scholarly journals Deep-Learning-Based Label-Free Segmentation of Cell Nuclei in Time-Lapse Refractive Index Tomograms

IEEE Access ◽  
2019 ◽  
Vol 7 ◽  
pp. 83449-83460 ◽  
Author(s):  
Jimin Lee ◽  
Hyejin Kim ◽  
Hyungjoo Cho ◽  
YoungJu Jo ◽  
Yujin Song ◽  
...  
Keyword(s):  
Refractive Index ◽  
Deep Learning ◽  
Time Lapse ◽  
Label Free ◽  
Cell Nuclei

scholarly journals Deep-learning-based label-free segmentation of cell nuclei in time-lapse refractive index tomograms

2018 ◽  
Author(s):  
Jimin Lee ◽  
Hyejin Kim ◽  
Hyungjoo Cho ◽  
YoungJu Jo ◽  
Yujin Song ◽  
...  
Keyword(s):  
Deep Learning ◽  
Fluorescent Proteins ◽  
Time Lapse ◽  
Optical Diffraction ◽  
Live Cells ◽  
Label Free ◽  
Cell Nuclei ◽  
Learning Framework ◽  
Optical Diffraction Tomography ◽  
Exogenous Agents

AbstractIn order to identify cell nuclei, fluorescent proteins or staining agents has been widely used. However, use of exogenous agents inevitably prevents from long-term imaging of live cells and rapid analysis, and even interferes with intrinsic physiological conditions. In this work, we proposed a method of label-free segmentation of cell nuclei in optical diffraction tomography images by exploiting a deep learning framework. The proposed method was applied for precise cell nucleus segmentation in two, three, and four-dimensional label-free imaging. A novel architecture with optimised training strategies was validated through cross-modality and cross-laboratory experiments. The proposed method would bring out broad and immediate biomedical applications with our framework publicly available.

scholarly journals Label-Free White Blood Cell Classification Using Refractive Index Tomography and Deep Learning

BME Frontiers ◽  
2021 ◽  
Vol 2021 ◽  
pp. 1-9
Author(s):  
DongHun Ryu ◽  
Jinho Kim ◽  
Daejin Lim ◽  
Hyun-Seok Min ◽  
In Young Yoo ◽  
...  
Keyword(s):  
Bone Marrow ◽  
Refractive Index ◽  
Deep Learning ◽  
Blood Cell ◽  
White Blood Cell ◽  
Blood Cells ◽  
Hematologic Malignancy ◽  
Label Free ◽  
Cell Classification

Objective and Impact Statement. We propose a rapid and accurate blood cell identification method exploiting deep learning and label-free refractive index (RI) tomography. Our computational approach that fully utilizes tomographic information of bone marrow (BM) white blood cell (WBC) enables us to not only classify the blood cells with deep learning but also quantitatively study their morphological and biochemical properties for hematology research. Introduction. Conventional methods for examining blood cells, such as blood smear analysis by medical professionals and fluorescence-activated cell sorting, require significant time, costs, and domain knowledge that could affect test results. While label-free imaging techniques that use a specimen’s intrinsic contrast (e.g., multiphoton and Raman microscopy) have been used to characterize blood cells, their imaging procedures and instrumentations are relatively time-consuming and complex. Methods. The RI tomograms of the BM WBCs are acquired via Mach-Zehnder interferometer-based tomographic microscope and classified by a 3D convolutional neural network. We test our deep learning classifier for the four types of bone marrow WBC collected from healthy donors (n=10): monocyte, myelocyte, B lymphocyte, and T lymphocyte. The quantitative parameters of WBC are directly obtained from the tomograms. Results. Our results show >99% accuracy for the binary classification of myeloids and lymphoids and >96% accuracy for the four-type classification of B and T lymphocytes, monocyte, and myelocytes. The feature learning capability of our approach is visualized via an unsupervised dimension reduction technique. Conclusion. We envision that the proposed cell classification framework can be easily integrated into existing blood cell investigation workflows, providing cost-effective and rapid diagnosis for hematologic malignancy.

scholarly journals Rapid and label-free identification of individual bacterial pathogens exploiting three-dimensional quantitative phase imaging and deep learning

2019 ◽  
Author(s):  
Geon Kim ◽  
Daewoong Ahn ◽  
Minhee Kang ◽  
YoungJu Jo ◽  
Donghun Ryu ◽  
...  
Keyword(s):  
Refractive Index ◽  
Deep Learning ◽  
Infectious Diseases ◽  
Bacterial Pathogens ◽  
Bacterial Species ◽  
Three Dimensional ◽  
Phase Imaging ◽  
Label Free ◽  
Quantitative Phase Imaging ◽  
Quantitative Phase

ABSTRACTFor appropriate treatments of infectious diseases, rapid identification of the pathogens is crucial. Here, we developed a rapid and label-free method for identifying common bacterial pathogens as individual bacteria by using three-dimensional quantitative phase imaging and deep learning. We achieved 95% accuracy in classifying 19 bacterial species by exploiting the rich information in three-dimensional refractive index tomograms with a convolutional neural network classifier. Extensive analysis of the features extracted by the trained classifier was carried out, which supported that our classifier is capable of learning species-dependent characteristics. We also confirmed that utilizing three-dimensional refractive index tomograms was crucial for identification ability compared to two-dimensional imaging. This method, which does not require time-consuming culture, shows high feasibility for diagnosing patients with infectious diseases who would benefit from immediate and adequate antibiotic treatment.

scholarly journals Label-free bone marrow white blood cell classification using refractive index tomograms and deep learning

