Highly Efficient Training, Refinement, and Validation of a Knowledge-based Planning Quality-Control System for Radiation Therapy Clinical Trials

Abstract

Purpose: To demonstrate an efficient method for training and validation of a knowledge-based planning (KBP) system as a radiation therapy clinical trial plan quality-control system.

Methods and materials: We analyzed 86 patients with stage IB through IVA cervical cancer treated with intensity modulated radiation therapy at 2 institutions according to the standards of the INTERTECC (International Evaluation of Radiotherapy Technology Effectiveness in Cervical Cancer, National Clinical Trials Network identifier: 01554397) protocol. The protocol used a planning target volume and 2 primary organs at risk: pelvic bone marrow (PBM) and bowel. Secondary organs at risk were rectum and bladder. Initial unfiltered dose-volume histogram (DVH) estimation models were trained using all 86 plans. Refined training sets were created by removing sub-optimal plans from the unfiltered sample, and DVH estimation models… and DVH estimation models were constructed by identifying 30 of 86 plans emphasizing PBM sparing (comparing protocol-specified dosimetric cutpoints V₁₀ (percentage volume of PBM receiving at least 10 Gy dose) and V₂₀ (percentage volume of PBM receiving at least 20 Gy dose) with unfiltered predictions) and another 30 of 86 plans emphasizing bowel sparing (comparing V₄₀ (absolute volume of bowel receiving at least 40 Gy dose) and V₄₅ (absolute volume of bowel receiving at least 45 Gy dose), 9 in common with the PBM set). To obtain deliverable KBP plans, refined models must inform patient-specific optimization objectives and/or priorities (an auto-planning "routine"). Four candidate routines emphasizing different tradeoffs were composed, and a script was developed to automatically re-plan multiple patients with each routine. After selection of the routine that best met protocol objectives in the 51-patient training sample (KBP_FINAL), protocol-specific DVH metrics and normal tissue complication probability were compared for original versus KBP_FINAL plans across the 35-patient validation set. Paired t tests were used to test differences between planning sets.

Results: KBP_FINAL plans outperformed manual planning across the validation set in all protocol-specific DVH cutpoints. The mean normal tissue complication probability for gastrointestinal toxicity was lower for KBP_FINAL versus validation-set plans (48.7% vs 53.8%, P<.001). Similarly, the estimated mean white blood cell count nadir was higher (2.77 vs 2.49 k/mL, P<.001) with KBP_FINAL plans, indicating lowered probability of hematologic toxicity.

Conclusions: This work demonstrates that a KBP system can be efficiently trained and refined for use in radiation therapy clinical trials with minimal effort. This patient-specific plan quality control resulted in improvements on protocol-specific dosimetric endpoints.

Figure 1

Flow Diagram of this study.

Figure 2

Comparison of average DVHs of the original and KBP_FINAL plans for 35 validation patients. a). Average DVH comparison. PTV, planning target volume; PBM, pelvic bone marrow. b). Difference of average DVH between original and KBP_FINAL. Note that the regions of improvement are in the protocol-specified 10–20 Gy region of the PBM DVH and in the high dose region >40 Gy region of the bowel DVH.

Figure 3

Comparison of the PBM and Bowel DVH metrics between original and KBP_FINAL in the training and validation sets. PBM a) V₁₀ and b) V₂₀ comparison between original plan and KBP_FINAL for each patient. Bowel c) V₄₀ and d) V₄₅ comparison between original plan and KBP_FINAL for each patient.

Figure 4

Frequency histogram of the difference of NTCP and estimated WBC nadir between original and KBP_FINAL plans across the training set (grey) and validation set (white).