Chi Liu

Localizing and Extracting Filament Distributions from Microscopy Images

Detailed quantitative measurements of biological filament networks represent a crucial step in understanding architecture and structure of cells and tissues, which in turn explain important biological events such as wound healing and cancer metastases. Microscopic images of biological specimens marked for different structural proteins constitute an important source for observing and measuring meaningful parameters of biological networks. Unfortunately, current efforts at quantitative estimation of architecture and orientation of biological filament networks from microscopy images are predominantly limited to visual estimation and indirect experimental inference. Here, we describe a new method for localizing and extracting filament distributions from 2D microscopy images of different modalities. The method combines a filter‐based detection of pixels likely to contain a filament with a constrained reverse diffusion‐based approach for localizing the filaments centrelines. We show with qualitative and quantitative experiments, using both simulated and real data, that the new method can provide more accurate centreline estimates of filament in comparison to other approaches currently available. In addition, we show the algorithm is more robust with respect to variations in the initial filter‐based filament detection step often used. We demonstrate the application of the method in extracting quantitative parameters from confocal microscopy images of actin filaments and atomic force microscopy images of DNA fragments.

Detecting and segmenting cell nuclei in two-dimensional microscopy images

Introduction: Cell nuclei are important indicators of cellular processes and diseases. Segmentation is an essential stage in systems for quantitative analysis of nuclei extracted from microscopy images. Given the wide variety of nuclei appearance in different organs and staining procedures, a plethora of methods have been described in the literature to improve the segmentation accuracy and robustness. Materials and Methods: In this paper, we propose an unsupervised method for cell nuclei detection and segmentation in two-dimensional microscopy images. The nuclei in the image are detected automatically using a matching-based method. Next, edge maps are generated at multiple image blurring levels followed by edge selection performed in polar space. The nuclei contours are refined iteratively in the constructed edge pyramid. The validation study was conducted over two cell nuclei datasets with manual labeling, including 25 hematoxylin and eosin-stained liver histopathology images and 35 Papanicolaou-stained thyroid images. Results: The nuclei detection accuracy was measured by miss rate, and the segmentation accuracy was evaluated by two types of error metrics. Overall, the nuclei detection efficiency of the proposed method is similar to the supervised template matching method. In comparison to four existing state-of-the-art segmentation methods, the proposed method performed the best with average segmentation error 10.34% and 0.33 measured by area error rate and normalized sum of distances (×10). Conclusion: Quantitative analysis showed that the method is automatic and accurate when segmenting cell nuclei from microscopy images with noisy background and has the potential to be used in clinic settings.

Epithelium-stroma classification via convolutional neural networks and unsupervised domain adaptation in histopathological images

Epithelium-stroma classification is a necessary preprocessing step in histopathological image analysis. Current deep learning based recognition methods for histology data require collection of large volumes of labeled data in order to train a new neural network when there are changes to the image acquisition procedure. However, it is extremely expensive for pathologists to manually label sufficient volumes of data for each pathology study in a professional manner, which results in limitations in real-world applications. A very simple but effective deep learning method, that introduces the concept of unsupervised domain adaptation to a simple convolutional neural network (CNN), has been proposed in this paper. Inspired by transfer learning, our paper assumes that the training data and testing data follow different distributions, and there is an adaptation operation to more accurately estimate the kernels in CNN in feature extraction, in order to enhance performance by transferring knowledge from labeled data in source domain to unlabeled data in target domain. The model has been evaluated using three independent public epithelium-stroma datasets by cross-dataset validations. The experimental results demonstrate that for epithelium-stroma classification, the proposed framework outperforms the state-of-the-art deep neural network model, and it also achieves better performance than other existing deep domain adaptation methods. The proposed model can be considered to be a better option for real-world applications in histopathological image analysis, since there is no longer a requirement for large-scale labeled data in each specified domain.

