Machine Learning for Head and Neck Cancer: A Safe Bet?—A Clinically Oriented Systematic Review for the Radiation Oncologist
Background and PurposeMachine learning (ML) is emerging as a feasible approach to optimize patients’ care path in Radiation Oncology. Applications include autosegmentation, treatment planning optimization, and prediction of oncological and toxicity outcomes. The purpose of this clinically oriented s...
| Main Authors: | , , , , , , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Frontiers Media S.A.
2021-11-01
|
| Series: | Frontiers in Oncology |
| Subjects: | |
| Online Access: | https://www.frontiersin.org/articles/10.3389/fonc.2021.772663/full |
| _version_ | 1819003871896272896 |
|---|---|
| author | Stefania Volpe Stefania Volpe Matteo Pepa Mattia Zaffaroni Federica Bellerba Riccardo Santamaria Riccardo Santamaria Giulia Marvaso Giulia Marvaso Lars Johannes Isaksson Sara Gandini Anna Starzyńska Maria Cristina Leonardi Roberto Orecchia Daniela Alterio Barbara Alicja Jereczek-Fossa Barbara Alicja Jereczek-Fossa |
| author_facet | Stefania Volpe Stefania Volpe Matteo Pepa Mattia Zaffaroni Federica Bellerba Riccardo Santamaria Riccardo Santamaria Giulia Marvaso Giulia Marvaso Lars Johannes Isaksson Sara Gandini Anna Starzyńska Maria Cristina Leonardi Roberto Orecchia Daniela Alterio Barbara Alicja Jereczek-Fossa Barbara Alicja Jereczek-Fossa |
| author_sort | Stefania Volpe |
| collection | DOAJ |
| description | Background and PurposeMachine learning (ML) is emerging as a feasible approach to optimize patients’ care path in Radiation Oncology. Applications include autosegmentation, treatment planning optimization, and prediction of oncological and toxicity outcomes. The purpose of this clinically oriented systematic review is to illustrate the potential and limitations of the most commonly used ML models in solving everyday clinical issues in head and neck cancer (HNC) radiotherapy (RT).Materials and MethodsElectronic databases were screened up to May 2021. Studies dealing with ML and radiomics were considered eligible. The quality of the included studies was rated by an adapted version of the qualitative checklist originally developed by Luo et al. All statistical analyses were performed using R version 3.6.1.ResultsForty-eight studies (21 on autosegmentation, four on treatment planning, 12 on oncological outcome prediction, 10 on toxicity prediction, and one on determinants of postoperative RT) were included in the analysis. The most common imaging modality was computed tomography (CT) (40%) followed by magnetic resonance (MR) (10%). Quantitative image features were considered in nine studies (19%). No significant differences were identified in global and methodological scores when works were stratified per their task (i.e., autosegmentation).Discussion and ConclusionThe range of possible applications of ML in the field of HN Radiation Oncology is wide, albeit this area of research is relatively young. Overall, if not safe yet, ML is most probably a bet worth making. |
| first_indexed | 2024-12-20T23:27:54Z |
| format | Article |
| id | doaj.art-38f4a301a277435aba628cbb701dbb26 |
| institution | Directory Open Access Journal |
| issn | 2234-943X |
| language | English |
| last_indexed | 2024-12-20T23:27:54Z |
| publishDate | 2021-11-01 |
| publisher | Frontiers Media S.A. |
| record_format | Article |
| series | Frontiers in Oncology |
