Heterogeneity in head and neck IMRT target design and clinical practice

Increasing radiation therapy and lower survival for human papillomavirus-related oropharynx cancer associated with a shift to community cancer center care

BACKGROUND

Studies have shown lower overall survival for patients with head and neck cancer treated at low-volume or community cancer centers. As the incidence of human papillomavirus (HPV)-related oropharyngeal squamous cell carcinoma steadily rises in the United States, we hypothesized that a greater proportion of patients with HPV-related oropharyngeal squamous cell carcinoma is being treated at community cancer centers, with a shift toward primary nonsurgical treatment.

METHODS

This cohort study included patients from the US National Cancer Database who received a diagnosis of HPV-related oropharyngeal squamous cell carcinoma from 2010 to 2019 and underwent treatment at a community cancer center or academic cancer center. The proportion of patients with HPV-related oropharyngeal squamous cell carcinoma treated at community cancer centers and receiving primary nonsurgical treatment was analyzed over time. Four-year overall survival was compared between community cancer centers and academic cancer centers.

RESULTS

The majority (67.4%) of 20 298 patients were treated at an academic cancer center, yet the proportion of patients treated at community cancer centers increased by 10% from 2010 to 2019 (P < .01 for trend). The proportion of patients undergoing primary nonsurgical treatment increased from 62.1% to 73.7% from 2010 to 2019 (P < .01 for trend), and patients were statistically significantly more likely to undergo nonsurgical treatment at community cancer centers than at academic cancer centers (adjusted odds ratio = 1.20, 95% confidence interval = 1.18 to 1.22). Treatment at community cancer centers was associated with worse survival overall (adjusted hazard ratio = 1.19, 95% confidence interval = 1.09 to 1.31), specifically for patients receiving primary nonsurgical treatment (adjusted hazard ratio = 1.22, 95% confidence interval = 1.11 to 1.34).

CONCLUSIONS

Treatment of HPV-related oropharyngeal squamous cell carcinoma has recently shifted to community cancer centers, with an increase in the proportion of nonsurgical treatment and worse overall survival at these centers compared with academic cancer centers. Concentration of care for HPV-related oropharyngeal squamous cell carcinoma at academic cancer centers and dedicated head and neck cancer centers may increase access to all available treatment modalities and improve survival.

Systematic Implementation of Effective Quality Assurance Processes for the Assessment of Radiation Target Volumes in Head and Neck Cancer

PURPOSE

Significant heterogeneity exists in clinical quality assurance (QA) practices within radiation oncology departments, with most chart rounds lacking prospective peer-reviewed contour evaluation. This has the potential to significantly affect patient outcomes, particularly for head and neck cancers (HNC) given the large variance in target volume delineation. With this understanding, we incorporated a prospective systematic peer contour-review process into our workflow for all patients with HNC. This study aims to assess the effectiveness of implementing prospective peer review into practice for our National Cancer Institute Designated Cancer Center and to report factors associated with contour modifications.

METHODS AND MATERIALS

Starting in November 2020, our department adopted a systematic QA process with real-time metrics, in which contours for all patients with HNC treated with radiation therapy were prospectively peer reviewed and graded. Contours were graded with green (unnecessary), yellow (minor), or red (major) colors based on the degree of peer-recommended modifications. Contours from November 2020 through September 2021 were included for analysis.

RESULTS

Three hundred sixty contours were included. Contour grades were made up of 89.7% green, 8.9% yellow, and 1.4% red grades. Physicians with >12 months of clinical experience were less likely to have contour changes requested than those with <12 months (8.3% vs 40.9%; P < .001). Contour grades were significantly associated with physician case load, with physicians presenting more than the median number of 50 cases having significantly less modifications requested than those presenting <50 (6.7% vs 13.3%; P = .013). Physicians working with a resident or fellow were less likely to have contour changes requested than those without a trainee (5.2% vs 12.6%; P = .039). Frequency of major modification requests significantly decreased over time after adoption of prospective peer contour review, with no red grades occurring >6 months after adoption.

CONCLUSIONS

This study highlights the importance of prospective peer contour-review implementation into systematic clinical QA processes for HNC. Physician experience proved to be the highest predictor of approved contours. A growth curve was demonstrated, with major modifications declining after prospective contour review implementation. Even within a high-volume academic practice with subspecialist attendings, >10% of patients had contour changes made as a direct result of prospective peer review.

Artificial Intelligence-Based Radiotherapy Contouring and Planning to Improve Global Access to Cancer Care

PURPOSE

Increased automation has been identified as one approach to improving global cancer care. The Radiation Planning Assistant (RPA) is a web-based tool offering automated radiotherapy (RT) contouring and planning to low-resource clinics. In this study, the RPA workflow and clinical acceptability were assessed by physicians around the world.

METHODS

The RPA output for 75 cases was reviewed by at least three physicians; 31 radiation oncologists at 16 institutions in six countries on five continents reviewed RPA contours and plans for clinical acceptability using a 5-point Likert scale.

RESULTS

For cervical cancer, RPA plans using bony landmarks were scored as usable as-is in 81% (with minor edits 93%); using soft tissue contours, plans were scored as usable as-is in 79% (with minor edits 96%). For postmastectomy breast cancer, RPA plans were scored as usable as-is in 44% (with minor edits 91%). For whole-brain treatment, RPA plans were scored as usable as-is in 67% (with minor edits 99%). For head/neck cancer, the normal tissue autocontours were acceptable as-is in 89% (with minor edits 97%). The clinical target volumes (CTVs) were acceptable as-is in 40% (with minor edits 93%). The volumetric-modulated arc therapy (VMAT) plans were acceptable as-is in 87% (with minor edits 96%). For cervical cancer, the normal tissue autocontours were acceptable as-is in 92% (with minor edits 99%). The CTVs for cervical cancer were scored as acceptable as-is in 83% (with minor edits 92%). The VMAT plans for cervical cancer were acceptable as-is in 99% (with minor edits 100%).

CONCLUSION

The RPA, a web-based tool designed to improve access to high-quality RT in low-resource settings, has high rates of clinical acceptability by practicing clinicians around the world. It has significant potential for successful implementation in low-resource clinics.

A statistical deformation model-based data augmentation method for volumetric medical image segmentation

The accurate delineation of organs-at-risk (OARs) is a crucial step in treatment planning during radiotherapy, as it minimizes the potential adverse effects of radiation on surrounding healthy organs. However, manual contouring of OARs in computed tomography (CT) images is labor-intensive and susceptible to errors, particularly for low-contrast soft tissue. Deep learning-based artificial intelligence algorithms surpass traditional methods but require large datasets. Obtaining annotated medical images is both time-consuming and expensive, hindering the collection of extensive training sets. To enhance the performance of medical image segmentation, augmentation strategies such as rotation and Gaussian smoothing are employed during preprocessing. However, these conventional data augmentation techniques cannot generate more realistic deformations, limiting improvements in accuracy. To address this issue, this study introduces a statistical deformation model-based data augmentation method for volumetric medical image segmentation. By applying diverse and realistic data augmentation to CT images from a limited patient cohort, our method significantly improves the fully automated segmentation of OARs across various body parts. We evaluate our framework on three datasets containing tumor OARs from the head, neck, chest, and abdomen. Test results demonstrate that the proposed method achieves state-of-the-art performance in numerous OARs segmentation challenges. This innovative approach holds considerable potential as a powerful tool for various medical imaging-related sub-fields, effectively addressing the challenge of limited data access.

A deep learning-based semiautomated workflow for triaging follow-up MR scans in treated nasopharyngeal carcinoma

It is imperative to optimally utilize virtues and obviate defects of fully automated analysis and expert knowledge in new paradigms of healthcare. We present a deep learning-based semiautomated workflow (RAINMAN) with 12,809 follow-up scans among 2,172 patients with treated nasopharyngeal carcinoma from three centers (ChiCTR.org.cn, Chi-CTR2200056595). A boost of diagnostic performance and reduced workload was observed in RAINMAN compared with the original manual interpretations (internal vs. external: sensitivity, 2.5% [p = 0.500] vs. 3.2% [p = 0.031]; specificity, 2.9% [p < 0.001] vs. 0.3% [p = 0.302]; workload reduction, 79.3% vs. 76.2%). The workflow also yielded a triaging performance of 83.6%, with increases of 1.5% in sensitivity (p = 1.000) and 0.6%-1.3% (all p < 0.05) in specificity compared to three radiologists in the reader study. The semiautomated workflow shows its unique superiority in reducing radiologist's workload by eliminating negative scans while retaining the diagnostic performance of radiologists.

