast/SCF target coverage to compare organs at risk (OARs). Normal tissue index (NTI) and homogeneity index (HI) were compared for plan quality as well as for evaluating OARs.

Results

The hIMRT technique showed statistically significant improvements in NTI and HI, as well as improvement in maximum brachial plexus and thyroid doses. There was a negligible increase in maximum oesophagus dose which could be improved if used in optimisation. Other OAR doses in the irradiated region were comparable to the 3D‐CRT plans, however maximum doses were reduced overall.

Conclusion

The hIMRT planning technique maintained clinically acceptable doses to OARs and reduced normal tissue dose while maintaining equivalent dose coverage to breast and SCF planning target volumes with improved conformity and homogeneity. The reduction in maximum doses promotes a favourable toxicity profile, with potential benefit of improved long‐term cosmesis.

A Preliminary Experience of Implementing Deep-Learning Based Auto-Segmentation in Head and Neck Cancer: A Study on Real-World Clinical Cases

Purpose

While artificial intelligence has shown great promise in organs-at-risk (OARs) auto segmentation for head and neck cancer (HNC) radiotherapy, to reach the level of clinical acceptance of this technology in real-world routine practice is still a challenge. The purpose of this study was to validate a U-net-based full convolutional neural network (CNN) for the automatic delineation of OARs of HNC, focusing on clinical implementation and evaluation.

Methods

In the first phase, the CNN was trained on 364 clinical HNC patients’ CT images with annotated contouring from routine clinical cases by different oncologists. The automated delineation accuracy was quantified using the Dice similarity coefficient (DSC) and 95% Hausdorff distance (HD). To assess efficiency, the time required to edit the auto-contours to a clinically acceptable standard was evaluated by a questionnaire. For subjective evaluation, expert oncologists (more than 10 years’ experience) were randomly presented with automated delineations or manual contours of 15 OARs for 30 patient cases. In the second phase, the network was retrained with an additional 300 patients, which were generated by pre-trained CNN and edited by oncologists until to meet clinical acceptance.

Results

Based on DSC, the CNN performed best for the spinal cord, brainstem, temporal lobe, eyes, optic nerve, parotid glands and larynx (DSC >0.7). Higher conformity for the OARs delineation was achieved by retraining our architecture, largest DSC improvement on oral cavity (0.53 to 0.93). Compared with the manual delineation time, after using auto-contouring, this duration was significantly shortened from hours to minutes. In the subjective evaluation, two observes showed an apparent inclination on automatic OARs contouring, even for relatively low DSC values. Most of the automated OARs segmentation can reach the clinical acceptance level compared to manual delineations.

Conclusions

After retraining, the CNN developed for OARs automated delineation in HNC was proved to be more robust, efficiency and consistency in clinical practice. Deep learning-based auto-segmentation shows great potential to alleviate the labor-intensive contouring of OAR for radiotherapy treatment planning.

Dosimetric comparison of organs at risk in 5 different radiotherapy plans in patients with preoperatively irradiated rectal cancer

BACKGROUND

Intensity-modulated radiotherapy (IMRT) is a widely used irradiation technique in rectal cancer patients. We aimed to compare 4 different IMRT plans with 3-dimensional conformal radiotherapy (3D-CRT) considering organs at risk (OARs) in patients with rectal carcinoma.

METHODS

This retrospective study included 27 rectal cancer patients who were irradiated preoperatively between January 2016 and December 2018. Five different plans (4-field 3D-CRT in 2 phases, 7-field IMRT in 2 phases, 9-field IMRT in 2 phases, 7-field simultaneous integrated boost [SIB] IMRT, and 9-field SIB IMRT) were generated for each patient. Comparison of 5 different plans according to bladder and bilateral femoral head mean doses, bladder V40, bilateral femoral head V40, and small bowel V35 values were evaluated.

RESULTS

Most of the OAR parameters significantly favored IMRT plans compared to the 3D-CRT plan. The largest difference was observed in bladder V40 values (reduction of V40 value up to 51.2% reduction) in favor of IMRT. In addition, SIB plans showed significantly better reduction in OARs than phase plans except for small bowel V35 values.

CONCLUSIONS

IMRT plans reduced almost all the OARs doses compared with the 3D-CRT plan in rectal cancer patients. Furthermore, SIB plans demonstrated lower OAR doses than the phase plans. IMRT techniques, especially SIB plans, reduce OAR doses and provide safer doses for the treatment of rectal carcinoma.

