Interobserver variations in the delineation of target volumes and organs at risk and their impact on dose distribution in intensity-modulated radiation therapy for nasopharyngeal carcinoma

A multicenter dataset for lymph node clinical target volume delineation of nasopharyngeal carcinoma

The deep learning (DL)-based prediction of accurate lymph node (LN) clinical target volumes (CTVs) for nasopharyngeal carcinoma (NPC) radiotherapy (RT) remains challenging. One of the main reasons is the variability of contours despite standardization processes by expert guidelines in combination with scarce data sharing in the community. Therefore, we retrospectively generated a 262-subjects dataset from four centers to develop the DL models for LN CTVs delineation. This dataset included 440 computed tomography images from different scanning phases, disease stages and treatment strategies. Three clinical expert boards, each comprising two experts (totalling six experts), manually delineated six basic LN CTVs on separate cohorts as the ground truth according to LN involvement and clinical requirements. Several state-of-the-art segmentation algorithms were evaluated on this benchmark, showing promising results for LN CTV segmentation. In conclusion, this work built a multicenter LN CTV segmentation dataset, which may be the first dataset for automatic LN CTV delineation development and evaluation, serving as a benchmark for future research.

Gross failure rates and failure modes for a commercial AI-based auto-segmentation algorithm in head and neck cancer patients

PURPOSE

Artificial intelligence (AI) based commercial software can be used to automatically delineate organs at risk (OAR), with potential for efficiency savings in the radiotherapy treatment planning pathway, and reduction of inter- and intra-observer variability. There has been little research investigating gross failure rates and failure modes of such systems.

METHOD

50 head and neck (H&N) patient data sets with "gold standard" contours were compared to AI-generated contours to produce expected mean and standard deviation values for the Dice Similarity Coefficient (DSC), for four common H&N OARs (brainstem, mandible, left and right parotid). An AI-based commercial system was applied to 500 H&N patients. AI-generated contours were compared to manual contours, outlined by an expert human, and a gross failure was set at three standard deviations below the expected mean DSC. Failures were inspected to assess reason for failure of the AI-based system with failures relating to suboptimal manual contouring censored. True failures were classified into 4 sub-types (setup position, anatomy, image artefacts and unknown).

RESULTS

There were 24 true failures of the AI-based commercial software, a gross failure rate of 1.2%. Fifteen failures were due to patient anatomy, four were due to dental image artefacts, three were due to patient position and two were unknown. True failure rates by OAR were 0.4% (brainstem), 2.2% (mandible), 1.4% (left parotid) and 0.8% (right parotid).

CONCLUSION

True failures of the AI-based system were predominantly associated with a non-standard element within the CT scan. It is likely that these non-standard elements were the reason for the gross failure, and suggests that patient datasets used to train the AI model did not contain sufficient heterogeneity of data. Regardless of the reasons for failure, the true failure rate for the AI-based system in the H&N region for the OARs investigated was low (∼1%).

Embracing Personalized Strategies in Radiotherapy for Nasopharyngeal Carcinoma: Beyond the Conventional Bounds of Fields and Borders

Radiotherapy is the primary treatment modality for non-metastatic nasopharyngeal carcinoma (NPC) across all TN-stages. Locoregional control rates have been impressive even from the 2D radiotherapy (RT) era, except when the ability to deliver optimal dose coverage to the tumor is compromised. However, short- and long-term complications following head and neck RT are potentially debilitating, and thus, there has been much research investigating technological advances in RT delivery over the past decades, with the primary goal of limiting normal tissue damage. On this note, with a plateau in gains of therapeutic ratio by modern RT techniques, future advances have to be focused on individualization of RT, both in terms of dose prescription and the delineation of target volumes. In this review, we analyzed the guidelines and evidence related to contouring methods, and dose prescription for early and locoregionally advanced (LA-) NPC. Next, with the preference for induction chemotherapy (IC) in patients with LA-NPC, we assessed the evidence concerning radiotherapy adaptations guided by IC response, as well as functional imaging and contour changes during treatment. Finally, we discussed on RT individualization that is guided by EBV DNA assessment, and its importance in the era of combinatorial immune checkpoint blockade therapy with RT.

Comprehensive Evaluation of a Deep Learning Model for Automatic Organs-at-Risk Segmentation on Heterogeneous Computed Tomography Images for Abdominal Radiation Therapy

PURPOSE

Our purpose was to develop a deep learning model (AbsegNet) that produces accurate contours of 16 organs at risk (OARs) for abdominal malignancies as an essential part of fully automated radiation treatment planning.

METHODS AND MATERIALS

Three data sets with 544 computed tomography scans were retrospectively collected. Data set 1 was split into 300 training cases and 128 test cases (cohort 1) for AbsegNet. Data set 2, including cohort 2 (n = 24) and cohort 3 (n = 20), were used to validate AbsegNet externally. Data set 3, including cohort 4 (n = 40) and cohort 5 (n = 32), were used to clinically assess the accuracy of AbsegNet-generated contours. Each cohort was from a different center. The Dice similarity coefficient and 95th-percentile Hausdorff distance were calculated to evaluate the delineation quality for each OAR. Clinical accuracy evaluation was classified into 4 levels: no revision, minor revisions (0% < volumetric revision degrees [VRD] ≤ 10%), moderate revisions (10% ≤ VRD < 20%), and major revisions (VRD ≥20%).

RESULTS

For all OARs, AbsegNet achieved a mean Dice similarity coefficient of 86.73%, 85.65%, and 88.04% in cohorts 1, 2, and 3, respectively, and a mean 95th-percentile Hausdorff distance of 8.92, 10.18, and 12.40 mm, respectively. The performance of AbsegNet outperformed SwinUNETR, DeepLabV3+, Attention-UNet, UNet, and 3D-UNet. When experts evaluated contours from cohorts 4 and 5, 4 OARs (liver, kidney_L, kidney_R, and spleen) of all patients were scored as having no revision, and over 87.5% of patients with contours of the stomach, esophagus, adrenals, or rectum were considered as having no or minor revisions. Only 15.0% of patients with colon and small bowel contours required major revisions.

