Inter-observer variability in target delineation increases during adaptive treatment of head-and-neck and lung cancer

Adaptive radiotherapy for head and neck cancer: Pitfalls and possibilities from the radiation oncologist's point of view

BACKGROUND

Patients with head and neck cancer (HNC) may experience substantial anatomical changes during the course of radiotherapy treatment. The implementation of adaptive radiotherapy (ART) proves effective in managing the consequent impact on the planned dose distribution.

METHODS

This narrative literature review comprehensively discusses the diverse strategies of ART in HNC and the documented dosimetric and clinical advantages associated with these approaches, while also addressing the current challenges for integration of ART into clinical practice.

RESULTS AND CONCLUSION

Although based on mainly non-randomized and retrospective trials, there is accumulating evidence that ART has the potential to reduce toxicity and improve quality of life and tumor control in HNC patients treated with RT. However, several questions remain regarding accurate patient selection, the ideal frequency and timing of replanning, and the appropriate way for image registration and dose calculation. Well-designed randomized prospective trials, with a predetermined protocol for both image registration and dose summation, are urgently needed to further investigate the dosimetric and clinical benefits of ART.

Contouring aid tools in radiotherapy. Smoothing: the false friend

OBJECTIVE

Contouring accuracy is critical in modern radiotherapy. Several tools are available to assist clinicians in this task. This study aims to evaluate the performance of the smoothing tool in the ARIA system to obtain more consistent volumes.

METHODS

Eleven different geometric shapes were delineated in ARIA v15.6 (Sphere, Cube, Square Prism, Six-Pointed Star Prism, Arrow Prism, And Cylinder and the respective volumes at 45° of axis deviation (_45)) in 1, 3, 5, 7, and 10 cm side or diameter each. Post-processing drawing tools to smooth those first-generated volumes were applied in different options (2D-ALL vs 3D) and grades (1, 3, 5, 10, 15, and 20). These volumetric transformations were analyzed by comparing different parameters: volume changes, center of mass, and DICE similarity coefficient index. Then we studied how smoothing affected two different volumes in a head and neck cancer patient: a single rounded node and the volume delineating cervical nodal areas.

RESULTS

No changes in data were found between 2D-ALL or 3D smoothing. Minimum deviations were found (range from 0 to 0.45 cm) in the center of mass. Volumes and the DICE index decreased as the degree of smoothing increased. Some discrepancies were found, especially in figures with cleft and spikes that behave differently. In the clinical case, smoothing should be applied only once throughout the target delineation process, preferably in the largest volume (PTV) to minimize errors.

CONCLUSION

Smoothing is a good tool to reduce artifacts due to the manual delineation of radiotherapy volumes. The resulting volumes must be always carefully reviewed.

A fast and robust constraint-based online re-optimization approach for automated online adaptive intensity modulated proton therapy in head and neck cancer

Objective. In head-and-neck cancer intensity modulated proton therapy, adaptive radiotherapy is currently restricted to offline re-planning, mitigating the effect of slow changes in patient anatomies. Daily online adaptations can potentially improve dosimetry. Here, a new, fully automated online re-optimization strategy is presented. In a retrospective study, this online re-optimization approach was compared to our trigger-based offline re-planning (offlineTBre-planning) schedule, including extensive robustness analyses.Approach. The online re-optimization method employs automated multi-criterial re-optimization, using robust optimization with 1 mm setup-robustness settings (in contrast to 3 mm for offlineTBre-planning). Hard planning constraints and spot addition are used to enforce adequate target coverage, avoid prohibitively large maximum doses and minimize organ-at-risk doses. For 67 repeat-CTs from 15 patients, fraction doses of the two strategies were compared for the CTVs and organs-at-risk. Per repeat-CT, 10.000 fractions with different setup and range robustness settings were simulated using polynomial chaos expansion for fast and accurate dose calculations.Main results. For 14/67 repeat-CTs, offlineTBre-planning resulted in <50% probability ofD98%≥ 95% of the prescribed dose (Dpres) in one or both CTVs, which never happened with online re-optimization. With offlineTBre-planning, eight repeat-CTs had zero probability of obtainingD98%≥ 95%Dpresfor CTV7000, while the minimum probability with online re-optimization was 81%. Risks of xerostomia and dysphagia grade ≥ II were reduced by 3.5 ± 1.7 and 3.9 ± 2.8 percentage point [mean ± SD] (p< 10-5for both). In online re-optimization, adjustment of spot configuration followed by spot-intensity re-optimization took 3.4 min on average.Significance. The fast online re-optimization strategy always prevented substantial losses of target coverage caused by day-to-day anatomical variations, as opposed to the clinical trigger-based offline re-planning schedule. On top of this, online re-optimization could be performed with smaller setup robustness settings, contributing to improved organs-at-risk sparing.

