Main description:

This book introduces time-stretch quantitative phase imaging (TS-QPI), a high-throughput label-free imaging flow cytometer developed for big data acquisition and analysis in phenotypic screening. TS-QPI is able to capture quantitative optical phase and intensity images simultaneously, enabling high-content cell analysis, cancer diagnostics, personalized genomics, and drug development. The authors also demonstrate a complete machine learning pipeline that performs optical phase measurement, image processing, feature extraction, and classification, enabling high-throughput quantitative imaging that achieves record high accuracy in label -free cellular phenotypic screening and opens up a new path to data-driven diagnosis.

Contents:

I Time stretch imaging1 Introduction2 Background2.1 Time Stretch Imaging2.2 Cell Classification Using Time Stretch Imaging2.3 Label-free Phenotypic Screening2.4 Warped Time Stretch for Data CompressionII Inspection and vision3 Nanometer-resolved imaging vibrometer3.1 Introduction3.2 Experimental demonstration3.3 Theoretical study of the vibrometer performance3.4 Experimental results3.5 Conclusion4 Three-dimensional ultrafast laser scanner4.1 Introduction4.2 Principle of hybrid dispersion laser scanner4.3 Applications of hybrid dispersion laser scannerIII Biomedical applications5 Label-free High-throughput Phenotypic Screening5.1 Introduction5.2 Experimental Setup5.3 Results and Discussion5.4 Conclusion6 Time Stretch Quantitative Phase Imaging6.1 Background6.2 Time Stretch Quantitative Phase Imaging6.2.1 Overview6.2.2 Imaging system6.2.3 System performance and resolvable points6.2.4 Microuidic channel design and fabrication6.2.5 Coherent Detection and Phase Extraction6.2.6 Cell Transmittance Extraction6.2.7 Image Reconstruction6.3 Image Processing Pipeline6.3.1 Feature Extraction6.3.2 Multivariate Features Enabled by Sensor Fusion6.3.3 System Calibration6.4 ConclusionIV Big data and artifitial intelligence7 Big data acquisition and processing in real-time7.1 Introduction7.2 Technical description of the acquisition system7.3 Big data acquisition results7.4 Conclusion8 Deep Learning and Classification8.1 Background8.2 Machine Learning8.3 Applications8.3.1 Blood Screening: Demonstration in Classification of OT-II and SW-480 Cells8.3.2 Biofuel: Demonstration in Algae Lipid Content Classification8.4 Further Discussions in Machine Learning8.4.1 Learning Curves8.4.2 Principal Component Analysis (PCA)8.4.3 Cross Validation8.4.4 Computation Time8.4.5 Data Cleaning8.5 ConclusionV Data compression9 Optical Data Compression in Time Stretch Imaging9.1 Background9.2 Warped Stretch Imaging9.3 Optical Image Compression9.4 Experimental Design and Results9.5 Conclusion10 Design of Warped Stretch Transform10.1 Overview10.2 Kernel Design10.2.1 Spectral Resolution10.2.2 Group Delay Profile Design10.2.3 Simulation Model10.2.4 Spectrograms10.3 Discussion10.4 Conclusion11 Concluding Remarks and Future WorkReferences