A robust recognition error recovery for micro-flow cytometer by machine-learning enhanced single-frame super-resolution processing

Huang, Xiwei; Wang, Xiaolong; Yan, Mei; Yu, Hao

doi:10.1016/j.vlsi.2014.07.004

Cited by 13 publications

(4 citation statements)

References 27 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…A lensless imaging system has a basic hardware setup, which directly integrates a microfluidic channel on a small CIS, and a white light source illuminates from above at a distance of D ls to sensor array [5]. When blood cell samples flow through the microfluidic channel at an objective distance D obj to the sensor array, their diffracted shadow images are recorded by the CIS underneath without any magnification by lens elements, as shown in Figure 1a.…”

Section: Introductionmentioning

confidence: 99%

Machine Learning Based Single-Frame Super-Resolution Processing for Lensless Blood Cell Counting

Huang

Jiang

Liu

et al. 2016

Sensors

Self Cite

View full text Add to dashboard Cite

A lensless blood cell counting system integrating microfluidic channel and a complementary metal oxide semiconductor (CMOS) image sensor is a promising technique to miniaturize the conventional optical lens based imaging system for point-of-care testing (POCT). However, such a system has limited resolution, making it imperative to improve resolution from the system-level using super-resolution (SR) processing. Yet, how to improve resolution towards better cell detection and recognition with low cost of processing resources and without degrading system throughput is still a challenge. In this article, two machine learning based single-frame SR processing types are proposed and compared for lensless blood cell counting, namely the Extreme Learning Machine based SR (ELMSR) and Convolutional Neural Network based SR (CNNSR). Moreover, lensless blood cell counting prototypes using commercial CMOS image sensors and custom designed backside-illuminated CMOS image sensors are demonstrated with ELMSR and CNNSR. When one captured low-resolution lensless cell image is input, an improved high-resolution cell image will be output. The experimental results show that the cell resolution is improved by 4×, and CNNSR has 9.5% improvement over the ELMSR on resolution enhancing performance. The cell counting results also match well with a commercial flow cytometer. Such ELMSR and CNNSR therefore have the potential for efficient resolution improvement in lensless blood cell counting systems towards POCT applications.

show abstract

Section: Introductionmentioning

confidence: 99%

Machine Learning Based Single-Frame Super-Resolution Processing for Lensless Blood Cell Counting

Huang

Jiang

Liu

et al. 2016

Sensors

Self Cite

View full text Add to dashboard Cite

show abstract

“…Blood cell counting provides important indicators for fast diagnosis of disease . Several ML-based microfluidic cytometers were reported. − Extreme learning machine based super-resolution (ELMSR) and CNN based super-resolution (CNNSR) were compared for a lensless blood cell counting device integrating microfluidic channel and a complementary metal oxide semiconductor (CMOS) image sensor . The cell resolution was improved four times, and CNNSR showed 9.5% improved quality over the ELMSR on resolution enhancement.…”

Section: Different Biosensors With MLmentioning

confidence: 99%

Advancing Biosensors with Machine Learning

et al. 2020

View full text Add to dashboard Cite

Chemometrics play a critical role in biosensorsbased detection, analysis, and diagnosis. Nowadays, as a branch of artificial intelligence (AI), machine learning (ML) have achieved impressive advances. However, novel advanced ML methods, especially deep learning, which is famous for image analysis, facial recognition, and speech recognition, has remained relatively elusive to the biosensor community. Herein, how ML can be beneficial to biosensors is systematically discussed. The advantages and drawbacks of most popular ML algorithms are summarized on the basis of sensing data analysis. Specially, deep learning methods such as convolutional neural network (CNN) and recurrent neural network (RNN) are emphasized. Diverse ML-assisted electrochemical biosensors, wearable electronics, SERS and other spectra-based biosensors, fluorescence biosensors and colorimetric biosensors are comprehensively discussed. Furthermore, biosensor networks and multibiosensor data fusion are introduced. This review will nicely bridge ML with biosensors, and greatly expand chemometrics for detection, analysis, and diagnosis.

show abstract

“…As such, it has no iterative backward-propagation solution, which is time consuming. Therefore, ELM is extremely fast for training speed [11,12].…”

Section: A Single-frame Elm-srmentioning

confidence: 99%

“…The recognition and counting for different types of flowing cells can then be performed accurately by only checking for the strongest structure similarity (SSIM) [11] of the recovered SR images with reference to the off-line static HR images.…”

Section: A Single-frame Elm-srmentioning

confidence: 99%

A Single-Frame Superresolution Algorithm for Lab-on-a-Chip Lensless Microfluidic Imaging

Huang

Liu

et al. 2015

IEEE Des. Test

View full text Add to dashboard Cite

With the recent advance of microfluidics-based lab-on-a-chip technology, lensless microfluidic imaging system with super-resolution (SR) has become a promising solution to miniaturize the conventional bulky lens-based microscope for high-throughput cell detection under specified resolution. The previous lensless system employing multi-frame SR processing limits the throughput due to the need to capture sub-pixel movement of capillary flowing cells. In this paper, we introduce two single-frame SR algorithms: one is interpolation-based method and the other one is machine-learning-based method. Both methods have shown great potential for on-chip implementation for cell detection with balanced resolution and throughput.

show abstract

A robust recognition error recovery for micro-flow cytometer by machine-learning enhanced single-frame super-resolution processing

Cited by 13 publications

References 27 publications

Machine Learning Based Single-Frame Super-Resolution Processing for Lensless Blood Cell Counting

Machine Learning Based Single-Frame Super-Resolution Processing for Lensless Blood Cell Counting

Advancing Biosensors with Machine Learning

A Single-Frame Superresolution Algorithm for Lab-on-a-Chip Lensless Microfluidic Imaging

Contact Info

Product

Resources

About