Interobserver variability studies in diagnostic imaging: a methodological systematic review

OBJECTIVES

To review the methodology of interobserver variability studies; including current practice and quality of conducting and reporting studies.

METHODS

Interobserver variability studies between January 2019 and January 2020 were included; extracted data comprised of study characteristics, populations, variability measures, key results, and conclusions. Risk of bias was assessed using the COSMIN tool for assessing reliability and measurement error.

RESULTS

Seventy-nine full-text studies were included covering various imaging tests and clinical areas. The median number of patients was 47 (IQR:23-88), and observers were 4 (IQR:2-7), with sample size justified in 12 (15%) studies. Most studies used static images (n = 75, 95%), where all observers interpreted images for all patients (n = 67, 85%). Intraclass correlation coefficients (ICC) (n = 41, 52%), Kappa (κ) statistics (n = 31, 39%) and percentage agreement (n = 15, 19%) were most commonly used. Interpretation of variability estimates often did not correspond with study conclusions. The COSMIN risk of bias tool gave a very good/adequate rating for 52 studies (66%) including any studies that used variability measures listed in the tool. For studies using static images, some study design standards were not applicable and did not contribute to the overall rating.

CONCLUSIONS

Interobserver variability studies have diverse study designs and methods, the impact of which requires further evaluation. Sample size for patients and observers was often small without justification. Most studies report ICC and κ values, which did not always coincide with the study conclusion. High ratings were assigned to many studies using the COSMIN risk of bias tool, with certain standards scored 'not applicable' when static images were used.

ADVANCES IN KNOWLEDGE

The sample size for both patients and observers was often small without justification.For most studies, observers interpreted static images and did not evaluate the process of acquiring the imaging test, meaning it was not possible to assess many COSMIN risk of bias standards for studies with this design.Most studies reported intraclass correlation coefficient and κ statistics; study conclusions often did not correspond with results.

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.

Exploring trade-offs in treatment planning for brain tumor cases with a probabilistic definition of the clinical target volume

PURPOSE

This study demonstrates how a novel probabilistic clinical target volume (CTV) concept-the clinical target distribution (CTD)-can be used to navigate the trade-off between target coverage and organ sparing with a semi-interactive treatment planning approach.

METHODS

Two probabilistic treatment planning methods are presented that use tumor probabilities to balance tumor control with organ-at-risk (OAR) sparing. The first method explores OAR dose reduction by systematically discarding x % $x\%$ of CTD voxels with an unfavorable dose-to-probability ratio from the minimum dose coverage objective. The second method sequentially expands the target volume from the GTV edge, calculating the CTD coverage versus OAR sparing trade-off after dosing each expansion. Each planning method leads to estimated levels of tumor control under specific statistical models of tumor infiltration: an independent tumor islets model and contiguous circumferential tumor growth model. The methods are illustrated by creating proton therapy treatment plans for two glioblastoma patients with the clinical goal of sparing the hippocampus and brainstem. For probabilistic plan evaluation, the concept of a dose-expected-volume histogram is introduced, which plots the dose to the expected tumor volume ⟨ v ⟩ $\langle v \rangle$ considering tumor probabilities.

