Cross-platform dataset of multiplex fluorescent cellular object image annotations.

Area of Science:

• Computational Biology
• Biomedical Imaging
• Machine Learning

Background:

• Cell segmentation is crucial for single-cell analysis in multiplex imaging but faces challenges.
• Current machine learning segmentation methods require extensive, high-quality training data, which is often unavailable.
• A scarcity of publicly accessible, well-annotated datasets hinders algorithm development and benchmarking.

Purpose of the Study:

• To address the lack of annotated data for cell segmentation in multiplex imaging.
• To provide a valuable resource for developing and validating machine learning algorithms.
• To advance the field of cellular image analysis by enabling community-driven improvements.

Main Methods:

• Collected and curated 105,774 cellular annotations, focusing on tumor and immune cells.
• Utilized over 40 antibody markers across three fluorescent imaging platforms.
• Included data from diverse tissue types and cellular morphologies.

Main Results:

• A comprehensive dataset of oncological cellular annotations was generated.
• The dataset covers a wide range of imaging conditions and biological contexts.
• Annotations were created using accessible techniques to ensure modifiability.

Conclusions:

• The released dataset significantly enhances the availability of annotated data for cell segmentation research.
• This resource is expected to accelerate the development of robust segmentation algorithms for multiplex imaging.
• The community-driven dataset aims to foster innovation in single-cell analysis.