Search

Total package time, or the time from diagnosis to completion of definitive treatment, has been associated with outcomes for a variety of tumor sites, but especially to head and neck (HN) cancer. Patients with HN cancer often undergo a complex diagnosis and treatment process involving multiple disciplines both within and outside of oncology. This complexity can lead to longer package times, and each involved discipline has the responsibility to maintain an efficient and effective process. Strategic intervention to improve package time must involve not only new technology or tools, but also "soft" components such as accountability, motivation, and leadership. This combination is necessary to truly optimize radiation therapy for HN cancer, leading to shorter total package times for these patients.Two interventions were strategically executed to improve radiation therapy workflow: upgrade of the treatment planning system and implementation of an automated patient management and accountability system. The radiation therapy-related timelines of 112 patients with HN cancer treated over 2 years were reviewed, and the average time differences were compared between the patient populations before and after the strategic interventions.Purely upgrading the treatment planning system did not show significant improvements, but when combined with the patient management system, significant improvement in radiation-related package time can be noted for every time point. The overall reduction of radiation-related package time was statistically significant at 22.85 days (On face value, the patient management system could be credited as responsible for the improvement, but on qualitative analysis, it is noted that the new system is only a tool that can be ignored or underused. Owing to the addition of important "soft" components such as accountability, motivation, and leadership, the patient management system was optimized and implemented in such a manner as to have the desired effect.

Introduction Stereotactic body radiation therapy (SBRT) is an effective treatment for early-stage non-small cell lung cancer (NSCLC) patients who are either medically inoperable or who decline surgery. SBRT improves tumor control and overall survival (OS) in medically inoperable, early-stage, NSCLC patients. In this study, we investigated the effectiveness of two different SBRT doses commonly used and present our institutional experience. Purpose To determine the clinical outcomes between two treatment regiments (50 Gray [Gy] vs. 55 Gy in five fractions) among Stage I NSCLC patients treated with SBRT at a state academic medical center. Methods We performed a retrospective analysis of 114 patients with Stage I (T1-2 N0 M0) NSCLC treated at a state academic medical center between October 2009 and April 2019. Survival analyses with treatment regimens of 50 Gy and 55 Gy in five fractions were conducted to detect any improvement in outcomes associated with the higher dose. The primary endpoints of this study included OS, local control (LC), and disease-free survival (DFS). Log-rank test and the Kaplan-Meier method were used to analyze the survival curves of the two treatment doses. The SPSS v.24.0 (IBM Corp., Armonk, NY, USA) was used for statistical analyses. Results The 114 early-stage NSCLC patients (median age, 68 years; range 12 to 87 years) had a median follow-up of 25 months (range two to 86 months). The number of males (n = 72; 63.2 %) exceeded the number of females (n = 42; 36.8 %). The majority of patients in this study were Caucasians (n = 68; 59.6 %) and 46 patients were African Americans (40.4 %). Two-thirds of the patients (n = 76; 66.7 %) were treated with 50 Gy in five fractions, and 38 patients (33.3 %) with 55 Gy in five fractions. The one-, two-, and three-year OS and DFS rates were improved in the patients treated with 55 Gy [OS, 81.7 % vs. 72.8 %; 81.7 % vs. 58.9 %; 81.7 % vs. 46.7 % (p = 0.049)], [DFS, 69.7 % vs. 69.7 %; 61.9 % vs. 55.7 %; 61.9 % vs. 52.0 % (p = 0.842)], compared to those treated with 50 Gy. Adenocarcinoma was the most common histology in both groups (51.3 % and 68.4 %). Failure rates were elevated for the 50 Gy regimen [39 (34.2 %) vs. 12 (8.5 %)]. Three year control rates were (66.3 % vs. 96.6 %; p = 0.002) local control; (63.3 % vs. 94.4 %; p = 0.000) regional control; and (65.7 % vs. 97.1 %; p = 0.000) distant control, compared to those treated with 55 Gy. Conclusion Early-stage NSCLC patients treated with SBRT 55 Gy in five fractions did better in terms of local control, overall survival, and disease-free survival rates compared to the 50 Gy in five fractions group.

Cervical cancer remains a major health challenge in the United States (US), especially among the low socioeconomic and African American populations. The demographics of Mississippi constitute a relatively high percentage of this high-risk population. External beam radiation therapy (EBRT) combined with concurrent chemotherapy and followed by brachytherapy is the gold standard of treatment for stage IB3 through IVA cervical cancer. Arguably, brachytherapy is the most important component of this treatment process. Patterns of Care studies (PCS) and other more recent studies have shown that brachytherapy cannot be omitted or replaced by conventional or image-guided EBRT. The last decade has witnessed the expanding use of image-guided brachytherapy (IGBT). Studies have established the superiority of IGBT over point-based brachytherapy. MRI is associated with superior soft tissue definition compared with CT and is emerging as the new standard of care. The Gynaecological Groupe Europeen de Curietherapie and the European Society for Radiotherapy and Oncology [(GYN) GEC-ESTRO] have recommended that the dose be prescribed to the high-risk clinical target volume (HR-CTV). This volume includes residual tumor present at the time of brachytherapy, the cervix, and any gray areas seen on the scan. The (GYN) GEC-ESTRO has shown that a dose of >8500 cGy delivered in