RESULTS

Both probabilistic planning approaches generate a library of treatment plans to interactively navigate the planning trade-offs. In the first probabilistic approach, a significant reduction of hippocampus dose could be achieved by excluding merely 1% of CTD voxels without compromising expected tumor control probability (TCP) or CTD coverage: the hippocampus D 2 % $D_{2\%}$ dose reduces with 9.5 and 5.3 Gy for Patient 1 and 2, while the TCP loss remains below 1%. Moreover, discarding up to 10% of the CTD voxels does not significantly diminish the expected CTD dose, even though evaluation with a binary volume suggests poor CTD coverage. In the second probabilistic approach, the expected CTD D ⟨ 98 % ⟩ $D_{\langle 98\%\rangle }$ and TCP depend more strongly on the extent of the high-dose region: the target volume margin cannot be reduced by more than 2 mm if one aims at keeping the expected CTD D ⟨ 98 % ⟩ $D_{\langle 98\%\rangle }$ loss and TCP loss under 1 Gy and 2%, respectively. Therefore, there is less potential for improved OAR sparing without compromising TCP or expected CTD coverage.

CONCLUSIONS

This study proposes and implements treatment planning strategies to explore trade-offs using tumor probabilities.

Clinical implementation and validation of an automated adaptive workflow for proton therapy

Background and purpose

Treatment quality of proton therapy can be monitored by repeat-computed tomography scans (reCTs). However, manual re-delineation of target contours can be time-consuming. To improve the workflow, we implemented an automated reCT evaluation, and assessed if automatic target contour propagation would lead to the same clinical decision for plan adaptation as the manual workflow.

Materials and methods

This study included 79 consecutive patients with a total of 250 reCTs which had been manually evaluated. To assess the feasibility of automated reCT evaluation, we propagated the clinical target volumes (CTVs) deformably from the planning-CT to the reCTs in a commercial treatment planning system. The dose-volume-histogram parameters were extracted for manually re-delineated (CTV_manual) and deformably mapped target contours (CTV_auto). It was compared if CTV_manual and CTV_auto both satisfied/failed the clinical constraints. Duration of the reCT workflows was also recorded.

Results

In 92% (N = 229) of the reCTs correct flagging was obtained. Only 4% (N = 9) of the reCTs presented with false negatives (i.e., at least one clinical constraint failed for CTV_manual, but all constraints were satisfied for CTV_auto), while 5% (N = 12) of the reCTs led to a false positive. Only for one false negative reCT a plan adaption was made in clinical practice, i.e., only one adaptation would have been missed, suggesting that automated reCT evaluation was possible. Clinical introduction hereof led to a time reduction of 49 h (from 65 to 16 h).

Conclusion

Deformable target contour propagation was clinically acceptable. A script-based automatic reCT evaluation workflow has been introduced in routine clinical practice.

Immunohistochemical analyses of paraffin-embedded sections after primary surgery or trimodality treatment in esophageal carcinoma

•

Changes in the tumor microenvironment of esophageal cancers, both in squamous cell carcinoma and adenocarcinoma, were found when comparing tumor resection specimen having undergone neoadjuvant radiochemotherapy followed by resection or resection only.

•

Selected markers of the tumor microenvironment, i.e., Ki67, p53, CXCR4 and PD1 were found to be downregulated in hypoxic regions compared to normoxic regions.

•

These findings will be correlated with microscopic tumor extension measurements in a subsequent, prospectively included cohort of esophageal cancer patients.

Background

The microscopic tumor extension before, during or after radiochemotherapy (RCHT) and its correlation with the tumor microenvironment (TME) are presently unknown. This information is, however, crucial in the era of image-guided, adaptive high-precision photon or particle therapy.

Materials and methods

In this pilot study, we analyzed formalin-fixed paraffin-embedded (FFPE) tumor resection specimen from patients with histologically confirmed squamous cell carcinoma (SCC; n = 10) or adenocarcinoma (A; n = 10) of the esophagus, having undergone neoadjuvant radiochemotherapy followed by resection (NRCHT + R) or resection (R)]. FFPE tissue sections were analyzed by immunohistochemistry regarding tumor hypoxia (HIF-1α), proliferation (Ki67), immune status (PD1), cancer cell stemness (CXCR4), and p53 mutation status. Marker expression in HIF-1α subvolumes was part of a sub-analysis. Statistical analyses were performed using one-sided Mann-Whitney tests and Bland-Altman analysis.

