Machine Learning Based Lens-Free Shadow Imaging Technique for Field-Portable Cytometry

Abstract

The lens-free shadow imaging technique (LSIT) is a well-established technique for the characterization of microparticles and biological cells. Due to its simplicity and cost-effectiveness, various low-cost solutions have been developed, such as automatic analysis of complete blood count (CBC), cell viability, 2D cell morphology, 3D cell tomography, etc. The developed auto characterization algorithm so far for this custom-developed LSIT cytometer was based on the handcrafted features of the cell diffraction patterns from the LSIT cytometer, that were determined from our empirical findings on thousands of samples of individual cell types, which limit the system in terms of induction of a new cell type for auto classification or characterization. Further, its performance suffers from poor image (cell diffraction pattern) signatures due to their small signal or background noise. In this work, we address these issues by leveraging the artificial intelligence-powered auto signal enhancing scheme such as denoising autoencoder and adaptive cell characterization technique based on the transfer of learning in deep neural networks. The performance of our proposed method shows an increase in accuracy >98% along with the signal enhancement of >5 dB for most of the cell types, such as red blood cell (RBC) and white blood cell (WBC). Furthermore, the model is adaptive to learn new type of samples within a few learning iterations and able to successfully classify the newly introduced sample along with the existing other sample types.

Impedimetric Detection of Cancer Markers Based on Nanofiber Copolymers

“…However, these techniques are time consuming; require sophisticated, expensive equipment and highly trained technicians for processing; and are a risk to human health due to radiation exposure [4]. Recently, they have been developed based on artificial intelligence and machine learning capabilities [5,6]. However, their development has been slowed by some systematic challenges, such as dataset availability, which is often the guidance for methods research rather than clinical relevance, and research incentives, such as optimization for publication [7].…”

Label-Free CD34+ Cell Identification Using Deep Learning and Lens-Free Shadow Imaging Technology

“…Lens-free shadow imaging technology (LSIT) is a well-established method for characterizing microparticles and biological cells [35]. In LSIT, the diffraction pattern produced by an object is directly recorded using CCD/CMOS technology, thereby avoiding the use of lens elements and offering a broad field of view [36,37].…”

“…These parameters facilitate the analysis of various cellular attributes including cell viability, morphology, size, and type. Furthermore, there is an opportunity to enhance the accuracy and precision of LSIT using advanced techniques such as deep learning (DL), which has garnered considerable attention in recent years [35].…”

Intelligent Biosignal Processing in Wearable and Implantable Sensors

“…Roy et al [ 9 ] developed an auto-characterization algorithm to leverage the AI-powered auto-signal-enhancing scheme such as denoising autoencoder and adaptive cell characterization technique based on the transfer of learning in deep neural networks. They reported a considerable increase in accuracy and signal enhancement.…”