CONCLUSIONS

We propose a novel deep-learning model to delineate OARs on diverse data sets. Most contours produced by AbsegNet are accurate and robust and are, therefore, clinically applicable and helpful to facilitate radiation therapy workflow.

Deep learning algorithm performance in contouring head and neck organs at risk: a systematic review and single-arm meta-analysis

PURPOSE

The contouring of organs at risk (OARs) in head and neck cancer radiation treatment planning is a crucial, yet repetitive and time-consuming process. Recent studies have applied deep learning (DL) algorithms to automatically contour head and neck OARs. This study aims to conduct a systematic review and meta-analysis to summarize and analyze the performance of DL algorithms in contouring head and neck OARs. The objective is to assess the advantages and limitations of DL algorithms in contour planning of head and neck OARs.

METHODS

This study conducted a literature search of Pubmed, Embase and Cochrane Library databases, to include studies related to DL contouring head and neck OARs, and the dice similarity coefficient (DSC) of four categories of OARs from the results of each study are selected as effect sizes for meta-analysis. Furthermore, this study conducted a subgroup analysis of OARs characterized by image modality and image type.

RESULTS

149 articles were retrieved, and 22 studies were included in the meta-analysis after excluding duplicate literature, primary screening, and re-screening. The combined effect sizes of DSC for brainstem, spinal cord, mandible, left eye, right eye, left optic nerve, right optic nerve, optic chiasm, left parotid, right parotid, left submandibular, and right submandibular are 0.87, 0.83, 0.92, 0.90, 0.90, 0.71, 0.74, 0.62, 0.85, 0.85, 0.82, and 0.82, respectively. For subgroup analysis, the combined effect sizes for segmentation of the brainstem, mandible, left optic nerve, and left parotid gland using CT and MRI images are 0.86/0.92, 0.92/0.90, 0.71/0.73, and 0.84/0.87, respectively. Pooled effect sizes using 2D and 3D images of the brainstem, mandible, left optic nerve, and left parotid gland for contouring are 0.88/0.87, 0.92/0.92, 0.75/0.71 and 0.87/0.85.

CONCLUSIONS

The use of automated contouring technology based on DL algorithms is an essential tool for contouring head and neck OARs, achieving high accuracy, reducing the workload of clinical radiation oncologists, and providing individualized, standardized, and refined treatment plans for implementing "precision radiotherapy". Improving DL performance requires the construction of high-quality data sets and enhancing algorithm optimization and innovation.

Human factors in the clinical implementation of deep learning-based automated contouring of pelvic organs at risk for MRI-guided radiotherapy

PURPOSE

Deep neural nets have revolutionized the science of auto-segmentation and present great promise for treatment planning automation. However, little data exists regarding clinical implementation and human factors. We evaluated the performance and clinical implementation of a novel deep learning-based auto-contouring workflow for 0.35T magnetic resonance imaging (MRI)-guided pelvic radiotherapy, focusing on automation bias and objective measures of workflow savings.

METHODS

An auto-contouring model was developed using a UNet-derived architecture for the femoral heads, bladder, and rectum in 0.35T MR images. Training data was taken from 75 patients treated with MRI-guided radiotherapy at our institution. The model was tested against 20 retrospective cases outside the training set, and subsequently was clinically implemented. Usability was evaluated on the first 30 clinical cases by computing Dice coefficient (DSC), Hausdorff distance (HD), and the fraction of slices that were used un-modified by planners. Final contours were retrospectively reviewed by an experienced planner and clinical significance of deviations was graded as negligible, low, moderate, and high probability of leading to actionable dosimetric variations. In order to assess whether the use of auto-contouring led to final contours more or less in agreement with an objective standard, 10 pre-treatment and 10 post-treatment blinded cases were re-contoured from scratch by three expert planners to get expert consensus contours (EC). EC was compared to clinically used (CU) contours using DSC. Student's t-test and Levene's statistic were used to test statistical significance of differences in mean and standard deviation, respectively. Finally, the dosimetric significance of the contour differences were assessed by comparing the difference in bladder and rectum maximum point doses between EC and CU before and after the introduction of automation.

RESULTS

Median (interquartile range) DSC for the retrospective test data were 0.92(0.02), 0.92(0.06), 0.93(0.06), 0.87(0.04) for the post-processed contours for the right and left femoral heads, bladder, and rectum, respectively. Post-implementation median DSC were 1.0(0.0), 1.0(0.0), 0.98(0.04), and 0.98(0.06), respectively. For each organ, 96.2, 95.4, 59.5, and 68.21 percent of slices were used unmodified by the planner. DSC between EC and pre-implementation CU contours were 0.91(0.05*), 0.91*(0.05*), 0.95(0.04), and 0.88(0.04) for right and left femoral heads, bladder, and rectum, respectively. The corresponding DSC for post-implementation CU contours were 0.93(0.02*), 0.93*(0.01*), 0.96(0.01), and 0.85(0.02) (asterisks indicate statistically significant difference). In a retrospective review of contours used for planning, a total of four deviating slices in two patients were graded as low potential clinical significance. No deviations were graded as moderate or high. Mean differences between EC and CU rectum max-doses were 0.1 ± 2.6 Gy and -0.9 ± 2.5 Gy for pre- and post-implementation, respectively. Mean differences between EC and CU bladder/bladder wall max-doses were -0.9 ± 4.1 Gy and 0.0 ± 0.6 Gy for pre- and post-implementation, respectively. These differences were not statistically significant according to Student's t-test.

CONCLUSION

We have presented an analysis of the clinical implementation of a novel auto-contouring workflow. Substantial workflow savings were obtained. The introduction of auto-contouring into the clinical workflow changed the contouring behavior of planners. Automation bias was observed, but it had little deleterious effect on treatment planning.