Results

In both SCC and AC patients, the overall percentages of positive tumor cells among the five TME markers, namely HIF-1α, Ki67, p53, CXCR4 and PD1 after NRCHT were lower than in the R cohort. However, only PD1 in SCC and Ki67 in AC showed significant association (Ki67: p = 0.03, PD1: p = 0.02). In the sub-analysis of hypoxic subvolumes among the AC patients, the percentage of positive tumor cells within hypoxic regions were statistically significantly lower in the NRCHT than in the R cohort across all the markers except for PD1.

Conclusion

In this pilot study, we showed changes in the TME induced by NRCHT in both SCC and AC. These findings will be correlated with microscopic tumor extension measurements in a subsequent cohort of patients.

Augmenting inter-rater concordance of radiologic extranodal extension in HPV-positive oropharyngeal carcinoma: A multicenter study

OBJECTIVES

To assess intra- and inter-institutional concordance and identify methods to increase precision in radiologic extranodal extension (rENE) ascertainment in HPV+ oropharyngeal carcinoma.

METHODS

Six radiologists, blinded to clinical outcomes, from three centers assessed rENE in two phases: Phase-I (20 cases) utilized each individual's a priori appreciation of the literature. Phase-II (30 additional cases) was performed after deliberating experience and consolidating operating definitions. Intra- and inter-institutional Kappa were calculated at >50% and >75% certainty levels, respectively.

RESULTS

The Phase-I intra-institutional kappa was 0.76, 0.32, and 0.44 at >50% certainty and improved to 0.89, 0.61, and 0.66 at >75% certainty. Inter-institutional Fleiss' kappa also improved with higher certainty (from 0.40 to 0.57, p = 0.039).  The Phase-II inter-rater kappa was significantly higher than Phase-I at the same certainty level (both p < 0.001).

CONCLUSION

A learning curve exists for rENE assessment. Strategies to augment reliability include high certainty for declaration, consolidated operating definitions, and sharing experience among radiologists.

Towards a safe and efficient clinical implementation of machine learning in radiation oncology by exploring model interpretability, explainability and data-model dependency

The interest in machine learning (ML) has grown tremendously in recent years, partly due to the performance leap that occurred with new techniques of deep learning, convolutional neural networks for images, increased computational power, and wider availability of large datasets. Most fields of medicine follow that popular trend and, notably, radiation oncology is one of those that are at the forefront, with already a long tradition in using digital images and fully computerized workflows. ML models are driven by data, and in contrast with many statistical or physical models, they can be very large and complex, with countless generic parameters. This inevitably raises two questions, namely, the tight dependence between the models and the datasets that feed them, and the interpretability of the models, which scales with its complexity. Any problems in the data used to train the model will be later reflected in their performance. This, together with the low interpretability of ML models, makes their implementation into the clinical workflow particularly difficult. Building tools for risk assessment and quality assurance of ML models must involve then two main points: interpretability and data-model dependency. After a joint introduction of both radiation oncology and ML, this paper reviews the main risks and current solutions when applying the latter to workflows in the former. Risks associated with data and models, as well as their interaction, are detailed. Next, the core concepts of interpretability, explainability, and data-model dependency are formally defined and illustrated with examples. Afterwards, a broad discussion goes through key applications of ML in workflows of radiation oncology as well as vendors' perspectives for the clinical implementation of ML.

ProCaLung - Peer review in stage III, mediastinal node-positive, non-small-cell lung cancer: How to benchmark clinical practice of nodal target volume definition and delineation in Belgium☆

BACKGROUND AND PURPOSE

The Quality Assurance project for stage III non-small cell lung cancer radiotherapy ProCaLung performed a multicentric two-step exercise evaluating mediastinal nodal Target Volume Definition and Delineation (TVD) variability and the opportunity for standardization. The TVD variability before and after providing detailed guidelines and the value of qualitative contour reviewing before applying quantitative measures were investigated.

