Trichomonas Vaginalis Segmentation in Microscope Images

TL;DR

This paper introduces TVMI3K, a large-scale dataset for Trichomonas vaginalis segmentation, and proposes TVNet, a deep learning model that achieves superior performance in microscopic image analysis for disease diagnosis.

Contribution

The paper provides the first large-scale dataset for Trichomonas vaginalis segmentation and develops a novel deep learning model tailored for this task.

Findings

TVNet outperforms existing models in segmentation accuracy.

The TVMI3K dataset enables robust training and evaluation.

High-quality annotations improve model performance.

Abstract

Trichomoniasis is a common infectious disease with high incidence caused by the parasite Trichomonas vaginalis, increasing the risk of getting HIV in humans if left untreated. Automated detection of Trichomonas vaginalis from microscopic images can provide vital information for the diagnosis of trichomoniasis. However, accurate Trichomonas vaginalis segmentation (TVS) is a challenging task due to the high appearance similarity between the Trichomonas and other cells (e.g., leukocyte), the large appearance variation caused by their motility, and, most importantly, the lack of large-scale annotated data for deep model training. To address these challenges, we elaborately collected the first large-scale Microscopic Image dataset of Trichomonas Vaginalis, named TVMI3K, which consists of 3,158 images covering Trichomonas of various appearances in diverse backgrounds, with high-quality annotations including object-level mask labels, object boundaries, and challenging attributes. Besides, we propose a simple yet effective baseline, termed TVNet, to automatically segment Trichomonas from microscopic images, including high-resolution fusion and foreground-background attention modules. Extensive experiments demonstrate that our model achieves superior segmentation performance and outperforms various cutting-edge object detection models both quantitatively and qualitatively, making it a promising framework to promote future research in TVS tasks. The dataset and results will be publicly available at: https://github.com/CellRecog/cellRecog.