We are pleased to share the poster titled Pretrained Vision Models for Predicting High-Risk Breast Cancer Stage authored by Nightingale community members Bonaventure F. P. Dossou, Yeno Gbenou, and Miglanche Ghomsi.
The poster was presented at the 2023 ICLR First Workshop on Machine Learning & Global Health, a hybrid conference held Kigali, Rwanda in May 2023.
The authors describe: “In this paper, using the Nightingale Open Science dataset of digital pathology (breast biopsy) images, we leverage the capabilities of pre-trained computer vision models for the breast cancer stage prediction task. While individual models achieve decent performances and demonstrate usefulness to the task at hand, we find out that the predictions of an ensemble model are more efficient.”
Congratulations to the authors!
This research was done on the Nightingale platform using the High Risk Breast Cancer data set from Providence St. Joseph Health. The data set was published with generous financial support from the Gordon and Betty Moore Foundation’s Diagnostic Excellence Initiative, and in-kind support from Hammamatsu to digitize the biopsy slides. We thank them for their support.