Impact of consensus guidelines on delineation of primary tumor clinical target volume (CTVp) for head and neck cancer: Results of a national review project

BACKGROUND AND PURPOSE

A significant interobserver variability (IOV) for clinical target volume of the primary tumor (CTVp) delineation was shown in a previous national review project. Since then, international expert consensus guidelines (CG) for the delineation of CTVp were published. The aim of this follow-up study was to 1) objectify the extent of implementation of the CG, 2) assess its impact on delineation quality and consistency, 3) identify any remaining ambiguities.

MATERIALS AND METHODS

All Belgian RT departments were invited to complete an online survey and submit CTVp for 5 reference cases. Organs at risk and GTV of the primary tumor were predefined. Margins, volumes, IOV between all participating centers (IOVall) and IOV compared to a reference consensus delineation (IOVref) were calculated and compared to the previous analysis. A qualitative analysis was performed assessing the correct interpretation of the CG for each case.

RESULTS

17 RT centers completed both survey and delineations, of which 88% had implemented CG. Median DSCref for CTVp_total was 0.80-0.92. IOVall and IOVref improved significantly for the centers following CG (p = 0.005). IOVref for CTVp_high was small with a DSC higher than 0.90 for all cases. A significant volume decrease for the CTVp receiving 70 Gy was observed. Interpretation of CG was more accurate for (supra)glottic carcinoma. 60% of the radiation oncologists thinks clarification of CG is indicated.

CONCLUSION

Implementation of consensus guidelines for CTVp delineation is already fairly advanced on a national level, resulting in significantly increased delineation uniformity. The accompanying substantial decrease of CTV receiving high dose RT calls for caution and correct interpretation of CG. Clarification of the existing guidelines seems appropriate especially for oropharyngeal and hypopharyngeal carcinoma.

The Feasibility of Quality Assurance in the TOPGEAR International Phase 3 Clinical Trial of Neoadjuvant Chemoradiation Therapy for Gastric Cancer (an Intergroup Trial of the AGITG/TROG/NHMRC CTC/EORTC/CCTG)

PURPOSE

The TOPGEAR phase 3 trial hypothesized that adding preoperative chemoradiation therapy (CRT) to perioperative chemotherapy will improve survival in patients with gastric cancer. Owing to the complexity of gastric irradiation, a comprehensive radiation therapy quality assurance (RTQA) program was implemented. Our objective is to describe the RTQA methods and outcomes.

METHODS AND MATERIALS

RTQA was undertaken in real time before treatment for the first 5 patients randomized to CRT from each center. Once acceptable quality was achieved, RTQA was completed for one-third of subsequent cases. RTQA consisted of evaluating (1) clinical target volume and organ-at-risk contouring and (2) radiation therapy planning parameters. Protocol violations between high- (20+ patients enrolled) and low-volume centers were compared using the Fisher exact test.

RESULTS

TOPGEAR enrolled 574 patients, of whom 286 were randomized to receive preoperative CRT and 203 (71%) were included for RTQA. Of these, 67 (33%) and 136 (67%) patients were from high- and low-volume centers, respectively. The initial RTQA pass rate was 72%. In total, 28% of cases required resubmission. In total, 200 of 203 cases (99%) passed RTQA before treatment. Cases from low-volume centers required resubmission more often (44/136 [33%] vs 13/67 [18%]; P = .078). There was no change in the proportion of cases requiring resubmission over time. Most cases requiring resubmission had multiple protocol violations. At least 1 aspect of the clinical target volume had to be adjusted in all cases. Inadequate coverage of the duodenum was most common (53% major violation, 25% minor violation). For the remaining cases, the resubmission process was triggered secondary to poor contour/plan quality.

CONCLUSIONS

In a large multicenter trial, RTQA is feasible and effective in achieving high-quality treatment plans. Ongoing education should be performed to ensure consistent quality during the entire study period.

Deep learning-based recurrence detector on magnetic resonance scans in nasopharyngeal carcinoma: A multicenter study

OBJECTIVES

Accuracy in the detection of recurrent nasopharyngeal carcinoma (NPC) on follow-up magnetic resonance (MR) scans needs to be improved.

MATERIAL AND METHODS

A total of 5 035 follow-up MR scans from 5 035 survivors with treated NPC between April 2007 and July 2020 were retrospectively collected from three cancer centers for developing and evaluating the deep learning (DL) model MODERN (MR-based Deep learning model for dEtecting Recurrent Nasopharyngeal carcinoma). In a reader study with 220 scans, the accuracy of two radiologists in detecting recurrence on scans with vs without MODERN was evaluated. The performance was measured using the area under the receiver operating characteristic curve (ROC-AUC) and accuracy with a 95% confidence interval (CI).

RESULTS

MODERN exhibited sound performance in the validation cohort (internal: ROC-AUC, 0.88, 95% CI, 0.86-0.90; external 1: ROC-AUC, 0.88, 95% CI, 0.86-0.90; external 2: ROC-AUC, 0.85, 95% CI, 0.82-0.88). In a reader study, MODERN alone achieved reliable accuracy compared to that of radiologists (MODERN: 84.1%, 95% CI, 79.3%-88.9%; competent: 80.9%, 95% CI, 75.7%-86.1%, P < 0.001; expert: 85.9%, 95% CI, 81.3%-90.5%, P < 0.001). The accuracy of radiologists was boosted by the MODERN score (competent with MODERN score: 84.6%, 95% CI, 79.8%-89.3%, P < 0.001; expert with MODERN score: 87.7%, 95% CI, 83.4%-92.1%, P < 0.001).

CONCLUSION

We developed a DL model for recurrence detection with reliable performance. Computer-human collaboration has the potential to refine the workflow in interpreting surveillant MR scans among patients with treated NPC.

Outcomes among oropharyngeal and oral cavity cancer patients treated with postoperative volumetric modulated arctherapy

Background

Presently, there are few published reports on postoperative radiation therapy for oropharyngeal and oral cavity cancers treated with IMRT/VMAT technique. This study aimed to assess the oncological outcomes of this population treated with postoperative VMAT in our institution, with a focus on loco-regional patterns of failure.

Material and methods

Between 2011 and 2019, 167 patients were included (40% of oropharyngeal cancers, and 60% of oral cavity cancers). The median age was 60 years. There was 64.2% of stage IV cancers. All patients had both T and N surgery. 34% had a R1 margin, 42% had perineural invasion. 72% had a positive neck dissection and 42% extranodal extension (ENE). All patients were treated with VMAT with simultaneous integrated boost with three dose levels: 66Gy in case of R1 margin and/or ENE, 59.4-60Gy on the tumor bed, and 54Gy on the prophylactic areas. Concomittant cisplatin was administrated concomitantly when feasible in case of R1 and/or ENE.

Results

The 1- and 2-year loco-regional control rates were 88.6% and 85.6% respectively. Higher tumor stage (T3/T4), the presence of PNI, and time from surgery >45 days were significant predictive factors of worse loco-regional control in multivariate analysis (p=0.02, p=0.04, and p=0.02). There were 17 local recurrences: 11 (64%) were considered as infield, 4 (24%) as marginal, and 2 (12%) as outfield. There were 9 regional recurrences only, 8 (89%) were considered as infield, and 1 (11%) as outfield. The 1- and 2-year disease-free survival (DFS) rates were 78.9% and 71.8% respectively. The 1- and 2-year overall survival (OS) rates were 88.6% and 80% respectively. Higher tumor stage (T3/T4) and the presence of ENE were the two prognostic factors significantly associated with worse DFS and OS in multivariate analysis.

