Implementation of a knowledge-based decision support system for treatment plan auditing through automation.

BACKGROUND: Independent auditing is a necessary component of a comprehensive quality assurance (QA) program and can also be utilized for continuous quality improvement (QI) in various radiotherapy processes. Two senior physicists at our institution have been performing a time intensive manual audit of cross-campus treatment plans annually, with the aim of further standardizing our planning procedures, updating policies and guidelines, and providing training opportunities of all staff members. PURPOSE: A knowledge-based automated anomaly-detection algorithm to provide decision support and strengthen our manual retrospective plan auditing process was developed. This standardized and improved the efficiency of the assessment of our external beam radiotherapy (EBRT) treatment planning across all eight campuses of our institution. METHODS: A total of 843 external beam radiotherapy plans for 721 lung patients from January 2020 to March 2021 were automatically acquired from our clinical treatment planning and management systems. From each plan, 44 parameters were automatically extracted and pre-processed. A knowledge-based anomaly detection algorithm, namely, "isolation forest" (iForest), was then applied to the plan dataset. An anomaly score was determined for each plan using recursive partitioning mechanism. Top 20 plans ranked with the highest anomaly scores for each treatment technique (2D/3D/IMRT/VMAT/SBRT) including auto-populated parameters were used to guide the manual auditing process and validated by two plan auditors. RESULTS: The two auditors verified that 75.6% plans with the highest iForest anomaly scores have similar concerning qualities that may lead to actionable recommendations for our planning procedures and staff training materials. The time to audit a chart was approximately 20.8 min on average when done manually and 14.0 min when done with the iForest guidance. Approximately 6.8 min were saved per chart with the iForest method. For our typical internal audit review of 250 charts annually, the total time savings are approximately 30 hr per year. CONCLUSION: iForest effectively detects anomalous plans and strengthens our cross-campus manual plan auditing procedure by adding decision support and further improve standardization. Due to the use of automation, this method was efficient and will be used to establish a standard plan auditing procedure, which could occur more frequently.

Pancreatic cancer planning: Complex conformal vs modulated therapies.

To compare the roles of intensity-modulated radiation therapy (IMRT) and volumetric- modulated arc therapy (VMAT) therapy as compared to simple and complex 3-dimensional chemoradiotherpy (3DCRT) planning for resectable and borderline resectable pancreatic cancer. In all, 12 patients who received postoperative radiotherapy (8) or neoadjuvant concurrent chemoradiotherapy (4) were evaluated retrospectively. Radiotherapy planning was performed for 4 treatment techniques: simple 4-field box, complex 5-field 3DCRT, 5 to 6-field IMRT, and single-arc VMAT. All volumes were approved by a single observer in accordance with Radiation Therapy Oncology Group (RTOG) Pancreas Contouring Atlas. Plans included tumor/tumor bed and regional lymph nodes to 45Gy; with tumor/tumor bed boosted to 50.4Gy, at least 95% of planning target volume (PTV) received the prescription dose. Dose-volume histograms (DVH) for multiple end points, treatment planning, and delivery time were assessed. Complex 3DCRT, IMRT, and VMAT plans significantly (p < 0.05) decreased mean kidney dose, mean liver dose, liver (V30, V35), stomach (D10%), stomach (V45), mean right kidney dose, and right kidney (V15) as compared with the simple 4-field plans that are most commonly reported in the literature. IMRT plans resulted in decreased mean liver dose, liver (V35), and left kidney (V15, V18, V20). VMAT plans decreased small bowel (D10%, D15%), small bowel (V35, V45), stomach (D10%, D15%), stomach (V35, V45), mean liver dose, liver (V35), left kidney (V15, V18, V20), and right kidney (V18, V20). VMAT plans significantly decreased small bowel (D10%, D15%), left kidney (V20), and stomach (V45) as compared with IMRT plans. Treatment planning and delivery times were most efficient for simple 4-field box and VMAT. Excluding patient setup and imaging, average treatment delivery was within 10minutes for simple and complex 3DCRT, IMRT, and VMAT treatments. This article shows significant improvements in 3D plan performance with complex planning over the more frequently compared 3- or 4-field simple 3D planning techniques. VMAT plans continue to demonstrate potential for the most organ sparing. However, further studies are required to identify if dosimetric benefits associated with inverse optimized planning can be translated into clinical benefits and if these treatment techniques are value-added therapies for this group of patients with cancer.

Optimizing parametrial aperture design utilizing HDR brachytherapy isodose distribution.

Treatment of cervical cancer includes combination of external beam radiation therapy (EBRT) and brachytherapy (BRT). Traditionally, coronal images displaying dose distribution from a ring and tandem (R&T) implant aid in construction of parametrial boost fields. This research aimed to evaluate a method of shaping parametrial fields utilizing contours created from the high-dose-rate (HDR) BRT dose distribution. Eleven patients receiving HDR-BRT via R&T were identified. The BRT and EBRT CT scans were sent to FocalSim (v4.62)(®) and fused based on bony anatomy. The contour of the HDR isodose line was transferred to the EBRT scan. The EBRT scan was sent to CMS-XIO (v4.62)(®) for planning. This process provides an automated, potentially more accurate method of matching the medial parametrial border to the HDR dose distribution. This allows for a 3D-view of dose from HDR-BRT for clinical decision-making, utilizes a paperless process and saves time over the traditional technique.

Re-implantation of suboptimal prostate seed implantation: technique with intraoperative treatment planning.

PURPOSE: Post-implant dosimetry following prostate seed implantation (PSI) occasionally reveals suboptimal dosimetric coverage of the gland. Published reports of re-implantation techniques have focused on earlier-generation techniques, including preplanned approaches and stranded seeds. The purpose of this case report is to describe a customizable approach to perform corrective re-implantation using loose seeds and intraoperative planning technique. MATERIAL AND METHODS: This case report describes a 63-year-old male with favorable risk prostate adenocarcinoma receiving PSI. Thirty day post-implant dosimetric evaluation revealed suboptimal coverage of the base of the gland. Using guidance from post-implant CT-images and real-time planning, the patient received a corrective re-implantation with intraoperative planning. RESULTS: Post-implant dosimetry after re-implantation procedure with intraoperative planning yielded improved target volume coverage that achieved standard dosimetric criteria. CONCLUSIONS: Re-implantation as a salvage treatment technique after sub-optimal PSI is a valid treatment option performed with intraoperative real-time planning.