An Analysis of Learning Curve Effect on the Speed and Quality of High Dose Rate Prostate Brachytherapy Procedures

Systematic Review and Meta-analysis of the Association Between Radiation Therapy Treatment Volume and Patient Outcomes

PURPOSE

Evidence of a volume-outcome association in cancer surgery has shaped the centralization of cancer services; however, it is unknown whether a similar association exists for radiation therapy. The objective of this study was to determine the association between radiation therapy treatment volume and patient outcomes.

METHODS AND MATERIALS

This systematic review and meta-analysis included studies that compared outcomes of patients who underwent definitive radiation therapy at high-volume radiation therapy facilities (HVRFs) versus low-volume facilities (LVRFs). The systematic review used Ovid MEDLINE and Embase. For the meta-analysis, a random effects model was used. Absolute effects and hazard ratios (HRs) were used to compare patient outcomes.

RESULTS

The search identified 20 studies assessing the association between radiation therapy volume and patient outcomes. Seven of the studies looked at head and neck cancers (HNCs). The remaining studies covered cervical (4), prostate (4), bladder (3), lung (2), anal (2), esophageal (1), brain (2), liver (1), and pancreatic cancer (1). The meta-analysis demonstrated that HVRFs were associated with a lower chance of death compared with LVRFs (pooled HR, 0.90; 95% CI, 0.87- 0.94). HNCs had the strongest evidence of a volume-outcome association for both nasopharyngeal cancer (pooled HR, 0.74; 95% CI, 0.62-0.89) and nonnasopharyngeal HNC subsites (pooled HR, 0.80; 95% CI, 0.75-0.84), followed by prostate cancer (pooled HR, 0.92; 95% CI, 0.86-0.98). The remaining cancer types showed weak evidence of an association. The results also demonstrate that some centers defined as HVRFs are undertaking very few procedures per annum (<5 radiation therapy cases per year).

CONCLUSIONS

An association between radiation therapy treatment volume and patient outcomes exists for most cancer types. Centralization of radiation therapy services should be considered for cancer types with the strongest volume-outcome association, but the effect on equitable access to services needs to be explicitly considered.

The Challenges Facing Deep Learning based Catheter Localization for Ultrasound Guided High-Dose-Rate Prostate Brachytherapy

BACKGROUND

Automated catheter localization for ultrasound guided high-dose-rate prostate brachytherapy faces challenges relating to imaging noise and artifacts. To date, catheter reconstruction during the clinical procedure is performed manually. Deep learning has been successfully applied to a wide variety of complex tasks and has the potential to tackle the unique challenges associated with multiple catheter localization on ultrasound. Such a task is well suited for automation, with the potential to improve productivity and reliability.

PURPOSE

We developed a deep learning model for automated catheter reconstruction and investigated potential factors influencing model performance. The model was designed to integrate into a clinical workflow, with a proposed reconstruction confidence metric to aid in planner verification.

METHODS

Datasets from 242 patients treated from 2016 to 2020 were collected retrospectively. The anonymized dataset comprises of 31,000 transverse images reconstructed from 3D sagittal ultrasound acquisitions and 3,500 implanted catheters manually localized by the planner. Each catheter was retrospectively ranked based on the severity of imaging artifacts affecting reconstruction difficulty. The U-NET deep learning architecture was trained to localize implanted catheters on transverse images. A five-fold cross-validation method was used, allowing for evaluation over the entire dataset. The post-processing software combined the predictions with patient-specific implant information to reconstructed catheters in 3D space, uniquely matched to the implanted grid positions. A reconstruction confidence metric was calculated based on the number and probability of localized predictions per catheter. For each patient, deep learning prediction and post-processing reconstruction was completed in under two minutes on a non-performance PC.

RESULTS

Overall, 80% of catheter reconstructions were accurate, within 2 mm along 90% of the length. The catheter tip was often not detected and required extrapolation during reconstruction. The reconstruction accuracy was 89% for the easiest catheter ranking and decreased to 13% for the highest difficulty ranking, when the aid of live ultrasound would have been recommended. Even when limited to the easiest ranked catheters, the reconstruction accuracy decreased at distal grid positions, down to 50%. Individual implantation style was found to influence the frequency of severe artifacts, slightly impacting the model accuracy. A reconstruction confidence metric identified the difficult catheters, removed the observed individual variation, and increased the overall accuracy to 91% while excluding 27% of the reconstructions.

CONCLUSIONS

The deep learning model localized implanted catheters over a large clinical dataset, with overall promising results. The model faced challenges due to ultrasound artifacts and image degradation distal to the probe, underlining the continued importance of maintaining image quality and minimizing artifacts. A potential workflow for integration into the clinical procedure was demonstrated, including the use of a confidence metric to predict low accuracy reconstructions. Comparison between models evaluated on different datasets should also consider underlying differences, such as the frequency and severity of imaging artifacts. This article is protected by copyright. All rights reserved.