Conclusion

Our outcomes for postoperative VMAT for oral cavity and oropharyngeal cancers are encouraging, with high rates of loco-regional control. However, the management of ENE still seems challenging.

Artificial intelligence in cancer diagnosis and therapy: Current status and future perspective

Artificial intelligence (AI) in healthcare plays a pivotal role in combating many fatal diseases, such as skin, breast, and lung cancer. AI is an advanced form of technology that uses mathematical-based algorithmic principles similar to those of the human mind for cognizing complex challenges of the healthcare unit. Cancer is a lethal disease with many etiologies, including numerous genetic and epigenetic mutations. Cancer being a multifactorial disease is difficult to be diagnosed at an early stage. Therefore, genetic variations and other leading factors could be identified in due time through AI and machine learning (ML). AI is the synergetic approach for mining the drug targets, their mechanism of action, and drug-organism interaction from massive raw data. This synergetic approach is also facing several challenges in data mining but computational algorithms from different scientific communities for multi-target drug discovery are highly helpful to overcome the bottlenecks in AI for drug-target discovery. AI and ML could be the epicenter in the medical world for the diagnosis, treatment, and evaluation of almost any disease in the near future. In this comprehensive review, we explore the immense potential of AI and ML when integrated with the biological sciences, specifically in the context of cancer research. Our goal is to illuminate the many ways in which AI and ML are being applied to the study of cancer, from diagnosis to individualized treatment. We highlight the prospective role of AI in supporting oncologists and other medical professionals in making informed decisions and improving patient outcomes by examining the intersection of AI and cancer control. Although AI-based medical therapies show great potential, many challenges must be overcome before they can be implemented in clinical practice. We critically assess the current hurdles and provide insights into the future directions of AI-driven approaches, aiming to pave the way for enhanced cancer interventions and improved patient care.

Increasing Quality and Efficiency of the Radiotherapy Treatment Planning Process by Constructing and Implementing a Workflow-Monitoring Application

PURPOSE

To demonstrate how the efficiency of the treatment planning processes of a university radiation oncology department (2,500 new patients/year) could be improved by constructing and implementing a workflow-monitoring application.

METHODS

A web-based application was developed in house, which enhanced the process management tools of the clinic's oncology information system. The application calculates the days left for the next task in the treatment planning process and visualizes the information on a browser-based whiteboard. Workflow monitoring considers tumor types (breast, prostate, lung, etc) and treatment techniques and is backward planned from the planned start of treatment. The effect of introducing this application was analyzed over four phases: (1) baseline data without the workflow-monitoring application, (2) after introducing workflow visualization via a browser-based whiteboard, (3) after upgrading the whiteboard and introducing backend rules, and (4) after updating these rules on the basis of data from the previous phase.

RESULTS

Implementing the workflow-monitoring application and the introduced measures significantly reduced delays and, consequently, stress and a negative working atmosphere in the treatment planning process. Most notably, the amount of last-minute physics checks (on the day of the treatment start) could be reduced by 50%.

CONCLUSION

The study showed what measures can help organize and prioritize the treatment planning workflow. The increased efficiency is believed to improve the quality and reduce the risk of human error.

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

Purpose

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

Materials and methods

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

Results

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

Conclusions

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

Deep Learning Architecture to Improve Edge Accuracy of Auto-Contouring for Head and Neck Radiotherapy

Deep learning (DL) methods have shown great promise in auto-segmentation problems. However, for head and neck cancer, we show that DL methods fail at the axial edges of the gross tumor volume (GTV) where the segmentation is dependent on information closer to the center of the tumor. These failures may decrease trust and usage of proposed auto-contouring systems. To increase performance at the axial edges, we propose the spatially adjusted recurrent convolution U-Net (SARC U-Net). Our method uses convolutional recurrent neural networks and spatial transformer networks to push information from salient regions out to the axial edges. On average, our model increased the Sørensen-Dice coefficient (DSC) at the axial edges of the GTV by 11% inferiorly and 19.3% superiorly over a baseline 2D U-Net, which has no inherent way to capture information between adjacent slices. Over all slices, our proposed architecture achieved a DSC of 0.613, whereas a 3D and 2D U-Net achieved a DSC of 0.586 and 0.540, respectively. SARC U-Net can increase accuracy at the axial edges of GTV contours while also increasing accuracy over baseline models, creating a more robust contour.

Benefits of automated gross tumor volume segmentation in head and neck cancer using multi-modality information

PURPOSE

Gross tumor volume (GTV) delineation for head and neck cancer (HNC) radiation therapy planning is time consuming and prone to interobserver variability (IOV). The aim of this study was (1) to develop an automated GTV delineation approach of primary tumor (GTVp) and pathologic lymph nodes (GTVn) based on a 3D convolutional neural network (CNN) exploiting multi-modality imaging input as required in clinical practice, and (2) to validate its accuracy, efficiency and IOV compared to manual delineation in a clinical setting.

METHODS

Two datasets were retrospectively collected from 150 clinical cases. CNNs were trained for GTV delineation with consensus delineation as ground truth, with either single (CT) or co-registered multi-modal (CT + PET or CT + MRI) imaging data as input. For validation, GTVs were delineated on 20 new cases by two observers, once manually, once by correcting the delineations generated by the CNN.

RESULTS

Both multi-modality CNNs performed better than the single-modality CNN and were selected for clinical validation. Mean Dice Similarity Coefficient (DSC) for (GTVp, GTVn) respectively between automated and manual delineations was (69%, 79%) for CT + PET and (59%,71%) for CT + MRI. Mean DSC between automated and corrected delineations was (81%,89%) for CT + PET and (69%,77%) for CT + MRI. Mean DSC between observers was (76%,86%) for manual delineations and (95%,96%) for corrected delineations, indicating a significant decrease in IOV (p < 10^-5), while efficiency increased significantly (48%, p < 10^-5).

CONCLUSION

Multi-modality automated delineation of GTV of HNC was shown to be more efficient and consistent compared to manual delineation in a clinical setting and beneficial over a single-modality approach.

Overview of Artificial Intelligence in Breast Cancer Medical Imaging

The heavy global burden and mortality of breast cancer emphasize the importance of early diagnosis and treatment. Imaging detection is one of the main tools used in clinical practice for screening, diagnosis, and treatment efficacy evaluation, and can visualize changes in tumor size and texture before and after treatment. The overwhelming number of images, which lead to a heavy workload for radiologists and a sluggish reporting period, suggests the need for computer-aid detection techniques and platform. In addition, complex and changeable image features, heterogeneous quality of images, and inconsistent interpretation by different radiologists and medical institutions constitute the primary difficulties in breast cancer screening and imaging diagnosis. The advancement of imaging-based artificial intelligence (AI)-assisted tumor diagnosis is an ideal strategy for improving imaging diagnosis efficient and accuracy. By learning from image data input and constructing algorithm models, AI is able to recognize, segment, and diagnose tumor lesion automatically, showing promising application prospects. Furthermore, the rapid advancement of "omics" promotes a deeper and more comprehensive recognition of the nature of cancer. The fascinating relationship between tumor image and molecular characteristics has attracted attention to the radiomic and radiogenomics, which allow us to perform analysis and detection on the molecular level with no need for invasive operations. In this review, we integrate the current developments in AI-assisted imaging diagnosis and discuss the advances of AI-based breast cancer precise diagnosis from a clinical point of view. Although AI-assisted imaging breast cancer screening and detection is an emerging field and draws much attention, the clinical application of AI in tumor lesion recognition, segmentation, and diagnosis is still limited to research or in limited patients' cohort. Randomized clinical trials based on large and high-quality cohort are lacking. This review aims to describe the progress of the imaging-based AI application in breast cancer screening and diagnosis for clinicians.

