Label-free Cell Classification Research Articles

A Miniaturized and Intelligent Lensless Holographic Imaging System With Auto-Focusing and Deep Learning-Based Object Detection for Label-Free Cell Classification

A Miniaturized and Intelligent Lensless Holographic Imaging System With Auto-Focusing and Deep Learning-Based Object Detection for Label-Free Cell Classification

Label-free cell classification in holographic flow cytometry through an unbiased learning strategy.

Nowadays, label-free imaging flow cytometry at the single-cell level is considered the stepforward lab-on-a-chip technology to address challenges in clinical diagnostics, biology, life sciences and healthcare. In this framework, digital holography in microscopy promises to be a powerful imaging modality thanks to its multi-refocusing and label-free quantitative phase imaging capabilities, along with the encoding of the highest information content within the imaged samples. Moreover, the recent achievements of new data analysis tools for cell classification based on deep/machine learning, combined with holographic imaging, are urging these systems toward the effective implementation of point of care devices. However, the generalization capabilities of learning-based models may be limited from biases caused by data obtained from other holographic imaging settings and/or different processing approaches. In this paper, we propose a combination of a Mask R-CNN to detect the cells, a convolutional auto-encoder, used to the image feature extraction and operating on unlabelled data, thus overcoming the bias due to data coming from different experimental settings, and a feedforward neural network for single cell classification, that operates on the above extracted features. We demonstrate the proposed approach in the challenging classification task related to the identification of drug-resistant endometrial cancer cells.

On-chip label-free cell classification based directly on off-axis holograms and spatial-frequency-invariant deep learning

We present a rapid label-free imaging flow cytometry and cell classification approach based directly on raw digital holograms. Off-axis holography enables real-time acquisition of cells during rapid flow. However, classification of the cells typically requires reconstruction of their quantitative phase profiles, which is time-consuming. Here, we present a new approach for label-free classification of individual cells based directly on the raw off-axis holographic images, each of which contains the complete complex wavefront (amplitude and quantitative phase profiles) of the cell. To obtain this, we built a convolutional neural network, which is invariant to the spatial frequencies and directions of the interference fringes of the off-axis holograms. We demonstrate the effectiveness of this approach using four types of cancer cells. This approach has the potential to significantly improve both speed and robustness of imaging flow cytometry, enabling real-time label-free classification of individual cells.

Accurate holographic cytometry using three-dimensional hydrodynamic focusing

We present a microfluidic holographic cytometry technique using three-dimensional (3D) hydrodynamic focusing for accurate visualization, classification, and quantification of the cells and particles from a mixture. Our approach uses high-resolution, single-shot digital holographic microscopy to image moving cells and particles in a specially-designed microfluidic device that orders the cells and particles in a single file close to the bottom wall of the channel. Our 3D-focusing microfluidic device allows high-magnification holographic imaging without the need for computationally-expensive numerical refocusing used by the existing holographic cytometry techniques. Our microfluidic device also prevents the clustering of cells and can be fabricated at a low-cost using micromilling. To demonstrate the efficacy of our method, we consider a challenging case of classification from a mixture of unstained red blood cells and polystyrene particles, which are otherwise indistinguishable in brightfield and phase-contrast microscopy. Through experiments with cell-particle mixtures with varying proportions, we show that our holographic cytometry technique can precisely count and classify the cells and particles based on their reconstructed phase values. Our holographic cytometry technique has the potential for label-free classification and quantification of infected cells for applications such as disease diagnostics, cancer research, and genomics.

