MEDIAR: Harmony of Data-Centric and Model-Centric for Multi-Modality Microscopy
This work addresses the challenge of cell instance segmentation for computational biology in multi-modality environments, representing an incremental improvement.
The authors tackled the problem of limited generality in cell segmentation algorithms under multi-modality microscopy by proposing MEDIAR, a holistic pipeline that harmonizes data-centric and model-centric approaches, achieving a 0.9067 F1-score on validation data.
Cell segmentation is a fundamental task for computational biology analysis. Identifying the cell instances is often the first step in various downstream biomedical studies. However, many cell segmentation algorithms, including the recently emerging deep learning-based methods, still show limited generality under the multi-modality environment. Weakly Supervised Cell Segmentation in Multi-modality High-Resolution Microscopy Images was hosted at NeurIPS 2022 to tackle this problem. We propose MEDIAR, a holistic pipeline for cell instance segmentation under multi-modality in this challenge. MEDIAR harmonizes data-centric and model-centric approaches as the learning and inference strategies, achieving a 0.9067 F1-score at the validation phase while satisfying the time budget. To facilitate subsequent research, we provide the source code and trained model as open-source: https://github.com/Lee-Gihun/MEDIAR