Establishing a Point-of-Care Virtual Planning and 3D Printing Program

Virtual surgical planning (VSP) and three-dimensional (3D) printing have become a standard of care at our institution, transforming the surgical care of complex patients. Patient-specific, anatomic models and surgical guides are clinically used to improve multidisciplinary communication, presurgical planning, intraoperative guidance, and the patient informed consent. Recent innovations have allowed both VSP and 3D printing to become more accessible to various sized hospital systems. Insourcing such work has several advantages including quicker turnaround times and increased innovation through collaborative multidisciplinary teams. Centralizing 3D printing programs at the point-of-care provides a greater cost-efficient investment for institutions. The following article will detail capital equipment needs, institutional structure, operational personnel, and other considerations necessary in the establishment of a POC manufacturing program.

Robotic lateral oropharyngectomy following diagnostic tonsillectomy is oncologically safe in patients with human papillomavirus-related squamous cell cancer: Long-term results

INTRODUCTION

To report the long-term oncological and functional outcomes of en bloc TORS lateral oropharyngectomy to address the close/involved margin following diagnostic tonsillectomy in HPV-related SCC of unknown primary.

MATERIAL AND METHODS

A single tertiary center observational cohort over a 4-year period. Primary outcome measures were disease-specific survival (DSS), overall survival (OS), and PSS NOD (Performance Status Scale-Normalcy of Diet) scores.

RESULTS

TORS specimens did not evidence residual carcinoma in 93% of patients. Of 14 patients, 50% received surgery alone (median follow-up 57 months; range 46-96), the remainder surgery and adjuvant therapy (median follow-up of 58 months; range 51-69) with 100% DSS, OS and no deterioration of PSS NOD scores.

CONCLUSIONS

Long-term oncological outcomes confirm TORS lateral oropharyngectomy alone is an oncologically safe treatment. Due consideration of this approach is warranted to mitigate against the morbidity of adjuvant radiotherapy treatment in this group of patients.

Intensity-modulated radiotherapy in locally advanced head-and-neck cancers in elderly patients

Introduction

Head and neck cancer is one of the most common malignancies in Indian males. Due to poor socioeconomic status, presentation is usually in advanced stage. Treatment option is limited to radiotherapy with or without chemotherapy. Intensity-modulated radiotherapy (IMRT) provides highly conformal dose distributions creating nonuniform spatial intensity using different segments in the beam. Concomitant chemoradiation is highly toxic in this age group.

Material and Methods

During 2016-2017, 44 patients with locally advanced head-and-neck cancers were treated with a curative intent with IMRT. They were in the age range of 65-75. The median age was 69 years. Thirty five were male and nine were female. Histopathologically, all had squamous cell carcinoma. Stage wise, all were T3N2 or more. The standard technique of IMRT was used with sparing of organs at risk and defining treatment volumes: gross, clinical, and planning. Patients were assessed after 4 weeks of completion of treatment for response and toxicities.

Results

Response vise, 14 patients achieved complete response, 28 patients had partial response, and 2 had stable disease. There was no treatment-related mortality. Six patients had treatment interruptions due to toxicity. Incidence of mucositis was of Grade 1-2 in all patients. No hematological toxicity was seen. Patients having dysphagia during treatment were given nasogastric feed.

Head and neck radiotherapy quality assurance conference for dedicated review of delineated targets and organs at risk: results of a prospective study

Purpose

Head and neck (HN) radiotherapy (RT) is complex, involving multiple target and organ at risk (OAR) structures delineated by the radiation oncologist. Site-agnostic peer review after RT plan completion is often inadequate for thorough review of these structures. In-depth review of RT contours is critical to maintain high-quality RT and optimal patient outcomes.

Materials and Methods

In August 2020, the HN RT Quality Assurance Conference, a weekly teleconference that included at least one radiation oncology HN specialist, was activated at our institution. Targets and OARs were reviewed in detail prior to RT plan creation. A parallel implementation study recorded patient factors and outcomes of these reviews. A major change was any modification to the high-dose planning target volume (PTV) or the prescription dose/fractionation; a minor change was modification to the intermediate-dose PTV, low-dose PTV, or any OAR. We analysed the results of consecutive RT contour review in the first 20 months since its initiation.

Results

A total of 208 patients treated by 8 providers were reviewed: 86·5% from the primary tertiary care hospital and 13·5% from regional practices. A major change was recommended in 14·4% and implemented in 25 of 30 cases (83·3%). A minor change was recommended in 17·3% and implemented in 32 of 36 cases (88·9%). A survey of participants found that all (n = 11) strongly agreed or agreed that the conference was useful.

Conclusion

Dedicated review of RT targets/OARs with a HN subspecialist is associated with substantial rates of suggested and implemented modifications to the contours.

Delineation uncertainties of tumour volumes on MRI of head and neck cancer patients

•

Role of target delineation uncertainties in head and neck cancer patients.

•

Knowing contouring variations for MRI allows better adaptation of MRLinac for H&N cancers.

•

An interobserver variation for GTV among 8 observers was below 2 mm using MRI.

•

Variability between observers might improve using other imaging modalities.

Background

During the last decade, radiotherapy using MR Linac has gone from research to clinical implementation for different cancer locations. For head and neck cancer (HNC), target delineation based only on MR images is not yet standard, and the utilisation of MRI instead of PET/CT in radiotherapy planning is not well established. We aimed to analyse the inter-observer variation (IOV) in delineating GTV (gross tumour volume) on MR images only for patients with HNC.

Material/methods

32 HNC patients from two independent departments were included. Four clinical oncologists from Denmark and four radiation oncologists from Australia had independently contoured primary tumour GTVs (GTV-T) and nodal GTVs (GTV-N) on T2-weighted MR images obtained at the time of treatment planning. Observers were provided with sets of images, delineation guidelines and patient synopsis. Simultaneous truth and performance level estimation (STAPLE) reference volumes were generated for each structure using all observer contours. The IOV was assessed using the DICE Similarity Coefficient (DSC) and mean absolute surface distance (MASD).

Results

32 GTV-Ts and 68 GTV-Ns were contoured per observer. The median MASD for GTV-Ts and GTV-Ns across all patients was 0.17 cm (range 0.08–0.39 cm) and 0.07 cm (range 0.04–0.33 cm), respectively. Median DSC relative to a STAPLE volume for GTV-Ts and GTV-Ns across all patients were 0.73 and 0.76, respectively. A significant correlation was seen between median DSCs and median volumes of GTV-Ts (Spearman correlation coefficient 0.76, p < 0.001) and of GTV-Ns (Spearman correlation coefficient 0.55, p < 0.001).

Conclusion

Contouring GTVs in patients with HNC on MRI showed that the median IOV for GTV-T and GTV-N was below 2 mm, based on observes from two separate radiation departments. However, there are still specific regions in tumours that are difficult to resolve as either malignant tissue or oedema that potentially could be improved by further training in MR-only delineation.

Clinical evaluation of deep learning-based clinical target volume three-channel auto-segmentation algorithm for adaptive radiotherapy in cervical cancer

Objectives

Accurate contouring of the clinical target volume (CTV) is a key element of radiotherapy in cervical cancer. We validated a novel deep learning (DL)-based auto-segmentation algorithm for CTVs in cervical cancer called the three-channel adaptive auto-segmentation network (TCAS).

Methods

A total of 107 cases were collected and contoured by senior radiation oncologists (ROs). Each case consisted of the following: (1) contrast-enhanced CT scan for positioning, (2) the related CTV, (3) multiple plain CT scans during treatment and (4) the related CTV. After registration between (1) and (3) for the same patient, the aligned image and CTV were generated. Method 1 is rigid registration, method 2 is deformable registration, and the aligned CTV is seen as the result. Method 3 is rigid registration and TCAS, method 4 is deformable registration and TCAS, and the result is generated by a DL-based method.

Results

From the 107 cases, 15 pairs were selected as the test set. The dice similarity coefficient (DSC) of method 1 was 0.8155 ± 0.0368; the DSC of method 2 was 0.8277 ± 0.0315; the DSCs of method 3 and 4 were 0.8914 ± 0.0294 and 0.8921 ± 0.0231, respectively. The mean surface distance and Hausdorff distance of methods 3 and 4 were markedly better than those of method 1 and 2.

Conclusions

The TCAS achieved comparable accuracy to the manual delineation performed by senior ROs and was significantly better than direct registration.

