Saved in:
Bibliographic Details
Main Authors: Zhang, Maoquan, Raytchev, Bisser, Sun, Xiujuan
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2507.21608
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866909710480834560
author Zhang, Maoquan
Raytchev, Bisser
Sun, Xiujuan
author_facet Zhang, Maoquan
Raytchev, Bisser
Sun, Xiujuan
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2507_21608
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Semantic Segmentation of iPS Cells: Case Study on Model Complexity in Biomedical Imaging
Zhang, Maoquan
Raytchev, Bisser
Sun, Xiujuan
Computer Vision and Pattern Recognition
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.
title Semantic Segmentation of iPS Cells: Case Study on Model Complexity in Biomedical Imaging
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2507.21608