Predictive nuclear chromatin characteristics of melanoma and dysplastic nevi

Background: The diagnosis of malignant melanoma (MM) is among the diagnostic challenges pathologists encounter on a routine basis. Melanoma may arise in patients with preexisting dysplastic nevi (DN) and it is still the cause of 1.7% of all cancer-related deaths. Melanomas often have overlapping histological features with DN, especially those with severe dysplasia. Nucleotyping for identifying nuclear textural features can analyze nuclear DNA structure and organization. The aim of this study is to differentiate MM and DN using these methodologies. Methods: Dermatopathology slides diagnosed as MM and DN were retrieved. The glass slides were scanned using an Aperio ScanScopeXT at ×40 (0.25 μ/pixel). Whole slide images (WSI) were annotated for nuclei selection. Nuclear features to distinguish between MM and DN based on chromatin distributions were extracted from the WSI. The morphological characteristics for each nucleus were quantified with the optimal transport-based linear embedding in the continuous domain. Label predictions for individual cell nucleus are achieved through a modified version of linear discriminant analysis, coupled with the k-nearest neighbor classifier. Label for an unknown patient was set by the voting strategy with its pertaining cell nuclei. Results: Nucleotyping of 139 patient cases of melanoma (n = 67) and DN (n = 72) showed that our method had superior classification accuracy of 81.29%. This is a 6.4% gain in differentiating MM and DN, compared with numerical feature-based method. The distribution differences in nuclei morphology between MM and DN can be visualized with biological interpretation. Conclusions: Nucleotyping using quantitative and qualitative analyses may provide enough information for differentiating MM from DN using pixel image data. Our method to segment cell nuclei may offer a practical and inexpensive solution in aiding in the accurate diagnosis of melanoma.

A supervised learning framework for pancreatic islet segmentation with multi-scale color-texture features and rolling guidance filters.

Islet cell quantification and function is important for developing novel therapeutic interventions for diabetes. Existing methods of pancreatic islet segmentation in histopathological images depend strongly on cell/nuclei detection, and thus are limited due to a wide variance in the appearance of pancreatic islets. In this paper, we propose a supervised learning pipeline to segment pancreatic islets in histopathological images, which does not require cell detection. The proposed framework firstly partitions images into superpixels, and then extracts multi‐scale color‐texture features from each superpixel and processes these features using rolling guidance filters, in order to simultaneously reduce inter‐class ambiguity and intra‐class variation. Finally, a linear support vector machine (SVM) is trained and applied to segment the testing images. A total of 23 hematoxylin‐and‐eosin‐stained histopathological images with pancreatic islets are used for verifying the framework. With an average accuracy of 95%, training time of 20 min and testing time of 1 min per image, the proposed framework outperforms existing approaches with better segmentation performance and lower computational cost.

Extraction of individual filaments from 2D confocal microscopy images of flat cells

A crucial step in understanding the architecture of cells and tissues from microscopy images, and consequently explain important biological events such as wound healing and cancer metastases, is the complete extraction and enumeration of individual filaments from the cellular cytoskeletal network. Current efforts at quantitative estimation of filament length distribution, architecture and orientation from microscopy images are predominantly limited to visual estimation and indirect experimental inference. Here we demonstrate the application of a new algorithm to reliably estimate centerlines of biological filament bundles and extract individual filaments from the centerlines by systematically disambiguating filament intersections. We utilize a filament enhancement step followed by reverse diffusion based filament localization and an integer programming based set combination to systematically extract accurate filaments automatically from microscopy images. Experiments on simulated and real confocal microscope images of flat cells (2D images) show efficacy of the new method.