Validation of clinical acceptability of deep-learning-based automated segmentation of organs-at-risk for head-and-neck radiotherapy treatment planning

Introduction

Organ-at-risk segmentation for head and neck cancer radiation therapy is a complex and time-consuming process (requiring up to 42 individual structure, and may delay start of treatment or even limit access to function-preserving care. Feasibility of using a deep learning (DL) based autosegmentation model to reduce contouring time without compromising contour accuracy is assessed through a blinded randomized trial of radiation oncologists (ROs) using retrospective, de-identified patient data.

Methods

Two head and neck expert ROs used dedicated time to create gold standard (GS) contours on computed tomography (CT) images. 445 CTs were used to train a custom 3D U-Net DL model covering 42 organs-at-risk, with an additional 20 CTs were held out for the randomized trial. For each held-out patient dataset, one of the eight participant ROs was randomly allocated to review and revise the contours produced by the DL model, while another reviewed contours produced by a medical dosimetry assistant (MDA), both blinded to their origin. Time required for MDAs and ROs to contour was recorded, and the unrevised DL contours, as well as the RO-revised contours by the MDAs and DL model were compared to the GS for that patient.

Results

Mean time for initial MDA contouring was 2.3 hours (range 1.6-3.8 hours) and RO-revision took 1.1 hours (range, 0.4-4.4 hours), compared to 0.7 hours (range 0.1-2.0 hours) for the RO-revisions to DL contours. Total time reduced by 76% (95%-Confidence Interval: 65%-88%) and RO-revision time reduced by 35% (95%-CI,-39%-91%). All geometric and dosimetric metrics computed, agreement with GS was equivalent or significantly greater (p<0.05) for RO-revised DL contours compared to the RO-revised MDA contours, including volumetric Dice similarity coefficient (VDSC), surface DSC, added path length, and the 95%-Hausdorff distance. 32 OARs (76%) had mean VDSC greater than 0.8 for the RO-revised DL contours, compared to 20 (48%) for RO-revised MDA contours, and 34 (81%) for the unrevised DL OARs.

Conclusion

DL autosegmentation demonstrated significant time-savings for organ-at-risk contouring while improving agreement with the institutional GS, indicating comparable accuracy of DL model. Integration into the clinical practice with a prospective evaluation is currently underway.

Assessing Interobserver Variability in the Delineation of Structures in Radiation Oncology: A Systematic Review

PURPOSE

The delineation of target volumes and organs at risk is the main source of uncertainty in radiation therapy. Numerous interobserver variability (IOV) studies have been conducted, often with unclear methodology and nonstandardized reporting. We aimed to identify the parameters chosen in conducting delineation IOV studies and assess their performances and limits.

METHODS AND MATERIALS

We conducted a systematic literature review to highlight major points of heterogeneity and missing data in IOV studies published between 2018 and 2021. For the main used metrics, we did in silico analyses to assess their limits in specific clinical situations.

RESULTS

All disease sites were represented in the 66 studies examined. Organs at risk were studied independently of tumor site in 29% of reviewed IOV studies. In 65% of studies, statistical analyses were performed. No gold standard (GS; ie, reference) was defined in 36% of studies. A single expert was considered as the GS in 21% of studies, without testing intraobserver variability. All studies reported both absolute and relative indices, including the Dice similarity coefficient (DSC) in 68% and the Hausdorff distance (HD) in 42%. Limitations were shown in silico for small structures when using the DSC and dependence on irregular shapes when using the HD. Variations in DSC values were large between studies, and their thresholds were inconsistent. Most studies (51%) included 1 to 10 cases. The median number of observers or experts was 7 (range, 2-35). The intraclass correlation coefficient was reported in only 9% of cases. Investigating the feasibility of studying IOV in delineation, a minimum of 8 observers with 3 cases, or 11 observers with 2 cases, was required to demonstrate moderate reproducibility.

CONCLUSIONS

Implementation of future IOV studies would benefit from a more standardized methodology: clear definitions of the gold standard and metrics and a justification of the tradeoffs made in the choice of the number of observers and number of delineated cases should be provided.

Nasopharyngeal cancer: the impact of guidelines and teaching on radiation target volume delineation

Target volume delineation in the radiation treatment of nasopharyngeal cancer is challenging due to several reasons such as the complex anatomy of the site, the need for the elective coverage of definite anatomical regions, the curative intent of treatment and the rarity of the disease, especially in non-endemic areas. We aimed to analyze the impact of educational interactive teaching courses on target volume delineation accuracy between Italian radiation oncology centers. Only one contour dataset per center was admitted. The educational course consisted in three parts: (1) The completely anonymized image dataset of a T4N1 nasopharyngeal cancer patient was shared between centers before the course with the request of target volume and organs at risk delineation; (2) the course was held online with dedicated multidisciplinary sessions on nasopharyngeal anatomy, nasopharyngeal cancer pattern of diffusion and on the description and explanation of international contouring guidelines. At the end of the course, the participating centers were asked to resubmit the contours with appropriate corrections; (3) the pre- and post-course contours were analyzed and quantitatively and qualitatively compared with the benchmark contours delineated by the panel of experts. The analysis of the 19 pre- and post-contours submitted by the participating centers revealed a significant improvement in the Dice similarity index in all the clinical target volumes (CTV1, CTV2 and CTV3) passing from 0.67, 0.51 and 0.48 to 0.69, 0.65 and 0.52, respectively. The organs at risk delineation was also improved. The qualitative analysis consisted in the evaluation of the inclusion of the proper anatomical regions in the target volumes; it was conducted following internationally validated guidelines of contouring for nasopharyngeal radiation treatment. All the sites were properly included in target volume delineation by  >50% of the centers after correction. A significant improvement was registered for the skull base, the sphenoid sinus and the nodal levels. These results demonstrated the important role that educational courses with interactive sessions could have in such a challenging task as target volume delineation in modern radiation oncology.

