The Big Data Africa School aims to introduce fundamental data science tools & techniques to talented young science and engineering graduates across various disciplines interested in developing their skills and knowledge in working efficiently on extremely large datasets in any research environment. The 4th Big Data Africa School allowed students to work on real-life datasets in healthcare, focusing on biomedical imaging.
The students worked in teams and developed data and ML pipelines around problems like model interpretability, segmentation, data augmentation, 2D to 3D reconstruction, and out-of-distribution detection across different biomedical datasets (dermatoscopic and blood microscope images, breast mammograms, cardiovascular magnetic resonance, and X-rays).
During the BDAS 2023, students learned and developed state-of-the-art data and modeling techniques to address different problems in the medical imagining domain. Each team presented daily updates and preliminary results. Ultimately, each team pitched their work (20′ talks), from defining the problem statement, approach, experimental setup, and evaluation to discussing limitations and lessons learned. Additionally, the school included introductory lectures to Python for Data Science and Machine Learning, Community talks, invited technical talks in medical imaging, and communication skill sessions.