Department of Software Engineering, Faculty of Engineering and Natural Sciences, Bandırma Onyedi Eylül University, 10200, Bandırma, Balıkesir, Turkey.
Comput Biol Med. 2022 Sep;148:105635. doi: 10.1016/j.compbiomed.2022.105635. Epub 2022 Jun 3.
Malaria is a disease caused by the Plasmodium parasite, which results in millions of deaths in the human population worldwide each year. It is therefore considered a major global health issue with a massive disease burden. Accurate and rapid diagnosis of malaria is important for treatment. Rapid diagnosis of this disease will be very valuable for patients, as traditional methods require tedious work for its detection. The aim of the study is to classify malaria cell images using machine learning and deep learning methods.
MATERIAL & METHODS: The National Institutes of Health (NIH) database was used for malaria cell images classification as infected and uninfected, with a total of 27,558 malaria cell images used in the experimental study. Additionally, the training option parameters (initial learning rate, L2 regularization, and momentum values) of the Residual Convolutional Neural Network (CNN) were optimized using the Bayesian method. In the study, Residual CNN, k-Nearest Neighbors (k-NN), and Support Vector Machine (SVM) classifiers were used to classify the malaria cell images. Neighborhood Components Analysis (NCA) were observed to increase the performance of classifiers used in the classification of malaria cell images.
The Accuracy (Acc), Sensitivity (Se), Specificity (Spe), and F-score were used as the performance metrics for the classifier performances. The best classification results were achieved with SVM (Acc 99.90%, Se 99.98%, Spe 87.50%, and F-Score 99.90%). As a result, a high level of classification performance was achieved from creating a hybrid model with Bayesian optimization and Deep Residual CNN features.
疟疾是由疟原虫寄生虫引起的疾病，每年导致全球数百万人死亡。因此，它被认为是一个主要的全球健康问题，具有巨大的疾病负担。疟疾的准确和快速诊断对治疗很重要。这种疾病的快速诊断对患者非常有价值，因为传统方法需要繁琐的工作来进行检测。本研究的目的是使用机器学习和深度学习方法对疟原虫细胞图像进行分类。
使用美国国立卫生研究院（NIH）数据库对疟原虫细胞图像进行分类，分为感染和未感染两种，实验研究共使用了 27558 张疟原虫细胞图像。此外，使用贝叶斯方法优化了残差卷积神经网络（CNN）的训练选项参数（初始学习率、L2 正则化和动量值）。在研究中，使用残差 CNN、k-最近邻（k-NN）和支持向量机（SVM）分类器对疟原虫细胞图像进行分类。观察到邻域成分分析（NCA）可提高用于疟原虫细胞图像分类的分类器的性能。
Accuracy（Acc）、Sensitivity（Se）、Specificity（Spe）和 F-score 被用作分类器性能的性能指标。SVM 的分类效果最佳（Acc 为 99.90%、Se 为 99.98%、Spe 为 87.50%和 F-Score 为 99.90%）。因此，通过创建具有贝叶斯优化和 Deep Residual CNN 特征的混合模型，可以实现高水平的分类性能。
