相关实验视频
Updated: Jun 14, 2025

Live Imaging of Mitosis in the Developing Mouse Embryonic Cortex
Published on: June 4, 2014
ConvNext 线粒症识别-你只看一次 (CNMI-YOLO):在数字病理学中进行域适应性和强大的线粒症识别
Yasemin Topuz1, Serdar Yıldız2, Songül Varlı1
1Department of Computer Engineering, Yıldız Technical University, Istanbul, Turkey; Health Institutes of Türkiye, Istanbul, Turkey.
本研究介绍了CNMI-YOLO,这是一种深度学习方法,用于在数字病理图像中准确检测线粒分裂. 它通过增强跨多种数据集的线粒细胞的识别,显著改善了癌症诊断.
科学领域:
- 数字病理学数字病理学
- 计算病理学计算病理学
- 机器学习在瘤学中
背景情况:
- 精确的线粒分裂检测对于癌症诊断和数字病理学的预后至关重要.
- 挑战包括细胞形态变异性和域转移,阻碍模型概括.
- 现有的方法在不同数据源的稳定性方面扎.
研究的目的:
- 开发一个强大的深度学习模型,用于在组织病理图像中准确识别线粒分裂.
- 提高跨不同癌症类型,扫描仪和物种的真菌分裂检测模型的概括能力.
- 通过改进线粒细胞检测来提高癌症诊断和预后.
主要方法:
- 介绍了ConvNext Mitosis识别-你只看一次 (CNMI-YOLO),这是一个两阶段的深度学习方法.
- 使用YOLOv7进行细胞检测,并使用ConvNeXt进行细胞分类.
- 在Mitosis Domain Generalization Challenge 2022数据集和外部测试集上验证了模型.
主要成果:
- CNMI-YOLO在2022年Mitosis域泛化挑战数据集上获得了0.795的优异F1得分.
- 证明了强大的泛化,在黑色素瘤上F1得分为0.783,在肉瘤测试集上为0.759.
- 在精度,回忆和F1分数方面表现优于现有模型,在未见数据上表现强.
结论:
- CNMI-YOLO模型在数字病理学中自动检测线粒变异方面取得了重大进展.
- 该模型表现出强大的稳定性和概括能力,适合于现实世界的临床应用.
- 这种方法有可能提高癌症诊断和预后的准确性和效率.
更多相关视频
08:33Combining Mitotic Cell Synchronization and High Resolution Confocal Microscopy to Study the Role of Multifunctional Cell Cycle Proteins During Mitosis
Published on: December 5, 2017
12:56An Automated Method to Perform The In Vitro Micronucleus Assay using Multispectral Imaging Flow Cytometry
Published on: May 13, 2019
相关概念视频
Mitosis and Cytokinesis
The processes of the cell cycle occur over approximately 24 hours (in typical human cells) and in two major distinguishable stages. The...
Meiosis vs. Mitosis
Before the start of mitosis and meiosis I, the cell synthesizes DNA, resulting in two homologous copies of each chromosome. DNA synthesis is...
Imaging Biological Samples with Optical Microscopy
In optical microscopy, the specimen to be viewed is placed on a glass slide and clipped on the stage...
Confocal Fluorescence Microscopy
Centrosome Duplication
To ensure that each daughter cell receives a centrosome after cell division, centrosome duplication...
Phase Contrast and Differential Interference Contrast Microscopy
In-phase-contrast microscopes, interference between light directly passing through a cell and light refracted by cellular components is used to create high-contrast, high-resolution images without staining. It is the oldest and simplest type of microscope that creates an image by altering the wavelengths of light rays passing through the specimen. Altered wavelength paths are created using an annular stop in the condenser. The annular stop produces a hollow cone of...