Artificial Intelligence for Response Assessment in Neuro Oncology (AI-RANO), part 2: recommendations for standardisation, validation, and good clinical practice - 29/10/24

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

Spyridon Bakas, PhD ^a,^b,^c,^d,^e,^f,⁎ , Philipp Vollmuth, ProfMD MBA ^g,^h,ⁱ, Norbert Galldiks, ProfMD ^j,^k, Thomas C Booth, MD PhD ^l,^m, Hugo J W L Aerts, PhD ^n,^p,^q, Wenya Linda Bi, MD PhD ^o, Benedikt Wiestler, MD PhD ^r, Pallavi Tiwari, PhD ^s, Sarthak Pati, MSc ^a, Ujjwal Baid, PhD ^a,^b,^e, Evan Calabrese, MD PhD ^t, Philipp Lohmann, PhD ^j,^w, Martha Nowosielski, MD PhD ^x, Rajan Jain, ProfMD ^y, Rivka Colen, ProfMD ^z, Marwa Ismail, PhD ^s, Ghulam Rasool, PhD ^ag, Janine M Lupo, ProfPhD ^u, Hamed Akbari, MD PhD ^aa, Joerg C Tonn, ProfMD ^ab,^ac, David Macdonald, ProfMD ^ad, Michael Vogelbaum, ProfMD PhD ^ae,^af,^ah, Susan M Chang, ProfMD ^v, Christos Davatzikos, ProfPhD ^ai,^aj, Javier E Villanueva-Meyer, MD ^u, Raymond Y Huang, MD PhD ⁿ
for the
Response Assessment in Neuro Oncology (RANO) group

^a Department of Pathology & Laboratory Medicine, Division of Computational Pathology, Indiana University, Indianopolis, IN, USA

^b Department of Radiology & Imaging Sciences, School of Medicine, Indiana University, Indianapolis, IN, USA

^c Department of Neurological Surgery, School of Medicine, Indiana University, Indianapolis, IN, USA

^d Department of Biostatistics and Health Data Science, School of Medicine, Indiana University, Indianapolis, IN, USA

^e Indiana University Melvin and Bren Simon Comprehensive Cancer Center, Indianopolis, IN, USA

^f Department of Computer Science, Luddy School of Informatics, Computing, and Engineering, Indiana University, Indianapolis, IN, USA

^g Division for Computational Radiology and Clinical AI, Clinic for Neuroradiology, University Hospital Bonn, Bonn, Germany

^h Faculty of Medicine, University of Bonn, Bonn, Germany

ⁱ Division for Medical Image Computing, German Cancer Research Center, Heidelberg, Germany

^j Department of Neurology, Faculty of Medicine and University Hospital Cologne, Cologne, Germany

^k Institute of Neuroscience and Medicine, Research Center Juelich, Juelich, Germany

^l School of Biomedical Engineering & Imaging Sciences, King’s College London, London, UK

^m Department of Neuroradiology, King’s College Hospital NHS Foundation Trust, London, UK

ⁿ Department of Radiology, Brigham and Women’s Hospital, Harvard Medical School, Boston, MA, USA

^o Department of Neurosurgery, Brigham and Women’s Hospital, Harvard Medical School, Boston, MA, USA

^p Artificial Intelligence in Medicine Program, Mass General Brigham, Harvard Medical School, Boston, MA, USA

^q Radiology and Nuclear Medicine, Maastricht University, Maastricht, Netherlands

^r Department of Neuroradiology, University Hospital, Technical University of Munich, Munich, Germany

^s Department of Radiology, School of Medicine and Public Health, University of Wisconsin, Madison, WI, USA

^t Department of Radiology, School of Medicine, Duke University, Durham, NC, USA

^u Department of Radiology and Biomedical Imaging, University of California San Francisco, San Francisco, CA, USA

^v Department of Neurological Surgery, Division of Neuro-Oncology, University of California San Francisco, San Francisco, CA, USA

^w Department of Nuclear Medicine, University Hospital RWTH Aachen, Aachen, Germany

^x Department of Neurology, Medical University Innsbruck, Innsbruck, Austria

^y Department of Radiology and Department of Neurosurgery, NYU Grossman School of Medicine, New York, NY, USA

^z Department of Radiology, Neuroradiology Division, Center for Artificial Intelligence Innovation in Medical Imaging, University of Pittsburgh, Pittsburgh, PA, USA