2020 ◽  
Author(s):  
DongHun Ryu ◽  
Jinho Kim ◽  
Daejin Lim ◽  
Hyun-Seok Min ◽  
Inyoung You ◽  
...  
Keyword(s):  
Bone Marrow ◽  
Refractive Index ◽  
Deep Learning ◽  
Blood Cell ◽  
White Blood Cell ◽  
Hematologic Malignancy ◽  
White Blood Cells ◽  
Label Free ◽  
Cell Classification

AbstractIn this study, we report a label-free bone marrow white blood cell classification framework that captures the three-dimensional (3D) refractive index (RI) distributions of individual cells and analyzes with deep learning. Without using labeling or staining processes, 3D RI distributions of individual white blood cells were exploited for accurate profiling of their subtypes. Powered by deep learning, our method used the high-dimensional information of the WBC RI tomogram voxels and achieved high accuracy. The results show >99 % accuracy for the binary classification of myeloids and lymphoids and >96 % accuracy for the four-type classification of B, T lymphocytes, monocytes, and myelocytes. Furthermore, the feature learning of our approach was visualized via an unsupervised dimension reduction technique. We envision that this framework can be integrated into existing workflows for blood cell investigation, thereby providing cost-effective and rapid diagnosis of hematologic malignancy.

Using Deep Learning to Identify Cell and Particle in Live-Cell Time-lapse Images

2018 ◽  
Author(s):  
Hui-Jun Cheng ◽  
Chun-Yuan Lin ◽  
Cheng-Xian Wu ◽  
Che-Lun Hung ◽  
Wei-Hsiang Chen ◽  
...  
Keyword(s):  
Deep Learning ◽  
Time Lapse ◽  
Live Cell

scholarly journals Critical angle reflection imaging for quantification of molecular interactions on glass surface

2021 ◽  
Vol 12 (1) ◽  
Author(s):  
Guangzhong Ma ◽  
Runli Liang ◽  
Zijian Wan ◽  
Shaopeng Wang
Keyword(s):  
Refractive Index ◽  
Small Molecule ◽  
Molecular Interactions ◽  
Glass Surface ◽  
Critical Angle ◽  
Dynamic Range ◽  
Refractive Index Change ◽  
Label Free ◽  
Index Change ◽  
Sensing Range

AbstractQuantification of molecular interactions on a surface is typically achieved via label-free techniques such as surface plasmon resonance (SPR). The sensitivity of SPR originates from the characteristic that the SPR angle is sensitive to the surface refractive index change. Analogously, in another interfacial optical phenomenon, total internal reflection, the critical angle is also refractive index dependent. Therefore, surface refractive index change can also be quantified by measuring the reflectivity near the critical angle. Based on this concept, we develop a method called critical angle reflection (CAR) imaging to quantify molecular interactions on glass surface. CAR imaging can be performed on SPR imaging setups. Through a side-by-side comparison, we show that CAR is capable of most molecular interaction measurements that SPR performs, including proteins, nucleic acids and cell-based detections. In addition, we show that CAR can detect small molecule bindings and intracellular signals beyond SPR sensing range. CAR exhibits several distinct characteristics, including tunable sensitivity and dynamic range, deeper vertical sensing range, fluorescence compatibility, broader wavelength and polarization of light selection, and glass surface chemistry. We anticipate CAR can expand SPR′s capability in small molecule detection, whole cell-based detection, simultaneous fluorescence imaging, and broader conjugation chemistry.

scholarly journals Perfect Absorption and Refractive-Index Sensing by Metasurfaces Composed of Cross-Shaped Hole Arrays in Metal Substrate

Nanomaterials ◽  
2020 ◽  
Vol 11 (1) ◽  
pp. 63
Author(s):  
Zhendong Yan ◽  
Chaojun Tang ◽  
Guohua Wu ◽  
Yumei Tang ◽  
Ping Gu ◽  
...  
Keyword(s):  
Refractive Index ◽  
High Performance ◽  
Narrow Band ◽  
Label Free ◽  
Hybrid Mode ◽  
Perfect Absorption ◽  
Refractive Index Sensing ◽  
Sensing Applications ◽  
Silver Substrate ◽  
Hole Arrays

Achieving perfect electromagnetic wave absorption with a sub-nanometer bandwidth is challenging, which, however, is desired for high-performance refractive-index sensing. In this work, we theoretically study metasurfaces for sensing applications based on an ultra-narrow band perfect absorption in the infrared region, whose full width at half maximum (FWHM) is only 1.74 nm. The studied metasurfaces are composed of a periodic array of cross-shaped holes in a silver substrate. The ultra-narrow band perfect absorption is related to a hybrid mode, whose physical mechanism is revealed by using a coupling model of two oscillators. The hybrid mode results from the strong coupling between the magnetic resonances in individual cross-shaped holes and the surface plasmon polaritons on the top surface of the silver substrate. Two conventional parameters, sensitivity (S) and figure of merit (FOM), are used to estimate the sensing performance, which are 1317 nm/RIU and 756, respectively. Such high-performance parameters suggest great potential for the application of label-free biosensing.

Label free high throughput screening for apoptosis inducing chemicals using time-lapse microscopy signal processing

APOPTOSIS ◽  
2014 ◽  
Vol 19 (9) ◽  
pp. 1411-1418 ◽  
Author(s):  
Obaid Aftab ◽  
Madiha Nazir ◽  
Mårten Fryknäs ◽  
Ulf Hammerling ◽  
Rolf Larsson ◽  
...  
Keyword(s):  
Signal Processing ◽  
High Throughput ◽  
High Throughput Screening ◽  
Time Lapse ◽  
Label Free ◽  
Time Lapse Microscopy
Sign in / Sign up

Export Citation Format

Share Document