Identification of drug-resistant cancer cells in flow cytometry combining 3D holographic tomography with machine learning

Identifying drug-resistant cancer cells is of fundamental importance to afford disease and find the most effective therapies for the patients. Recently, label-free imaging flow cytometry has been deeply investigated in cell recognition. In particular, the combination of flow cytometry and machine learning allows for achieving high accuracy in cell identification and high throughput. Despite the encouraging results, the potentialities of digital holography (DH) in flow-cytometry modality have not been exploited in full. Up to now, only 2D phase maps have been used in all previously reported research about the use of DH for analyzing flowing cells. Here we show that having access to the whole 3D information of each flowing cell can improve the cells identification. We used digital holographic flow cytometry to collect images of flowing cells and reconstructed their 3D tomographic phase. And for the first time, we extracted scores of meaningful morphometric features from the 3D and 2D phase maps through machine learning methods and finally compare their classification performance. The results show that 3D features can achieve higher classification accuracy with respect to sole 2D analysis demonstrating that 3D morphology information can yield advantages in recognizing drug-resistant endometrial cancer cells, thus allowing a significant step forward in performance of label-free cell classification.

High-content video flow cytometry with digital cell filtering for label-free cell classification by machine learning.

Recent development of imaging flow cytometry (IFC) has enabled the measurements of single cells with high throughput, where fluorescent labels provide specificity for cellular diagnosis. The fluorescent labels may disturb the cell functions, and the requirements for high-throughput measurements limit the cell image quality. Here, we develop the high-content video flow cytometry (VFC) that measures unlabeled single cells with a rate of approximately 1000 cells per minute. For the obtained big data, the frame of interest (FOI) is automatically prepared by a digital cell filtering technique with machine learning. Cervical carcinoma cell lines (Caski, HeLa and C33-A cells) are differentiated with an accuracy of 91.5%, 90.5%, and 90.5% by deep learning in a three-way classification, respectively. The high-content VFC not only provides high-quality images of single cells with high throughput and rewinding, but also performs automatic digital cell filtering and label-free cell classification that may have clinical applications.

Accurate profiling of blood components in microliter with position-insensitive coplanar electrodes-based cytometry

Differentiating and counting blood cell subtypes are essential for medical diagnosis. Microfluidic impedance-based cytometry has been discussed in the past decade as cost-effective and label-free cell classification using multi-cellular electrical properties. The coplanar electrode configuration is particularly desirable since it can dramatically reduce the device fabrication complexity and cost. However, very few research demonstrated accurate leukocyte classification with coplanar electrodes due to the in-channel height-dependent sensitivity variation in cell profiling caused by nonuniform electric field. Herein we propose a microfluidic high-throughput (up to 1000 cells/second) impedance cytometry with a unique coplanar electrode configuration to eliminate height-dependent sensitivity variation for accurate electrical cell profiling. The proposed position-insensitive cytometry enables an accurate 3-part leukocyte classification and quantification comparable with fluorescence-based cytometry. In addition, unlike conventional leukocyte classification approaches that require red blood cell lysis to remove noises caused by erythrocytes, the position-insensitive cytometry can distinguish erythrocytes simply based on cell sizes and characterize the mean size and distribution width of erythrocytes with leukocyte classification simultaneously, offering red blood cell indices for diagnosis with reduced test time. The position-insensitive impedance cytometry has the great potential to provide a point-of-care blood analysis for clinical utility in many diseases (i.e., infections, cancers and HIV).

Abstract 188: Deep learning enables label-free profiling of the tumor microenvironment and enrichment of rare cancer cells

