Semantic Segmentation of iPS Cells: Case Study on Model Complexity in Biomedical Imaging
This work addresses the challenge of accurate and robust segmentation for biomedical imaging in regenerative medicine, indicating that incremental adaptations of existing methods can be sufficient for domain-specific applications.
The study tackled the problem of segmenting induced pluripotent stem (iPS) cell colonies in medical images, showing that a configured DeepLabv3 model outperformed larger foundation models like SAM2 and MedSAM2 under experimental conditions, suggesting simpler models can be more effective for specialized tasks with subtle boundaries.
Medical image segmentation requires not only accuracy but also robustness under challenging imaging conditions. In this study, we show that a carefully configured DeepLabv3 model can achieve high performance in segmenting induced pluripotent stem (iPS) cell colonies, and, under our experimental conditions, outperforms large-scale foundation models such as SAM2 and its medical variant MedSAM2 without structural modifications. These results suggest that, for specialized tasks characterized by subtle, low-contrast boundaries, increased model complexity does not necessarily translate to better performance. Our work revisits the assumption that ever-larger and more generalized architectures are always preferable, and provides evidence that appropriately adapted, simpler models may offer strong accuracy and practical reliability in domain-specific biomedical applications. We also offer an open-source implementation that includes strategies for small datasets and domain-specific encoding, with the aim of supporting further advances in semantic segmentation for regenerative medicine and related fields.