Generative optical modeling of whole blood for detecting platelets in lens-free images

Abstract

In this paper, we consider the task of detecting platelets in images of diluted whole blood taken with a lens-free microscope. Despite having several advantages over traditional microscopes, lens-free imaging systems have the significant challenge that the resolution of the system is typically limited by the pixel dimensions of the image sensor. As a result of this limited resolution, detecting platelets is very difficult even by manual inspection of the images due to the fact that platelets occupy just a few pixels of the reconstructed image. To address this challenge, we develop an optical model of diluted whole blood to generate physically realistic simulated holograms suitable for training machine learning models in a supervised manner. We then use this model to train a convolutional neural network (CNN) for platelet detection and validate our approach by developing a novel optical configuration which allows collecting both lens-free and fluorescent microscopy images of the same field of view of diluted whole blood samples with fluorescently labeled platelets.

Identification of Ancient Chinese Medical Prescriptions and Case Data Analysis Under Artificial Intelligence GPT Algorithm: A Case Study of Song Dynasty Medical Literature

“…Haefele et al constructed a prescription dictionary from biomedical resources using the template matching method and then denoised the dictionary. The denoised dictionary could identify the prescriptions' in and outside the database [13]. Liang et al used the Dictionary-based Method (DBM) to search and identify the text's prescriptions, disease names, and gene names.…”

Lens free holographic imaging for urinary tract infection screening

“…To reconstruct images from LFI holograms, we implemented a 3D sparse phase recovery reconstruction algorithm developed previously by our group [26], [27]. Briefly, sparse regularization is applied to a wide angular spectrum model of diffraction where alternating minimization allows for closed-form updates and recovery of missing phase information in a 3D volume.…”

Optical Technologies for Improving Healthcare in Low-Resource Settings: introduction to the feature issue

“…The whole slide imaging system described by Rai et al [12] uses deep learning to enable automated focusing of microscopy data that is comparable to the natural ability of human operators. In Haeffele et al [13], a lens-free microscope is augmented by a convolutional neural network trained for platelet detection. This system allows collection of lens-free and fluorescent microscopy images in the same field of view of diluted whole blood samples with fluorescently labeled platelets.…”