Abstract Understanding the tumor microenvironment and detecting rare circulating tumor cells from blood are two major challenges faced by cancer biologists and oncologists. Both require high sensitivity and accuracy in classifying and isolating single cells in a complex and heterogeneous environment. Classical cell classification and sorting techniques are limited by their reliance on pre-selected cell biomarkers or physical characteristics. Recent breakthroughs in machine learning have achieved unprecedented accuracy across a wide range of image classification problems. We have developed a platform that combines high-resolution imaging of unlabeled cells in microfluidic flow with real-time deep neural network (DNN) based classification and sorting. The DNN classifier was trained on more than 25 million high-resolution cell images of multiple types imaged on the platform. Our model was trained to discriminate among multiple cell classes, including immune cell subtypes, non-small-cell lung cancer cells (NSCLC), hepatocellular carcinomas (HCC), and stromal cells (including endothelial, epithelial, fibroblasts, smooth muscle cells). We then assessed model performance on a separate validation set of cell images, including cell lines not used in the training data. Our classifier accurately identifies NSCLC and HCC against a background of blood cells with an area under the ROC curve (AUC) of > 0.999. In addition we demonstrate the enrichment of NSCLC cells from spike-in mixtures with WBCs or whole blood at concentrations as low as 1:100,000, achieving an enrichment of > 25,000x on multiple cell lines. Using dissociated lung cancer tissue, we demonstrate that our label-free classification of tumor cells closely matches results from both standard flow cytometer analysis and single cell RNA sequencing. Additionally we were able to enrich the tumor cell fraction from dissociated tumor tissue thereby improving the sensitivity of mutation detection and enabling refined downstream single-cell genomic analysis. This work demonstrates that deep learning using high-resolution cell images collected at scale can achieve a high classification accuracy and can enable the label-free isolation of rare cells of interest for a wide range of applications. This system can be used to analyze tumor biopsies and liquid biopsies and has the potential to enable the study of tumor cells and tumor microenvironment with novel dimension and insight. Citation Format: Mahyar Salek, Hou-pu Chou, Prashast Khandelwal, Krishna P. Pant, Thomas J. Musci, Nianzhen Li, Christina Chang, Andreja Jovic, Esther Lee, Stephanie Huang, Jeff Walker, Phuc Nguyen, Kiran Saini, Jeanette Mei, Quillan F. Smith, Maddison Masaeli. Deep learning enables label-free profiling of the tumor microenvironment and enrichment of rare cancer cells [abstract]. In: Proceedings of the American Association for Cancer Research Annual Meeting 2021; 2021 Apr 10-15 and May 17-21. Philadelphia (PA): AACR; Cancer Res 2021;81(13_Suppl):Abstract nr 188.

Abstract 1305: Classification of cell morphology using machine learning and label-free live-cell imaging

Abstract Cell morphology is incredibly diverse and provides valuable insight into cellular dynamics, including cell health and differentiation. For ease of analysis, morphology studies often focus on quantifying one or two metrics, e.g. circularity or area. However, this may lead to incorrect conclusions as information about cell size, shape, brightness and texture all capture different nuances of morphology. By using multivariate data analysis (MVDA), multiple properties can be combined into a single metric that simultaneously describes the many different aspects of cell morphology. Supervised machine learning tools further enable identifying subpopulations of cells by their morphology alone. Here we describe a workflow for label-free classification of heterogeneous cells using phase contrast images. Classification of live and dead cells across range of cancer cell types was evaluated. Cells were seeded into 96-well plates and maintained in a physiologically relevant environment to ensure morphology was unperturbed. After 24h, cells were treated with compounds exerting cytotoxic effects via a range of mechanisms. All plates contained camptothecin (CMP, 10 µM) as a control for cell death and were in the presence of a fluorescent cell health reagent (Incucyte® Annexin V) to verify cell death. Images were acquired using an Incucyte® Live-Cell Analysis System (10x objective, every 2h for 3 days) and were segmented using the integrated Incucyte® Cell-by-Cell Analysis Software Module. For validation, cells were also classified based on fluorescence (Annexin V positive) to yield a dead cell percentage. An MVDA regression model was trained for each cell type using only the label-free morphology metrics extracted from the segmented phase contrast images of live (untreated cells, range of confluence values) and dead (10 µM CMP, 72h only) cells. This model was subsequently applied to all acquired images to classify every cell as live or dead. Time- and concentration-dependent increases in the fraction of dead cells closely matched that of the fluorescence classification for all tested conditions. For example, A549 cells treated with CMP produced EC50 values of 0.53 µM (label-free) and 0.66 µM (fluorescence). The analysis proved robust across multiple cell types and compounds, even in cases where morphological change occurred unrelated to cell death. In conclusion, our data demonstrates the utility of an MVDA approach for measuring cell morphology change using label-free live/dead classification as validation. Similar classifications may be applied to alternative biological paradigms which undergo morphological change, such as cell differentiation. Additionally, as the use of morphology metrics for classification requires accurate delineation of cells, improved cell segmentation tools utilizing convolutional neural network models may further enable application of these methods to more challenging cell types. Citation Format: Gillian F. Lovell, Daniel A. Porto, Timothy R. Jackson, Jasmine Trigg, Nicola Bevan, Christoffer Edlund, Rickard Sjöegren, Nevine Holtz, Daniel M. Appledorn, Timothy Dale. Classification of cell morphology using machine learning and label-free live-cell imaging [abstract]. In: Proceedings of the American Association for Cancer Research Annual Meeting 2021; 2021 Apr 10-15 and May 17-21. Philadelphia (PA): AACR; Cancer Res 2021;81(13_Suppl):Abstract nr 1305.