Classify epithelium-stroma in histopathological images based on deep transferable network: CLASSIFY EPITHELIUM-STROMA IN HISTOPATHOLOGICAL IMAGES

Recently, the deep learning methods have received more attention in histopathological image analysis. However, the traditional deep learning methods assume that training data and test data have the same distributions, which causes certain limitations in real‐world histopathological applications. However, it is costly to recollect a large amount of labeled histology data to train a new neural network for each specified image acquisition procedure even for similar tasks. In this paper, an unsupervised domain adaptation is introduced into a typical deep convolutional neural network (CNN) model to mitigate the repeating of the labels. The unsupervised domain adaptation is implemented by adding two regularisation terms, namely the feature‐based adaptation and entropy minimisation, to the object function of a widely used CNN model called the AlexNet. Three independent public epithelium‐stroma datasets were used to verify the proposed method. The experimental results have demonstrated that in the epithelium‐stroma classification, the proposed method can achieve better performance than the commonly used deep learning methods and some existing deep domain adaptation methods. Therefore, the proposed method can be considered as a better option for the real‐world applications of histopathological image analysis because there is no requirement for recollection of large‐scale labeled data for every specified domain.

Epithelium-stroma classification in histopathological images via convolutional neural networks and self-taught learning

Epithelium-stroma classification is always considered as an important preprocessing step for morphological quantitative analysis in image-based histological researches of oncologic diseases. However, large-scale accurate ground-truth labeling is expensive in histopathological image analysis, thus the classification performances will still be limited with the insufficient labeled training samples. Considering that acquisition of public unlabeled histopathological images is much cheaper, an epithelium-stroma classification framework is developed, based on the deep convolutional neural network framework and the strategies of self-taught learning. The method has the ability of taking advantage of large-scale unlabeled public histopathological data as auxiliary data, and then transferring the knowledge to enhance the performances in epithelium-stroma classification with limited labeled training data. The experiments demonstrate that the proposed method outperforms traditional CNNs when the labeled training data size is decreasing dramatically.

Impact of altering various image parameters on human epidermal growth factor receptor 2 image analysis data quality

Introduction: The quality of data obtained from image analysis can be directly affected by several preanalytical (e.g., staining, image acquisition), analytical (e.g., algorithm, region of interest [ROI]), and postanalytical (e.g., computer processing) variables. Whole-slide scanners generate digital images that may vary depending on the type of scanner and device settings. Our goal was to evaluate the impact of altering brightness, contrast, compression, and blurring on image analysis data quality. Methods: Slides from 55 patients with invasive breast carcinoma were digitized to include a spectrum of human epidermal growth factor receptor 2 (HER2) scores analyzed with Visiopharm (30 cases with score 0, 10 with 1+, 5 with 2+, and 10 with 3+). For all images, an ROI was selected and four parameters (brightness, contrast, JPEG2000 compression, out-of-focus blurring) then serially adjusted. HER2 scores were obtained for each altered image. Results: HER2 scores decreased with increased illumination, higher compression ratios, and increased blurring. HER2 scores increased with greater contrast. Cases with HER2 score 0 were least affected by image adjustments. Conclusion: This experiment shows that variations in image brightness, contrast, compression, and blurring can have major influences on image analysis results. Such changes can result in under- or over-scoring with image algorithms. Standardization of image analysis is recommended to minimize the undesirable impact such variations may have on data output.

Hierarchical Feature Extraction for Nuclear Morphometry-Based Cancer Diagnosis

Cell and nuclear morphology, as observed from histopathology microscopy images, have long been known as important indicators of disease states. Due to the large amount of data, obtaining expert pathologists annotations at the individual cell level is impractical in many applications, however. Thus the majority of the approaches currently available for automated classification and cancer detection are based on utilizing the patient label for each segmented cell, and patient classification is performed by classifying single morphological exemplars (e.g. cells or subcellular features) in combination with a majority voting procedure. Here we propose a new hierarchical method for classifying sets of nuclei. The method can be interpreted as a type of multiple instance learning (MIL) method in that it embeds data from each patient into a hierarchical feature space. The feature space, and classification boundary, are alternatively optimized utilizing the support vector machine (SVM) cost function. We demonstrate the application of the method in the diagnosis of thyroid lesions and compare to existing MIL methods showing significant improvements in classification accuracy.