Deep-Learning-Based Image Reconstruction and Enhancement in Optical Microscopy

Proceedings of the IEEE, Journal Year: 2019, Volume and Issue: 108(1), P. 30 - 50

Published: Nov. 14, 2019

In recent years, deep learning has been shown to be one of the leading machine techniques for a wide variety inference tasks. addition its mainstream applications, such as classification, it created transformative opportunities image reconstruction and enhancement in optical microscopy. Some these emerging applications range from transformations between microscopic imaging systems adding new capabilities existing techniques, well solving various inverse problems based on microscopy data. Deep is helping us move toward data-driven instrument designs that blend computing achieve what neither can do alone. This article provides an overview some work using neural networks advance computational sensing systems, also covering their current future biomedical applications.

Language: Английский

---

Deep learning-enabled point-of-care sensing using multiplexed paper-based sensors

npj Digital Medicine, Journal Year: 2020, Volume and Issue: 3(1)

Published: May 7, 2020

Abstract We present a deep learning-based framework to design and quantify point-of-care sensors. As use-case, we demonstrated low-cost rapid paper-based vertical flow assay (VFA) for high sensitivity C-Reactive Protein (hsCRP) testing, commonly used assessing risk of cardio-vascular disease (CVD). A machine was developed (1) determine an optimal configuration immunoreaction spots conditions, spatially-multiplexed on sensing membrane, (2) accurately infer target analyte concentration. Using custom-designed handheld VFA reader, clinical study with 85 human samples showed competitive coefficient-of-variation 11.2% linearity R 2 = 0.95 among blindly-tested VFAs in the hsCRP range (i.e., 0–10 mg/L). also mitigation hook-effect due multiplexed immunoreactions membrane. This computational could expand access CVD presented can be broadly cost-effective mobile

Language: Английский

---

Quantitative phase imaging trends in biomedical applications

Optics and Lasers in Engineering, Journal Year: 2020, Volume and Issue: 135, P. 106188 - 106188

Published: June 24, 2020

Language: Английский

---

Deep Learning for Biospectroscopy and Biospectral Imaging: State-of-the-Art and Perspectives

Analytical Chemistry, Journal Year: 2021, Volume and Issue: 93(8), P. 3653 - 3665

Published: Feb. 18, 2021

With the advances in instrumentation and sampling techniques, there is an explosive growth of data from molecular cellular samples. The call to extract more information large sets has greatly challenged conventional chemometrics method. Deep learning, which utilizes very for finding hidden features therein making accurate predictions a wide range applications, been applied unbelievable pace biospectroscopy biospectral imaging recent 3 years. In this Feature, we first introduce background basic knowledge deep learning. We then focus on emerging applications learning preprocessing, feature detection, modeling biological samples spectral analysis spectroscopic imaging. Finally, highlight challenges limitations outlook future directions.

Language: Английский

---

Label-free multiplexed microtomography of endogenous subcellular dynamics using generalizable deep learning

Nature Cell Biology, Journal Year: 2021, Volume and Issue: 23(12), P. 1329 - 1337

Published: Dec. 1, 2021

Language: Английский

---