Label-free classification of dead and live colonic adenocarcinoma cells based on 2D light scattering and deep learning analysis.

The measurement of cell viability plays an essential role in the area of cell biology. At present, the common methods for cell viability assay mainly on the responses of cells to different dyes. However, the additional steps of cell staining will consequently cause time-consuming and laborious efforts. Furthermore, the process of cell staining is invasive and may cause internal structure damage of cells, restricting their reuse in subsequent experiments. In this work, we proposed a label-free method to classify live and dead colonic adenocarcinoma cells by 2D light scattering combined with the deep learning algorithm. The deep convolutional network of YOLO-v3 was used to identify and classify light scattering images of live and dead HT29 cells. This method achieved an excellent sensitivity (93.6%), specificity (94.4%), and accuracy (94%). The results showed that the combination of 2D light scattering images and deep neural network may provide a new label-free method for cellular analysis.

Non-invasive cell classification using the Paint Raman Express Spectroscopy System (PRESS)

Raman scattering represents the distribution and abundance of intracellular molecules, including proteins and lipids, facilitating distinction between cellular states non-invasively and without staining. However, the scattered light obtained from cells is faint and cells have complex structures, making it difficult to obtain a Raman spectrum covering the entire cell in a short time using conventional methods. This also prevents efficient label-free cell classification. In the present study, we developed the Paint Raman Express Spectroscopy System, which uses two fast-rotating galvano mirrors to obtain spectra from a wide area of a cell. By using this system and applying machine learning, we were able to acquire broad spectra of a variety of human and mouse cell types, including pluripotent stem cells and confirmed that each cell type can be classified with high accuracy. Moreover, we classified different activation states of human T cells, despite their similar morphology. This system could be used for rapid and low-cost drug evaluation and quality management for drug screening in cell-based assays.

Abstract 5376: Label-free classification of cells based on supervised machine learning of subcellular structures for negative selection of circulating tumor cells

