Deep-learning assisted detection and quantification of (oo)cysts of Giardia and Cryptosporidium on smartphone microscopy images

The consumption of microbial-contaminated food and water is responsible for the deaths of millions of people annually. Smartphone-based microscopy systems are portable, low-cost, and more accessible alternatives for the detection of Giardia and Cryptosporidium than traditional brightfield microscopes. However, the images from smartphone microscopes are noisier and require manual cyst identification by trained technicians, usually unavailable in resource-limited settings. Automatic detection of (oo)cysts using deep-learning-based object detection could offer a solution for the limitation. Automatic detection of (oo)cysts using deep-learning-based object detection could offer a solution for the limitation. We evaluate the performance of three state-of-the-art object detectors to detect (oo)cysts of Giardia and Cryptosporidium} on a custom dataset that includes both smartphone and brightfield microscopic images from the vegetable samples. Faster RCNN, RetinaNet, and you only look once (YOLOv8s) deep-learning models were employed to explore their efficacy and limitations. Our results show that while the deep-learning models perform better with the brightfield microscopy image dataset than the smartphone microscopy image dataset, the smartphone microscopy predictions are still comparable to the prediction performance of non-experts.

每年因摄入受微生物污染的食物与饮水而死亡的人数高达数百万。相较于传统明场显微镜，基于智能手机的显微系统是一种便携、低成本且更易获取的贾第鞭毛虫（Giardia）与隐孢子虫（Cryptosporidium）检测方案。但此类智能手机显微镜采集的图像噪声更高，且需要经过专业培训的技术人员手动识别（卵）囊，而在资源匮乏地区往往难以配备这类专业人员。基于深度学习的目标检测（object detection）技术实现（卵）囊自动检测，可为该局限提供解决方案。基于深度学习的目标检测技术实现（卵）囊自动检测，可为该局限提供解决方案。我们基于一套涵盖蔬菜样本的智能手机显微镜与明场显微镜图像的定制数据集，评估了三款最先进的目标检测模型对贾第鞭毛虫与隐孢子虫（卵）囊的检测性能。本次研究选用Faster RCNN、RetinaNet以及你只看一次（YOLOv8s）三款深度学习模型，以探究它们的检测效能与局限性。研究结果显示，尽管深度学习模型在明场显微镜图像数据集上的表现优于智能手机显微镜图像数据集，但智能手机显微镜图像的预测性能仍可与非专业人员的识别效果相媲美。

搜集汇总

背景与挑战

背景概述

该数据集是一个用于深度学习辅助检测和量化贾第虫和隐孢子虫（卵）囊的智能手机显微镜图像集合，包含来自蔬菜样本的智能手机和明场显微镜图像，旨在通过自动对象检测解决资源有限环境下微生物检测的局限性。数据集大小为5.3 GB，发布于2023年，采用开源许可，支持使用Faster RCNN、RetinaNet和YOLOv8s等模型进行性能评估。