MATERIALS AND METHODS

The case of a patient with stage III NSCLC and involved mediastinal lymph nodes was used as a basis for this study. Twenty-two radiation oncologists from nineteen centers in Belgium and Luxembourg participated in at least one of two phases of the project (before and after introduction of ProCaLung contouring guidelines). The resulting thirty-three mediastinal nodal GTV and CTV contours were then evaluated using a qualitative-before-quantitative (QBQ) approach. First, a qualitative analysis was performed, evaluating adherence to most recent guidelines. From this, a list of observed deviations was created and these were used to evaluate contour conformity. The second analysis was quantitative, using overlap and surface distance measures to compare contours within qualitative groups and between phases. A 'most robust' reference volume for these analyses was created using the STAPLE-algorithm and an averaging method.

RESULTS

Five GTV and seven CTV qualitative groups were identified. Second step contours were more often in higher-conformity groups (p = 0.012 for GTV and p = 0.024 for CTV). Median Residual Mean Square Distances improved from 2.34 mm to 1.36 mm for GTV (p = 0.01) and from 4.53 mm to 1.58 mm for CTV (p < 0.0001). Median Dice coefficients increased from 0.81 to 0.84 for GTV (p = 0.07) and from 0.82 to 0.89 for CTV (p ≤ 0.001). Using HC-contours only to generate references translated in more robust quantitative evaluations.

CONCLUSION

Variability of mediastinal nodal TVD was reduced after providing the ProCaLung consensus guidelines. A qualitative review was essential for providing meaningful quantitative measures.

Comparing different CT, PET and MRI multi-modality image combinations for deep learning-based head and neck tumor segmentation

BACKGROUND

Manual delineation of gross tumor volume (GTV) is essential for radiotherapy treatment planning, but it is time-consuming and suffers inter-observer variability (IOV). In clinics, CT, PET, and MRI are used to inform delineation accuracy due to their different complementary characteristics. This study aimed to investigate deep learning to assist GTV delineation in head and neck squamous cell carcinoma (HNSCC) by comparing various modality combinations.

MATERIALS AND METHODS

This retrospective study had 153 patients with multiple sites of HNSCC including their planning CT, PET, and MRI (T1-weighted and T2-weighted). Clinical delineations of gross tumor volume (GTV-T) and involved lymph nodes (GTV-N) were collected as the ground truth. The dataset was randomly divided into 92 patients for training, 31 for validation, and 30 for testing. We applied a residual 3 D UNet as the deep learning architecture. We independently trained the UNet with four different modality combinations (CT-PET-MRI, CT-MRI, CT-PET, and PET-MRI). Additionally, analogical to post-processing, an average fusion of three bi-modality combinations (CT-PET, CT-MRI, and PET-MRI) was produced as an ensemble. Segmentation accuracy was evaluated on the test set, using Dice similarity coefficient (Dice), Hausdorff Distance 95 percentile (HD95), and Mean Surface Distance (MSD).

RESULTS

All imaging combinations including PET provided similar average scores in range of Dice: 0.72-0.74, HD95: 8.8-9.5 mm, MSD: 2.6-2.8 mm. Only CT-MRI had a lower score with Dice: 0.58, HD95: 12.9 mm, MSD: 3.7 mm. The average of three bi-modality combinations reached Dice: 0.74, HD95: 7.9 mm, MSD: 2.4 mm.

CONCLUSION

Multimodal deep learning-based auto segmentation of HNSCC GTV was demonstrated and inclusion of the PET image was shown to be crucial. Training on combined MRI, PET, and CT data provided limited improvements over CT-PET and PET-MRI. However, when combining three bimodal trained networks into an ensemble, promising improvements were shown.

