Learning to segment clustered amoeboid cells from brightfield microscopy via multi-task learning with adaptive weight selection
This addresses the challenge of automated cell segmentation in life sciences, particularly for brightfield microscopy with poor contrast, offering a solution for applications requiring high accuracy without manual intervention.
The paper tackles the problem of segmenting individual cells in brightfield microscopy images, especially when cells are clustered, by introducing a supervised multi-task learning method with adaptive weight selection, achieving a Dice score of 0.93 and improving over recent methods by up to 15.9%.
Detecting and segmenting individual cells from microscopy images is critical to various life science applications. Traditional cell segmentation tools are often ill-suited for applications in brightfield microscopy due to poor contrast and intensity heterogeneity, and only a small subset are applicable to segment cells in a cluster. In this regard, we introduce a novel supervised technique for cell segmentation in a multi-task learning paradigm. A combination of a multi-task loss, based on the region and cell boundary detection, is employed for an improved prediction efficiency of the network. The learning problem is posed in a novel min-max framework which enables adaptive estimation of the hyper-parameters in an automatic fashion. The region and cell boundary predictions are combined via morphological operations and active contour model to segment individual cells. The proposed methodology is particularly suited to segment touching cells from brightfield microscopy images without manual interventions. Quantitatively, we observe an overall Dice score of 0.93 on the validation set, which is an improvement of over 15.9% on a recent unsupervised method, and outperforms the popular supervised U-net algorithm by at least $5.8\%$ on average.