Systematic evaluation of computational methods for cell segmentation
Open Access
- 7 January 2026
- journal article
- Published by Oxford University Press (OUP) in Briefings in Bioinformatics
- Vol. 27 (1)
Abstract
Cell segmentation plays a crucial role in elucidating cell structure and function, understanding disease mechanisms, and aiding pathological diagnosis. Current surveys primarily categorize methods by their technical evolution stages, which may not fully capture the paradigm shift brought by deep learning. Moreover, their evaluation scope is largely confined to image-only approaches, overlooking the significant potential of multimodal data in enhancing cell/nucleus segmentation performance. Therefore, we propose a dual-dimensional classification framework for deep learning methods. It categorizes such methods into two types: task-oriented (e.g. semantic or instance segmentation) and data-oriented (e.g. single or multimodal inputs). Based on this, we systematically classify and summarize methods across various segmentation tasks and imaging modalities. We also develop a benchmark test that covers both single-modal and multimodal methods. This test uses five diverse datasets, among which four are from conventional microscopy and one integrates sequencing with image data. Furthermore, it assesses seven algorithms based on three dimensions: effectiveness, robustness, and efficiency. Key findings indicate that deep learning models generally outperform traditional algorithms, with their advantage becoming more pronounced when image data is integrated with sequencing information.Keywords
Funding Information
- National Science and Technology Major Project of China (2022ZD0117702)
- National Natural Science Foundation of China (T2325009)
- National Natural Science Foundation of China (62032007)
- National Natural Science Foundation of China (U24A20370)
- National Natural Science Foundation of China (32270789)
- National Natural Science Foundation of China (62402144)
- National Natural Science Foundation of China (32400643)
- National Natural Science Foundation of China (32470689)
- National Natural Science Foundation of China (32470691)
- National Natural Science Foundation of China (T2495273)
- National Natural Science Foundation of China (32360172)
- New Era Longjiang Outstanding Master’s and Doctoral Thesis Project (LJYXL2024–020)
This publication has 149 references indexed in Scilit:
- A Rapid and Efficient 2D/3D Nuclear Segmentation Method for Analysis of Early Mouse Embryo and Stem Cell Image DataStem Cell Reports, 2014
- Semiautomatic White Blood Cell Segmentation Based on Multiscale AnalysisIEEE Journal of Biomedical and Health Informatics, 2013
- A New Framework for Particle Detection in Low-SNR Fluorescence Live-Cell Images and Its Application for Improved Particle TrackingIEEE Transactions on Biomedical Engineering, 2012
- Extracting, recognizing, and counting white blood cells from microscopic images by using complex-valued neural networksJournal of Medical Signals & Sensors, 2012
- Coupled minimum-cost flow cell tracking for high-throughput quantitative analysisMedical Image Analysis, 2011
- Image segmentation and dynamic lineage analysis in single‐cell fluorescence microscopyCytometry Part A, 2009
- A Unified Framework for Automated 3-D Segmentation of Surface-Stained Living Cells and a Comprehensive Segmentation EvaluationIEEE Transactions on Medical Imaging, 2009
- Laplacian Operator-Based Edge DetectorsIEEE Transactions on Pattern Analysis and Machine Intelligence, 2007
- Supervised Learning-Based Cell Image Segmentation for P53 ImmunohistochemistryIEEE Transactions on Biomedical Engineering, 2006
- Atlas Guided Identification of Brain Structures by Combining 3D Segmentation and SVM ClassificationLecture Notes in Computer Science, 2006