TOP-GAN: Stain-free cancer cell classification using deep learning with a small training set.

We propose a new deep learning approach for medical imaging that copes with the problem of a small training set, the main bottleneck of deep learning, and apply it for classification of healthy and cancer cell lines acquired by quantitative phase imaging. The proposed method, called transferring of pre-trained generative adversarial network (TOP-GAN), is hybridization between transfer learning and generative adversarial networks (GANs). Healthy cells and cancer cells of different metastatic potential have been imaged by low-coherence off-axis holography.

Stain-free interferometric phase microscopy correlation with DNA fragmentation stain in human spermatozoa.

Acridine orange (AO) staining is used to diagnose DNA fragmentation status in sperm cells. Interferometric phase microscopy (IPM) is an optical imaging method based on digital holographic microscopy that provides quantitative morphological and refractive index imaging of cells in vitro without the need for staining. We have imaged sperm cells using stain-free IPM in order to estimate different cellular parameters, such as acrosome dry mass and size, in addition to an embryologist evaluation according to the World Health Organization (WHO)-2010 criteria.