Improving 3D deep learning segmentation with biophysically motivated cell synthesis
This addresses the bottleneck of time-consuming manual annotation for biomedical researchers using 3D cell culture models, offering an incremental improvement in synthetic data generation.
The paper tackled the problem of generating high-quality 3D training data for cell segmentation by introducing a framework that integrates biophysical modeling for realistic cell synthesis, resulting in synthetic data that outperforms manual annotation and pretrained models in segmentation performance.
Biomedical research increasingly relies on 3D cell culture models and AI-based analysis can potentially facilitate a detailed and accurate feature extraction on a single-cell level. However, this requires for a precise segmentation of 3D cell datasets, which in turn demands high-quality ground truth for training. Manual annotation, the gold standard for ground truth data, is too time-consuming and thus not feasible for the generation of large 3D training datasets. To address this, we present a novel framework for generating 3D training data, which integrates biophysical modeling for realistic cell shape and alignment. Our approach allows the in silico generation of coherent membrane and nuclei signals, that enable the training of segmentation models utilizing both channels for improved performance. Furthermore, we present a new GAN training scheme that generates not only image data but also matching labels. Quantitative evaluation shows superior performance of biophysical motivated synthetic training data, even outperforming manual annotation and pretrained models. This underscores the potential of incorporating biophysical modeling for enhancing synthetic training data quality.