Artificial Intelligence for Response Assessment in Neuro Oncology (AI-RANO), part 2: recommendations for standardisation, validation, and good clinical practice

Spyridon Bakas; Philipp Vollmuth; Norbert Galldiks; Thomas c Booth; Hugo j w l Aerts; Wenya linda Bi; Benedikt Wiestler; Pallavi Tiwari; Sarthak Pati; Ujjwal Baid; Evan Calabrese; Philipp Lohmann; Martha Nowosielski; Rajan Jain; Rivka Colen; Marwa Ismail; Ghulam Rasool; Janine m Lupo; Hamed Akbari; Joerg c Tonn; David Macdonald; Michael Vogelbaum; Susan m Chang; Christos Davatzikos; Javier e Villanueva-Meyer; Raymond y Huang

doi:10.1016/S1470-2045(24)00315-2

Artificial Intelligence for Response Assessment in Neuro Oncology (AI-RANO), part 2: recommendations for standardisation, validation, and good clinical practice

Spyridon Bakas, Philipp Vollmuth, Norbert Galldiks, Thomas c Booth, Hugo j w l Aerts, Wenya linda Bi, Benedikt Wiestler, Pallavi Tiwari, Sarthak Pati, Ujjwal Baid, Evan Calabrese, Philipp Lohmann, Martha Nowosielski, Rajan Jain, Rivka Colen, Marwa Ismail, Ghulam Rasool, Janine m Lupo, Hamed Akbari, Joerg c TonnDavid Macdonald, Michael Vogelbaum, Susan m Chang, Christos Davatzikos, Javier e Villanueva-Meyer, Raymond y Huang

Cancer Imaging

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

6 Citations (Scopus)

Abstract

Technological advancements have enabled the extended investigation, development, and application of computational approaches in various domains, including health care. A burgeoning number of diagnostic, predictive, prognostic, and monitoring biomarkers are continuously being explored to improve clinical decision making in neuro-oncology. These advancements describe the increasing incorporation of artificial intelligence (AI) algorithms, including the use of radiomics. However, the broad applicability and clinical translation of AI are restricted by concerns about generalisability, reproducibility, scalability, and validation. This Policy Review intends to serve as the leading resource of recommendations for the standardisation and good clinical practice of AI approaches in health care, particularly in neuro-oncology. To this end, we investigate the repeatability, reproducibility, and stability of AI in response assessment in neuro-oncology in studies on factors affecting such computational approaches, and in publicly available open-source data and computational software tools facilitating these goals. The pathway for standardisation and validation of these approaches is discussed with the view of trustworthy AI enabling the next generation of clinical trials. We conclude with an outlook on the future of AI-enabled neuro-oncology.

Original language	English
Pages (from-to)	e589-e601
Journal	The Lancet Oncology
Volume	25
Issue number	11
Early online date	28 Oct 2024
DOIs	https://doi.org/10.1016/S1470-2045(24)00315-2
Publication status	Published - 1 Nov 2024

Access to Document

10.1016/S1470-2045(24)00315-2

https://linkinghub.elsevier.com/retrieve/pii/S1470204524003152

Cite this

Bakas, S., Vollmuth, P., Galldiks, N., Booth, T. C., Aerts, H. J. W. L., Bi, W. L., Wiestler, B., Tiwari, P., Pati, S., Baid, U., Calabrese, E., Lohmann, P., Nowosielski, M., Jain, R., Colen, R., Ismail, M., Rasool, G., Lupo, J. M., Akbari, H., ... Huang, R. Y. (2024). Artificial Intelligence for Response Assessment in Neuro Oncology (AI-RANO), part 2: recommendations for standardisation, validation, and good clinical practice. The Lancet Oncology, 25(11), e589-e601. https://doi.org/10.1016/S1470-2045(24)00315-2

@article{a6862afd6b644ff38bcb1994faea291b,

title = "Artificial Intelligence for Response Assessment in Neuro Oncology (AI-RANO), part 2: recommendations for standardisation, validation, and good clinical practice",

abstract = "Technological advancements have enabled the extended investigation, development, and application of computational approaches in various domains, including health care. A burgeoning number of diagnostic, predictive, prognostic, and monitoring biomarkers are continuously being explored to improve clinical decision making in neuro-oncology. These advancements describe the increasing incorporation of artificial intelligence (AI) algorithms, including the use of radiomics. However, the broad applicability and clinical translation of AI are restricted by concerns about generalisability, reproducibility, scalability, and validation. This Policy Review intends to serve as the leading resource of recommendations for the standardisation and good clinical practice of AI approaches in health care, particularly in neuro-oncology. To this end, we investigate the repeatability, reproducibility, and stability of AI in response assessment in neuro-oncology in studies on factors affecting such computational approaches, and in publicly available open-source data and computational software tools facilitating these goals. The pathway for standardisation and validation of these approaches is discussed with the view of trustworthy AI enabling the next generation of clinical trials. We conclude with an outlook on the future of AI-enabled neuro-oncology.",