| spelling | doaj.art-38f4a301a277435aba628cbb701dbb262022-12-21T19:23:20ZengFrontiers Media S.A.Frontiers in Oncology2234-943X2021-11-011110.3389/fonc.2021.772663772663Machine Learning for Head and Neck Cancer: A Safe Bet?—A Clinically Oriented Systematic Review for the Radiation OncologistStefania Volpe0Stefania Volpe1Matteo Pepa2Mattia Zaffaroni3Federica Bellerba4Riccardo Santamaria5Riccardo Santamaria6Giulia Marvaso7Giulia Marvaso8Lars Johannes Isaksson9Sara Gandini10Anna Starzyńska11Maria Cristina Leonardi12Roberto Orecchia13Daniela Alterio14Barbara Alicja Jereczek-Fossa15Barbara Alicja Jereczek-Fossa16Division of Radiation Oncology, European Institute of Oncology (IEO) Istituto di Ricovero e Cura a Carattere Scientifico (IRCCS), Milan, ItalyDepartment of Oncology and Hemato-Oncology, University of Milan, Milan, ItalyDivision of Radiation Oncology, European Institute of Oncology (IEO) Istituto di Ricovero e Cura a Carattere Scientifico (IRCCS), Milan, ItalyDivision of Radiation Oncology, European Institute of Oncology (IEO) Istituto di Ricovero e Cura a Carattere Scientifico (IRCCS), Milan, ItalyMolecular and Pharmaco-Epidemiology Unit, Department of Experimental Oncology, European Institute of Oncology (IEO) Istituto di Ricovero e Cura a Carattere Scientifico (IRCCS), Milan, ItalyDivision of Radiation Oncology, European Institute of Oncology (IEO) Istituto di Ricovero e Cura a Carattere Scientifico (IRCCS), Milan, ItalyDepartment of Oncology and Hemato-Oncology, University of Milan, Milan, ItalyDivision of Radiation Oncology, European Institute of Oncology (IEO) Istituto di Ricovero e Cura a Carattere Scientifico (IRCCS), Milan, ItalyDepartment of Oncology and Hemato-Oncology, University of Milan, Milan, ItalyDivision of Radiation Oncology, European Institute of Oncology (IEO) Istituto di Ricovero e Cura a Carattere Scientifico (IRCCS), Milan, ItalyMolecular and Pharmaco-Epidemiology Unit, Department of Experimental Oncology, European Institute of Oncology (IEO) Istituto di Ricovero e Cura a Carattere Scientifico (IRCCS), Milan, ItalyDepartment of Oral Surgery, Medical University of Gdańsk, Gdańsk, PolandDivision of Radiation Oncology, European Institute of Oncology (IEO) Istituto di Ricovero e Cura a Carattere Scientifico (IRCCS), Milan, ItalyScientific Directorate, European Institute of Oncology (IEO) Istituto di Ricovero e Cura a Carattere Scientifico (IRCCS), Milan, ItalyDivision of Radiation Oncology, European Institute of Oncology (IEO) Istituto di Ricovero e Cura a Carattere Scientifico (IRCCS), Milan, ItalyDivision of Radiation Oncology, European Institute of Oncology (IEO) Istituto di Ricovero e Cura a Carattere Scientifico (IRCCS), Milan, ItalyDepartment of Oncology and Hemato-Oncology, University of Milan, Milan, ItalyBackground and PurposeMachine learning (ML) is emerging as a feasible approach to optimize patients’ care path in Radiation Oncology. Applications include autosegmentation, treatment planning optimization, and prediction of oncological and toxicity outcomes. The purpose of this clinically oriented systematic review is to illustrate the potential and limitations of the most commonly used ML models in solving everyday clinical issues in head and neck cancer (HNC) radiotherapy (RT).Materials and MethodsElectronic databases were screened up to May 2021. Studies dealing with ML and radiomics were considered eligible. The quality of the included studies was rated by an adapted version of the qualitative checklist originally developed by Luo et al. All statistical analyses were performed using R version 3.6.1.ResultsForty-eight studies (21 on autosegmentation, four on treatment planning, 12 on oncological outcome prediction, 10 on toxicity prediction, and one on determinants of postoperative RT) were included in the analysis. The most common imaging modality was computed tomography (CT) (40%) followed by magnetic resonance (MR) (10%). Quantitative image features were considered in nine studies (19%). No significant differences were identified in global and methodological scores when works were stratified per their task (i.e., autosegmentation).Discussion and ConclusionThe range of possible applications of ML in the field of HN Radiation Oncology is wide, albeit this area of research is relatively young. Overall, if not safe yet, ML is most probably a bet worth making.https://www.frontiersin.org/articles/10.3389/fonc.2021.772663/fullsystematic reviewartificial intelligencemachine learningradiotherapyhead and neck cancer |
