Development of full‐field optical spatial coherence tomography system for automated identification of malaria using the multilevel ensemble classifier

Abstract

Malaria is a life-threatening infectious blood disease affecting humans and other animals caused by parasitic protozoans belonging to the Plasmodium type especially in developing countries. The gold standard method for the detection of malaria is through the microscopic method of chemically treated blood smears. We developed an automated optical spatial coherence tomographic system using a machine learning approach for a fast identification of malaria cells. In this study, 28 samples (15 healthy, 13 malaria infected stages of red blood cells) were imaged by the developed system and 13 features were extracted. We designed a multilevel ensemble-based classifier for the quantitative prediction of different stages of the malaria cells. The proposed classifier was used by repeating k-fold cross validation dataset and achieve a high-average accuracy of 97.9% for identifying malaria infected late trophozoite stage of cells. Overall, our proposed system and multilevel ensemble model has a substantial quantifiable potential to detect the different stages of malaria infection without staining or expert.

Machine learning‐based in‐line holographic sensing of unstained malaria‐infected red blood cells

“…QPI techniques have been also applied to investigate the modifications in biophysical properties of iRBCs and to diagnose malaria disease without staining . Several studies have extracted the morphological features from 3D RBC phase images and have obtained relatively high detection accuracies of iRBCs (>91%) by adopting shape correlation or machine learning algorithms . Although QPI techniques provide information on the optical phase delay that could be used to directly extract the 3D morphological parameters, a complicated optical setup with a high magnification is required and the number of RBCs in the field of view (FOV) is limited (≤10).…”

“…Furthermore, quantitative phase‐contrast imaging (QPI) techniques combined with machine learning algorithms have been utilized to recognize types of cells or classify the states of biosamples, including bacteria , cancer cells , sperm cells , lymphocytes , macrophage activation , microorganisms , microobjects and RBCs . Since QPI techniques provide valuable phase information related with 3D morphology and biophysical properties of samples, iRBCs could be distinguished from healthy RBCs (hRBCs) with a relatively high accuracy (>91%) . However, the interferometric setups, such as common‐path type and Mach‐Zhender type, are relatively complicated and their throughputs are low due to high magnification.…”

Machine Learning Assisted Classification of Cell Lines and Cell States on Quantitative Phase Images

“…Analysis of subcellular structures on automatically segmented quantitative phase images was also used for robust distinguishing between white blood cells and cancer cells [25]. Aside from investigation of cancer cells sperm cells at norm and under oxidative stress were classified using SVM algorithm on the base of 11 parameters obtained from quantitative phase images and used as predictor variables [26], malaria infected red blood cells were identified using multilevel ensemble classifier [27]. The combination of digital holographic recording and machine-learning classification algorithms was applied for identification of dead and living microalgae cells in the sea [28].…”

“…Quantitative phase imaging (QPI) techniques using coherent or partially coherent radiation [29,30] allow for reconstruction of phase images of individual cells and for computation of a wide variety of cellular parameters, discussed and listed in [27,31] and elsewhere. The obtained optical parameters of cells depend on both morphological characteristics and refractive index distributions, related to dry mass density in different cellular compartments.…”

High‐resolution single‐shot phase‐shifting interference microscopy using deep neural network for quantitative phase imaging of biological samples

“…[2][3][4] The experimental and computational advancement in QPI is being widely adopted for extracting quantitative information about various industrial and biological applications such as human red blood cells (RBC), tissue sections, and sperm samples, among others. [5][6][7][8][9] Various newly developed QPI techniques have been implemented which mainly focuses on to improve the resolution, temporal phase sensitivity, acquisition rate and spatial phase sensitivity of the system. 1 In QPI system, the spatial phase sensitivity and data acquisition rate are inversely related to each other.…”