BIAS: Transparent reporting of biomedical image analysis challenges

Lena Maier-Hein (1) , Annika Reinke (1) , Michal Kozubek (2) , Anne L Martel (3) , Tal Arbel (4) , Matthias Eisenmann (1) , Allan Hanbury (5) , Pierre Jannin (6) , Henning Muller (7, 8) , Sinan Onogur (1) , Julio Saez-Rodriguez (9) , Bram van Ginneken (10) , Annette Kopp-Schneider (1) , Bennett A Landman (11)

1 DKFZ - German Cancer Research Center - Deutsches Krebsforschungszentrum [Heidelberg]
2 MUNI - Masaryk University [Brno]
3 University of Toronto
4 McGill University = Université McGill [Montréal, Canada]
5 TU Wien - Vienna University of Technology = Technische Universität Wien
6 LTSI - Laboratoire Traitement du Signal et de l'Image
7 HES-SO - University of Applied Sciences and Arts of Western Switzerland
8 UNIGE - Université de Genève = University of Geneva
9 Universität Heidelberg [Heidelberg] = Heidelberg University
10 Radboud University Medical Center [Nijmegen]
11 Vanderbilt University [Nashville]

The number of biomedical image analysis challenges organized per year is steadily increasing. These international competitions have the purpose of benchmarking algorithms on common data sets, typically to identify the best method for a given problem. Recent research, however, revealed that common practice related to challenge reporting does not allow for adequate interpretation and reproducibility of results. To address the discrepancy between the impact of challenges and the quality (control), the Biomedical Image Analysis ChallengeS (BIAS) initiative developed a set of recommendations for the reporting of challenges. The BIAS statement aims to improve the transparency of the reporting of a biomedical image analysis challenge regardless of field of application, image modality or task category assessed. This article describes how the BIAS statement was developed and presents a checklist which authors of biomedical image analysis challenges are encouraged to include in their submission when giving a paper on a challenge into review. The purpose of the checklist is to standardize and facilitate the review process and raise interpretability and reproducibility of challenge results by making relevant information explicit.

Mots clés: Biomedical challenges; Biomedical image analysis; Good scientific practice; Guideline

Domaines: Ingénierie biomédicale

Lena Maier-Hein, Annika Reinke, Michal Kozubek, Anne L Martel, Tal Arbel, et al.. BIAS: Transparent reporting of biomedical image analysis challenges. Medical Image Analysis, 2020, 66, pp.101796. ⟨10.1016/j.media.2020.101796⟩. ⟨hal-02958995⟩