Abstract Background: Circulating tumor cells (CTCs) are used as a liquid biopsy target in the treatment of cancer patients and are important for personalized medicine. Most CTC detection technologies are based on their surface markers such as EpCAM and cytokeratin. However, those positive selection methodologies appear to count only some CTCs because invasive tumor cells tend to change their surface markers during progression. Because the vast majority of nucleated cells circulating in the bloodstream are white blood cells (WBCs), eliminating WBCs from circulation is an efficient method to purify CTCs by negative selection. In this study, we demonstrate the development of cell recognition by computer vision technologies for pattern recognition based on the morphological features of live cells. Materials and methods: Blood samples obtained from healthy volunteers, and five cancer cell lines, SW480, DLD-1, HCT116, Panc-1, and HepG2 were imaged by quantitative phase microscopy (QPM), which provides morphological information without staining quantitatively in terms of optical thickness of cells. Subcellular features were then extracted from the obtained images as training data sets for the machine learning. WBC recognition algorithm was developed using computer vision technologies for pattern recognition based on the histogram-oriented gradient (HOG) features extracted from QPM images (QPIs). Results: We observed WBCs and five cell line cells by QPM, extracted certain features from the obtained images as training data for pattern recognition, and created an algorithm to differentiate WBCs from cell lines. The obtained algorithm successfully differentiated WBCs from cell lines (AUC=0.996). This image recognition methods was then applied to QPIs of the cells flowing in the chamber, and properly differentiated WBCs from cell line cells flowing in the chamber (AUC=0.99). Finally, we applied this method to blood samples obtained from a healthy volunteer and patients with advanced cancer, and identified CTC fractions which were much higher in blood of a cancer patient than that of a healthy volunteer. In addition, in esophageal cancer patients who received neoadjuvant chemotherapy followed by surgery, CTC fractions changed over time consistently with therapeutic effects. Conclusions: We developed a novel method for label-free image identification of live cells by computer vision technologies for pattern recognition based on the features of QPIs. Our novel method is expected to apply to detecting CTCs in a noncytotoxic manner, thus providing good opportunities for studying intact CTCs Citation Format: Hirotoshi Kikuchi, Amane Hirotsu, Yusuke Ozaki, Hidenao Yamada, Daisuke Yamashita, Shigetoshi Okazaki, Yukio Ueda, Tomohiro Matsumoto, Yoshihiro Hiramatsu, Kinji Kamiya, Yoshifumi Morita, Takanori Sakaguchi, Hiroyuki Konno, Hiroya Takeuchi. Label-free classification of cells based on supervised machine learning of subcellular structures for negative selection of circulating tumor cells [abstract]. In: Proceedings of the Annual Meeting of the American Association for Cancer Research 2020; 2020 Apr 27-28 and Jun 22-24. Philadelphia (PA): AACR; Cancer Res 2020;80(16 Suppl):Abstract nr 5376.

Label-free detection of rare circulating tumor cells by image analysis and machine learning

Detection and characterization of rare circulating tumor cells (CTCs) in patients' blood is important for the diagnosis and monitoring of cancer. The traditional way of counting CTCs via fluorescent images requires a series of tedious experimental procedures and often impacts the viability of cells. Here we present a method for label-free detection of CTCs from patient blood samples, by taking advantage of data analysis of bright field microscopy images. The approach uses the convolutional neural network, a powerful image classification and machine learning algorithm to perform label-free classification of cells detected in microscopic images of patient blood samples containing white blood cells and CTCs. It requires minimal data pre-processing and has an easy experimental setup. Through our experiments, we show that our method can achieve high accuracy on the identification of rare CTCs without the need for advanced devices or expert users, thus providing a faster and simpler way for counting and identifying CTCs. With more data becoming available in the future, the machine learning model can be further improved and can serve as an accurate and easy-to-use tool for CTC analysis.

Machine learning of diffraction image patterns for accurate classification of cells modeled with different nuclear sizes.

Measurement of nuclear-to-cytoplasm (N:C) ratios plays an important role in detection of atypical and tumor cells. Yet, current clinical methods rely heavily on immunofluroescent staining and manual reading. To achieve the goal of rapid and label-free cell classification, realistic optical cell models (OCMs) have been developed for simulation of diffraction imaging by single cells. A total of 1892 OCMs were obtained with varied nuclear volumes and orientations to calculate cross-polarized diffraction image (p-DI) pairs divided into three nuclear size groups of OCMS , OCMO and OCML based on three prostate cell structures. Binary classifications were conducted among the three groups with image parameters extracted by the algorithm of gray-level co-occurrence matrix. The averaged accuracy of support vector machine (SVM) classifier on test dataset of p-DI was found to be 98.8% and 97.5% respectively for binary classifications of OCMS vs OCMO and OCMO vs OCML for the prostate cancer cell structure. The values remain about the same at 98.9% and 97.8% for the smaller prostate normal cell structures. The robust performance of SVM over clustering classifiers suggests that the high-order correlations of diffraction patterns are potentially useful for label-free detection of single cells with large N:C ratios.

Mechano-Optical Analysis of Single Cells with Transparent Microcapillary Resonators.