Intra- and inter-physician variability in target volume delineation in radiation therapy

Reduction in setup errors is advocated through daily imaging and adaptive therapy, where the target volume is drawn daily. Previous studies suggest that inter-physician volume variation is significant (1.5 cm standard deviation [SD]); however, there are limited data for intra-physician consistency in daily target volume delineation, which is investigated in this study. Seven patients with lung cancer were chosen based on the perceived difficulty of contouring their disease, varying from simple parenchymal lung nodules to lesions with extensive adjacent atelectasis. Four physicians delineated the gross tumor volume (GTV) for each patient on 10 separate days to see the intra- and inter-physician contouring. Isocenter coordinates (x, y and z), target volume (cm3), and largest dimensions on anterior-posterior (AP) and lateral views were recorded for each GTV. Our results show that the variability among the physicians was reflected by target volumes ranging from +109% to -86% from the mean while isocenter coordinate changes were minimal; 3.8, 1.7 and 1.9 mm for x, y and z coordinates, respectively. The orthogonal image (AP and lateral) change varied 16.3 mm and 15.0 mm respectively among days and physicians. We conclude than when performing daily imaging, random variability in contouring resulted in isocenter changes up to ±3.8 mm in our study. The shape of the target varied within ±16 mm. This study suggests that when using daily imaging to track isocenter, target volume, or treatment parameters, physicians should be aware of personal variability when considering margins added to the target volume in daily decision making especially for difficult cases.

An Adversarial Deep-Learning-Based Model for Cervical Cancer CTV Segmentation With Multicenter Blinded Randomized Controlled Validation

Purpose

To propose a novel deep-learning-based auto-segmentation model for CTV delineation in cervical cancer and to evaluate whether it can perform comparably well to manual delineation by a three-stage multicenter evaluation framework.

Methods

An adversarial deep-learning-based auto-segmentation model was trained and configured for cervical cancer CTV contouring using CT data from 237 patients. Then CT scans of additional 20 consecutive patients with locally advanced cervical cancer were collected to perform a three-stage multicenter randomized controlled evaluation involving nine oncologists from six medical centers. This evaluation system is a combination of objective performance metrics, radiation oncologist assessment, and finally the head-to-head Turing imitation test. Accuracy and effectiveness were evaluated step by step. The intra-observer consistency of each oncologist was also tested.

Results

In stage-1 evaluation, the mean DSC and the 95HD value of the proposed model were 0.88 and 3.46 mm, respectively. In stage-2, the oncologist grading evaluation showed the majority of AI contours were comparable to the GT contours. The average CTV scores for AI and GT were 2.68 vs. 2.71 in week 0 (P = .206), and 2.62 vs. 2.63 in week 2 (P = .552), with no significant statistical differences. In stage-3, the Turing imitation test showed that the percentage of AI contours, which were judged to be better than GT contours by ≥5 oncologists, was 60.0% in week 0 and 42.5% in week 2. Most oncologists demonstrated good consistency between the 2 weeks (P > 0.05).

Conclusions

The tested AI model was demonstrated to be accurate and comparable to the manual CTV segmentation in cervical cancer patients when assessed by our three-stage evaluation framework.

The impact of organ-at-risk contour variations on automatically generated treatment plans for NSCLC

BACKGROUND AND PURPOSE

Quality of automatic contouring is generally assessed by comparison with manual delineations, but the effect of contour differences on the resulting dose distribution remains unknown. This study evaluated dosimetric differences between treatment plans optimized using various organ-at-risk (OAR) contouring methods.

MATERIALS AND METHODS

OARs of twenty lung cancer patients were manually and automatically contoured, after which user-adjustments were made. For each contour set, an automated treatment plan was generated. The dosimetric effect of intra-observer contour variation and the influence of contour variations on treatment plan evaluation and generation were studied using dose-volume histogram (DVH)-parameters for thoracic OARs.

RESULTS

Dosimetric effect of intra-observer contour variability was highest for Heart D_max (3.4 ± 6.8 Gy) and lowest for Lungs-GTV D_mean (0.3 ± 0.4 Gy). The effect of contour variation on treatment plan evaluation was highest for Heart D_max (6.0 ± 13.4 Gy) and Esophagus D_max (8.7 ± 17.2 Gy). Dose differences for the various treatment plans, evaluated on the reference (manual) contour, were on average below 1 Gy/1%. For Heart D_mean, higher dose differences were found for overlap with PTV (median 0.2 Gy, 95% 1.7 Gy) vs. no PTV overlap (median 0 Gy, 95% 0.5 Gy). For D_max-parameters, largest dose difference was found between 0-1 cm distance to PTV (median 1.5 Gy, 95% 4.7 Gy).

