Automatic genetic planning for volumetric modulated arc therapy: A large multi-centre validation for prostate cancer

Christian Fiandra; Linda Rossi; Alessandro Alparone; Stefania Zara; Claudio Vecchi; Anna Sardo; Sara Bartoncini; Gianfranco Loi; Carla Pisani; Eva Gino; Maria Grazia Ruo Redda; Gian Marco Deotto; Paolo Tini; Stefania Comi; Dario Zerini; Gianluca Ametrano; Valentina Borzillo; Lidia Strigari; Silvia Strolin; Alessandro Savini; Antonino Romeo; Sonia Reccanello; Imad Abu Rumeileh; Nunzia Ciscognetti; Flavia Guerrisi; Gabriella Balestra; Umberto Ricardi; Ben Heijmen

doi:10.1016/j.radonc.2020.04.020

Automatic genetic planning for volumetric modulated arc therapy: A large multi-centre validation for prostate cancer

Christian Fiandra, Linda Rossi, Alessandro Alparone, Stefania Zara, Claudio Vecchi, Anna Sardo, Sara Bartoncini, Gianfranco Loi, Carla Pisani, Eva Gino, Maria Grazia Ruo Redda, Gian Marco Deotto, Paolo Tini, Stefania Comi, Dario Zerini, Gianluca Ametrano, Valentina Borzillo, Lidia Strigari, Silvia Strolin, Alessandro SaviniAntonino Romeo, Sonia Reccanello, Imad Abu Rumeileh, Nunzia Ciscognetti, Flavia Guerrisi, Gabriella Balestra, Umberto Ricardi, Ben Heijmen

Research output: Contribution to journal › Article › peer-review

Abstract

PURPOSE: The first clinical genetic autoplanning algorithm (Genetic Planning Solution, GPS) was validated in ten radiotherapy centres for prostate cancer VMAT by comparison with manual planning (Manual).

METHODS: Although there were large differences among centres in planning protocol, GPS was tuned with the data of a single centre and then applied everywhere without any centre-specific fine-tuning. For each centre, ten Manual plans were compared with autoGPS plans, considering dosimetric plan parameters and the Clinical Blind Score (CBS) resulting from blind clinician plan comparisons. AutoGPS plans were used as is, i.e. there was no patient-specific fine-tuning.

RESULTS: For nine centres, all ten plans were clinically acceptable. In the remaining centre, only one plan was acceptable. For the 91% acceptable plans, differences between Manual and AutoGPS in target coverage were negligible. OAR doses were significantly lower in AutoGPS plans (p < 0.05); rectum D15% and Dmean were reduced by 8.1% and 17.9%, bladder D25% and Dmean by 5.9% and 10.3%. According to clinicians, 69% of the acceptable AutoGPS plans were superior to the corresponding Manual plan. In case of preferred Manual plans (31%), perceived advantages compared to autoGPS were minor. QA measurements demonstrated that autoGPS plans were deliverable. A quick configuration adjustment in the centre with unacceptable plans rendered 100% of plans acceptable.

CONCLUSION: A novel, clinically applied genetic autoplanning algorithm was validated in 10 centres for in total 100 prostate cancer patients. High quality plans could be generated at different centres without centre-specific algorithm tuning.

Original language	English
Pages (from-to)	126-132
Number of pages	7
Journal	Radiotherapy and Oncology
Volume	148
DOIs	https://doi.org/10.1016/j.radonc.2020.04.020
Publication status	Published - Jul 2020

Access to Document

10.1016/j.radonc.2020.04.020

Fingerprint Dive into the research topics of 'Automatic genetic planning for volumetric modulated arc therapy: A large multi-centre validation for prostate cancer'. Together they form a unique fingerprint.

Cite this

Fiandra, C., Rossi, L., Alparone, A., Zara, S., Vecchi, C., Sardo, A., Bartoncini, S., Loi, G., Pisani, C., Gino, E., Ruo Redda, M. G., Marco Deotto, G., Tini, P., Comi, S., Zerini, D., Ametrano, G., Borzillo, V., Strigari, L., Strolin, S., ... Heijmen, B. (2020). Automatic genetic planning for volumetric modulated arc therapy: A large multi-centre validation for prostate cancer. Radiotherapy and Oncology, 148, 126-132. https://doi.org/10.1016/j.radonc.2020.04.020

Automatic genetic planning for volumetric modulated arc therapy: A large multi-centre validation for prostate cancer. / Fiandra, Christian; Rossi, Linda; Alparone, Alessandro; Zara, Stefania; Vecchi, Claudio; Sardo, Anna; Bartoncini, Sara; Loi, Gianfranco; Pisani, Carla; Gino, Eva; Ruo Redda, Maria Grazia; Marco Deotto, Gian; Tini, Paolo; Comi, Stefania ; Zerini, Dario; Ametrano, Gianluca; Borzillo, Valentina; Strigari, Lidia ; Strolin, Silvia; Savini, Alessandro; Romeo, Antonino; Reccanello, Sonia; Rumeileh, Imad Abu; Ciscognetti, Nunzia; Guerrisi, Flavia; Balestra, Gabriella; Ricardi, Umberto; Heijmen, Ben.