Background Peer review systems within radiation oncology are important to ensure quality radiation care. Several individualized methods for radiation oncology peer review have been described. However, despite the importance of peer review in radiation oncology barriers may exist to its effective implementation in practice. The purpose of this study was to quantify the rate of plan changes based on our group peer review process as well as the quantify amount of time and resources needed for this process. Methods Data on cases presented in our institutional group consensus peer review conference were prospectively collected. Cases were then retrospectively analyzed to determine the rate of major change (plan rejection) and any change in plans after presentation as well as the median time of presentation. Univariable logistic regression was used to determine factors associated with major change and any change. Results There were 73 cases reviewed over a period of 11 weeks. The rate of major change was 8.2% and the rate of any change was 23.3%. The majority of plans (53.4%) were presented in 6–10 min. Overall, the mean time of presentation was 8 min. On univariable logistic regression, volumetric modulated arc therapy plans were less likely to undergo a plan change but otherwise there were no factors significantly associated with major plan change or any type of change. Conclusion Group consensus peer review allows for a large amount of informative clinical and technical data to be presented per case prior to the initiation of radiation treatment in a thorough yet efficient manner to ensure plan quality and patient safety.

Purpose/Objective(s) The extracapsular extension (ECE) is a strong predictor of patients' survival outcomes with head and neck squamous cell carcinoma (HNSCC). ECE occurs when metastatic tumor cells within the lymph node break through the nodal capsule into surrounding tissues. It is crucial to identify the occurrence of ECE as it changes staging and management for the patients. Current clinical ECE detection relying on radiologists' visual identification is extremely labor-intensive, time-consuming, and error-prone, and consequently, pathologic confirmation is required. Therefore, we aim to perform ECE identification automatically using a deep learning-based technique to analyze the presence or absence of ECE and correlate that with gold standard histopathological findings. Materials/Methods This research proposes a novel deep learning method to detect ECE from 3D computed tomography (CT) scans. The proposed network has multi-scale input that captures both local and global information. The two types of inputs are fitted into two pathways with deep convolutional neural networks (DCNNs), 3D CNN baseline and 3D DenseNet. A sliding-cube approach is applied to extract small paired 3D patches from patient data with different scales at data preparation. The network will classify the patient based on patch-level classification results. Different training scenarios are designed for the experimental test. Results Based on five-fold cross-validation, the experimental results have demonstrated that our model can identify ECE and non-ECE patients, specifically in the patch-level. We have achieved the ECE detection with 96.92% accuracy 98.84% AUC. Detailed results are shown in the Table 1. Conclusion The study demonstrates the ability to use a deep learning-based method for ECE direct detection. The proposed local-global network can help capture sufficient features and achieve high classification accuracy. The outcome of this research is expected to promote the implementation of artificial intelligence for ECE identification for head and neck cancer diagnosis in the radiology computer vision field.

Purpose: The Joint Commission has encouraged the healthcare industry to become “High Reliability Organizations” by “Chasing Zero Harm” in patient care. In radiation oncology, the time point of quality checks determines whether errors are prevented or only mitigated. Thus, to “chase zero” in radiation oncology, peer review has to be implemented prior to treatment initiation. A multidisciplinary group consensus peer review (GCPR) model is used pre-treatment at our institution and has been successful in our efforts to “chase zero harm” in patient care. Methods: With the GCPR model, policy-defined complex cases go through a treatment planning conference, which includes physicians, residents, physicists, and dosimetrists. Three major plan aspects are reviewed: target volumes, target and normal tissue dose coverage, and dose distributions. During the review, any team member can ask questions and afterwards a group consensus is taken regarding plan approval. Results: The GCPR model has been implemented through a commitment to peer review and creative conference scheduling. Automated analysis software is used to depict color-coded results for department approved target coverage and dose constraints. About 8% of plans required re-planning while about 23% required minor changes. The mean time for review of each plan was 8 min. Conclusions: Catching errors prior to treatment is the only way to “chase zero” in radiation oncology. Various types of errors may exist in treatment plans and our GCPR model succeeds in preventing many errors of all shapes and sizes in target definition, dose prescriptions, and treatment plans from ever reaching the patients.