Automatic segmentation of thoracic CT images using three deep learning models

PURPOSE

Deep learning (DL) techniques are widely used in medical imaging and in particular for segmentation. Indeed, manual segmentation of organs at risk (OARs) is time-consuming and suffers from inter- and intra-observer segmentation variability. Image segmentation using DL has given very promising results. In this work, we present and compare the results of segmentation of OARs and a clinical target volume (CTV) in thoracic CT images using three DL models.

MATERIALS AND METHODS

We used CT images of 52 patients with breast cancer from a public dataset. Automatic segmentation of the lungs, the heart and a CTV was performed using three models based on the U-Net architecture. Three metrics were used to quantify and compare the segmentation results obtained with these models: the Dice similarity coefficient (DSC), the Jaccard coefficient (J) and the Hausdorff distance (HD).

RESULTS

The obtained values of DSC, J and HD were presented for each segmented organ and for the three models. Examples of automatic segmentation were presented and compared to the corresponding ground truth delineations. Our values were also compared to recent results obtained by other authors.

CONCLUSION

The performance of three DL models was evaluated for the delineation of the lungs, the heart and a CTV. This study showed clearly that these 2D models based on the U-Net architecture can be used to delineate organs in CT images with a good performance compared to other models. Generally, the three models present similar performances. Using a dataset with more CT images, the three models should give better results.

The Accuracy and Radiomics Feature Effects of Multiple U-net-Based Automatic Segmentation Models for Transvaginal Ultrasound Images of Cervical Cancer

Ultrasound (US) imaging has been recognized and widely used as a screening and diagnostic imaging modality for cervical cancer all over the world. However, few studies have investigated the U-net-based automatic segmentation models for cervical cancer on US images and investigated the effects of automatic segmentations on radiomics features. A total of 1102 transvaginal US images from 796 cervical cancer patients were collected and randomly divided into training (800), validation (100) and test sets (202), respectively, in this study. Four U-net models (U-net, U-net with ResNet, context encoder network (CE-net), and Attention U-net) were adapted to segment the target of cervical cancer automatically on these US images. Radiomics features were extracted and evaluated from both manually and automatically segmented area. The mean Dice similarity coefficient (DSC) of U-net, Attention U-net, CE-net, and U-net with ResNet were 0.88, 0.89, 0.88, and 0.90, respectively. The average Pearson coefficients for the evaluation of the reliability of US image-based radiomics were 0.94, 0.96, 0.94, and 0.95 for U-net, U-net with ResNet, Attention U-net, and CE-net, respectively, in their comparison with manual segmentation. The reproducibility of the radiomics parameters evaluated by intraclass correlation coefficients (ICC) showed robustness of automatic segmentation with an average ICC coefficient of 0.99. In conclusion, high accuracy of U-net-based automatic segmentations was achieved in delineating the target area of cervical cancer US images. It is feasible and reliable for further radiomics studies with features extracted from automatic segmented target areas.

Comprehensive Quantitative Evaluation of Variability in MR-guided Delineation of Oropharyngeal Gross Tumor Volumes and High-risk Clinical Target Volumes: An R-IDEAL Stage 0 Prospective Study

PURPOSE

Tumor and target volume manual delineation remains a challenging task in head-and-neck cancer radiotherapy. The purpose of this study was to conduct a multi-institutional evaluation of manual delineations of gross tumor volume (GTV), high-risk clinical target volume (CTV), parotids, and submandibular glands on treatment simulation MR scans of oropharyngeal cancer (OPC) patients.

METHODS

Pre-treatment T1-weighted (T1w), T1-weighted with gadolinium contrast (T1w+C) and T2-weighted (T2w) MRI scans were retrospectively collected for 4 OPC patients under an IRB-approved protocol. The scans were provided to twenty-six radiation oncologists from seven international cancer centers who participated in this delineation study. In addition, patients' clinical history and physical examination findings, along with a medical photographic image and radiological results, were provided. The contours were compared using overlap/distance metrics using both STAPLE and pair-wise comparisons. Lastly, participants completed a brief questionnaire to assess participants' experience and CTV delineation institutional practices.

RESULTS

Large variability was measured between observers' delineations for GTVs and CTVs. The mean Dice Similarity Coefficient values across all physicians' delineations for GTVp, GTVn, CTVp, and CTVn were 0.77, 0.67, 0.77, and 0.69, respectively, for STAPLE comparison and 0.67, 0.60, 0.67, and 0.58, respectively, for pair-wise analysis. Normal tissue contours were defined more consistently when considering overlap/distance metrics. The median radiation oncology clinical experience was 7 years. The median experience delineating on MRI was 3.5 years. The GTV-to-CTV margin used was 10 mm for six of seven participant institutions. One institution used 8 mm and three participants (from three different institutions) used a margin of 5 mm.

CONCLUSION

The data from this study suggests that appropriate guidelines, contouring quality assurance sessions, and training are still needed for the adoption of MR-based treatment planning for head-and-neck cancers. Such efforts should play a critical role in reducing delineation variation and ensure standardization of target design across clinical practices.

Deep learning-based auto-segmentation of clinical target volumes for radiotherapy treatment of cervical cancer

Objectives

Because radiotherapy is indispensible for treating cervical cancer, it is critical to accurately and efficiently delineate the radiation targets. We evaluated a deep learning (DL)‐based auto‐segmentation algorithm for automatic contouring of clinical target volumes (CTVs) in cervical cancers.

Methods

Computed tomography (CT) datasets from 535 cervical cancers treated with definitive or postoperative radiotherapy were collected. A DL tool based on VB‐Net was developed to delineate CTVs of the pelvic lymph drainage area (dCTV1) and parametrial area (dCTV2) in the definitive radiotherapy group. The training/validation/test number is 157/20/23. CTV of the pelvic lymph drainage area (pCTV1) was delineated in the postoperative radiotherapy group. The training/validation/test number is 272/30/33. Dice similarity coefficient (DSC), mean surface distance (MSD), and Hausdorff distance (HD) were used to evaluate the contouring accuracy. Contouring times were recorded for efficiency comparison.

Results

The mean DSC, MSD, and HD values for our DL‐based tool were 0.88/1.32 mm/21.60 mm for dCTV1, 0.70/2.42 mm/22.44 mm for dCTV2, and 0.86/1.15 mm/20.78 mm for pCTV1. Only minor modifications were needed for 63.5% of auto‐segmentations to meet the clinical requirements. The contouring accuracy of the DL‐based tool was comparable to that of senior radiation oncologists and was superior to that of junior/intermediate radiation oncologists. Additionally, DL assistance improved the performance of junior radiation oncologists for dCTV2 and pCTV1 contouring (mean DSC increases: 0.20 for dCTV2, 0.03 for pCTV1; mean contouring time decrease: 9.8 min for dCTV2, 28.9 min for pCTV1).

Conclusions

DL‐based auto‐segmentation improves CTV contouring accuracy, reduces contouring time, and improves clinical efficiency for treating cervical cancer.

Application of deep learning to auto-delineation of target volumes and organs at risk in radiotherapy

The technological advancement heralded the arrival of precision radiotherapy (RT), thereby increasing the therapeutic ratio and decreasing the side effects from treatment. Contour of target volumes (TV) and organs at risk (OARs) in RT is a complicated process. In recent years, automatic contouring of TV and OARs has rapidly developed due to the advances in deep learning (DL). This technology has the potential to save time and to reduce intra- or inter-observer variability. In this paper, the authors provide an overview of RT, introduce the concept of DL, summarize the data characteristics of the included literature, summarize the possible challenges for DL in the future, and discuss the possible research directions.

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

PURPOSE

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

METHODS

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

RESULTS

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

CONCLUSIONS

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

Recurrence Patterns After IMRT/VMAT in Head and Neck Cancer

Purpose

Intensity-modulated radiotherapy (IMRT) and volumetric modulated arc therapy (VMAT), two advanced modes of high-precision radiotherapy (RT), have become standard of care in the treatment of head and neck cancer. The development in RT techniques has markedly increased the complexity of target volume definition and accurate treatment delivery. The aim of this study was to indirectly investigate the quality of current TV delineation and RT delivery by analyzing the patterns of treatment failure for head and neck cancer patients in our high-volume RT center.

