Producción CyT
Clinical Image-Based Procedures, Fairness of AI in Medical Imaging, and Ethical and Philosophical Issues in Medical Imaging
Libro
Autoría:
Stefan Wesarg ; Esther Puyol Antón ; John S. H. Baxter ; Marius Erdt ; Klaus Drechsler ; Cristina Oyarzun Laura ; Moti Freiman ; Yufei Chen ; Islem Rekik ; Roy Eagleson ; Aasa Feragen ; Andrew P. King ; Veronika Cheplygina ; Melani Ganz-Benjaminsen ; FERRANTE, ENZO ; Ben Glocker ; Daniel Moyer ; Eike PetersenFecha:
2023Editorial y Lugar de Edición:
Springer NatureISBN:
978-3-031-45249-9Resumen *
During the last few years, research in the area of fairness in machine learning has highlighted the potential risks associated with biased systems in various application sce- narios. A large body of research studies has shown that machine learning systems can be biased in terms of demographic attributes like gender, ethnicity, age or geographical distribution, presenting unequal behaviour on disadvantaged or underrepresented sub- populations. Even though fairness in machine learning has been extensively studied in decision-making scenarios like job hiring, credit scoring and criminal justice, it wasn’t until recently that researchers started to study and characterize bias and design mitiga- tion strategies for systems in medical image computing (MIC) and computer assisted interventions (CAI).Aiming to continue and expand the discussion, the Fairness of AI in Medical Imaging (FAIMI) MICCAI 2023 workshop was devoted to creating awareness about potential fairness issues that can emerge in the context of machine learning. Moreover, our goal was also to bring together researchers from the MIC, CAI, machine learning and fairness communities who use and develop models for the analysis of biomedical images and encourage discussions about bias assessment and mitigation strategies. To this end, our workshop was divided into three sessions (1) a presentation from an expert keynote speaker; (2) oral presentations provided by the authors of accepted papers; and (3) poster presentations. All accepted papers were presented as posters by their authors during the workshop and the attendees also voted for the recipient of the Best Paper Award.To select the peer-reviewed papers we leveraged the CMT tool. We applied a double- blind review process and had each submitted paper reviewed by three independent reviewers. The papers were assigned to reviewers taking into account (and avoiding) potential conflicts of interest and recent work collaborations between peers. Of the 20 papers submitted, 19 papers were accepted for publication. The best four regular papers were invited to give oral presentations.This is the first time that MICCAI has had a workshop on Fairness in AI for medical imaging, and we would like to thank all authors, reviewers and organizers for their time, efforts, contributions and support in making FAIMI 2023 a successful event.October 2023Esther Puyol-Antón Aasa Feragen Andrew P. King Enzo Ferrante Veronika Cheplygina Melanie Ganz Ben Glocker Daniel Moyer Eike Petersen Información suministrada por el agente en SIGEVAPalabras Clave
machine learningfairnessmedical imaging