Nightingale, Association for Health Learning & Inference (AHLI) and Providence St. Joseph Health hosted a High Risk Breast Cancer Prediction Contest 1 that ended in January, 2023. We are now pleased to announce the results.
Every year, 40 million women get a mammogram; some go on to have an invasive biopsy to better examine a concerning area. Underneath these routine tests lies a deep—and disturbing—mystery. Since the 1990s, we have found far more ‘cancers’, which has in turn prompted vastly more surgical procedures and chemotherapy. But death rates from metastatic breast cancer have hardly changed.
There is already evidence that algorithms can predict which cancers will metastasize and harm patients on the basis of the biopsy image. Fascinatingly, these algorithms also hone in on features that humans neglect, for example, the nature of the non-cancerous tissue surrounding the tumor. But to date, the datasets linking biopsy images to patient outcomes—metastasis, death—have been far smaller than what is needed to apply modern approaches.
To advance medical knowledge on identifying features of cancers that will metastasize, we launched a machine learning contest to identify the cancer stage from more than 72,000 biopsy slides provided by Providence Oncology. 42 teams entered the contest. Seven of them submitted their results by the deadline. The top 2 submissions as of the interim checkpoint where invited to present at the ML4H conference in November 2022, co-located with NeurIPS in New Orleans. The final results are now in.
We are pleased to announce the top 3 teams that submitted the best solutions in the contest and have won cash prizes totaling $10,000.
Team name: csabAIbio
Team members: András M. Biricz1, Zsolt Bedőházi1,2, Oz Kilim1, István Csabai1
Organization: Eötvös Loránd University (ELTE), Budapest, 1117, Hungary
(1) Eötvös Loránd University (ELTE), Department of Complex Systems in Physics, Budapest, 1117, Hungary
(2) Eötvös Loránd University (ELTE), Doctoral School of Informatics, Budapest, 1117, Hungary
Code on GitHub
Team name/member: Bonaventure Dossou
Organization: McGill University, Mila Quebec AI Institute, Montreal, Quebec, Canada
Code on GitHub
Team name: PKU-Edinburgh
Team members: Yinghao Zhu1, Junyi Gao2,3, Xinze Li1, Yifan He1, Wenqing Wang1, Liantao Ma1
Organizations: (1) Peking University, Beijing, China, (2) University of Edinburgh, Edinburgh, UK, (3) Health Data Research UK, UK
Code on GitHub
Congratulations to the winners and all the participating teams!
To support repeatable science and collaborative research, the winners have open sourced their solutions according to contest rules. We invite healthcare ML researchers worldwide to move the needle forward in our understanding of cancer.
The second phase of this contest is now launched. We invite academic/non-profit healthcare ML researchers worldwide to participate in this contest.