Methods

Between 2004 and 2014, 385 patients with pharyngeal, laryngeal, and oral cavity tumors were curatively treated with primary RT (IMRT/VMAT). We retrospectively investigated locoregional recurrences (LRR), distant metastases (DM), and overall survival (OS).

Results

Median follow-up was 6.4 years (IQR 4.7–8.3 years) during which time 122 patients (31.7%) developed LRR (22.1%) and DM (17.7%). The estimated 2- and 5-year locoregional control was 78.2% (95% CI 73.3, 82.3) and 74.2% (95% CI 69.0, 78.8). One patient developed a local recurrence outside the high-dose volume and five patients developed a regional recurrence outside the high-dose volume. Four patients (1.0%) suffered a recurrence in the electively irradiated neck and two patients had a recurrence outside the electively irradiated neck. No marginal failures were observed. The estimated 2- and 5-year DM-free survival rates were 83.3% (95% CI 78.9, 86.9) and 80.0% (95% CI 75.2, 84.0). The estimated 2- and 5-year OS rates were 73.6% (95% CI 68.9, 77.8) and 52. 6% (95% CI 47.3, 57.6). Median OS was 5.5 years (95% CI 4.5, 6.7).

Conclusion

Target volume definition and treatment delivery were performed accurately, as only few recurrences occurred outside the high-dose regions and no marginal failures were observed. Research on dose intensification and identification of high-risk subvolumes might decrease the risk of locoregional relapses. The results of this study may serve as reference data for comparison with future studies, such as dose escalation or proton therapy trials.

Manufacturing and evaluation of a multi-purpose Iranian head and neck anthropomorphic phantom called MIHAN

A new multi-purpose Iranian head and neck (MIHAN) anthropomorphic phantom was designed and manufactured to be used in diagnostic and therapeutic applications. Geometry of MIHAN phantom was determined based on the average dimensions acquired by CT scans of twenty patients without any medical problems in their head and neck site. Because the phantom was expected to be used with different modalities with a wide range of photon energies, attenuation coefficients of some selected materials were determined using Monte Carlo simulation. Based on analytical and simulation results, acrylonitrile butadiene styrene (ABS) and polylactic acid (PLA) were found suitable choices for soft and bony tissues, respectively. They were used in the 3D printer to build the phantom. The suitability of the materials was checked by CT number value comparison between the organs included in the phantom and the corresponding body tissues and also film dosimetry of a typical intensity-modulated radiation therapy (IMRT) plan.. Hounsfield Unit agreement and 95% ± 2% pass rate for the IMRT plan verification proved the suitability of material selection. Also, the film dosimetry showed feasibility of using MIHAN in radiotherapy plan verification workflow. In addition, PLA was introduced as a spongy bone tissue substitute for the first time.

Effects of sample size and data augmentation on U-Net-based automatic segmentation of various organs

Deep learning has demonstrated high efficacy for automatic segmentation in contour delineation, which is crucial in radiation therapy planning. However, the collection, labeling, and management of medical imaging data can be challenging. This study aims to elucidate the effects of sample size and data augmentation on the automatic segmentation of computed tomography images using U-Net, a deep learning method. For the chest and pelvic regions, 232 and 556 cases are evaluated, respectively. We investigate multiple conditions by changing the sum of the training and validation datasets across a broad range of values: 10-200 and 10-500 cases for the chest and pelvic regions, respectively. A U-Net is constructed, and horizontal-flip data augmentation, which produces left and right inverse images resulting in twice the number of images, is compared with no augmentation for each training session. All lung cases and more than 100 prostate, bladder, and rectum cases indicate that adding horizontal-flip data augmentation is almost as effective as doubling the number of cases. The slope of the Dice similarity coefficient (DSC) in all organs decreases rapidly until approximately 100 cases, stabilizes after 200 cases, and shows minimal changes as the number of cases is increased further. The DSCs stabilize at a smaller sample size with the incorporation of data augmentation in all organs except the heart. This finding is applicable to the automation of radiation therapy for rare cancers, where large datasets may be difficult to obtain.

Standardization for oncologic head and neck surgery

The inherent variability in performing specific surgical procedures for head and neck cancer remains a barrier for accurately assessing treatment outcomes, particularly in clinical trials. While non-surgical modalities for cancer therapeutics have evolved to become far more uniform, there remains the challenge to standardize surgery. The purpose of this review is to identify the barriers in achieving uniformity and to highlight efforts by surgical groups to standardize selected operations and nomenclature. While further improvements in standardization will remain a challenge, we must encourage surgical groups to focus on strategies that provide such a level.

A deep learning-based auto-segmentation system for organs-at-risk on whole-body computed tomography images for radiation therapy

BACKGROUND AND PURPOSE

Delineating organs at risk (OARs) on computed tomography (CT) images is an essential step in radiation therapy; however, it is notoriously time-consuming and prone to inter-observer variation. Herein, we report a deep learning-based automatic segmentation (AS) algorithm (WBNet) that can accurately and efficiently delineate all major OARs in the entire body directly on CT scans.

MATERIALS AND METHODS

We collected 755 CT scans of the head and neck, thorax, abdomen, and pelvis and manually delineated 50 OARs on the CT images. The CT images with contours were split into training and test sets consisting of 505 and 250 cases, respectively, to develop and validate WBNet. The volumetric Dice similarity coefficient (DSC) and 95th-percentile Hausdorff distance (95% HD) were calculated to evaluate delineation quality for each OAR. We compared the performance of WBNet with three AS algorithms: one commercial multi-atlas-based automatic segmentation (ABAS) software, and two deep learning-based AS algorithms, namely, AnatomyNet and nnU-Net. We have also evaluated the time saving and dose accuracy of WBNet.

RESULTS

WBNet achieved average DSCs of 0.84 and 0.81 on in-house and public datasets, respectively, which outperformed ABAS, AnatomyNet, and nnU-Net. WBNet could reduce the delineation time significantly and perform well in treatment planning, with clinically acceptable dose differences compared with those in manual delineation.

CONCLUSION

This study shows the feasibility and benefits of using WBNet in clinical practice.

Artificial intelligence in rectal cancer

Accurate and rapid diagnosis is essential for correct treatment in rectal cancer. Determining the optimal treatment plan for a patient with rectal cancer is a complex process, and the oncological results and toxicity are not the same in every patient with the same treatment at the same stage. In recent years, the increasing interest in artificial intelligence in all fields of science has also led to the development of innovative tools in oncology. Artificial intelligence studies have increased in many steps from diagnosis to follow-up in rectal cancer. It is thought that artificial intelligence will provide convenience in many ways from personalized treatment to reducing the workload of the physician. Prediction algorithms can be standardized by sharing data between centers, diversifying data, and creating big data.

Evolving target volume concepts in locally advanced non-small cell lung cancer

Radiotherapy (RT) target volume concepts for locally advanced lung cancer have been under discussion for years. Although they may be as important as treatment doses, many aspects of them are still based on conventions, which, due to the paucity of prospective data, rely on long-term practice or on clinical knowledge and experience (e.g., on patterns of spread or recurrence). However, in recent years, large improvements have been made in medical imaging and molecular imaging methods have been implemented, which are of great interest in RT. For lung cancer, in recent years, 18F-fluoro-desoxy-glucose (FDG)-positron-emission tomography (PET)/computed tomography (CT) has shown a superior diagnostic accuracy as compare to conventional imaging and has become an indispensable standard tool for diagnostic workup, staging and response assessment. This offers the chance to optimize target volume concepts in relation to modern imaging. While actual recommendations as the EORTC or ESTRO-ACROP guidelines already include imaging standards, the recently published PET-Plan trial prospectively investigated conventional versus imaging guided target volumes in relation to patient outcome. The results of this trial may help to further refine standards. The current review gives a practical overview on procedures for pre-treatment imaging and target volume delineation in locally advanced non-small cell lung cancer (NSCLC) in synopsis of the procedures established by the PET-Plan trial with the actual EORTC and ACROP guidelines.