| spellingShingle | Stefania Volpe Stefania Volpe Matteo Pepa Mattia Zaffaroni Federica Bellerba Riccardo Santamaria Riccardo Santamaria Giulia Marvaso Giulia Marvaso Lars Johannes Isaksson Sara Gandini Anna Starzyńska Maria Cristina Leonardi Roberto Orecchia Daniela Alterio Barbara Alicja Jereczek-Fossa Barbara Alicja Jereczek-Fossa Machine Learning for Head and Neck Cancer: A Safe Bet?—A Clinically Oriented Systematic Review for the Radiation Oncologist Frontiers in Oncology systematic review artificial intelligence machine learning radiotherapy head and neck cancer |
| title | Machine Learning for Head and Neck Cancer: A Safe Bet?—A Clinically Oriented Systematic Review for the Radiation Oncologist |
| title_full | Machine Learning for Head and Neck Cancer: A Safe Bet?—A Clinically Oriented Systematic Review for the Radiation Oncologist |
| title_fullStr | Machine Learning for Head and Neck Cancer: A Safe Bet?—A Clinically Oriented Systematic Review for the Radiation Oncologist |
| title_full_unstemmed | Machine Learning for Head and Neck Cancer: A Safe Bet?—A Clinically Oriented Systematic Review for the Radiation Oncologist |
| title_short | Machine Learning for Head and Neck Cancer: A Safe Bet?—A Clinically Oriented Systematic Review for the Radiation Oncologist |
| title_sort | machine learning for head and neck cancer a safe bet a clinically oriented systematic review for the radiation oncologist |
| topic | systematic review artificial intelligence machine learning radiotherapy head and neck cancer |
| url | https://www.frontiersin.org/articles/10.3389/fonc.2021.772663/full |
| work_keys_str_mv | AT stefaniavolpe machinelearningforheadandneckcancerasafebetaclinicallyorientedsystematicreviewfortheradiationoncologist AT stefaniavolpe machinelearningforheadandneckcancerasafebetaclinicallyorientedsystematicreviewfortheradiationoncologist AT matteopepa machinelearningforheadandneckcancerasafebetaclinicallyorientedsystematicreviewfortheradiationoncologist AT mattiazaffaroni machinelearningforheadandneckcancerasafebetaclinicallyorientedsystematicreviewfortheradiationoncologist AT federicabellerba machinelearningforheadandneckcancerasafebetaclinicallyorientedsystematicreviewfortheradiationoncologist AT riccardosantamaria machinelearningforheadandneckcancerasafebetaclinicallyorientedsystematicreviewfortheradiationoncologist AT riccardosantamaria machinelearningforheadandneckcancerasafebetaclinicallyorientedsystematicreviewfortheradiationoncologist AT giuliamarvaso machinelearningforheadandneckcancerasafebetaclinicallyorientedsystematicreviewfortheradiationoncologist AT giuliamarvaso machinelearningforheadandneckcancerasafebetaclinicallyorientedsystematicreviewfortheradiationoncologist AT larsjohannesisaksson machinelearningforheadandneckcancerasafebetaclinicallyorientedsystematicreviewfortheradiationoncologist AT saragandini machinelearningforheadandneckcancerasafebetaclinicallyorientedsystematicreviewfortheradiationoncologist AT annastarzynska machinelearningforheadandneckcancerasafebetaclinicallyorientedsystematicreviewfortheradiationoncologist AT mariacristinaleonardi machinelearningforheadandneckcancerasafebetaclinicallyorientedsystematicreviewfortheradiationoncologist AT robertoorecchia machinelearningforheadandneckcancerasafebetaclinicallyorientedsystematicreviewfortheradiationoncologist AT danielaalterio machinelearningforheadandneckcancerasafebetaclinicallyorientedsystematicreviewfortheradiationoncologist AT barbaraalicjajereczekfossa machinelearningforheadandneckcancerasafebetaclinicallyorientedsystematicreviewfortheradiationoncologist AT barbaraalicjajereczekfossa machinelearningforheadandneckcancerasafebetaclinicallyorientedsystematicreviewfortheradiationoncologist |