微观寄生虫疟疾分类使用基于一般化正常分布优化最佳特征选择
Javeria Amin1, Muhammad Almas Anjum2, Abraz Ahmad1
1University of Wah, Department of Computer Science, Wah Cantt, Pakistan.
PeerJ. Computer science
|January 10, 2024
概括
这项研究引入了一种用于疟疾诊断的新型机器学习方法,通过显微镜图像对疟疾寄生虫进行分类,达到99%的准确性. 这种方法提高了诊断效率和准确性,克服了传统显微镜的局限性.
科学领域:
- 医学诊断 医学诊断 医学诊断
- 计算生物学 计算生物学
- 寄生虫学的寄生虫学
背景情况:
- 疟疾诊断依赖于显微镜,这需要专门的技能,并且可能是主观的.
- 由于疟疾的潜在致命性质,准确及时检测疟疾至关重要.
- 当前诊断方法的局限性需要先进的自动化解决方案.
研究的目的:
- 开发和评估一种基于机器/深度学习的方法,用于准确地分类疟疾寄生虫.
- 与传统显微镜相比,提高疟疾诊断的效率和可靠性.
- 为疟疾图像分析提出一个强大的特征提取和选择管道.
主要方法:
- 使用双边过器进行图像增强.
- 提取基于形状的特征 (Pyramid Histograms of Oriented Gradients - PHOG) 和深度特征 (ResNet-50,ResNet-18) 的特征. 这种特征是基于形状的特征 (Pyramid Histograms of Oriented Gradients - PHOG) 和深度特征 (ResNet-50,ResNet-18) 的特征的提取.
- 提取的特征的序列融合,然后使用通用正常分布优化 (GNDO) 进行特征选择.
主要成果:
- 拟议的方法在微观疟疾寄生虫数据集上实现了99%的分类准确性.
- 集成的功能集 (PHOG + ResNet 功能) 显示出卓越的性能.
- 使用GNDO选择的特征子集有效地优化了分类模型.
结论:
- 开发的深度学习模型为疟疾诊断提供了一个高度准确和高效的替代方案.
- 自动化疟疾寄生虫分类可以显著帮助迅速和可靠的疾病识别.
- 这种方法有望改善资源有限的环境中疟疾检测.
相关概念视频
Fungal Phylum Microsporidia
Microsporidia are a group of obligate intracellular fungi that were initially classified as protists but were later reclassified based on phylogenetic, molecular, and structural evidence linking them to the Chytridiomycota. These unicellular, non-motile organisms are highly specialized parasites that infect a wide range of animal hosts, including humans. They have evolved extensive genomic and metabolic reductions, making them highly dependent on their hosts for survival.Morphology and Genomic...
Malaria
Malaria pathogenesis in humans reflects a delicate interplay between parasite biology and host response. Clinical illness reflects a host’s immune response to the parasite’s asexual replication cycle, which is often asymptomatic in individuals with partial immunity. From the parasite's perspective, transmission between mosquito and human with minimal host pathology is evolutionarily advantageous. Among the six Plasmodium species infecting humans, P. falciparum and P. vivax dominate in global...