Training deep-learning segmentation models from severely limited data

PURPOSE

To enable generation of high-quality deep learning segmentation models from severely limited contoured cases (e.g., ~10 cases).

METHODS

Thirty head and neck computed tomography (CT) scans with well-defined contours were deformably registered to 200 CT scans of the same anatomic site without contours. Acquired deformation vector fields were used to train a principal component analysis (PCA) model for each of the 30 contoured CT scans by capturing the mean deformation and most prominent variations. Each PCA model can produce an infinite number of synthetic CT scans and corresponding contours by applying random deformations. We used 300, 600, 1000, and 2000 synthetic CT scans and contours generated from one PCA model to train V-Net, a 3D convolutional neural network architecture, to segment parotid and submandibular glands. We repeated the training using same numbers of training cases generated from 7, 10, 20, and 30 PCA models, with the data distributed evenly between each PCA model. Performance of the segmentation models was evaluated with Dice similarity coefficients between auto-generated contours and physician-drawn contours on 162 test CT scans for parotid glands and another 21 test CT scans for submandibular glands.

RESULTS

Dice values varied with the number of synthetic CT scans and the number of PCA models used to train the network. By using 2000 synthetic CT scans generated from 10 PCA models, we achieved Dice values of 82.8% ± 6.8% for right parotid, 82.0% ± 6.9% for left parotid, and 74.2% ± 6.8% for submandibular glands. These results are comparable with those obtained from state-of-the-art auto-contouring approaches, including a deep learning network trained from more than 1000 contoured patients and a multi-atlas algorithm from 12 well-contoured atlases. Improvement was marginal when >10 PCA models or >2000 synthetic CT scans were used.

CONCLUSIONS

We demonstrated an effective data augmentation approach to train high-quality deep learning segmentation models from a limited number of well-contoured patient cases.

Fully convolutional network-based multi-output model for automatic segmentation of organs at risk in thorax

PURPOSE

To propose a multi-output fully convolutional network (MOFCN) to segment bilateral lung, heart and spinal cord in the planning thoracic computed tomography (CT) slices automatically and simultaneously.

METHODS

The MOFCN includes two components: one main backbone and three branches. The main backbone extracts the features about lung, heart and spinal cord. The extracted features are transferred to three branches which correspond to three organs respectively. The longest branch to segment spinal cord is nine layers, including input and output layers. The MOFCN was evaluated on 19,277 CT slices from 966 patients with cancer in the thorax. In these slices, the organs at risk (OARs) were delineated and validated by experienced radiation oncologists, and served as ground truth for training and evaluation. The data from 61 randomly chosen patients were used for training and validation. The remaining 905 patients' slices were used for testing. The metric used to evaluate the similarity between the auto-segmented organs and their ground truth was Dice. Besides, we compared the MOFCN with other published models. To assess the distinct output design and the impact of layer number and dilated convolution, we compared MOFCN with a multi-label learning model and its variants. By analyzing the not good performances, we suggested possible solutions.

RESULTS

MOFCN achieved Dice of 0.95 ± 0.02 for lung, 0.91 ± 0.03 for heart and 0.87 ± 0.06 for spinal cord. Compared to other models, MOFCN could achieve a comparable accuracy with the least time cost.

CONCLUSION

The results demonstrated the MOFCN's effectiveness. It uses less parameters to delineate three OARs simultaneously and automatically, and thus shows a relatively low requirement for hardware and has potential for broad application.

68Ga-DOTATOC PET/CT Follow Up after Single or Hypofractionated Gamma Knife ICON Radiosurgery for Meningioma Patients

⁶⁸Ga-DOTATOC represents a useful tool in tumor contouring for radiosurgery planning. We present a case series of patients affected by meningiomas on who we performed ⁶⁸Ga-DOTATOC positron emission tomography (PET)/CT pre-operatively, a subgroup of which also underwent a post-operative ⁶⁸Ga-DOTATOC PET/CT to evaluate the standardized uptake value (SUV) modification after Gamma Knife ICON treatment in single or hypofractionated fractions. Twenty patients were enrolled/included in this study: ten females and ten males. The median age was 52 years (range 33-80). The median tumor diameter was 3.68 cm (range 0.12-22.26 cm), and the median pre-radiotherapy maximum SUV value was 11 (range 2.3-92). The average of the relative percentage changes between SUVs at baseline and follow up was -6%, ranging from -41% to 56%. The SUV was reduced in seven out of 12 patients (58%), stable in two out of 12 (17%), and increased in three out of 12 (25%), suggesting a biological response of the tumor to the Gamma Knife treatment in most of the cases. ⁶⁸Ga-DOTATOC-PET represents a valuable tool in assessing the meningioma diagnosis for primary radiosurgery; it is also promising for follow-up assessment.

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.

Probabilistic definition of the clinical target volume-implications for tumor control probability modeling and optimization

Evidence has been presented that moving beyond the binary definition of clinical target volume (CTV) towards a probabilistic CTV can result in better treatment plans. The probabilistic CTV takes the likelihood of disease spread outside of the gross tumor into account. An open question is: how to optimize tumor control probability (TCP) based on the probabilistic CTV. We derive expressions for TCP under the assumptions of voxel independence and dependence. For the dependent case, we make the assumption that tumors grow outward from the gross tumor volume. We maximize the (non-convex) TCP under convex dose constraints for all models. For small numbers of voxels, and when a dose-influence matrix is not used, we use exhaustive search or Lagrange multiplier theory to compute optimal dose distributions. For larger cases we present (1) a multi-start strategy using linear programming with a random cost vector to provide random feasible starting solutions, followed by a local search, and (2) a heuristic strategy that greedily selects which subvolumes to dose, and then for each subvolume assignment runs a convex approximation of the optimization problem. The optimal dose distributions are in general different for the independent and dependent models even though the probabilities of each voxel being tumorous are set to the same in both cases. We observe phase transitions, where a subvolume is either dosed to a high level, or it gets 'sacrificed' by not dosing it at all. The greedy strategy often yields solutions indistinguishable from the multi-start solutions, but for the 2D case involving organs-at-risk and the dependent TCP model, discrepancies of around 5% (absolute) for TCP are observed. For realistic geometries, although correlated voxels is a more reasonable assumption, the correlation function is in general unknown. We demonstrate a tractable heuristic that works very well for the independent models and reasonably well for the dependent models. All data are provided.

Using Auto-Segmentation to Reduce Contouring and Dose Inconsistency in Clinical Trials: The Simulated Impact on RTOG 0617

PURPOSE

Contouring inconsistencies are known but understudied in clinical radiation therapy trials. We applied auto-contouring to the Radiation Therapy Oncology Group (RTOG) 0617 dose escalation trial data. We hypothesized that the trial heart doses were higher than reported due to inconsistent and insufficient heart segmentation. We tested our hypothesis by comparing doses between deep-learning (DL) segmented hearts and trial hearts.

METHODS AND MATERIALS

The RTOG 0617 data were downloaded from The Cancer Imaging Archive; the 442 patients with trial hearts and dose distributions were included. All hearts were resegmented using our DL pipeline and quality assured to meet the requirements for clinical implementation. Dose (V5%, V30%, and mean heart dose) was compared between the 2 sets of hearts (Wilcoxon signed-rank test). Each dose metric was associated with overall survival (Cox proportional hazards). Lastly, 18 volume similarity metrics were assessed for the hearts and correlated with |Dose_DL - Dose_RTOG0617| (linear regression; significance: P ≤ .0028; corrected for 18 tests).

RESULTS

Dose metrics were significantly higher for DL hearts compared with trial hearts (eg, mean heart dose: 15 Gy vs 12 Gy; P = 5.8E-16). All 3 DL heart dose metrics were stronger overall survival predictors than those of the trial hearts (median, P = 2.8E-5 vs 2.0E-4). Thirteen similarity metrics explained |Dose_DL - Dose_RTOG0617|; the axial distance between the 2 centers of mass was the strongest predictor (CENT_Axial; median, R² = 0.47; P = 6.1E-62). CENT_Axial agreed with the qualitatively identified inconsistencies in the superior direction. The trial's qualitative heart contouring score was not correlated with |Dose_DL - Dose_RTOG0617| (median, R² = 0.01; P = .02) or with any of the similarity metrics (median, Rs = 0.13 [range, -0.22 to 0.31]).

