Inception v3 based cervical cell classification combined with artificially extracted features

We consider the problem of high-dimensional light field reconstruction and develop a learning-based framework for spatial and angular super-resolution. Many current approaches either require disparity clues or restore the spatial and angular details separately. Such methods have difficulties with non-Lambertian surfaces or occlusions. In contrast, we formulate light field super-resolution (LFSR) as tensor restoration and develop a learning framework based on a two-stage restoration with 4-dimensional (4D) convolution. This allows our model to learn the features capturing the geometry information encoded in multiple adjacent views. Such geometric features vary near the occlusion regions and indicate the foreground object border. To train a feasible network, we propose a novel normalization operation based on a group of views in the feature maps, design a stage-wise loss function, and develop the multi-range training strategy to further improve the performance. Evaluations are conducted on a number of light field datasets including real-world scenes, synthetic data, and microscope light fields. The proposed method achieves superior performance and less execution time comparing with other state-of-the-art schemes.

High-Dimensional Dense Residual Convolutional Neural Network for Light Field Reconstruction

Imaging flow cytometry (IFC) produces up to 12 spectrally distinct, information-rich images of single cells at a throughput of 5,000 cells per second. Yet often, cell populations are still studied using manual gating, a technique that has several drawbacks, hence it would be advantageous to replace manual gating with an automated process. Ideally, this automated process would be based on stain-free measurements, as the currently used staining techniques are expensive and potentially confounding. These stain-free measurements originate from the brightfield and darkfield image channels, which capture transmitted and scattered light, respectively. To realize this automated, stain-free approach, advanced machine learning (ML) methods are required. Previous works have successfully tested this approach on cell cycle phase classification with both a classical ML approach based on manually engineered features, and a deep learning (DL) approach. In this work, we compare both approaches extensively on the problem of white blood cell classification. Four human whole blood samples were assayed on an ImageStream-X MK II imaging flow cytometer. Two samples were stained for the identification of eight white blood cell types, while two other sample sets were stained for the identification of resting and active eosinophils. For both data sets, four ML classifiers were evaluated on stain-free imagery with stratified 5-fold cross-validation. On the white blood cell data set, the best obtained results were 0.778 and 0.703 balanced accuracy for classical ML and DL, respectively. On the eosinophil data set, this was 0.871 and 0.856 balanced accuracy. We conclude that classifying cell types based on only stain-free images is possible with all four classifiers. Noteworthy, we also find that the DL approaches tested in this work do not outperform the approaches based on manually engineered features. © 2019 International Society for Advancement of Cytometry.

Classification of Human White Blood Cells Using Machine Learning for Stain-Free Imaging Flow Cytometry

Recent advances in ultra-high-throughput microscopy have enabled a new generation of cell classification methodologies using image-based cell phenotypes alone. In contrast to current single-cell analysis techniques that rely solely on slow and costly genetic/epigenetic analysis, these image-based analyses allow morphological profiling and screening of thousands or even millions of single cells at a fraction of the cost, and have been proven to demonstrate the statistical significance required for understanding the role of cell heterogeneity in diverse biological applications, ranging from cancer screening to drug candidate identification/validation processes. This paper examines the efficacies and opportunities presented by machine learning algorithms in processing large scale datasets with millions of label-free cell images. An automatic single-cell classification framework using convolutional neural network (CNN) has been developed. A comparative analysis of its efficiency in classifying large datasets against conventional k-nearest neighbors (kNN) and support vector machine (SVM) based methods are also presented. Experiments have shown that our proposed framework can efficiently identify multiple types cells with over $99\%$ accuracy based on the phenotypic label-free bright-field images; and CNN-based models perform well and relatively stable against data volume compared with kNN and SVM.

Large-Scale Multi-Class Image-Based Cell Classification With Deep Learning

Immunology Driven by Large-Scale Single-Cell Sequencing.

This paper presents a data-driven approach to estimate the object depths from light field data using Convolutional Neural Networks (CNN). By exploring the relationship between the epipolar-plane images (EPI) and the corresponding depth map, we propose an enhanced EPI feature that encodes the depth information of each physical point in the light field and obtains the disparity map of the whole scene in a supervised manner. This work covers two major contributions, namely the extraction of the enhanced EPI features and the light field depth estimation with CNN. The proposed features augment the depth information of the corresponding points in the light field, and then our CNN architecture differentiates them into different depth layers. Forward propagation step of the CNN model allows rapid recognition of the disparity map of the test light field data. In the experiments, we apply our method on the HCI (Heidelberg Col-laboratory for Image Processing) benchmark dataset and demonstrate that it is significantly faster than the state-of-the-art light field depth estimation approaches while achieving satisfactory performance.

Data-driven light field depth estimation using deep Convolutional Neural Networks

Plenoptic cameras usually sacrifice the spatial resolution of their SAIs to acquire geometry information from different viewpoints. Several methods have been proposed to mitigate such spatio-angular trade-off, but seldom make use of the structural properties of the light field (LF) data efficiently. In this paper, we propose a novel high-order residual network to learn the geometric features hierarchically from the LF for reconstruction. An important component in the proposed network is the high-order residual block (HRB), which learns the local geometric features by considering the information from all input views. After fully obtaining the local features learned from each HRB, our model extracts the representative geometric features for spatio-angular upsampling through the global residual learning. Additionally, a refinement network is followed to further enhance the spatial details by minimizing a perceptual loss. Compared with previous work, our model is tailored to the rich structure inherent in the LF, and therefore can reduce the artifacts near non-Lambertian and occlusion regions. Experimental results show that our approach enables high-quality reconstruction even in challenging regions and outperforms state-of-the-art single image or LF reconstruction methods with both quantitative measurements and visual evaluation.

/pdf/high-order-residual-network-for-light-field-super-resolution-yesvys6fme.pdf

Nan Meng

Papers

High-Dimensional Dense Residual Convolutional Neural Network for Light Field Reconstruction

Large-Scale Multi-Class Image-Based Cell Classification With Deep Learning

Data-driven light field depth estimation using deep Convolutional Neural Networks

High-Order Residual Network for Light Field Super-Resolution

High-Order Residual Network for Light Field Super-Resolution