Explore the vast range of titles available.

Significance: Circulating tumor cells (CTCs) are important biomarkers for cancer management. Isolated CTCs from blood are stained to detect and enumerate CTCs. However, the staining process is laborious and moreover makes CTCs unsuitable for drug testing and molecular characterization. Aim: The goal is to develop and test deep learning (DL) approaches to detect unstained breast cancer cells in bright-field microscopy images that contain white blood cells (WBCs). Approach: We tested two convolutional neural network (CNN) approaches. The first approach allows investigation of the prominent features extracted by CNN to discriminate in vitro cancer cells from WBCs. The second approach is based on faster region-based convolutional neural network (Faster R-CNN). Results: Both approaches detected cancer cells with higher than 95% sensitivity and 99% specificity with the Faster R-CNN being more efficient and suitable for deployment presenting an improvement of 4% in sensitivity. The distinctive feature that CNN uses for discrimination is cell size, however, in the absence of size difference, the CNN was found to be capable of learning other features. The Faster R-CNN was found to be robust with respect to intensity and contrast image transformations. Conclusions: CNN-based DL approaches could be potentially applied to detect patient-derived CTCs from images of blood samples.

Approach: We tested two convolutional neural network (CNN) approaches. The first approach allows investigation of the prominent features extracted by CNN to discriminate in vitro cancer cells from WBCs. The second approach is based on faster region-based convolutional neural network (Faster R-CNN).

Inertial, size-based focusing was investigated in the microfluidic labyrinth device consisting of several U-shaped turns along with circular loops. Turns are associated with tight curvature, and therefore induce strong Dean forces for separating particles, however, systematic studies exploring this possibility do not exist. We characterized the focusing dynamics of different-sized rigid particles, cancer cells and white blood cells over a range of fluid Reynolds numbers Ref. Streak widths of the focused particle streams at all the turns showed intermittent fluctuations which were substantial for smaller particles and at higher Ref. In contrast, cell streaks were less prone to fluctuations. Computational fluid dynamics simulations revealed the existence of strong turn-induced Dean vortices which help explain the intermittent fluctuations seen in particle focusing. Next, we developed a measure of pairwise separability to evaluate the quality of separation between focused streams of two different particle sizes. Using this, we assessed the impact of a single sharp turn on separation. In general, the separability was found to vary significantly as particles traversed the tight-curvature U-turn. Comparing the separability at the entry and exit sections, we found that turns either improved or reduced separation between different-sized particles depending on Ref. Finally, we evaluated the separability at the downstream expansion section to quantify the performance of the labyrinth device in terms of achieving size-based enrichment of particles and cells. Overall, our results show that turns are better for cell focusing and separation given that they are more immune to curvature-driven fluctuations in comparison to rigid particles.

Currently, detection of circulating tumor cells (CTCs) in cancer patient blood samples relies on immunostaining, which does not provide access to live CTCs, limiting the breadth of CTC-based applications. As a first step to address this limitation, here, we demonstrate staining-free enumeration of tumor cells spiked into lysed blood samples using digital holographic microscopy (DHM), microfluidics and machine learning (ML). A 3D-printed module for laser assembly was developed to simplify the optical set up for holographic imaging of cells flowing through a sheath-based microfluidic device. Computational reconstruction of the holograms was performed to localize the cells in 3D and obtain the plane of best focus images to train deep learning models. First, we evaluated the classification performance of two convolutional neural networks (CNNs): ResNet-50 and a custom-designed shallow Network dubbed s-Net. The accuracy, sensitivity and specificity of these networks were found to range from 97.08% and 99.32%. Upon selecting the s-Net due to its simple architecture and low computational burden, we formulated a decision gating strategy to significantly lower the false positive rate (FPR). By applying an optimized decision threshold to mixed samples prepared in silico, the FPR was reduced from 1×10−2 to 2.77×10−4. Finally, the developed DHM-ML framework was successfully applied to enumerate spiked MCF-7 breast cancer cells from lysed blood samples containing a background of white blood cells (WBCs). We conclude by discussing the advances that need to be made to translate the DHM-ML approach to staining-free enumeration of CTCs in cancer patient blood samples.

Circulating tumor cells (CTCs) are important biomarkers for cancer management. Isolated CTCs from blood are stained to detect and enumerate CTCs. However, the staining process is laborious and moreover makes CTCs unsuitable for drug testing and molecular characterization. The goal is to develop and test deep learning (DL) approaches to detect unstained breast cancer cells in bright field microscopy images that contain white blood cells (WBCs). We tested two convolutional neural network (CNN) approaches. The first approach allows investigation of the prominent features extracted by CNN to discriminate cancer cells from WBCs. The second approach is based on Faster Region-based Convolutional Neural Network (Faster R-CNN). Both approaches detected cancer cells with high sensitivity and specificity with the Faster R-CNN being more efficient and suitable for deployment. The distinctive feature used by the CNN used to discriminate is cell size, however in the absence of size difference, the CNN was found to be capable of learning other features. The Faster R-CNN was found to be robust with respect to intensity and contrast image transformations. CNN-based deep learning approaches could be potentially applied to detect patient-derived CTCs from images of blood samples.