Extracapsular extension (ECE) is a decisive indication for treatment planning of patients with head and neck squamous cell carcinoma (HNSCC). ECE occurs when metastatic tumor cells within the lymph node break through the nodal capsule into surrounding tissues. It is crucial to identify whether ECE occurs in HNSCC patient treatment. Current ECE detection practice mainly relies on the visual identification of doctors and professionals, which can be extremely labor intensive and time-consuming. Therefore, we aim to automatically perform ECE detection using a machine learning technique to classify whether ECE appears or not. In this research, we propose a systematic machine learning approach to detect ECE from 3D computed tomography (CT) scans. The process includes four steps: 1) apply sliding-cube to extract small 3D samples from patient data; 2) various 3D features are extracted for each sample; and 3) three machine learning models, gradient boosting (GB), random forest (RF), and support vector machine (SVM), with feature extraction and selection approaches, are employed for sample classification task; 4) classify the patient based on sample classification result. Different training scenarios are designed for the experimental test. Based on five-fold cross-validation, the experimental results have demonstrated that our model is able to classify ECE and non-ECE patients. To check the explainability of the models, feature analysis is also conducted. The outcome of this research is expected to promote the implementation of artificial intelligence for ECE classification and detection as well as head and neck cancer diagnosis in the radiology computer vision field. Citation Format: Yibin Wang, William N. Duggar, Toms V. Thomas, Paul Roberts, Linkan Bian, Haifeng Wang. Artificial intelligence-based extracapsular extension prediction in head and neck cancer analysis [abstract]. In: Proceedings of the AACR Virtual Special Conference on Artificial Intelligence, Diagnosis, and Imaging; 2021 Jan 13-14. Philadelphia (PA): AACR; Clin Cancer Res 2021;27(5_Suppl):Abstract nr PO-039.

This study is to demonstrate the importance and a method of properly modeling the treatment couch for dose calculation in patient treatment using arc therapy. The 2 treatment couch tops-Aktina AK550 and Elekta iBEAM evo-of Elekta LINACs were scanned using Philips Brilliance Big Bore CT Simulator. Various parts of the couch tops were contoured, and their densities were measured and recorded on the Pinnacle treatment planning system (TPS) using the established computed tomography density table. These contours were saved as organ models to be placed beneath the patient during planning. Relative attenuation measurements were performed following procedures outlined by TG-176 as well as absolute dose comparison of static fields of 10 × 10 cm(2) that were delivered through the couch tops with that calculated in the TPS with the couch models. A total of 10 random arc therapy treatment plans (5 volumetric-modulated arc therapy [VMAT] and 5 stereotactic body radiation therapy [SBRT]), using 24 beams, were selected for this study. All selected plans were calculated with and without couch modeling. Each beam was evaluated using the Delta(4) dosimetry system (Delta(4)). The Student t-test was used to determine statistical significance. Independent reviews were exploited as per the Imaging and Radiation Oncology Core head and neck credentialing phantom. The selected plans were calculated on the actual patient anatomies with and without couch modeling to determine potential clinical effects. Large relative beam attenuations were noted dependent on which part of the couch top beams were passing through. Substantial improvements were also noted for static fields both calculated with the TPS and delivered physically when the couch models were included in the calculation. A statistically significant increase in agreement was noted for dose difference, distance to agreement, and γ-analysis with the Delta(4) on VMAT and SBRT plans. A credentialing review showed improvement in treatment delivery after couch modeling with both thermoluminescent dosimeter doses and film analysis. Furthermore, analysis of treatment plans with and without using the couch model showed a statistically significant reduction in planning target volume coverage and increase in skin dose. In conclusion, ignoring the treatment couch, a common practice when generating a patient treatment plan, can overestimate the dose delivered especially for arc therapy. This work shows that explicitly modeling the couch during planning can meaningfully improve the agreement between calculated and measured dose distributions. Because of this project, we have implemented the couch models clinically across all treatment plans.

Purpose/Objective(s): Stereotactic body radiation therapy (SBRT) is an effective treatment for patients with early-stage non-small cell lung cancer (NSCLC) who are not surgical candidates or who refuse surgical management. In this study, we report on our clinical outcomes and toxicity in the treatment of early-stage NSCLC with SBRT. Methods and Materials: Fifty-five patients with 59 T1-2N0M0 NSCLC lesions were treated at our institution between December 2009 and August 2014. The majority of the patients [38 (69%)] were treated with 50 Gy in 5 fractions, 7 patients (13%) with 48 Gy in 4 fractions, 8 patients (14%) with 60 Gy in 3 fractions, 1 patient (2%) with 62.5 Gy in 10 fractions, and 1 patient (2%) with 54 Gy in 3 fractions. Tumor response was evaluated using RECIST 1.1, and toxicity was graded using the CTCAE (Common Terminology Criteria for Adverse Events) version 3.0. The primary endpoints of this retrospective review included rates of overall survival, disease-free and progression-free survival, local failure, regional failure, and distant failure. A secondary endpoint included radiation-related toxicities. Results: The median follow-up was 23.8 months (range 1.1-57.6). The 3-year local control, progression-free survival, and overall survival rates were 91, 55, and 71%, respectively. The median age at diagnosis was 67.9 years (range 51.4-87.1). There were a total of 54 T1N0 tumors (92%) and 5 T2N0 lesions (8%). Adenocarcinoma was the most common pathology, comprising 54% of the lesions. A total of 16 of the patients (29%) failed. Among these, 5 local (9%), 14 regional (25%), and 4 distant failures (7%) were observed. On follow-up, one patient had grade 2 and another had grade 5 pneumonitis. Three patients experienced grade 2 chest wall tenderness. Two patients had grade 1 rib fractures, one of which could not be discerned from radiation-induced toxicity versus a traumatic fall. Conclusion: The University of Mississippi Medical Center SBRT experience has shown that SBRT provides satisfactory local control and overall survival rates with minimal toxicity in early-stage NSCLC patients.