CONCLUSIONS

Using a coherent heart definition, as enabled through our open-source DL algorithm, the trial heart doses in RTOG 0617 were found to be significantly higher than previously reported, which may have led to an even more rapid mortality accumulation. Auto-segmentation is likely to reduce contouring and dose inconsistencies and increase the quality of clinical RT trials.

The effect of designing a rotational planning target volume on sparing pharyngeal constrictor muscles in patients with oropharyngeal cancer

BACKGROUND

Planning target volume (PTV) has been used to account for variations in tissue, patient and beam position. In oropharyngeal cancers, an isotropic expanded PTV has been used.

AIM

The aim of this study was to design a new margin formula that would cover the space occupied by an oropharyngeal clinical target volume (CTV) with ±5-degree rotation around the spine in order to reduce the pharyngeal constrictors overlap with PTV compared to an isotropic expanded PTV.

METHODS

We retrospectively evaluated 20 volumetric-modulated arc therapy (VMAT) plans. In order to perform an off-axis rotation, a hypothetical point was placed through the center of the cervical spinal canal and the image was then rotated around the longitudinal axis ±5 degrees. This created a new set of CTVs that were combined to form the new rotational PTV. The overlap between the pharyngeal constrictor muscles (PCMs) and both PTVs was then evaluated.

RESULTS

The new rotational PTV causes reduction in the superior PCM overlap in the base of tongue (BOT) lesions compared to tonsillar lesion, 57.8% vs 25.8%, P = 0.01, as well as middle PCM overlap, 73% vs 49%, P = 0.04. Average percent change for PTV volume and overlap with the superior, middle, and inferior PCMs are as followed: -19%, -37%, -59.4%, and -45.2. The smallest isotropic expansion that covers the new rotational PTV was between 3 and 5mm with the average tumor center shift of 0.49 cm.

CONCLUSION

This new rotational PTV causes significant reduction of the overlap volume between PCMs and PTVs in order to spare the PCMs compared to isotropic expanded PTV.

Generating High-Quality Lymph Node Clinical Target Volumes for Head and Neck Cancer Radiation Therapy Using a Fully Automated Deep Learning-Based Approach

PURPOSE

To develop a deep learning model that generates consistent, high-quality lymph node clinical target volumes (CTV) contours for head and neck cancer (HNC) patients, as an integral part of a fully automated radiation treatment planning workflow.

METHODS AND MATERIALS

Computed tomography (CT) scans from 71 HNC patients were retrospectively collected and split into training (n = 51), cross-validation (n = 10), and test (n = 10) data sets. All had target volume delineations covering lymph node levels Ia through V (Ia-V), Ib through V (Ib-V), II through IV (II-IV), and retropharyngeal (RP) nodes, which were previously approved by a radiation oncologist specializing in HNC. Volumes of interest (VOIs) about nodal levels were automatically identified using computer vision techniques. The VOI (cropped CT image) and approved contours were used to train a U-Net autosegmentation model. Each lymph node level was trained independently, with model parameters optimized by assessing performance on the cross-validation data set. Once optimal model parameters were identified, overlap and distance metrics were calculated between ground truth and autosegmentations on the test set. Lastly, this final model was used on 32 additional patient scans (not included in original 71 cases) and autosegmentations visually rated by 3 radiation oncologists as being "clinically acceptable without requiring edits," "requiring minor edits," or "requiring major edits."

RESULTS

When comparing ground truths to autosegmentations on the test data set, median Dice Similarity Coefficients were 0.90, 0.90, 0.89, and 0.81, and median mean surface distance values were 1.0 mm, 1.0 mm, 1.1 mm, and 1.3 mm for node levels Ia-V, Ib-V, II-IV, and RP nodes, respectively. Qualitative scoring varied among physicians. Overall, 99% of autosegmented target volumes were either scored as being clinically acceptable or requiring minor edits (ie, stylistic recommendations, <2 minutes).

CONCLUSIONS

We developed a fully automated artificial intelligence approach to autodelineate nodal CTVs for patients with intact HNC. Most autosegmentations were found to be clinically acceptable after qualitative review when considering recommended stylistic edits. This promising work automatically delineates nodal CTVs in a robust and consistent manner; this approach can be implemented in ongoing efforts for fully automated radiation treatment planning.

Technical note: Atlas-based Auto-segmentation of masticatory muscles for head and neck cancer radiotherapy

PURPOSE

The study aimed to use quantitative geometric and dosimetric metrics to assess the accuracy of atlas-based auto-segmentation of masticatory muscles (MMs) compared to manual drawn contours for head and neck cancer (HNC) radiotherapy (RT).

MATERIALS AND METHODS

Fifty-eight patients with HNC treated with RT were analyzed. Paired MMs (masseter, temporalis, and medial and lateral pterygoids) were manually delineated on planning computed tomography (CT) images for all patients. Twenty-nine patients were used to generate the MM atlas. Using this atlas, automatic segmentation of the MMs was performed for the remaining 29 patients without manual correction. Auto-segmentation accuracy for MMs was compared using dice similarity coefficients (DSCs), Hausdorff distance (HD), HD95, and variation in the center of mass (∆COM). The dosimetric impact on MMs was calculated (∆dose) using dosimetric parameters (D99%, D95%, D50%, and D1%), and compared with the geometric indices to test correlation.

RESULTS

DSC_mean ranges from 0.79 ± 0.04 to 0.85 ± 0.04, HD_mean from 0.43 ± 0.08 to 0.82 ± 0.26 cm, HD95_mean from 0.32 ± 0.08 to 0.42 ± 0.16 cm, and ∆COM_mean from 0.18 ± 0.11 to 0.33 ± 0.23 cm. The mean MM volume difference was < 15%. The correlation coefficient (r) of geometric and dosimetric indices for the four MMs ranges between -0.456 and 0.300.

CONCLUSIONS

Atlas-based auto-segmentation for masticatory muscles provides geometrically accurate contours compared to manual drawn contours. Dose obtained from those auto-segmented contours is comparable to that from manual drawn contours. Atlas-based auto-segmentation strategy for MM in HN radiotherapy is readily availalbe for clinical implementation.

Factors Associated With the Choice of Radiation Therapy Treatment Facility in Head and Neck Cancer

OBJECTIVE

To analyze the clinicodemographic characteristics and treatment outcomes of patients receiving postoperative radiation therapy (PORT) at a different treatment facility rather than the initial surgical facility for head and neck cancer.

STUDY DESIGN

Retrospective cohort analysis.

METHODS

Utilizing the National Cancer Data Base, 2004 to 2015, patients with a diagnosis of oral cavity/oropharyngeal, hypopharyngeal, and laryngeal squamous cell carcinoma were studied. Multivariate analysis was completed with multivariate regression and Cox proportional hazard model, and survival outcomes were examined using Kaplan-Meier analysis.

RESULTS

A total of 15,181 patients who had surgery for a head and neck cancer at an academic/research center were included in the study population. Of the study population, 4,890 (32.2%) patients completed PORT at a different treatment facility. Treatment at a different facility was more common among patients who were ≥65 years old, white, Medicare recipients, those with a greater distance between residence and surgical treatment facility, and with lower income within area of residence (each P < .05). Overall survival was worse in patients completing PORT at a different treatment facility versus at the institution where surgery was completed (61.9% vs. 66.4%; P = .002).

CONCLUSIONS

PORT at a different facility was more common in older individuals, Medicare recipients, those with greater distance to travel, and lower-income individuals. Completing PORT outside the hospital where surgery was performed was associated with inferior survival outcomes among head and neck cancer patients.

LEVEL OF EVIDENCE

3 Laryngoscope, 131:1019-1025, 2021.