Cellular Image Classification

• Main Authors: Xu, Xiang, Wu, Xingkun, Lin, Feng
• Format: eBook
• Language: English
• Published: Cham Springer International Publishing AG 2016; Springer International Publishing
• Edition: 1
• Subjects: Engineering; Pattern Recognition; Physiological, Cellular and Medical Topics; Physiology_xMathematics; Signal, Image and Speech Processing

This book introduces new techniques for cellular image feature extraction, pattern recognition and classification. The authors use the antinuclear antibodies (ANAs) in patient serum as the subjects and the Indirect Immunofluorescence (IIF) technique as the imaging protocol to illustrate the applicat...

Table of Contents:

• 4.2.3 Locality-Constrained Linear Coding -- 4.3 Pooling -- 4.4 Summary -- References -- 5 Image Coding -- 5.1 Introduction -- 5.2 Linear Local Distance Coding Method -- 5.2.1 Distance Vector -- 5.2.2 Local Distance Vector -- 5.2.3 The Algorithm Framework -- 5.3 Experiments and Analyses -- 5.3.1 Experiment Setup -- 5.3.2 Experimental Results on the ICPR2012 Dataset -- 5.3.3 Experimental Results on the ICIP2013 Training Dataset -- 5.3.4 Discussion -- 5.4 Summary -- References -- 6 Encoding Image Features -- 6.1 Introduction -- 6.2 Encoding Rotation Invariant Features of Images -- 6.2.1 Pairwise LTPs with Spatial Rotation Invariant -- 6.2.2 Encoding the SIFT Features with BoW Framework -- 6.3 Experiments and Analyses -- 6.3.1 Experiment Setup -- 6.3.2 Experimental Results on the ICPR2012 Dataset -- 6.3.3 Experimental Results on the ICIP2013 Training Dataset -- 6.3.4 Discussion -- 6.4 Summary -- References -- 7 Defining Feature Space for Image Classification -- 7.1 Introduction -- 7.2 Adaptive Co-occurrence Differential Texton Space for Classification -- 7.2.1 Co-occurrence Differential Texton -- 7.2.2 Adaptive CoDT Feature Space -- 7.2.3 HEp-2 Cell Image Representation in the Adaptive CoDT Feature Space -- 7.3 Experiments and Analyses -- 7.3.1 Experiment Setup -- 7.3.2 Experimental Results on the ICPR2012 Dataset -- 7.3.3 Experimental Results on the ICIP2013 Training Dataset -- 7.3.4 Discussion -- 7.4 Summary -- References -- 8 Conclusions and Perspectives -- 8.1 Major Techniques Developed in the Book -- 8.2 Directions and Future Work -- References
• Intro -- Preface -- Contents -- 1 Introduction -- 1.1 Background -- 1.1.1 Clinical Problems: A Case Study on Autoimmune Diseases -- 1.1.2 Cellular Imaging: A Case Study on Indirect Immunofluorescence -- 1.2 Computer-Aided Diagnosis -- 1.3 Experimental Datasets in the Book -- 1.3.1 The ICPR2012 Dataset -- 1.3.2 The ICIP2013 Training Dataset -- 1.4 Structure of the Chapters -- References -- 2 Fundamentals -- 2.1 Optical Systems for Cellular Imaging -- 2.1.1 Laser Scanning Confocal Microscope -- 2.1.2 Multi-photon Fluorescence Imaging -- 2.1.3 Total Internal Reflection Fluorescence Microscope -- 2.1.4 Near-Field Scanning Optical Microscopy Imaging Technology -- 2.1.5 Optical Coherence Tomography Technology -- 2.2 Feature Extraction -- 2.2.1 Low-Level Features -- 2.2.2 Mid-Level Features -- 2.3 Classification -- 2.3.1 Support Vector Machine -- 2.3.2 Nearest Neighbor Classifier -- References -- 3 Optical Systems for Cellular Imaging -- 3.1 Introduction -- 3.2 Optical Tweezer -- 3.2.1 Introduction to Optical Tweezers -- 3.2.2 Gradient and Scattering Force of Optical Tweezers -- 3.2.3 Three-Dimensional Optical Trap -- 3.3 Low-Order Fiber Mode LP21 -- 3.3.1 Fiber Mode Coupling Theory -- 3.3.2 Analysis of Field Distribution in Optical Fiber -- 3.3.3 Solution to LP21 Mode -- 3.3.4 Selective Excitation of LP21 Mode -- 3.3.5 The Twisting and Bending Characteristics of LP21 Mode -- 3.3.6 Why LP21 Mode? -- 3.4 Optical Tweezer Using Focused LP21 Mode -- 3.4.1 Fiber Axicons -- 3.4.2 Cell Manipulation -- 3.5 Modeling of Optical Trapping Force -- 3.5.1 Force Analysis of Mie Particles in Optical Trap -- 3.5.2 Gaussian Beam -- 3.5.3 Simulation of Light Force on Mie Particle -- 3.6 Summary -- References -- 4 Image Representation with Bag-of-Words -- 4.1 Introduction -- 4.2 Coding -- 4.2.1 Vector Quantization -- 4.2.2 Soft Assignment Coding