Improved accuracy of auto-segmentation of organs at risk in radiotherapy planning for nasopharyngeal carcinoma based on fully convolutional neural network deep learning

OBJECTIVE

We examined a modified encoder-decoder architecture-based fully convolutional neural network, OrganNet, for simultaneous auto-segmentation of 24 organs at risk (OARs) in the head and neck, followed by validation tests and evaluation of clinical application.

MATERIALS AND METHODS

Computed tomography (CT) images from 310 radiotherapy plans were used as the experimental data set, of which 260 and 50 were used as the training and test sets, respectively. An improved U-Net architecture was established by introducing a batch normalization layer, residual squeeze-and-excitation layer, and unique organ-specific loss function for deep learning training. The performance of the trained network model was evaluated by comparing the manual-delineation and the STAPLE contour of 10 physicians from different centers.

RESULTS

Our model achieved good segmentation in all 24 OARs in nasopharyngeal cancer radiotherapy plan CT images, with an average Dice similarity coefficient of 83.75%. Specifically, the mean Dice coefficients in large-volume organs (brainstem, spinal cord, left/right parotid glands, left/right temporal lobes, and left/right mandibles) were 84.97% - 95.00%, and in small-volume organs (pituitary, lens, optic nerve, and optic chiasma) were 55.46% - 91.56%. respectively. Using the STAPLE contours as standard contour, the OrganNet achieved comparable or better DICE in organ segmentation then that of the manual-delineation as well.

CONCLUSION

The established OrganNet enables simultaneous automatic segmentation of multiple targets on CT images of the head and neck radiotherapy plans, effectively improves the accuracy of U-Net based segmentation for OARs, especially for small-volume organs.

Comparative evaluation of a prototype deep learning algorithm for autosegmentation of normal tissues in head and neck radiotherapy

PURPOSE

To introduce and validate a newly developed deep-learning (DL) auto-segmentation algorithm for head and neck (HN) organs at risk (OARs) and to compare its performance with a published commercial algorithm.

METHODS

A total of 864 HN cancer cases were available to train and evaluate a prototype algorithm. The algorithm is based on a fully convolutional network with combined U-Net and V-net. A Dice loss plus Cross-Entropy Loss function with Adam optimizer was used in training. For 75 validation cases, OAR sets were generated with three DL-based models (A: the prototype model trained with gold data, B: a commercial software trained with the same data, and C: the same software trained with data from another institution). The auto-segmented structures were evaluated with Dice similarity coefficient (DSC), Hausdorff distance (HD), voxel-penalty metric (VPM) and DSC of area under dose-volume histograms. A subjective qualitative evaluation was performed on 20 random cases.

RESULTS

Overall trend was for the prototype algorithm to be the closest to the gold data by all five metrics. The average DSC/VPM/HD for algorithms A, B, and C were 0.81/84.1/1.6 mm, 0.74/62.8/3.2 mm, and 0.66/46.8/3.3 mm, respectively. 93% of model A structures were evaluated to be clinically useful.

CONCLUSION

The superior performance of the prototype was validated, even when trained with the same data. In addition to the challenges of perfecting the algorithms, the auto-segmentation results can differ when the same algorithm is trained at different institutions.

Application of Multi-Scale Fusion Attention U-Net to Segment the Thyroid Gland on Localized Computed Tomography Images for Radiotherapy

Objective

To explore the performance of Multi-scale Fusion Attention U-Net (MSFA-U-Net) in thyroid gland segmentation on localized computed tomography (CT) images for radiotherapy.

Methods

We selected localized radiotherapeutic CT images from 80 patients with breast cancer or head and neck tumors; label images were manually delineated by experienced radiologists. The data set was randomly divided into the training set (n = 60), the validation set (n = 10), and the test set (n = 10). We expanded the data in the training set and evaluated the performance of the MSFA-U-Net model using the evaluation indices Dice similarity coefficient (DSC), Jaccard similarity coefficient (JSC), positive predictive value (PPV), sensitivity (SE), and Hausdorff distance (HD).

Results

For the MSFA-U-Net model, the DSC, JSC, PPV, SE, and HD values of the segmented thyroid gland in the test set were 0.90 ± 0.09, 0.82± 0.11, 0.91 ± 0.09, 0.90 ± 0.11, and 2.39 ± 0.54, respectively. Compared with U-Net, HRNet, and Attention U-Net, MSFA-U-Net increased DSC by 0.04, 0.06, and 0.04, respectively; increased JSC by 0.05, 0.08, and 0.04, respectively; increased SE by 0.04, 0.11, and 0.09, respectively; and reduced HD by 0.21, 0.20, and 0.06, respectively. The test set image results showed that the thyroid edges segmented by the MSFA-U-Net model were closer to the standard thyroid edges delineated by the experts than were those segmented by the other three models. Moreover, the edges were smoother, over-anti-noise interference was stronger, and oversegmentation and undersegmentation were reduced.

Conclusion

The MSFA-U-Net model could meet basic clinical requirements and improve the efficiency of physicians' clinical work.

Improving the accuracy and consistency of clinical target volume delineation for rectal cancer by an education program

BACKGROUND

Accurate target volume delineation is the premise for the implementation of precise radiotherapy. Inadequate target volume delineation may diminish tumor control or increase toxicity. Although several clinical target volume (CTV) delineation guidelines for rectal cancer have been published in recent years, significant interobserver variation (IOV) in CTV delineation still exists among radiation oncologists. However, proper education may serve as a bridge that connects complex guidelines with clinical practice.

AIM

To examine whether an education program could improve the accuracy and consistency of preoperative radiotherapy CTV delineation for rectal cancer.

METHODS

The study consisted of a baseline target volume delineation, a 150-min education intervention, and a follow-up evaluation. A 42-year-old man diagnosed with stage IIIC (T3N2bM0) rectal adenocarcinoma was selected for target volume delineation. CTVs obtained before and after the program were compared. Dice similarity coefficient (DSC), inclusiveness index (IncI), conformal index (CI), and relative volume difference [ΔV (%)] were analyzed to quantitatively evaluate the disparities between the participants’ delineation and the standard CTV. Maximum volume ratio (MVR) and coefficient of variation (CV) were calculated to assess the IOV. Qualitative analysis included four common controversies in CTV delineation concerning the upper boundary of the target volume, external iliac area, groin area, and ischiorectal fossa.

