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

## TL;DR

This paper introduces an AI-based tool to automatically classify two forms of the Trypanosoma brucei parasite using microscope images, improving efficiency and accuracy in disease research.

## Contribution

A novel deep learning pipeline combining Cellpose segmentation and Xception-based classification for automated, high-throughput analysis of T. brucei life cycle stages.

## Key findings

- The deep learning pipeline achieved 97% accuracy in classifying T. brucei bloodstream forms.
- The method outperformed standard architectures like InceptionV3 and ResNet50.
- The framework is effective with lower-resolution images, making it suitable for resource-limited settings.

## 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.

Trypanosoma brucei is a parasite responsible for African sleeping sickness in humans and animals. Identifying the different stages of its life cycle is essential for understanding the disease and its progression, but this process often requires skilled experts and high-quality microscope images. In our study, we developed an automated method using artificial intelligence to classify the two main forms of the parasite—slender and stumpy—based on microscope images. Our approach combines a powerful segmentation tool called Cellpose with a deep learning model to analyze thousands of individual parasite images. Importantly, our method works well even with lower-resolution images, which are common in resource-limited settings. This makes the tool especially useful in labs that may not have access to advanced imaging equipment. By offering a fast, reliable, and objective way to analyze parasite forms, our work supports better disease monitoring and research. It also opens the door for similar approaches to be used in studying other microscopic organisms.