In: Radiotherapy and Oncology, Vol. 148, 07.2020, p. 126-132.

Research output: Contribution to journal › Article › peer-review

Fiandra, C, Rossi, L, Alparone, A, Zara, S, Vecchi, C, Sardo, A, Bartoncini, S, Loi, G, Pisani, C, Gino, E, Ruo Redda, MG, Marco Deotto, G, Tini, P, Comi, S , Zerini, D, Ametrano, G, Borzillo, V, Strigari, L , Strolin, S, Savini, A, Romeo, A, Reccanello, S, Rumeileh, IA, Ciscognetti, N, Guerrisi, F, Balestra, G, Ricardi, U & Heijmen, B 2020, 'Automatic genetic planning for volumetric modulated arc therapy: A large multi-centre validation for prostate cancer', Radiotherapy and Oncology, vol. 148, pp. 126-132. https://doi.org/10.1016/j.radonc.2020.04.020

Fiandra, Christian ; Rossi, Linda ; Alparone, Alessandro ; Zara, Stefania ; Vecchi, Claudio ; Sardo, Anna ; Bartoncini, Sara ; Loi, Gianfranco ; Pisani, Carla ; Gino, Eva ; Ruo Redda, Maria Grazia ; Marco Deotto, Gian ; Tini, Paolo ; Comi, Stefania ; Zerini, Dario ; Ametrano, Gianluca ; Borzillo, Valentina ; Strigari, Lidia ; Strolin, Silvia ; Savini, Alessandro ; Romeo, Antonino ; Reccanello, Sonia ; Rumeileh, Imad Abu ; Ciscognetti, Nunzia ; Guerrisi, Flavia ; Balestra, Gabriella ; Ricardi, Umberto ; Heijmen, Ben. / Automatic genetic planning for volumetric modulated arc therapy: A large multi-centre validation for prostate cancer. In: Radiotherapy and Oncology. 2020 ; Vol. 148. pp. 126-132.

@article{170c48160bfa4cdbb867703580190361,

title = "Automatic genetic planning for volumetric modulated arc therapy: A large multi-centre validation for prostate cancer",

abstract = "PURPOSE: The first clinical genetic autoplanning algorithm (Genetic Planning Solution, GPS) was validated in ten radiotherapy centres for prostate cancer VMAT by comparison with manual planning (Manual).METHODS: Although there were large differences among centres in planning protocol, GPS was tuned with the data of a single centre and then applied everywhere without any centre-specific fine-tuning. For each centre, ten Manual plans were compared with autoGPS plans, considering dosimetric plan parameters and the Clinical Blind Score (CBS) resulting from blind clinician plan comparisons. AutoGPS plans were used as is, i.e. there was no patient-specific fine-tuning.RESULTS: For nine centres, all ten plans were clinically acceptable. In the remaining centre, only one plan was acceptable. For the 91% acceptable plans, differences between Manual and AutoGPS in target coverage were negligible. OAR doses were significantly lower in AutoGPS plans (p < 0.05); rectum D15% and Dmean were reduced by 8.1% and 17.9%, bladder D25% and Dmean by 5.9% and 10.3%. According to clinicians, 69% of the acceptable AutoGPS plans were superior to the corresponding Manual plan. In case of preferred Manual plans (31%), perceived advantages compared to autoGPS were minor. QA measurements demonstrated that autoGPS plans were deliverable. A quick configuration adjustment in the centre with unacceptable plans rendered 100% of plans acceptable.CONCLUSION: A novel, clinically applied genetic autoplanning algorithm was validated in 10 centres for in total 100 prostate cancer patients. High quality plans could be generated at different centres without centre-specific algorithm tuning.",

author = "Christian Fiandra and Linda Rossi and Alessandro Alparone and Stefania Zara and Claudio Vecchi and Anna Sardo and Sara Bartoncini and Gianfranco Loi and Carla Pisani and Eva Gino and {Ruo Redda}, {Maria Grazia} and {Marco Deotto}, Gian and Paolo Tini and Stefania Comi and Dario Zerini and Gianluca Ametrano and Valentina Borzillo and Lidia Strigari and Silvia Strolin and Alessandro Savini and Antonino Romeo and Sonia Reccanello and Rumeileh, {Imad Abu} and Nunzia Ciscognetti and Flavia Guerrisi and Gabriella Balestra and Umberto Ricardi and Ben Heijmen",

year = "2020",

month = jul,

doi = "10.1016/j.radonc.2020.04.020",

language = "English",

volume = "148",

pages = "126--132",

journal = "Radiotherapy and Oncology",

issn = "0167-8140",

publisher = "Elsevier Ireland Ltd",

}

TY - JOUR

T1 - Automatic genetic planning for volumetric modulated arc therapy: A large multi-centre validation for prostate cancer