RESULTS

Of the 18 radiation oncologists from 10 provinces in China, 13 completed two sets of CTVs. In quantitative analysis, the average CTV volume decreased from 809.82 cm³ to 705.21 cm³ (P = 0.001) after the education program. Regarding the indices for geometric comparison, the mean DSC, IncI, and CI increased significantly, while ΔV (%) decreased remarkably, indicating improved agreement between participants’ delineation and the standard CTV. Moreover, an 11.80% reduction in MVR and 18.19% reduction in CV were noted, demonstrating a smaller IOV in delineation after the education program. Regarding qualitative analysis, the greatest variations in baseline were observed at the external iliac area and ischiorectal fossa; 61.54% (8/13) and 53.85% (7/13) of the participants unnecessarily delineated the external iliac area and the ischiorectal fossa, respectively. However, the education program reduced these variations.

CONCLUSION

Wide variations in CTV delineation for rectal cancer are present among radiation oncologists in mainland China. A well-structured education program could improve delineation accuracy and reduce IOVs.

Evaluation of target autocrop function in nasopharyngeal carcinoma SIB IMRT plan

A new target autocrop function was introduced in the Varian Eclipse™ treatment planning software (version 15.5 above) (Lohynská in Klin Onkol 33(4):288-294, 2020). The study aimed to evaluate this new target autocrop impact on nasopharyngeal carcinoma (NPC) plan quality and delivery efficiency. Randomly 66 approved NPC simultaneous integrated boost (SIB) intensity-modulated radiation therapy (IMRT) treatment plans were retrospectively studied. The manual cropping-based plans served as reference and were designed using sliding-window IMRT. Reference plans were re-optimized with identical plan parameters following the institutional clinical protocol, except for the redundant optimization objective of the manual cropping targets deleted. Additionally, each target within 5 mm of another had one minimum objective at 100% volume and one maximum objective at 0% volume for the autocrop plans. Plan quality was assessed based on selected parameters, including TCP (tumor control probability), NTCP (normal tissue complication probability), conformality index (CI), homogeneity index (HI), and dose-volume characteristics. Additionally, the delivery efficiency, the total plan treatment time defined as a sum of monitor units (MUs) for each treated field, and delivery accuracy, γ passing rate of treatment plan quality assurance (QA) also were compared. Both the manual cropping plans and the autocrop plans could be approved by an experienced oncologist. Overall, the autocrop plans could provide approximately a 13% reduction in linac MU while maintaining comparable plan quality, radiobiological ranking, and accuracy to the manual cropping plans. The new target autocrop tip facilitated the SIB IMRT plans for nasopharyngeal cancer patients. The autocrop could guarantee the quality and delivery accuracy of the radiotherapy plan and improved the planning efficiency, treatment efficiency, and reduced machine wear and tear. It was a promising tool for optimal plan selection for NPC SIB IMRT.

The Chinese Society of Clinical Oncology (CSCO) clinical guidelines for the diagnosis and treatment of nasopharyngeal carcinoma

Nasopharyngeal carcinoma (NPC) is a malignant epithelial tumor originating in the nasopharynx and has a high incidence in Southeast Asia and North Africa. To develop these comprehensive guidelines for the diagnosis and management of NPC, the Chinese Society of Clinical Oncology (CSCO) arranged a multi‐disciplinary team comprising of experts from all sub‐specialties of NPC to write, discuss, and revise the guidelines. Based on the findings of evidence‐based medicine in China and abroad, domestic experts have iteratively developed these guidelines to provide proper management of NPC. Overall, the guidelines describe the screening, clinical and pathological diagnosis, staging and risk assessment, therapies, and follow‐up of NPC, which aim to improve the management of NPC.

Multivariate NTCP Model of Hypothyroidism After Intensity-Modulated Radiotherapy for Nasopharyngeal Carcinoma

Objective

To evaluate the incidence of hypothyroidism in patients with nasopharyngeal carcinoma after intensity-modulated radiotherapy (IMRT), analyze its correlation with multiple influencing factors such as thyroid exposure dose, thyroid volume, and gender, and construct a multivariate-based normal tissue complication probability (NTCP) model for the occurrence of hypothyroidism after IMRT.

Materials and Methods

The thyroid hormone levels of patients at different points in time before and after radiotherapy were tested, and statistics on the incidence of hypothyroidism after treatment were obtained. The dose-volume data of patients’ thyroids were converted into EQD2 equivalent dose values. The correlation between hypothyroidism after radiotherapy and thyroid exposure dose, thyroid volume, gender, and other factors was analyzed, and an NTCP model was constructed.

Results

A total of 69 patients with nasopharyngeal carcinoma were enrolled in this study. Twelve months after radiotherapy, a total of 24 patients (34.8%) developed hypothyroidism. Univariate analysis and multivariate analysis revealed that the average thyroid dose and thyroid volume are the most important factors affecting hypothyroidism after radiotherapy. The NTCP model constructed based on the average dose and thyroid volume has a good degree of fit.

Conclusion

The volume and average dose of the thyroid gland are the key factors affecting the occurrence of hypothyroidism in patients with nasopharyngeal carcinoma after radiotherapy. The NTCP model constructed based on multivariate construction suggests that reducing the average dose of the thyroid to the greatest extent is an effective way to protect thyroid functions.

