Suppr超能文献

使用深度学习算法对布氏锥虫哺乳动物生命周期阶段进行分类

Classification of Trypanosoma brucei mammalian life cycle stages using Deep Learning Algorithms.

作者信息

Cheraghi Hamid, López-Escobar Lara, Rino José, Figueiredo Luisa M, Szabó Bálint

机构信息

Department of Biological Physics, Eötvös Loránd University (ELTE), Budapest, Hungary.

CellSorter Scientific Company for Innovations, Budapest, Hungary.

出版信息

PLoS Negl Trop Dis. 2025 Aug 14;19(8):e0013298. doi: 10.1371/journal.pntd.0013298. eCollection 2025 Aug.

Abstract

Accurate classification of Trypanosoma brucei bloodstream forms, slender and stumpy, is essential for understanding parasite biology and transmission dynamics. Traditional classification methods rely on flourescent transgenic parasites, as distinguishing these forms visually is highly challenging. To address this, we developed a semi-automated deep-learning pipeline that segments and classifies T. brucei bloodstream forms from unlabeled microscopic images. The pipeline consists of two key stages: (1) a segmentation step using the Cellpose algorithm, which detects and extracts individual parasites while filtering out artifacts, and (2) a classification step utilizing a deep learning model based on the Xception architecture. The classification model, optimized through transfer learning and fine-tuning, achieved a 97% accuracy, outperforming standard architectures such as InceptionV3, ResNet50, and VGG16. Our results demonstrate the effectiveness of deep learning in parasite stage classification, offering a scalable and efficient approach for high-throughput analysis. Beyond T. brucei, our framework can be adapted for other single-cell classification tasks based on unlabeled morphology, contributing to advancements in biomedical imaging and automated cell analysis.

摘要

准确区分布氏锥虫血流形式(细长型和粗短型)对于理解寄生虫生物学和传播动态至关重要。传统的分类方法依赖于荧光转基因寄生虫,因为从视觉上区分这些形式极具挑战性。为了解决这个问题,我们开发了一种半自动深度学习流程,可从未标记的显微图像中分割并分类布氏锥虫血流形式。该流程包括两个关键阶段:(1)使用Cellpose算法的分割步骤,该步骤可检测并提取单个寄生虫,同时滤除伪像;(2)使用基于Xception架构的深度学习模型的分类步骤。通过迁移学习和微调优化的分类模型达到了97%的准确率,优于InceptionV3、ResNet50和VGG16等标准架构。我们的结果证明了深度学习在寄生虫阶段分类中的有效性,为高通量分析提供了一种可扩展且高效的方法。除了布氏锥虫,我们的框架还可基于未标记的形态学适用于其他单细胞分类任务,推动生物医学成像和自动化细胞分析的进展。

https://cdn.ncbi.nlm.nih.gov/pmc/blobs/c1cc/12352779/2e644a8fbaf8/pntd.0013298.g001.jpg

文献AI研究员

20分钟写一篇综述,助力文献阅读效率提升50倍。

立即体验

用中文搜PubMed

大模型驱动的PubMed中文搜索引擎

马上搜索

文档翻译

学术文献翻译模型,支持多种主流文档格式。

立即体验