RapidPlan knowledge based planning: iterative learning process and model ability to steer planning strategies
Abstract Purpose To determine if the performance of a knowledge based RapidPlan (RP) planning model could be improved with an iterative learning process, i.e. if plans generated by an RP model could be used as new input to re-train the model and achieve better performance. Methods Clinical VMAT plan...
| Main Authors: | , , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
BMC
2019-10-01
|
| Series: | Radiation Oncology |
| Subjects: | |
| Online Access: | http://link.springer.com/article/10.1186/s13014-019-1403-0 |
| _version_ | 1818346101249409024 |
|---|---|
| author | A. Fogliata L. Cozzi G. Reggiori A. Stravato F. Lobefalo C. Franzese D. Franceschini S. Tomatis M. Scorsetti |
| author_facet | A. Fogliata L. Cozzi G. Reggiori A. Stravato F. Lobefalo C. Franzese D. Franceschini S. Tomatis M. Scorsetti |
| author_sort | A. Fogliata |
| collection | DOAJ |
| description | Abstract Purpose To determine if the performance of a knowledge based RapidPlan (RP) planning model could be improved with an iterative learning process, i.e. if plans generated by an RP model could be used as new input to re-train the model and achieve better performance. Methods Clinical VMAT plans from 83 patients presenting with head and neck cancer were selected to train an RP model, CL-1. With this model, new plans on the same patients were generated, and subsequently used as input to train a novel model, CL-2. Both models were validated on a cohort of 20 patients and dosimetric results compared. Another set of 83 plans was realised on the same patients with different planning criteria, by using a simple template with no attempt to manually improve the plan quality. Those plans were employed to train another model, TP-1. The differences between the plans generated by CL-1 and TP-1 for the validation cohort of patients were compared with respect to the differences between the original plans used to build the two models. Results The CL-2 model presented an improvement relative to CL-1, with higher R2 values and better regression plots. The mean doses to parallel organs decreased with CL-2, while D1% to serial organs increased (but not significantly). The different models CL-1 and TP-1 were able to yield plans according to each original strategy. Conclusion A refined RP model allowed the generation of plans with improved quality, mostly for parallel organs at risk and, possibly, also the intrinsic model quality. |
| first_indexed | 2024-12-13T17:12:55Z |
| format | Article |
| id | doaj.art-0082381f44f64edd8bfbbc36dc8454c0 |
| institution | Directory Open Access Journal |
| issn | 1748-717X |
| language | English |
| last_indexed | 2024-12-13T17:12:55Z |
| publishDate | 2019-10-01 |
| publisher | BMC |
| record_format | Article |
| series | Radiation Oncology |
| spelling | doaj.art-0082381f44f64edd8bfbbc36dc8454c02022-12-21T23:37:29ZengBMCRadiation Oncology1748-717X2019-10-0114111210.1186/s13014-019-1403-0RapidPlan knowledge based planning: iterative learning process and model ability to steer planning strategiesA. Fogliata0L. Cozzi1G. Reggiori2A. Stravato3F. Lobefalo4C. Franzese5D. Franceschini6S. Tomatis7M. Scorsetti8Radiotherapy Department, Humanitas Research Hospital and Cancer CenterRadiotherapy Department, Humanitas Research Hospital and Cancer CenterRadiotherapy Department, Humanitas Research Hospital and Cancer CenterRadiotherapy Department, Humanitas Research Hospital and Cancer CenterRadiotherapy Department, Humanitas Research Hospital and Cancer CenterRadiotherapy Department, Humanitas Research Hospital and Cancer CenterRadiotherapy Department, Humanitas Research Hospital and Cancer CenterRadiotherapy Department, Humanitas Research Hospital and Cancer CenterRadiotherapy Department, Humanitas Research Hospital and Cancer CenterAbstract Purpose To determine if the performance of a knowledge based RapidPlan (RP) planning model could be improved with an iterative learning process, i.e. if plans generated by an RP model could be used as new input to re-train the model and achieve better performance. Methods Clinical VMAT plans from 83 patients presenting with head and neck cancer were selected to train an RP model, CL-1. With this model, new plans on the same patients were generated, and subsequently used as input to train a novel model, CL-2. Both models were validated on a cohort of 20 patients and dosimetric results compared. Another set of 83 plans was realised on the same patients with different planning criteria, by using a simple template with no attempt to manually improve the plan quality. Those plans were employed to train another model, TP-1. The differences between the plans generated by CL-1 and TP-1 for the validation cohort of patients were compared with respect to the differences between the original plans used to build the two models. Results The CL-2 model presented an improvement relative to CL-1, with higher R2 values and better regression plots. The mean doses to parallel organs decreased with CL-2, while D1% to serial organs increased (but not significantly). The different models CL-1 and TP-1 were able to yield plans according to each original strategy. Conclusion A refined RP model allowed the generation of plans with improved quality, mostly for parallel organs at risk and, possibly, also the intrinsic model quality.http://link.springer.com/article/10.1186/s13014-019-1403-0Knowledge based planningRapidPlan |
| spellingShingle | A. Fogliata L. Cozzi G. Reggiori A. Stravato F. Lobefalo C. Franzese D. Franceschini S. Tomatis M. Scorsetti RapidPlan knowledge based planning: iterative learning process and model ability to steer planning strategies Radiation Oncology Knowledge based planning RapidPlan |
| title | RapidPlan knowledge based planning: iterative learning process and model ability to steer planning strategies |
| title_full | RapidPlan knowledge based planning: iterative learning process and model ability to steer planning strategies |
| title_fullStr | RapidPlan knowledge based planning: iterative learning process and model ability to steer planning strategies |
| title_full_unstemmed | RapidPlan knowledge based planning: iterative learning process and model ability to steer planning strategies |
| title_short | RapidPlan knowledge based planning: iterative learning process and model ability to steer planning strategies |
| title_sort | rapidplan knowledge based planning iterative learning process and model ability to steer planning strategies |
| topic | Knowledge based planning RapidPlan |
| url | http://link.springer.com/article/10.1186/s13014-019-1403-0 |
| work_keys_str_mv | AT afogliata rapidplanknowledgebasedplanningiterativelearningprocessandmodelabilitytosteerplanningstrategies AT lcozzi rapidplanknowledgebasedplanningiterativelearningprocessandmodelabilitytosteerplanningstrategies AT greggiori rapidplanknowledgebasedplanningiterativelearningprocessandmodelabilitytosteerplanningstrategies AT astravato rapidplanknowledgebasedplanningiterativelearningprocessandmodelabilitytosteerplanningstrategies AT flobefalo rapidplanknowledgebasedplanningiterativelearningprocessandmodelabilitytosteerplanningstrategies AT cfranzese rapidplanknowledgebasedplanningiterativelearningprocessandmodelabilitytosteerplanningstrategies AT dfranceschini rapidplanknowledgebasedplanningiterativelearningprocessandmodelabilitytosteerplanningstrategies AT stomatis rapidplanknowledgebasedplanningiterativelearningprocessandmodelabilitytosteerplanningstrategies AT mscorsetti rapidplanknowledgebasedplanningiterativelearningprocessandmodelabilitytosteerplanningstrategies |