The importance of data science techniques in almost all fields of biomedicine is increasing at an enormous pace. This holds particularly true for the field of biomedical image analysis. While clinical trials are the state-of-the-art methods to assess the effect of new medication in a comparative manner, benchmarking in the field of image analysis is performed by challenges, that aim to assess the performance of multiple algorithms on identical data sets and encourage benchmarking. This talk is devoted to the topic of MICCAI grand challenges and comprises three parts:
(1) Statistics and recent developments: After 15 years of grand biomedical challenges at MICCAI, the MICCAI board has established a working group in 2018 dedicated to analyzing and critically questioning common practice with the goal of bringing challenges to the next level of quality, which was now converted to the board of a special interest group on challenges. The talk will review insights resulting from the activities of the special interest group, review statistics on past challenges, and present the strategy of the MICCAI society to overcome some of the current issues in the future.
(2) Highlights from 2021: The second part of the talk will present interesting findings and surprising insights from the most recent MICCAI challenges. To this end, selected MICCAI 2021 challenges will be highlighted to share exciting results.
(3) Best challenge reviewer awards: In 2018, a review process for challenge proposals was integrated as part of the challenge submission process to increase the quality of MICCAI challenges. This year, we will acknowledge the reviewers’ work with awards for outstanding reviewer performance.
- MICCAI Special Interest Group on Biomedical Image Analysis Challenges (SIG-BIAC): [ Ссылка ]
-Biomedical Image Analysis ChallengeS (BIAS) initiative: [ Ссылка ]&
- Maier-Hein et al. BIAS: Transparent reporting of biomedical image analysis challenges, Med Image Anal 2020: [ Ссылка ]
- Maier-Hein et al. Why rankings of biomedical image analysis competitions should be interpreted with care, Nat Commun 2018: [ Ссылка ]
- Reinke et al. Common Limitations of Image Processing Metrics: A Picture Story. ArXiv 2021: [ Ссылка ]
- Wiesenfarth et al. Methods and open-source toolkit for analyzing and visualizing challenge results. Scientific Reports 2021: [ Ссылка ]
- Isensee et al. nnU-Net: a self-configuring method for deep learning-based biomedical image segmentation, Nat Methods 2021: [ Ссылка ]