AU - Fiandra, Christian

AU - Rossi, Linda

AU - Alparone, Alessandro

AU - Zara, Stefania

AU - Vecchi, Claudio

AU - Sardo, Anna

AU - Bartoncini, Sara

AU - Loi, Gianfranco

AU - Pisani, Carla

AU - Gino, Eva

AU - Ruo Redda, Maria Grazia

AU - Marco Deotto, Gian

AU - Tini, Paolo

AU - Comi, Stefania

AU - Zerini, Dario

AU - Ametrano, Gianluca

AU - Borzillo, Valentina

AU - Strigari, Lidia

AU - Strolin, Silvia

AU - Savini, Alessandro

AU - Romeo, Antonino

AU - Reccanello, Sonia

AU - Rumeileh, Imad Abu

AU - Ciscognetti, Nunzia

AU - Guerrisi, Flavia

AU - Balestra, Gabriella

AU - Ricardi, Umberto

AU - Heijmen, Ben

PY - 2020/7

Y1 - 2020/7

N2 - PURPOSE: The first clinical genetic autoplanning algorithm (Genetic Planning Solution, GPS) was validated in ten radiotherapy centres for prostate cancer VMAT by comparison with manual planning (Manual).METHODS: Although there were large differences among centres in planning protocol, GPS was tuned with the data of a single centre and then applied everywhere without any centre-specific fine-tuning. For each centre, ten Manual plans were compared with autoGPS plans, considering dosimetric plan parameters and the Clinical Blind Score (CBS) resulting from blind clinician plan comparisons. AutoGPS plans were used as is, i.e. there was no patient-specific fine-tuning.RESULTS: For nine centres, all ten plans were clinically acceptable. In the remaining centre, only one plan was acceptable. For the 91% acceptable plans, differences between Manual and AutoGPS in target coverage were negligible. OAR doses were significantly lower in AutoGPS plans (p < 0.05); rectum D15% and Dmean were reduced by 8.1% and 17.9%, bladder D25% and Dmean by 5.9% and 10.3%. According to clinicians, 69% of the acceptable AutoGPS plans were superior to the corresponding Manual plan. In case of preferred Manual plans (31%), perceived advantages compared to autoGPS were minor. QA measurements demonstrated that autoGPS plans were deliverable. A quick configuration adjustment in the centre with unacceptable plans rendered 100% of plans acceptable.CONCLUSION: A novel, clinically applied genetic autoplanning algorithm was validated in 10 centres for in total 100 prostate cancer patients. High quality plans could be generated at different centres without centre-specific algorithm tuning.

AB - PURPOSE: The first clinical genetic autoplanning algorithm (Genetic Planning Solution, GPS) was validated in ten radiotherapy centres for prostate cancer VMAT by comparison with manual planning (Manual).METHODS: Although there were large differences among centres in planning protocol, GPS was tuned with the data of a single centre and then applied everywhere without any centre-specific fine-tuning. For each centre, ten Manual plans were compared with autoGPS plans, considering dosimetric plan parameters and the Clinical Blind Score (CBS) resulting from blind clinician plan comparisons. AutoGPS plans were used as is, i.e. there was no patient-specific fine-tuning.RESULTS: For nine centres, all ten plans were clinically acceptable. In the remaining centre, only one plan was acceptable. For the 91% acceptable plans, differences between Manual and AutoGPS in target coverage were negligible. OAR doses were significantly lower in AutoGPS plans (p < 0.05); rectum D15% and Dmean were reduced by 8.1% and 17.9%, bladder D25% and Dmean by 5.9% and 10.3%. According to clinicians, 69% of the acceptable AutoGPS plans were superior to the corresponding Manual plan. In case of preferred Manual plans (31%), perceived advantages compared to autoGPS were minor. QA measurements demonstrated that autoGPS plans were deliverable. A quick configuration adjustment in the centre with unacceptable plans rendered 100% of plans acceptable.CONCLUSION: A novel, clinically applied genetic autoplanning algorithm was validated in 10 centres for in total 100 prostate cancer patients. High quality plans could be generated at different centres without centre-specific algorithm tuning.

U2 - 10.1016/j.radonc.2020.04.020

DO - 10.1016/j.radonc.2020.04.020

M3 - Article

C2 - 32361572

VL - 148

SP - 126

EP - 132

JO - Radiotherapy and Oncology

JF - Radiotherapy and Oncology

SN - 0167-8140

ER -