Leveraging an Expert Knowledge-Based Plan Matching System Enables Meeting More Clinical Objectives for Prostate External Beam Radiation Therapy

Abstract

The creation of an ideal IMRT plan is a challenging and complex process utilizing a team of expert physicians, dosimetrists, medical physicists, and computer algorithms. Due to challenges with simultaneously optimizing multiple dosimetric indices, the full extent of achievable plan results (including plan trade-offs) are not known with high precision. Knowledge based treatment-planning (KBTP) aims to leverage past plan expertise to optimize new plans. The commercial software (QuickMatch™, Siris Medical Inc.) guides the dosimetrist through a library of previously approved plans to identify multiple achievable treatment plans for new patients. In general, the larger the database, the more insights that can be drawn from it. We report on treatment planning results from the largest known (to the best of our knowledge) plan database for treatment plan guidance of prostate plans. QuickMatch (QM) built a library with 1168 prostate patients (over 3,500 plans), spanning the years 2010-2016. These plans included pelvic node & non-pelvic node cases, with dose escalation to the Planning Target Volume (PTV) from 8100 to 8640 cGy using IMRT. We randomly identified 16 consecutive patients and planned them prospectively with QM. For each plan, a clinical dosimetrist using the same treatment planning system compared final dosimetry with respect to PTV coverages, bladder doses, rectal doses, and femur doses using standard planning techniques (SPT) compared to QM. We also retrospectively analyzed 1168 plans to identify those that did not meet either rectal, bladder, or femoral dose constraints using STP to determine if adding QM would result in improved dosimetry. Compared to STP alone, the addition of QM to STP improved overall dosimetry in the final prostate plans. In the 16 prospectively analyzed plans, nearly one more constraint per plan (mean difference = 0.8 constraints, matched pair t-test p=0.0044) was met without sacrificing other constraints or PTV coverage in every case (matched pair t-test p=0.86 that the means are different). QM guidance reduced rectal avoidance D10 in 85% of these patients. There were 561 instances where a clinical dose constraint was not met with STP. In these cases, QuickMatch improved the ability to meet clinical constraints, including PTV constraints, in 58% (323/561), in Rectal D10 in 67% (110/164), Rectal D50 in 59% (33/56), Bladder D10 in 54% (66/122), Bladder D50 in 25% (3/12), and femur D50 in 54% (111/207). We demonstrate the ability for an expert-trained knowledge based system to guide planning and to meet significantly more clinical dose constraints than standard planning for prostate RT.