CONCLUSION

Dose differences arising from automatic contour variations were of the same magnitude or lower than intra-observer contour variability. For Heart D_mean, we recommend delineation errors to be corrected when the heart overlaps with the PTV. For D_max-parameters, we recommend checking contours if the distance is close to PTV (<5 cm). For the lungs, only obvious large errors need to be adjusted.

Accuracy of automatic structure propagation for daily magnetic resonance image-guided head and neck radiotherapy

BACKGROUND AND PURPOSE

Deformable image registration (DIR) and contour propagation are used in daily online adaptation for hybrid MRI linac (MRL) treatments. The accuracy of the propagated contours may vary depending on the chosen workflow (WF), affecting the amount of required manual corrections. This study investigated the impact of three different WFs of contour propagations produced by a clinical treatment planning system for a high-field MRL on head and neck cancer patients.

METHODS

Seventeen patients referred for curative radiotherapy for oropharyngeal cancer underwent standard CT-based dose planning and MR scans in the treatment position for planning (pMR), and at the 10th (MR10), 20th (MR20) and 30th (MR30) fraction (±2). The primary tumour, a metastatic lymph node and 8 organs at risk were manually delineated on each set of T2 weighted images. Delineations were repeated one month later on the pMR by the same observer to determine the intra-observer variation (IOV). Three WFs were used to deform images in the treatment planning system for the high-field MRL: In WF1, only the planning image and contours were used as a reference for DIR and propagation to MR_10,20,30. The most recently acquired image set prior to the daily images was deformed and uncorrected (WF2) versus manually corrected (WF3) structures propagated to the session image. Dice similarity coefficient (DSC), mean surface distance (MSD) and Hausdorff distance (HD) were calculated for each structure in each model.

RESULTS

Population median DSC, MSD and HD for WF1 and WF3 were similar and slightly better than for WF2. WF3 provided higher accuracy than WF1 for structures that are likely to shrink. All DIR workflows were less accurate than the IOV.

CONCLUSIONS

WF1 and WF3 provide higher accuracy in structure propagation than WF2. Manual revision and correction of propagated structures are required for all evaluated workflows.

Self-channel-and-spatial-attention neural network for automated multi-organ segmentation on head and neck CT images

Accurate segmentation of organs at risk (OARs) is necessary for adaptive head and neck (H&N) cancer treatment planning, but manual delineation is tedious, slow, and inconsistent. A self-channel-and-spatial-attention neural network (SCSA-Net) is developed for H&N OAR segmentation on CT images. To simultaneously ease the training and improve the segmentation performance, the proposed SCSA-Net utilizes the self-attention ability of the network. Spatial and channel-wise attention learning mechanisms are both employed to adaptively force the network to emphasize the meaningful features and weaken the irrelevant features simultaneously. The proposed network was first evaluated on a public dataset, which includes 48 patients, then on a separate serial CT dataset, which contains ten patients who received weekly diagnostic fan-beam CT scans. On the second dataset, the accuracy of using SCSA-Net to track the parotid and submandibular gland volume changes during radiotherapy treatment was quantified. The Dice similarity coefficient (DSC), positive predictive value (PPV), sensitivity (SEN), average surface distance (ASD), and 95% maximum surface distance (95SD) were calculated on the brainstem, optic chiasm, optic nerves, mandible, parotid glands, and submandibular glands to evaluate the proposed SCSA-Net. The proposed SCSA-Net consistently outperforms the state-of-the-art methods on the public dataset. Specifically, compared with Res-Net and SE-Net, which is constructed from squeeze-and-excitation block equipped residual blocks, the DSC of the optic nerves and submandibular glands is improved by 0.06, 0.03 and 0.05, 0.04 by the SCSA-Net. Moreover, the proposed method achieves statistically significant improvements in terms of DSC on all and eight of nine OARs over Res-Net and SE-Net, respectively. The trained network was able to achieve good segmentation results on the serial dataset, but the results were further improved after fine-tuning of the model using the simulation CT images. For the parotids and submandibular glands, the volume changes of individual patients are highly consistent between the automated and manual segmentation (Pearson's correlation 0.97-0.99). The proposed SCSA-Net is computationally efficient to perform segmentation (sim 2 s/CT).