A rapid review of influential factors and appraised solutions on organ delineation uncertainties reduction in radiotherapy

Background and purpose.Accurate volume delineation plays an essential role in radiotherapy. Contouring is a potential source of uncertainties in radiotherapy treatment planning that could affect treatment outcomes. Therefore, reducing the degree of contouring uncertainties is crucial. The role of utilized imaging modality in the organ delineation uncertainties has been investigated. This systematic review explores the influential factors on inter-and intra-observer uncertainties of target volume and organs at risk (OARs) delineation focusing on the used imaging modality for these uncertainties reduction and the reported subsequent histopathology and follow-up assessment.Methods and materials.An inclusive search strategy has been conducted to query the available online databases (Scopus, Google Scholar, PubMed, and Medline). 'Organ at risk', 'target', 'delineation', 'uncertainties', 'radiotherapy' and their relevant terms were utilized using every database searching syntax. Final article extraction was performed following Preferred Reporting Items for Systematic Reviews and Meta-Analyses (PRISMA) guideline. Included studies were limited to the ones published in English between 1995 and 2020 and that just deal with computed tomography (CT) and magnetic resonance imaging (MRI) modalities.Results.A total of 923 studies were screened and 78 were included of which 31 related to the prostate 20 to the breast, 18 to the head and neck, and 9 to the brain tumor site. 98% of the extracted studies performed volumetric analysis. Only 24% of the publications reported the dose deviations resulted from variation in volume delineation Also, heterogeneity in studied populations and reported geometric and volumetric parameters were identified such that quantitative synthesis was not appropriate.Conclusion.This review highlightes the inter- and intra-observer variations that could lead to contouring uncertainties and impede tumor control in radiotherapy. For improving volume delineation and reducing inter-observer variability, the implementation of well structured training programs, homogeneity in following consensus and guidelines, reliable ground truth selection, and proper imaging modality utilization could be clinically beneficial.

Interobserver variability in target volume delineation in definitive radiotherapy for thoracic esophageal cancer: a multi-center study from China

Purpose

To investigate the interobserver variability (IOV) in target volume delineation of definitive radiotherapy for thoracic esophageal cancer (TEC) among cancer centers in China, and ultimately improve contouring consistency as much as possible to lay the foundation for multi-center prospective studies.

Methods

Sixteen cancer centers throughout China participated in this study. In Phase 1, three suitable cases with upper, middle, and lower TEC were chosen, and participants were asked to contour a group of gross tumor volume (GTV-T), nodal gross tumor volume (GTV-N) and clinical target volume (CTV) for each case based on their routine experience. In Phase 2, the same clinicians were instructed to follow a contouring protocol to re-contour another group of target volume. The variation of the target volume was analyzed and quantified using dice similarity coefficient (DSC).

Results

Sixteen clinicians provided routine volumes, whereas ten provided both routine and protocol volumes for each case. The IOV of routine GTV-N was the most striking in all cases, with the smallest DSC of 0.37 (95% CI 0.32–0.42), followed by CTV, whereas GTV-T showed high consistency. After following the protocol, the smallest DSC of GTV-N was improved to 0.64 (95% CI 0.45–0.83, P = 0.005) but the DSC of GTV-T and CTV remained constant in most cases.

Conclusion

Variability in target volume delineation was observed, but it could be significantly reduced and controlled using mandatory interventions.

Supplementary information

Supplementary information accompanies this paper at 10.1186/s13014-020-01691-4.

Feasibility of Continual Deep Learning-Based Segmentation for Personalized Adaptive Radiation Therapy in Head and Neck Area

Simple Summary

We analyzed the contouring data of 23 organs-at-risk from 100 patients with head and neck cancer who underwent definitive radiation therapy (RT). Deep learning-based segmentation (DLS) with continual training was compared to DLS with conventional training and deformable image registration (DIR) in both quantitative and qualitative (Turing’s test) methods. Results indicate the effectiveness of DLS over DIR and that of DLS with continual training over DLS with conventional training in contouring for head and neck region, especially for glandular structures. DLS with continual training might be beneficial for optimizing personalized adaptive RT in head and neck region.

Abstract

This study investigated the feasibility of deep learning-based segmentation (DLS) and continual training for adaptive radiotherapy (RT) of head and neck (H&N) cancer. One-hundred patients treated with definitive RT were included. Based on 23 organs-at-risk (OARs) manually segmented in initial planning computed tomography (CT), modified FC-DenseNet was trained for DLS: (i) using data obtained from 60 patients, with 20 matched patients in the test set (DLSm); (ii) using data obtained from 60 identical patients with 20 unmatched patients in the test set (DLSu). Manually contoured OARs in adaptive planning CT for independent 20 patients were provided as test sets. Deformable image registration (DIR) was also performed. All 23 OARs were compared using quantitative measurements, and nine OARs were also evaluated via subjective assessment from 26 observers using the Turing test. DLSm achieved better performance than both DLSu and DIR (mean Dice similarity coefficient; 0.83 vs. 0.80 vs. 0.70), mainly for glandular structures, whose volume significantly reduced during RT. Based on subjective measurements, DLS is often perceived as a human (49.2%). Furthermore, DLSm is preferred over DLSu (67.2%) and DIR (96.7%), with a similar rate of required revision to that of manual segmentation (28.0% vs. 29.7%). In conclusion, DLS was effective and preferred over DIR. Additionally, continual DLS training is required for an effective optimization and robustness in personalized adaptive RT.

Deep learning for elective neck delineation: More consistent and time efficient

BACKGROUND/PURPOSE

Delineation of the lymph node levels of the neck for irradiation of the elective clinical target volume in head and neck cancer (HNC) patients is time consuming and prone to interobserver variability (IOV), although international consensus guidelines exist. The aim of this study was to develop and validate a 3D convolutional neural network (CNN) for semi-automated delineation of all nodal neck levels, focussing on delineation accuracy, efficiency and consistency compared to manual delineation.

MATERIAL/METHODS

The CNN was trained on a clinical dataset of 69 HNC patients. For validation, 17 lymph node levels were manually delineated in 16 new patients by two observers, independently, using international consensus guidelines. Automated delineations were generated by applying the CNN and were subsequently corrected by both observers separately as needed for clinical acceptance. Both delineations were performed two weeks apart and blinded to each other. IOV was quantified using Dice similarity coefficient (DSC), mean surface distance (MSD) and Hausdorff distance (HD). To assess automated delineation accuracy, agreement between automated and corrected delineations were evaluated using the same measures. To assess efficiency, the time taken for manual and corrected delineations were compared. In a second step, only the clinically relevant neck levels were selected and delineated, once again manually and by applying and correcting the network.