author = "Spyridon Bakas and Philipp Vollmuth and Norbert Galldiks and Booth, {Thomas c} and Aerts, {Hugo j w l} and Bi, {Wenya linda} and Benedikt Wiestler and Pallavi Tiwari and Sarthak Pati and Ujjwal Baid and Evan Calabrese and Philipp Lohmann and Martha Nowosielski and Rajan Jain and Rivka Colen and Marwa Ismail and Ghulam Rasool and Lupo, {Janine m} and Hamed Akbari and Tonn, {Joerg c} and David Macdonald and Michael Vogelbaum and Chang, {Susan m} and Christos Davatzikos and Villanueva-Meyer, {Javier e} and Huang, {Raymond y}",

note = "Publisher Copyright: {\textcopyright} 2024 Elsevier Ltd",

year = "2024",

month = nov,

day = "1",

doi = "10.1016/S1470-2045(24)00315-2",

language = "English",

volume = "25",

pages = "e589--e601",

journal = "The Lancet Oncology",

issn = "1470-2045",

publisher = "Lancet Publishing Group",

number = "11",

}

Bakas, S, Vollmuth, P, Galldiks, N, Booth, TC, Aerts, HJWL, Bi, WL, Wiestler, B, Tiwari, P, Pati, S, Baid, U, Calabrese, E, Lohmann, P, Nowosielski, M, Jain, R, Colen, R, Ismail, M, Rasool, G, Lupo, JM, Akbari, H, Tonn, JC, Macdonald, D, Vogelbaum, M, Chang, SM, Davatzikos, C, Villanueva-Meyer, JE & Huang, RY 2024, 'Artificial Intelligence for Response Assessment in Neuro Oncology (AI-RANO), part 2: recommendations for standardisation, validation, and good clinical practice', The Lancet Oncology, vol. 25, no. 11, pp. e589-e601. https://doi.org/10.1016/S1470-2045(24)00315-2

TY - JOUR

T1 - Artificial Intelligence for Response Assessment in Neuro Oncology (AI-RANO), part 2: recommendations for standardisation, validation, and good clinical practice

AU - Bakas, Spyridon

AU - Vollmuth, Philipp

AU - Galldiks, Norbert

AU - Booth, Thomas c

AU - Aerts, Hugo j w l

AU - Bi, Wenya linda

AU - Wiestler, Benedikt

AU - Tiwari, Pallavi

AU - Pati, Sarthak

AU - Baid, Ujjwal

AU - Calabrese, Evan

AU - Lohmann, Philipp

AU - Nowosielski, Martha

AU - Jain, Rajan

AU - Colen, Rivka

AU - Ismail, Marwa

AU - Rasool, Ghulam

AU - Lupo, Janine m

AU - Akbari, Hamed

AU - Tonn, Joerg c

AU - Macdonald, David

AU - Vogelbaum, Michael

AU - Chang, Susan m

AU - Davatzikos, Christos

AU - Villanueva-Meyer, Javier e

AU - Huang, Raymond y

PY - 2024/11/1

Y1 - 2024/11/1

N2 - Technological advancements have enabled the extended investigation, development, and application of computational approaches in various domains, including health care. A burgeoning number of diagnostic, predictive, prognostic, and monitoring biomarkers are continuously being explored to improve clinical decision making in neuro-oncology. These advancements describe the increasing incorporation of artificial intelligence (AI) algorithms, including the use of radiomics. However, the broad applicability and clinical translation of AI are restricted by concerns about generalisability, reproducibility, scalability, and validation. This Policy Review intends to serve as the leading resource of recommendations for the standardisation and good clinical practice of AI approaches in health care, particularly in neuro-oncology. To this end, we investigate the repeatability, reproducibility, and stability of AI in response assessment in neuro-oncology in studies on factors affecting such computational approaches, and in publicly available open-source data and computational software tools facilitating these goals. The pathway for standardisation and validation of these approaches is discussed with the view of trustworthy AI enabling the next generation of clinical trials. We conclude with an outlook on the future of AI-enabled neuro-oncology.

AB - Technological advancements have enabled the extended investigation, development, and application of computational approaches in various domains, including health care. A burgeoning number of diagnostic, predictive, prognostic, and monitoring biomarkers are continuously being explored to improve clinical decision making in neuro-oncology. These advancements describe the increasing incorporation of artificial intelligence (AI) algorithms, including the use of radiomics. However, the broad applicability and clinical translation of AI are restricted by concerns about generalisability, reproducibility, scalability, and validation. This Policy Review intends to serve as the leading resource of recommendations for the standardisation and good clinical practice of AI approaches in health care, particularly in neuro-oncology. To this end, we investigate the repeatability, reproducibility, and stability of AI in response assessment in neuro-oncology in studies on factors affecting such computational approaches, and in publicly available open-source data and computational software tools facilitating these goals. The pathway for standardisation and validation of these approaches is discussed with the view of trustworthy AI enabling the next generation of clinical trials. We conclude with an outlook on the future of AI-enabled neuro-oncology.

UR - http://www.scopus.com/inward/record.url?scp=85207374676&partnerID=8YFLogxK

U2 - 10.1016/S1470-2045(24)00315-2

DO - 10.1016/S1470-2045(24)00315-2

M3 - Article

SN - 1470-2045

VL - 25

SP - e589-e601

JO - The Lancet Oncology

JF - The Lancet Oncology

IS - 11

ER -

Artificial Intelligence for Response Assessment in Neuro Oncology (AI-RANO), part 2: recommendations for standardisation, validation, and good clinical practice

Abstract

Access to Document

Other files and links

Fingerprint

Cite this