^aa Department of Bioengineering, School of Engineering, Santa Clara University, Santa Clara, CA, USA

^ab Department of Neurosurgery, Ludwig-Maximilians-University, Munich, Germany

^ac German Cancer Consortium, Partner Site Munich, Munich, Germany

^ad London Regional Cancer Programme, London, ON, Canada

^ae Department of Neuro-Oncology, H Lee Moffitt Cancer Center & Research Institute, Tampa, FL, USA

^af Department of Neurosurgery, H Lee Moffitt Cancer Center & Research Institute, Tampa, FL, USA

^ag Department of Machine Learning, H Lee Moffitt Cancer Center & Research Institute, Tampa, FL, USA

^ah H Lee Moffitt Cancer Center & Research Institute, Tampa, FL, USA

^ai Department of Radiology, Perelman School of Medicine, University of Pennsylvania, Philadelphia, PA, USA

^aj Center for Artificial Intelligence for Integrated Diagnostics and Center for Biomedical Image Computing and Analytics, University of Pennsylvania, Philadelphia, PA, USA

^* Correspondence to: Dr Spyridon Bakas, Department of Pathology & Laboratory Medicine, Division of Computational Pathology, Indiana University, Indianopolis, IN 46202, USA Department of Pathology & Laboratory Medicine Division of Computational Pathology Indiana University Indianopolis IN 46202 USA

Summary

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.

Le texte complet de cet article est disponible en PDF.

Plan

Introduction

Factors affecting the repeatability, reproducibility, and stability of health-care AI approaches

Patient population selection

Reference labels and standards

Image modalities and acquisition

Image preprocessing, harmonisation, and domain adaptation

Delineation of tumour boundaries

Parameterisation of feature extraction

Accounting for heterogeneity of molecular status

Towards standardisation and validation of AI models for clinical trials

Resources available for reproducible quantitative analyses

Future outlook

Conclusion

Contributors

Export

Vol 25 - N° 11

P. e589-e601 - novembre 2024 Retour au numéro

Article précédent

Artificial Intelligence for Response Assessment in Neuro Oncology (AI-RANO), part 1: review of current advancements
Javier E Villanueva-Meyer, Spyridon Bakas, Pallavi Tiwari, Janine M Lupo, Evan Calabrese, Christos Davatzikos, Wenya Linda Bi, Marwa Ismail, Hamed Akbari, Philipp Lohmann, Thomas C Booth, Benedikt Wiestler, Hugo J W L Aerts, Ghulam Rasool, Joerg C Tonn, Martha Nowosielski, Rajan Jain, Rivka R Colen, Sarthak Pati, Ujjwal Baid, Philipp Vollmuth, David Macdonald, Michael A Vogelbaum, Susan M Chang, Raymond Y Huang, Norbert Galldiks, Response Assessment in Neuro Oncology (RANO) group

| Article suivant

Fertility-sparing treatment and follow-up in patients with cervical cancer, ovarian cancer, and borderline ovarian tumours: guidelines from ESGO, ESHRE, and ESGE
Philippe Morice, Giovanni Scambia, Nadeem R Abu-Rustum, Maribel Acien, Alessandro Arena, Sara Brucker, Ying Cheong, Pierre Collinet, Francesco Fanfani, Francesca Filippi, Ane Gerda Zahl Eriksson, Sebastien Gouy, Philipp Harter, Xavier Matias-Guiu, George Pados, Maja Pakiz, Denis Querleu, Alexandros Rodolakis, Christine Rousset-Jablonski, Artem Stepanyan, Antonia Carla Testa, Kirsten Tryde Macklon, Dimitrios Tsolakidis, Michel De Vos, François Planchamp, Michaël Grynberg

Bienvenue sur EM-consulte, la référence des professionnels de santé.
L’accès au texte intégral de cet article nécessite un abonnement.

Déjà abonné à cette revue ?

connectez-vous ou créez un compte

Artificial Intelligence for Response Assessment in Neuro Oncology (AI-RANO), part 2: recommendations for standardisation, validation, and good clinical practice - 29/10/24

Summary

Plan

Export citations

Fichier

Contenu

Accès rapides

Mon compte

Aide & support

Plateformes Elsevier Masson

Déclaration CNIL