A slice classification model-facilitated 3D encoder-decoder network for segmenting organs at risk in head and neck cancer

For deep learning networks used to segment organs at risk (OARs) in head and neck (H&N) cancers, the class-imbalance problem between small volume OARs and whole computed tomography (CT) images results in delineation with serious false-positives on irrelevant slices and unnecessary time-consuming calculations. To alleviate this problem, a slice classification model-facilitated 3D encoder-decoder network was developed and validated. In the developed two-step segmentation model, a slice classification model was firstly utilized to classify CT slices into six categories in the craniocaudal direction. Then the target categories for different OARs were pushed to the different 3D encoder-decoder segmentation networks, respectively. All the patients were divided into training (n = 120), validation (n = 30) and testing (n = 20) datasets. The average accuracy of the slice classification model was 95.99%. The Dice similarity coefficient and 95% Hausdorff distance, respectively, for each OAR were as follows: right eye (0.88 ± 0.03 and 1.57 ± 0.92 mm), left eye (0.89 ± 0.03 and 1.35 ± 0.43 mm), right optic nerve (0.72 ± 0.09 and 1.79 ± 1.01 mm), left optic nerve (0.73 ± 0.09 and 1.60 ± 0.71 mm), brainstem (0.87 ± 0.04 and 2.28 ± 0.99 mm), right temporal lobe (0.81 ± 0.12 and 3.28 ± 2.27 mm), left temporal lobe (0.82 ± 0.09 and 3.73 ± 2.08 mm), right temporomandibular joint (0.70 ± 0.13 and 1.79 ± 0.79 mm), left temporomandibular joint (0.70 ± 0.16 and 1.98 ± 1.48 mm), mandible (0.89 ± 0.02 and 1.66 ± 0.51 mm), right parotid (0.77 ± 0.07 and 7.30 ± 4.19 mm) and left parotid (0.71 ± 0.12 and 8.41 ± 4.84 mm). The total segmentation time was 40.13 s. The 3D encoder-decoder network facilitated by the slice classification model demonstrated superior performance in accuracy and efficiency in segmenting OARs in H&N CT images. This may significantly reduce the workload for radiation oncologists.

Impact of Low-Dose Irradiation of the Lung and Heart on Toxicity and Pulmonary Function Parameters after Thoracic Radiotherapy

Simple Summary

To assess the impact of thoracic (low) dose irradiation on pulmonary function changes after thoracic radiotherapy (RT) data of 62 patients were analyzed. There were several significant correlations between pulmonary function and dose parameters of the lung and heart, most of which remained significant in the multivariate analysis.

Abstract

Objective: To assess the impact of (low) dose irradiation to the lungs and heart on the incidence of pneumonitis and pulmonary function changes after thoracic radiotherapy (RT). Methods/Material: Data of 62 patients treated with curative thoracic radiotherapy were analyzed. Toxicity data and pulmonary function tests (PFTs) were obtained before RT and at 6 weeks, at 12 weeks, and at 6 months after RT. PFTs included ventilation (e.g., vital capacity) and diffusion parameters (e.g., diffusion capacity for carbon monoxide (DL_CO)). Dosimetric data of the lung and heart were extracted to assess the impact of dose on PFT changes and radiation pneumonitis (RP). Results: No statistically significant correlations between dose parameters and changes in ventilation parameters were found. There were statistically significant correlations between DL_CO and low-dose parameters of the lungs (V_5Gy–V_30Gy (%)) and irradiation of the heart during the follow-up up to 6 months after RT, as well as a temporary correlation of the V_60Gy (%) on the blood gas parameters at 12 weeks after RT. On multivariate analysis, both heart and lung parameters had a significant impact on DL_CO. There was no statistically significant influence of any patient or treatment-related (including dose parameters) factors on the incidence of ≥G2 pneumonitis. Conclusion: There seems to be a lasting impact of low dose irradiation to the lung as well as irradiation to the heart on the DL_CO after thoracic radiotherapy. No influence on RP was found in this analysis.

Surveillance for radiation-related late effects in childhood cancer survivors: The impact of using volumetric dosimetry

BACKGROUND

Radiation-related screening guidelines for survivors of childhood cancer currently use irradiated regions (IR) to determine risk for late effects. However, contemporary radiotherapy techniques utilize volumetric dosimetry (VD) to determine organ-specific exposures, which could inform need for late effect surveillance.

METHODS

This cross-sectional cohort study involved patients treated for cancer using computerized tomography-planned irradiation at Children's Hospital Los Angeles from 2000-2016. Organs at risk were identified using both VD and IR. Under each method, Children's Oncology Group Long-Term Follow-Up Guidelines were applied to determine radiation-related potential late effects and their correlative recommended screening practices. Patients served as their own controls. Mean number of potential late effects per patient and recommended screening practices per patient per decade of follow-up were compared using paired t-tests; comparisons were adjusted for diagnosis and gender using random effects, repeated measure linear regression.

RESULTS

In this cohort (n = 132), median age at end of treatment was 10.6 years (range, 1.4-20.4). Brain tumor was the most common diagnosis (45%) and head/brain the most common irradiated region (61%). Under IR and VD, the mean number of potential late effects flagged was 24.4 and 21.7, respectively (-11.3%, p < 0.001); concordance between the two methods was 6.1%. Under VD, the difference in mean number of recommended screening practices per patient was -7.4% in aggregate but as large as -37.0% for diagnostic imaging and procedures (p < 0.001 for both).

CONCLUSION

Use of VD rather than IR is feasible and enhances precision of guideline-based screening for radiation-related late effects in long-term childhood cancer survivors.

