Feasibility of preference-driven radiotherapy dose treatment planning to support shared decision making in anal cancer

Random Forest Modeling of Acute Toxicity in Anal Cancer: Effects of Peritoneal Cavity Contouring Approaches on Model Performance

PURPOSE

Our purpose was to analyze the effect on gastrointestinal (GI) toxicity models when their dose-volume metrics predictors are derived from segmentations of the peritoneal cavity after different contouring approaches.

METHODS AND MATERIALS

A random forest machine learning approach was used to predict acute grade ≥3 GI toxicity from dose-volume metrics and clinicopathologic factors for 246 patients (toxicity incidence = 9.5%) treated with definitive chemoradiation for squamous cell carcinoma of the anus. Three types of random forest models were constructed based on different bowel bag segmentation approaches: (1) physician-delineated after Radiation Therapy Oncology Group (RTOG) guidelines, (2) autosegmented by a deep learning model (nnU-Net) following RTOG guidelines, and (3) autosegmented but spanning the entire bowel space. Each model type was evaluated using repeated cross-validation (100 iterations; 50%/50% training/test split). The performance of the models was assessed using area under the precision-recall curve (AUPRC) and the receiver operating characteristic curve (AUROCC), as well as optimal F1 score.

RESULTS

When following RTOG guidelines, the models based on the nnU-Net auto segmentations (mean values: AUROCC, 0.71 ± 0.07; AUPRC, 0.42 ± 0.09; F1 score, 0.46 ± 0.08) significantly outperformed (P < .001) those based on the physician-delineated contours (mean values: AUROCC, 0.67 ± 0.07; AUPRC, 0.34 ± 0.08; F1 score, 0.36 ± 0.07). When spanning the entire bowel space, the performance of the autosegmentation models improved considerably (mean values: AUROCC, 0.87 ± 0.05; AUPRC, 0.70 ± 0.09; F1 score, 0.68 ± 0.09).

CONCLUSIONS

Random forest models were superior at predicting acute grade ≥3 GI toxicity when based on RTOG-defined bowel bag autosegmentations rather than physician-delineated contours. Models based on autosegmentations spanning the entire bowel space show further considerable improvement in model performance. The results of this study should be further validated using an external data set.

Fully automated volumetric modulated arc therapy planning for locally advanced rectal cancer: feasibility and efficiency

BACKGROUND

Volumetric modulated arc therapy (VMAT) for locally advanced rectal cancer (LARC) has emerged as a promising technique, but the planning process can be time-consuming and dependent on planner expertise. We aimed to develop a fully automated VMAT planning program for LARC and evaluate its feasibility and efficiency.

METHODS

A total of 26 LARC patients who received VMAT treatment and the computed tomography (CT) scans were included in this study. Clinical target volumes and organs at risk were contoured by radiation oncologists. The automatic planning program, developed within the Raystation treatment planning system, used scripting capabilities and a Python environment to automate the entire planning process. The automated VMAT plan (auto-VMAT) was created by our automated planning program with the 26 CT scans used in the manual VMAT plan (manual-VMAT) and their regions of interests. Dosimetric parameters and time efficiency were compared between the auto-VMAT and the manual-VMAT created by experienced planners. All results were analyzed using the Wilcoxon signed-rank sum test.

RESULTS

The auto-VMAT achieved comparable coverage of the target volume while demonstrating improved dose conformity and uniformity compared with the manual-VMAT. V30 and V40 in the small bowel were significantly lower in the auto-VMAT compared with those in the manual-VMAT (p < 0.001 and < 0.001, respectively); the mean dose of the bladder was also significantly reduced in the auto-VMAT (p < 0.001). Furthermore, auto-VMAT plans were consistently generated with less variability in quality. In terms of efficiency, the auto-VMAT markedly reduced the time required for planning and expedited plan approval, with 93% of cases approved within one day.

CONCLUSION

We developed a fully automatic feasible VMAT plan creation program for LARC. The auto-VMAT maintained target coverage while providing organs at risk dose reduction. The developed program dramatically reduced the time to approval.

Observing the Implementation of Shared Decision-making in Routine Radiotherapy Cancer Nursing: An Explorative Longitudinal Questionnaire Study

BACKGROUND

Healthcare professionals have driven decision-making in the past. However, shared decision-making has the potential to increase quality of care.

OBJECTIVE

To determine to what degree patients undergoing routine pelvic radiotherapy care perceive decision-making as being shared between patient and healthcare professionals.

METHODS

This exploratory longitudinal study covered 193 patients undergoing pelvic radiotherapy, mostly women (n = 161 [84%]) treated for a gynecological (n = 132 [68%]) or colorectal (n = 54 [28%]) cancer. We collected data regarding self-perceived level of shared decision-making at the start of radiotherapy and quality of life (QoL) (91%-95% response rate per week) during the radiotherapy period.

RESULTS

The patients reported that they shared the decision-making with the healthcare professionals much (n = 137 [71%]), moderately (n = 33 [17%]), a little (n = 12 [6%]), or not at all (n = 11 [6%]). Male patients (P = .048), patients who did not live with their partner (P = .034), patients with higher education (P = .043), and patients with low functional capacity (P = .018) perceived lower levels of shared decision-making. A higher level of shared decision-making was related to higher QoL at baseline and during the first to third weeks of radiotherapy (P ranged from .001 to .044).

CONCLUSIONS

Almost 9 of 10 patients reported that they shared the decision-making moderately or much with the healthcare professionals. The study identified subgroups perceiving lower levels of shared decision-making and found that a higher level of shared decision-making was related to better QoL.

IMPLICATIONS

Healthcare professionals may need to pay extra attention to patients who may perceive that they share decision-making to a low extent.

Automation in intensity modulated radiotherapy treatment planning-a review of recent innovations

Radiotherapy treatment planning of complex radiotherapy techniques, such as intensity modulated radiotherapy and volumetric modulated arc therapy, is a resource-intensive process requiring a high level of treatment planner intervention to ensure high plan quality. This can lead to variability in the quality of treatment plans and the efficiency in which plans are produced, depending on the skills and experience of the operator and available planning time. Within the last few years, there has been significant progress in the research and development of intensity modulated radiotherapy treatment planning approaches with automation support, with most commercial manufacturers now offering some form of solution. There is a rapidly growing number of research articles published in the scientific literature on the topic. This paper critically reviews the body of publications up to April 2018. The review describes the different types of automation algorithms, including the advantages and current limitations. Also included is a discussion on the potential issues with routine clinical implementation of such software, and highlights areas for future research.