Evaluation of segmentation algorithms on cell populations using CDF curves

Target-Independent Domain Adaptation for WBC Classification Using Generative Latent Search

Automating the classification of camera-obtained microscopic images of White Blood Cells (WBCs) and related cell subtypes has assumed importance since it aids the laborious manual process of review and diagnosis. Several State-Of-The-Art (SOTA) methods developed using Deep Convolutional Neural Networks suffer from the problem of domain shift - severe performance degradation when they are tested on data (target) obtained in a setting different from that of the training (source). The change in the target data might be caused by factors such as differences in camera/microscope types, lenses, lighting-conditions etc. This problem can potentially be solved using Unsupervised Domain Adaptation (UDA) techniques albeit standard algorithms presuppose the existence of a sufficient amount of unlabelled target data which is not always the case with medical images. In this paper, we propose a method for UDA that is devoid of the need for target data. Given a test image from the target data, we obtain its 'closest-clone' from the source data that is used as a proxy in the classifier. We prove the existence of such a clone given that infinite number of data points can be sampled from the source distribution. We propose a method in which a latent-variable generative model based on variational inference is used to simultaneously sample and find the 'closest-clone' from the source distribution through an optimization procedure in the latent space. We demonstrate the efficacy of the proposed method over several SOTA UDA methods for WBC classification on datasets captured using different imaging modalities under multiple settings.

Strategies for robust and accurate experimental approaches to quantify nanomaterial bioaccumulation across a broad range of organisms

One of the key components for environmental risk assessment of engineered nanomaterials (ENMs) is data on bioaccumulation potential. Accurately measuring bioaccumulation can be critical for regulatory decision making regarding material hazard and risk, and for understanding the mechanism of toxicity. This perspective provides expert guidance for performing ENM bioaccumulation measurements across a broad range of test organisms and species. To accomplish this aim, we critically evaluated ENM bioaccumulation within three categories of organisms: single-celled species, multicellular species excluding plants, and multicellular plants. For aqueous exposures of suspended single-celled and small multicellular species, it is critical to perform a robust procedure to separate suspended ENMs and small organisms to avoid overestimating bioaccumulation. For many multicellular organisms, it is essential to differentiate between the ENMs adsorbed to external surfaces or in the digestive tract and the amount absorbed across epithelial tissues. For multicellular plants, key considerations include how exposure route and the role of the rhizosphere may affect the quantitative measurement of uptake, and that the efficiency of washing procedures to remove loosely attached ENMs to the roots is not well understood. Within each organism category, case studies are provided to illustrate key methodological considerations for conducting robust bioaccumulation experiments for different species within each major group. The full scope of ENM bioaccumulation measurements and interpretations are discussed including conducting the organism exposure, separating organisms from the ENMs in the test media after exposure, analytical methods to quantify ENMs in the tissues or cells, and modeling the ENM bioaccumulation results. One key finding to improve bioaccumulation measurements was the critical need for further analytical method development to identify and quantify ENMs in complex matrices. Overall, the discussion, suggestions, and case studies described herein will help improve the robustness of ENM bioaccumulation studies.

Myofibre segmentation in H&E stained adult skeletal muscle images using coherence-enhancing diffusion filtering

BACKGROUND

The correct segmentation of myofibres in histological muscle biopsy images is a critical step in the automatic analysis process. Errors occurring as a result of incorrect segmentations have a compounding effect on latter morphometric analysis and as such it is vital that the fibres are correctly segmented. This paper presents a new automatic approach to myofibre segmentation in H&E stained adult skeletal muscle images that is based on Coherence-Enhancing Diffusion filtering.

METHODS

The procedure can be broadly divided into four steps: 1) pre-processing of the images to extract only the eosinophilic structures, 2) performing of Coherence-Enhancing Diffusion filtering to enhance the myofibre boundaries whilst smoothing the interior regions, 3) morphological filtering to connect unconnected boundary regions and remove noise, and 4) marker controlled watershed transform to split touching fibres.

RESULTS

The method has been tested on a set of adult cases with a total of 2,832 fibres. Evaluation was done in terms of segmentation accuracy and other clinical metrics.

CONCLUSIONS

The results show that the proposed approach achieves a segmentation accuracy of 89% which is a significant improvement over existing methods.