Cone-Beam-CT Guided Adaptive Radiotherapy for Locally Advanced Non-small Cell Lung Cancer Enables Quality Assurance and Superior Sparing of Healthy Lung

Purpose

To evaluate the potential of cone-beam-CT (CB-CT) guided adaptive radiotherapy (ART) for locally advanced non-small cell lung cancer (NSCLC) for sparing of surrounding organs-at-risk (OAR).

Materials and Methods

In 10 patients with locally advanced NSCLC, daily CB-CT imaging was acquired during radio- (n = 4) or radiochemotherapy (n = 6) for simulation of ART. Patients were treated with conventionally fractionated intensity-modulated radiotherapy (IMRT) with total doses of 60–66 Gy (pPlan) (311 fraction CB-CTs). OAR were segmented on every daily CB-CT and the tumor volumes were modified weekly depending on tumor changes. Doses actually delivered were recalculated on daily images (dPlan), and voxel-wise dose accumulation was performed using a deformable registration algorithm. For simulation of ART, treatment plans were adapted using the new contours and re-optimized weekly (aPlan).

Results

CB-CT showed continuous tumor regression of 1.1 ± 0.4% per day, leading to a residual gross tumor volume (GTV) of 65.3 ± 13.4% after 6 weeks of radiotherapy (p = 0.005). Corresponding PTVs decreased to 83.7 ± 7.8% (p = 0.005). In the actually delivered plans (dPlan), both conformity (p = 0.005) and homogeneity (p = 0.059) indices were impaired compared to the initial plans (pPlan). This resulted in higher actual lung doses than planned: V_20Gy was 34.6 ± 6.8% instead of 32.8 ± 4.9% (p = 0.066), mean lung dose was 19.0 ± 3.1 Gy instead of 17.9 ± 2.5 Gy (p = 0.013). The generalized equivalent uniform dose (gEUD) of the lung was 18.9 ± 3.1 Gy instead of 17.8 ± 2.5 Gy (p = 0.013), leading to an increased lung normal tissue complication probability (NTCP) of 15.2 ± 13.9% instead of 9.6 ± 7.3% (p = 0.017). Weekly plan adaptation enabled decreased lung V_20Gy of 31.6 ± 6.2% (−3.0%, p = 0.007), decreased mean lung dose of 17.7 ± 2.9 Gy (−1.3 Gy, p = 0.005), and decreased lung gEUD of 17.6 ± 2.9 Gy (−1.3 Gy, p = 0.005). Thus, resulting lung NTCP was reduced to 10.0 ± 9.5% (−5.2%, p = 0.005). Target volume coverage represented by conformity and homogeneity indices could be improved by weekly plan adaptation (CI: p = 0.007, HI: p = 0.114) and reached levels of the initial plan (CI: p = 0.721, HI: p = 0.333).

Conclusion

IGRT with CB-CT detects continuous GTV and PTV changes. CB-CT-guided ART for locally advanced NSCLC is feasible and enables superior sparing of healthy lung at high levels of plan conformity.

Evaluation of deep learning-based auto-segmentation algorithms for delineating clinical target volume and organs at risk involving data for 125 cervical cancer patients

Objective

To evaluate the accuracy of a deep learning‐based auto‐segmentation mode to that of manual contouring by one medical resident, where both entities tried to mimic the delineation "habits" of the same clinical senior physician.

Methods

This study included 125 cervical cancer patients whose clinical target volumes (CTVs) and organs at risk (OARs) were delineated by the same senior physician. Of these 125 cases, 100 were used for model training and the remaining 25 for model testing. In addition, the medical resident instructed by the senior physician for approximately 8 months delineated the CTVs and OARs for the testing cases. The dice similarity coefficient (DSC) and the Hausdorff Distance (HD) were used to evaluate the delineation accuracy for CTV, bladder, rectum, small intestine, femoral‐head‐left, and femoral‐head‐right.

Results

The DSC values of the auto‐segmentation model and manual contouring by the resident were, respectively, 0.86 and 0.83 for the CTV (P < 0.05), 0.91 and 0.91 for the bladder (P > 0.05), 0.88 and 0.84 for the femoral‐head‐right (P < 0.05), 0.88 and 0.84 for the femoral‐head‐left (P < 0.05), 0.86 and 0.81 for the small intestine (P < 0.05), and 0.81 and 0.84 for the rectum (P > 0.05). The HD (mm) values were, respectively, 14.84 and 18.37 for the CTV (P < 0.05), 7.82 and 7.63 for the bladder (P > 0.05), 6.18 and 6.75 for the femoral‐head‐right (P > 0.05), 6.17 and 6.31 for the femoral‐head‐left (P > 0.05), 22.21 and 26.70 for the small intestine (P > 0.05), and 7.04 and 6.13 for the rectum (P > 0.05). The auto‐segmentation model took approximately 2 min to delineate the CTV and OARs while the resident took approximately 90 min to complete the same task.

Conclusion

The auto‐segmentation model was as accurate as the medical resident but with much better efficiency in this study. Furthermore, the auto‐segmentation approach offers additional perceivable advantages of being consistent and ever improving when compared with manual approaches.