Few-shot adaptation for morphology-independent cell instance segmentation
This addresses the problem of reducing annotation and computational costs for researchers in microscopy and biomedical fields, though it is incremental as it builds on existing domain adaptation methods.
The paper tackles the challenge of maintaining high accuracy in cell instance segmentation across variable microscopy data, especially for elongated and non-convex cells like bacteria, by proposing a few-shot domain adaptation approach that requires only 1-5 annotated cells and significantly boosts accuracy on challenging datasets.
Microscopy data collections are becoming larger and more frequent. Accurate and precise quantitative analysis tools like cell instance segmentation are necessary to benefit from them. This is challenging due to the variability in the data, which requires retraining the segmentation model to maintain high accuracy on new collections. This is needed especially for segmenting cells with elongated and non-convex morphology like bacteria. We propose to reduce the amount of annotation and computing power needed for retraining the model by introducing a few-shot domain adaptation approach that requires annotating only one to five cells of the new data to process and that quickly adapts the model to maintain high accuracy. Our results show a significant boost in accuracy after adaptation to very challenging bacteria datasets.