RESULTS

When all lymph node levels were delineated, time taken for correcting automated delineations compared to manual delineations was significantly shorter for both observers (mean: 35 vs 52 min, p < 10^-5). Based on DSC, automated delineation agreed best with corrected delineation for lymph node levels Ib, II-IVa, VIa, VIb, VIIa, VIIb (DSC >85%). Manual corrections necessary for clinical acceptance were 1.4 mm MSD on average and were especially low (<1mm) for levels II-IVa, VIa, VIIa and VIIb. IOV was significantly smaller with automated compared to manual delineations (MSD: 1.4 mm vs 2.5 mm, p < 10^-11). When delineating only the clinically relevant neck levels, the correction time was also significantly shorter (mean: 8 vs 15 min, p < 10^-5). Based on DSC, automated delineation agreed very well with corrected delineation (DSC > 87%). Manual corrections necessary for clinical acceptance were 1.3 mm MSD on average. IOV was significantly smaller with automated compared to manual delineations (MSD: 0.8 mm vs 2.3 mm, p < 10^-3).

CONCLUSION

The CNN developed for automated delineation of the elective lymph node levels in the neck in HNC was shown to be more efficient and consistent compared to manual delineation, which justifies its implementation in clinical practice.

Copper-Catalyzed Selective Arylation of Nitriles with Cyclic Diaryl Iodonium Salts: Direct Access to Structurally Diversified Diarylmethane Amides with Potential Neuroprotective and Anticancer Activities

A novel, simple, and high-yielding approach for the preparation of diarylmethane amide derivatives has been developed by reacting cyclic diaryl iodonium salts with nitriles using CuCl as a catalyst. The procedure is efficient with high atom economy and a wide substrate range. Importantly, selective arylation of nitriles was obtained without affecting the phenyl amino/hydroxyl groups. Furthermore, two of the diarylmethane amides (3k, 3s) displayed excellent neuroprotective and anticancer activities.

Deep learning vs. atlas-based models for fast auto-segmentation of the masticatory muscles on head and neck CT images

BACKGROUND

Impaired function of masticatory muscles will lead to trismus. Routine delineation of these muscles during planning may improve dose tracking and facilitate dose reduction resulting in decreased radiation-related trismus. This study aimed to compare a deep learning model with a commercial atlas-based model for fast auto-segmentation of the masticatory muscles on head and neck computed tomography (CT) images.

MATERIAL AND METHODS

Paired masseter (M), temporalis (T), medial and lateral pterygoid (MP, LP) muscles were manually segmented on 56 CT images. CT images were randomly divided into training (n = 27) and validation (n = 29) cohorts. Two methods were used for automatic delineation of masticatory muscles (MMs): Deep learning auto-segmentation (DLAS) and atlas-based auto-segmentation (ABAS). The automatic algorithms were evaluated using Dice similarity coefficient (DSC), recall, precision, Hausdorff distance (HD), HD95, and mean surface distance (MSD). A consolidated score was calculated by normalizing the metrics against interobserver variability and averaging over all patients. Differences in dose (∆Dose) to MMs for DLAS and ABAS segmentations were assessed. A paired t-test was used to compare the geometric and dosimetric difference between DLAS and ABAS methods.

RESULTS

DLAS outperformed ABAS in delineating all MMs (p < 0.05). The DLAS mean DSC for M, T, MP, and LP ranged from 0.83 ± 0.03 to 0.89 ± 0.02, the ABAS mean DSC ranged from 0.79 ± 0.05 to 0.85 ± 0.04. The mean value for recall, HD, HD95, MSD also improved with DLAS for auto-segmentation. Interobserver variation revealed the highest variability in DSC and MSD for both T and MP, and the highest scores were achieved for T by both automatic algorithms. With few exceptions, the mean ∆D98%, ∆D95%, ∆D50%, and ∆D2% for all structures were below 10% for DLAS and ABAS and had no detectable statistical difference (P > 0.05). DLAS based contours had dose endpoints more closely matched with that of the manually segmented when compared with ABAS.

CONCLUSIONS

DLAS auto-segmentation of masticatory muscles for the head and neck radiotherapy had improved segmentation accuracy compared with ABAS with no qualitative difference in dosimetric endpoints compared to manually segmented contours.

A Multicentre UK Study of Outcomes of Nasopharyngeal Carcinoma Treated With Intensity-Modulated Radiotherapy ± Chemotherapy

AIMS

To report the outcomes of nasopharyngeal carcinoma in adults across three large centres in a non-endemic region in the era of intensity-modulated radiotherapy (IMRT).

MATERIALS AND METHODS

Adult patients with nasopharyngeal carcinoma treated in three large cancer centres with IMRT ± chemotherapy with curative intent between 2009 and 2016 were identified from institutional databases. Radiotherapy was delivered with 70 Gy in 33-35 daily fractions. A univariable analysis was carried out to evaluate the relationship of patient, tumour and treatment factors with progression-free survival (PFS) and overall survival.

RESULTS

In total, 151 patients were identified with a median follow-up of 5.2 years. The median age was 52 years (range 18-85). Seventy-five per cent were of Caucasian origin; 75% had non-keratinising tumours; Epstein Barr virus status was only available in 23% of patients; 74% of patients had stage III or IV disease; 54% of patients received induction chemotherapy; 86% of patients received concurrent chemotherapy. Five-year overall survival, PFS, local disease-free survival, regional disease-free survival and distant disease-free survival were 70%, 65%, 91%, 94% and 82%, respectively. Keratinising squamous cell carcinoma, older age, worse performance status, smoking and alcohol intake were associated with inferior overall survival and PFS.

