Automated Detection of P. falciparum Using Machine Learning Algorithms with Quantitative Phase Images of Unstained Cells

Abstract

Malaria detection through microscopic examination of stained blood smears is a diagnostic challenge that heavily relies on the expertise of trained microscopists. This paper presents an automated analysis method for detection and staging of red blood cells infected by the malaria parasite Plasmodium falciparum at trophozoite or schizont stage. Unlike previous efforts in this area, this study uses quantitative phase images of unstained cells. Erythrocytes are automatically segmented using thresholds of optical phase and refocused to enable quantitative comparison of phase images. Refocused images are analyzed to extract 23 morphological descriptors based on the phase information. While all individual descriptors are highly statistically different between infected and uninfected cells, each descriptor does not enable separation of populations at a level satisfactory for clinical utility. To improve the diagnostic capacity, we applied various machine learning techniques, including linear discriminant classification (LDC), logistic regression (LR), and k-nearest neighbor classification (NNC), to formulate algorithms that combine all of the calculated physical parameters to distinguish cells more effectively. Results show that LDC provides the highest accuracy of up to 99.7% in detecting schizont stage infected cells compared to uninfected RBCs. NNC showed slightly better accuracy (99.5%) than either LDC (99.0%) or LR (99.1%) for discriminating late trophozoites from uninfected RBCs. However, for early trophozoites, LDC produced the best accuracy of 98%. Discrimination of infection stage was less accurate, producing high specificity (99.8%) but only 45.0%-66.8% sensitivity with early trophozoites most often mistaken for late trophozoite or schizont stage and late trophozoite and schizont stage most often confused for each other. Overall, this methodology points to a significant clinical potential of using quantitative phase imaging to detect and stage malaria infection without staining or expert analysis.

Automated analysis of individual sperm cells using stain‐free interferometric phase microscopy and machine learning

“…Note that because the refractive index of a sperm cell is not homogenous, one cannot extract the refractive index directly from the OPD measurement. In addition, the quantitative phase maps produced by IPM have been shown in the past to be an excellent source of quantitative data for the application of machine learning techniques (10)(11)(12)(13). Furthermore, new parameters such as the dry mass of the cells and cellular compartments can now be derived (9).…”

Holography, machine learning, and cancer cells

“…Cytometry Part A 91A: 754À756, 2017 identify four stages of red blood cell infection by the malaria parasite P. falciparum (13). Any single image parameter was not sufficient for infection staging.…”

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

“…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.…”