Automatic Spectral Unmixing of Leishmania Infection Macrophage Cell Cultures Image

Abstract

Evaluation of parasite infection indexes on in vitro cell cultures is a practice commonly employed by biomedical researchers to address biological questions or to test the efficacy of novel anti-parasitic compounds. In the case of Leishmania infantum, infection indexes are usually determined either by visual inspection of cells directly under the microscope or by counting digital images using appropriate software. In either case assessment of infection indexes is time consuming, thus motivating the creation of automatic image analysis approaches.

One problem in developing a fully automatic methodology for infection indexes evaluation is the low image quality that occur due to problem with the fluorescence of cells. In our previous work we approach cell and parasite segmentation using a Difference of Gaussians filter with a self tuning parametrization, but did not correct existing fluorescence problems. We propose an automatic linear spectral unmixing step that is integrated into our automatic segmentation approach loop to promote image quality improvements for higher analysis performance.

Results show that our approach can improve image quality and the final detection results when the image being processed presents overlapping spectral profiles.