The study of biophysical properties of single cells is becoming increasingly relevant in cell biology and pathology. The measurement and tracking of magnitudes such as cell stiffness, morphology, and mass or refractive index have brought otherwise inaccessible knowledge about cell physiology, as well as innovative methods for high-throughput label-free cell classification. In this work, we present hollow resonator devices based on suspended glass microcapillaries for the simultaneous measurement of single-cell buoyant mass and reflectivity with a throughput of 300 cells/minute. In the experimental methodology presented here, both magnitudes are extracted from the devices' response to a single probe, a focused laser beam that enables simultaneous readout of changes in resonance frequency and reflected optical power of the devices as cells flow within them. Through its application to MCF-7 human breast adenocarcinoma cells and MCF-10A nontumorigenic cells, we demonstrate that this mechano-optical technique can successfully discriminate pathological from healthy cells of the same tissue type.

Deep Cytometry: Deep learning with Real-time Inference in Cell Sorting and Flow Cytometry

Deep learning has achieved spectacular performance in image and speech recognition and synthesis. It outperforms other machine learning algorithms in problems where large amounts of data are available. In the area of measurement technology, instruments based on the photonic time stretch have established record real-time measurement throughput in spectroscopy, optical coherence tomography, and imaging flow cytometry. These extreme-throughput instruments generate approximately 1 Tbit/s of continuous measurement data and have led to the discovery of rare phenomena in nonlinear and complex systems as well as new types of biomedical instruments. Owing to the abundance of data they generate, time-stretch instruments are a natural fit to deep learning classification. Previously we had shown that high-throughput label-free cell classification with high accuracy can be achieved through a combination of time-stretch microscopy, image processing and feature extraction, followed by deep learning for finding cancer cells in the blood. Such a technology holds promise for early detection of primary cancer or metastasis. Here we describe a new deep learning pipeline, which entirely avoids the slow and computationally costly signal processing and feature extraction steps by a convolutional neural network that directly operates on the measured signals. The improvement in computational efficiency enables low-latency inference and makes this pipeline suitable for cell sorting via deep learning. Our neural network takes less than a few milliseconds to classify the cells, fast enough to provide a decision to a cell sorter for real-time separation of individual target cells. We demonstrate the applicability of our new method in the classification of OT-II white blood cells and SW-480 epithelial cancer cells with more than 95% accuracy in a label-free fashion.

Machine learning-driven label-free cell sorting for CAR-T cell manufacturing

Background & Aim We have developed a label-free high throughput machine learning-driven cell sorter based on cells’ morphological information. The cytometer acquires cell-specific waveform signals containing morphologic information from a defined training set. After a supervised machine learning model is developed from the training set, the cell of interest can be classified and sorted based on the scores obtained by the machine learning model. We investigated that the label-free cell classification and sorting of CAR-T cells to improve manufacturing process. CAR-T therapy has shown innovative therapeutic effects in leukemia treatment. However, many clinical studies have been conducted and the clinical results indicated that quality control for the therapeutic cell production process is always an issue for any cell therapy manufacturing process. Also, an ideal CAR-T cell population or “High-Quality CAR-T” with regard to a T cell subset, phenotype, and CAR construct is under investigation. Detailed analysis of CAR-T cells administered to CLL patients have been conducted and the results revealed the important features of clinically active CAR-T such as its glycolysis status, early memory phenotype or exhaustion low profile. Methods, Results & Conclusion To avoid CAR-T manufacturing failure and/or improve the CAR-T quality, it is necessary to collect enough healthy and functional T cells from the patient by leukapheresis in the manufacturing process. We investigated that our label-free cytometer can discriminate healthy T cells from samples after hemolysis process, wherein CD3 positive T cells and other cells were used as a training set to develop the T cell classifier model. The accuracy of the label-free discrimination of T cells was found to be very high. This label-free classification may allow us to perform the quality control of CAR-T manufacturing without the use of surface markers and at the minimal sample loss.