CONCLUSIONS

Local, regional and distant disease control are relatively high following IMRT ± chemotherapy in a non-endemic population. There was considerable heterogeneity in terms of radiotherapy treatment and the use of chemotherapy, encouraging the development of treatment protocols and expert peer review in non-endemic regions.

Superiority of intensity-modulated radiation therapy in nasopharyngeal carcinoma with skull-base invasion

PURPOSE

To compare the clinical results and functional outcomes between two-dimensional conventional radiation therapy (2DRT) and intensity-modulated radiation therapy (IMRT) in nasopharyngeal carcinoma (NPC) with skull-base invasion.

METHODS

A total of 1258 patients were subclassified into two groups: mild skull-base invasion group (792; 63%) and severe skull-base invasion group (466; 37%). Patients were pair matched (1:1 ratio) using six clinical factors into 2DRT or IMRT groups. The Kaplan-Meier method and Cox regression model were performed to assess overall survival (OS), disease-free survival (DFS), locoregional relapse-free survival (LRRFS) and distant metastasis-free survival (DMFS). Toxicities were evaluated.

RESULTS

IMRT significantly improved four-year OS compared with 2DRT (65.6% vs. 81.8%, P = 0.000), DFS (57.3% vs. 73.3%, P = 0.000) and LRRFS (76.5% vs. 87.5%, P = 0.003) in NPC with severe skull-base invasion, but similar results were observed in patients with mild skull-base invasion (P > 0.05). In patients with severe invasion, radiation therapy techniques were found to be an independent prognostic factor for OS (HR = 0.457, P = 0.000), DFS (HR = 0.547, P = 0.000) and LRRFS (HR = 0.503, P = 0.004). IMRT was associated with better OS. In subgroups analysis, IMRT group also had a better survival in OS, DFS (P < 0.05 for all rates) for patients received concurrent chemotherapy and sequential chemotherapy compared to 2DRT in the severe invasion group. The IMRT group displayed lower incidence of mucositis, xerostomia, trismus (< 1 cm) and temporal lobe necrosis than the 2DRT group.

CONCLUSIONS

IMRT significantly improved patient survival compared with 2DRT in NPC patients with severe skull-base invasion, but a similar survival rate was noted in mild invasion patients. Chemotherapy can improve survival in NPC patients with severe invasion. Among the two therapies, IMRT significantly decreased therapy-related toxicity.

A comparison of clinical outcomes between simultaneous integrated boost (SIB) versus sequential boost (SEQ) intensity modulated radiation therapy (IMRT) for head and neck cancer: A meta-analysis

BACKGROUND

The optimal intensity modulated radiation therapy (IMRT) technique for head and neck cancer (HNC) has not been determined yet. The present study aimed to compare the clinical outcomes of the simultaneous integrated boost (SIB)-IMRT versus the sequential boost (SEQ)-IMRT in HNC.

METHODS

A meta-analysis of 7 studies involving a total of 1049 patients was carried out to compare the treatment outcomes together with severe acute adverse effects of the SIB-IMRT versus the SEQ-IMRT in HNC patients.

RESULTS

Comparison of the SIB-IMRT and SEQ-IMRT showed no significant difference in the measurement of overall survival (OS) (hazard ratio [HR] 0.94; 95% confidence inerval [CI], 0.70-1.27; P = .71), progression free survival (PFS) (HR 1.03; 95% CI, 0.82-1.30; P = .79), locoregional recurrence free survival (LRFS) (HR 0.98; 95% CI, 0.65-1.47; P = .91), and distance metastasis free survival (DMFS) (HR 0.87; 95% CI, 0.50-1.53; P = .63). Moreover, there were no significant differences in adverse effect occurrence between the SIB-IMRT and SEQ-IMRT groups.

CONCLUSION

SIB-IMRT and SEQ-IMRT can provide comparable outcomes in the treatment of patients afflicted by HNC. Both IMRT techniques were found to carry a similar risk of severe acute adverse effect. SIB-IMRT may have advantages due to its convenience and short-course of treatment; however, the optimum fractionation and prescribed dose remained unclear. Furthermore, both IMRT techniques can be advocated as the technique of choice for HNC. Treatment plan should be individualized for patients.

A dosimetric study on radiation-induced hypothyroidism following intensity-modulated radiotherapy in patients with nasopharyngeal carcinoma

The objective of the present study was to investigate the association between thyroid gland-dosimetric parameters and hypothyroidism induced by intensity-modulated radiotherapy in patients with nasopharyngeal carcinoma (NPC). A total of 52 patients with NPC treated in the Department of Radiation Oncology of The Affiliated Hospital of Xuzhou Medical University, from May 2008 to December 2016 were retrospectively enrolled in the present study and divided into two groups based on thyroid function: The euthyroid and hypothyroid groups. The association between hypothyroidism and clinical or dosimetric parameters were analyzed. Females had a significantly increased probability of suffering from radiation-induced hypothyroidism (RIHT), compared with males (P=0.010). The occurrence of RIHT was significantly negatively associated with thyroid volume prior to radiotherapy (P=0.048). Furthermore, the mean dose (Dmean) and V50 in the hypothyroidism group were significantly increased, compared with the euthyroidism group (P=0.017 and P=0.023, respectively). During the treatment optimization period, dose constraints associated with the thyroid gland demonstrated a significantly protective effect on thyroid function compared with the unconstrained group (P=0.034). According to the receiver operating characteristic curves, the threshold value was 5,160 cGy for Dmean and 54.5% for V50. The 3-year cumulative incidence of RIHT was 67.8% when the Dmean value was >5,160 cGy and 44.6% when the Dmean was <5,160 cGy (log rank test, P=0.036). Furthermore, the 3-year cumulative incidence was 66.1% when the V50 was >54.5%, and 29.9% when the V50 was <54.5% (log rank test, P=0.025). In conclusion, RIHT is associated with radiation dose, particularly with Dmean and V50 of the thyroid gland. Dose constraints associated with the thyroid gland significantly reduced the incidence of hypothyroidism compared with the unconstrained group.