The role of computational methods for automating and improving clinical target volume definition

Treatment planning in radiotherapy distinguishes three target volume concepts: the gross tumor volume (GTV), the clinical target volume (CTV), and the planning target volume (PTV). Over time, GTV definition and PTV margins have improved through the development of novel imaging techniques and better image guidance, respectively. CTV definition is sometimes considered the weakest element in the planning process. CTV definition is particularly complex since the extension of microscopic disease cannot be seen using currently available in-vivo imaging techniques. Instead, CTV definition has to incorporate knowledge of the patterns of tumor progression. While CTV delineation has largely been considered the domain of radiation oncologists, this paper, arising from a 2019 ESTRO Physics research workshop, discusses the contributions that medical physics and computer science can make by developing computational methods to support CTV definition. First, we overview the role of image segmentation algorithms, which may in part automate CTV delineation through segmentation of lymph node stations or normal tissues representing anatomical boundaries of microscopic tumor progression. The recent success of deep convolutional neural networks has also enabled learning entire CTV delineations from examples. Second, we discuss the use of mathematical models of tumor progression for CTV definition, using as example the application of glioma growth models to facilitate GTV-to-CTV expansion for glioblastoma that is consistent with neuroanatomy. We further consider statistical machine learning models to quantify lymphatic metastatic progression of tumors, which may eventually improve elective CTV definition. Lastly, we discuss approaches to incorporate uncertainty in CTV definition into treatment plan optimization as well as general limitations of the CTV concept in the case of infiltrating tumors without natural boundaries.

Geometric and Dosimetric Evaluation of a Commercially Available Auto-segmentation Tool for Gross Tumour Volume Delineation in Locally Advanced Non-small Cell Lung Cancer: a Feasibility Study

AIMS

To quantify the reliability of a commercially available auto-segmentation tool in locally advanced non-small cell lung cancer using serial four-dimensional computed tomography (4DCT) scans during conventionally fractionated radiotherapy.

MATERIALS AND METHODS

Eight patients with serial 4DCT scans (n = 44) acquired over the course of radiotherapy were assessed. Each 4DCT had a physician-defined primary tumour manual contour (MC). An auto-contour (AC) and a user-adjusted auto-contour (UA-AC) were created for each scan. Geometric agreement of the AC and the UA-AC to the MC was assessed using the dice similarity coefficient (DSC), the centre of mass (COM) shift from the MC and the structure volume difference from the MC. Bland Altman analysis was carried out to assess agreement between contouring methods. Dosimetric reliability was assessed by comparison of planning target volume dose coverage on the MC and UA-AC. The time trend analysis of the geometric accuracy measures from the initial planning scan through to the final scan for each patient was evaluated using a Wilcoxon signed ranks test to assess the reliability of the UA-AC over the duration of radiotherapy.

RESULTS

User adjustment significantly improved all geometric comparison metrics over the AC alone. Improved agreement was observed in smaller tumours not abutting normal soft tissue and median values for geometric comparisons to the MC for DSC, tumour volume difference and COM offset were 0.80 (range 0.49-0.89), 0.8 cm³ (range 0.0-5.9 cm³) and 0.16 cm (range 0.09-0.69 cm), respectively. There were no significant differences in dose metrics measured from the MC and the UA-AC after Bonferroni correction. Variation in geometric agreement between the MC and the UA-AC were observed over the course of radiotherapy with both DSC (P = 0.035) and COM shift from the MC (ns) worsening. The median tumour volume difference from the MC improved at the later time point.

CONCLUSIONS

These findings suggest that the UA-AC can produce geometrically and dosimetrically acceptable contours for appropriately selected patients with non-small cell lung cancer. Larger studies are required to confirm the findings.