Label-free classification of cells based on supervised machine learning of subcellular structures

It is demonstrated that cells can be classified by pattern recognition of the subcellular structure of non-stained live cells, and the pattern recognition was performed by machine learning. Human white blood cells and five types of cancer cell lines were imaged by quantitative phase microscopy, which provides morphological information without staining quantitatively in terms of optical thickness of cells. Subcellular features were then extracted from the obtained images as training data sets for the machine learning. The built classifier successfully classified WBCs from cell lines (area under ROC curve = 0.996). This label-free, non-cytotoxic cell classification based on the subcellular structure of QPM images has the potential to serve as an automated diagnosis of single cells.

Abstract 2588: Label-free classification of live cells using quantitative phase microscopy images for negative selection of circulating tumor cells

Abstract Background: Circulating tumor cells (CTCs) are used as a liquid biopsy target in the treatment of cancer patients and are important for personalized medicine. Most CTC detection technologies are based on their surface markers such as EpCAM and cytokeratin. However, those positive selection methodologies appear to count only some CTCs because invasive tumor cells tend to change their surface markers during progression. Because the vast majority of nucleated cells circulating in the bloodstream are white blood cells (WBCs), eliminating WBCs from circulation is an efficient method to purify CTCs by negative selection. In this study, we demonstrate the development of cell recognition by computer vision technologies for pattern recognition based on the morphological features of live cells. Materials and methods: Blood samples were obtained from healthy volunteers. Five cancer cell lines, SW480, DLD-1, HCT116, Panc-1, and HepG2 were used as CTC models. We applied quantitative phase microscopy (QPM) that detects the small delay of the phase and image optical path lengths and provides quantitative morphological information of live cells with high contrast without staining. WBC recognition algorithm was developed using computer vision technologies for pattern recognition based on the histogram-oriented gradient (HOG) features extracted from QPM images (QPIs) for negative selection of CTCs. Results: We observed WBCs and five cell line cells by QPM, extracted certain features from the obtained images as training data for pattern recognition, and created an algorithm to differentiate WBCs from cell lines. The obtained algorithm successfully differentiated WBCs from cell lines (AUC=0.98). To simulate WBCs and cell lines with a small and strong change, respectively, in optical thickness (OT) at the center of the cell, we created a homogeneous hemi-ellipsoid model and a heterogeneous hemi-ellipsoid model, respectively. In these models, OT gradually increased from the edge to the center, but fluctuated around the center to simulate intracellular heterogeneity of a cancer cell. Based on these simulations, the classifier was interpreted to recognize intracellular heterogeneity, especially in the center of the cell. Finally, we applied our image recognition methods to QPIs of the cells flowing in the chamber, and properly differentiate WBCs from cell line cells flowing in the chamber (AUC=0.99). Conclusions: We developed a novel method for label-free image identification of live cells by computer vision technologies for pattern recognition based on the features of QPIs. Our study makes it possible to sort CTCs in a non-cytotoxic manner, thus providing good opportunities for molecular biological approaches to isolate CTCs. Citation Format: Hirotoshi Kikuchi, Yusuke Ozaki, Amane Hirotsu, Hidenao Yamada, Shigetoshi Okazaki, Tomohiro Murakami, Tomohiro Matsumoto, Yoshihiro Hiramatsu, Kinji Kamiya, Takanori Sakaguchi, Hiroyuki Konno, Hiroya Takeuchi. Label-free classification of live cells using quantitative phase microscopy images for negative selection of circulating tumor cells [abstract]. In: Proceedings of the American Association for Cancer Research Annual Meeting 2018; 2018 Apr 14-18; Chicago, IL. Philadelphia (PA): AACR; Cancer Res 2018;78(13 Suppl):Abstract nr 2588.

A sheath-less electric impedance micro-flow cytometry device for rapid label-free cell classification and viability testing

A sheath-less PDMS microfluidic IFC device with a simple structure was constructed, with a good performance in single-cell detection. The electrical conductance and susceptance were used to differentiate the beads/cells.