Testing Equality of Cell Populations Based on Shape and Geodesic Distance

Image cytometry has emerged as a valuable in vitro screening tool and advances in automated microscopy have made it possible to readily analyze large cellular populations of image data. The purpose of this paper is to illustrate the viability of using cell shape to test equality of cell populations based on image data. Shape space theory is reviewed, from which differences between shapes can be quantified in terms of geodesic distance. Several multivariate nonparametric statistical hypothesis tests are adapted to test equality of cell populations. It is illustrated that geodesic distance can be a better feature than cell spread area and roundness in distinguishing between cell populations. Tests based on geodesic distance are able to detect natural perturbations of cells, whereas Kolmogorov-Smirnov tests based on area and roundness are not.

Region-based progressive localization of cell nuclei in microscopic images with data adaptive modeling

Background

Segmenting cell nuclei in microscopic images has become one of the most important routines in modern biological applications. With the vast amount of data, automatic localization, i.e. detection and segmentation, of cell nuclei is highly desirable compared to time-consuming manual processes. However, automated segmentation is challenging due to large intensity inhomogeneities in the cell nuclei and the background.

Results

We present a new method for automated progressive localization of cell nuclei using data-adaptive models that can better handle the inhomogeneity problem. We perform localization in a three-stage approach: first identify all interest regions with contrast-enhanced salient region detection, then process the clusters to identify true cell nuclei with probability estimation via feature-distance profiles of reference regions, and finally refine the contours of detected regions with regional contrast-based graphical model. The proposed region-based progressive localization (RPL) method is evaluated on three different datasets, with the first two containing grayscale images, and the third one comprising of color images with cytoplasm in addition to cell nuclei. We demonstrate performance improvement over the state-of-the-art. For example, compared to the second best approach, on the first dataset, our method achieves 2.8 and 3.7 reduction in Hausdorff distance and false negatives; on the second dataset that has larger intensity inhomogeneity, our method achieves 5% increase in Dice coefficient and Rand index; on the third dataset, our method achieves 4% increase in object-level accuracy.

Conclusions

To tackle the intensity inhomogeneities in cell nuclei and background, a region-based progressive localization method is proposed for cell nuclei localization in fluorescence microscopy images. The RPL method is demonstrated highly effective on three different public datasets, with on average 3.5% and 7% improvement of region- and contour-based segmentation performance over the state-of-the-art.

Stain guided mean-shift filtering in automatic detection of human tissue nuclei

Background:

As a critical technique in a digital pathology laboratory, automatic nuclear detection has been investigated for more than one decade. Conventional methods work on the raw images directly whose color/intensity homogeneity within tissue/cell areas are undermined due to artefacts such as uneven staining, making the subsequent binarization process prone to error. This paper concerns detecting cell nuclei automatically from digital pathology images by enhancing the color homogeneity as a pre-processing step.

Methods:

Unlike previous watershed based algorithms relying on post-processing of the watershed, we present a new method that incorporates the staining information of pathological slides in the analysis. This pre-processing step strengthens the color homogeneity within the nuclear areas as well as the background areas, while keeping the nuclear edges sharp. Proof of convergence for the proposed algorithm is also provided. After pre-processing, Otsu's threshold is applied to binarize the image, which is further segmented via watershed. To keep a proper compromise between removing overlapping and avoiding over-segmentation, a naive Bayes classifier is designed to refine the splits suggested by the watershed segmentation.

Results:

The method is validated with 10 sets of 1000 × 1000 pathology images of lymphoma from one digital slide. The mean precision and recall rates are 87% and 91%, corresponding to a mean F-score equal to 89%. Standard deviations for these performance indicators are 5.1%, 1.6% and 3.2% respectively.

Conclusion:

The precision/recall performance obtained indicates that the proposed method outperforms several other alternatives. In particular, for nuclear detection, stain guided mean-shift (SGMS) is more effective than the direct application of mean-shift in pre-processing. Our experiments also show that pre-processing the digital pathology images with SGMS gives better results than conventional watershed algorithms. Nevertheless, as only one type of tissue is tested in this paper, a further study is planned to enhance the robustness of the algorithm so that other types of tissues/stains can also be processed reliably.