Robust segmentation of overlapping cells in histopathology specimens using parallel seed detection and repulsive level set

Robust selection-based sparse shape model for lung cancer image segmentation

Accurate cellular level segmentation of lung cancer is the prerequisite to extract objective morphological features in digitized pathology specimens. It is of great importance for image-guided diagnosis and prognosis. However, it is challenging to correctly and robustly segment cells in lung cancer images due to cell occlusion or touching, intracellular inhomogeneity, background clutter, etc. In this paper, we present a novel segmentation algorithm combining a robust selection-based sparse shape model (top-down) and an efficient local repulsive balloon snake deformable model (bottom-up) to tackle these challenges. The algorithm has been extensively tested on 62 cases with over 6000 tumor cells. We experimentally demonstrate that the proposed algorithm can produce better performance than other state-of-the-art methods.

NeuroGPS: automated localization of neurons for brain circuits using L1 minimization model

Drawing the map of neuronal circuits at microscopic resolution is important to explain how brain works. Recent progresses in fluorescence labeling and imaging techniques have enabled measuring the whole brain of a rodent like a mouse at submicron-resolution. Considering the huge volume of such datasets, automatic tracing and reconstruct the neuronal connections from the image stacks is essential to form the large scale circuits. However, the first step among which, automated location the soma across different brain areas remains a challenge. Here, we addressed this problem by introducing L1 minimization model. We developed a fully automated system, NeuronGlobalPositionSystem (NeuroGPS) that is robust to the broad diversity of shape, size and density of the neurons in a mouse brain. This method allows locating the neurons across different brain areas without human intervention. We believe this method would facilitate the analysis of the neuronal circuits for brain function and disease studies.

A robust cell counting approach based on a normalized 2D cross-correlation scheme for in-line holographic images

To achieve the important aims of identifying and marking disease progression, cell counting is crucial for various biological and medical procedures, especially in a Point-Of-Care (POC) setting. In contrast to the conventional manual method of counting cells, a software-based approach provides improved reliability, faster speeds, and greater ease of use. We present a novel software-based approach to count in-line holographic cell images using the calculation of a normalized 2D cross-correlation. This enables fast, computationally-efficient pattern matching between a set of cell library images and the test image. Our evaluation results show that the proposed system is capable of quickly counting cells whilst reliably and accurately following human counting capability. Our novel approach is 5760 times faster than manual counting and provides at least 68% improved accuracy compared to other image processing algorithms.

Charisma: an integrated approach to automatic H&E-stained skeletal muscle cell segmentation using supervised learning and novel robust clump splitting

Histological image analysis plays a key role in understanding the effects of disease and treatment responses at the cellular level. However, evaluating histology images by hand is time-consuming and subjective. While semi-automatic and automatic approaches for image segmentation give acceptable results in some branches of histological image analysis, until now this has not been the case when applied to skeletal muscle histology images. We introduce Charisma, a new top-down cell segmentation framework for histology images which combines image processing techniques, a supervised trained classifier and a novel robust clump splitting algorithm. We evaluate our framework on real-world data from intensive care unit patients. Considering both segmentation and cell property distributions, the results obtained by our method correspond well to the ground truth, outperforming other examined methods.

Attributed relational graphs for cell nucleus segmentation in fluorescence microscopy images

More rapid and accurate high-throughput screening in molecular cellular biology research has become possible with the development of automated microscopy imaging, for which cell nucleus segmentation commonly constitutes the core step. Although several promising methods exist for segmenting the nuclei of monolayer isolated and less-confluent cells, it still remains an open problem to segment the nuclei of more-confluent cells, which tend to grow in overlayers. To address this problem, we propose a new model-based nucleus segmentation algorithm. This algorithm models how a human locates a nucleus by identifying the nucleus boundaries and piecing them together. In this algorithm, we define four types of primitives to represent nucleus boundaries at different orientations and construct an attributed relational graph on the primitives to represent their spatial relations. Then, we reduce the nucleus identification problem to finding predefined structural patterns in the constructed graph and also use the primitives in region growing to delineate the nucleus borders. Working with fluorescence microscopy images, our experiments demonstrate that the proposed algorithm identifies nuclei better than previous nucleus segmentation algorithms.

Segmentation of clustered nuclei based on concave curve expansion

Segmentation of nuclei from images of tissue sections is important for many biological and biomedical studies. Many existing image segmentation algorithms may lead to oversegmentation or undersegmentation for clustered nuclei images. In this paper, we proposed a new image segmentation algorithm based on concave curve expansion to correctly and accurately extract markers from the original images. Marker-controlled watershed is then used to segment the clustered nuclei. The algorithm was tested on both synthetic and real images and better results are achieved compared with some other state-of-the-art methods.

Automated and accurate detection of soma location and surface morphology in large-scale 3D neuron images

Automated and accurate localization and morphometry of somas in 3D neuron images is essential for quantitative studies of neural networks in the brain. However, previous methods are limited in obtaining the location and surface morphology of somas with variable size and uneven staining in large-scale 3D neuron images. In this work, we proposed a method for automated soma locating in large-scale 3D neuron images that contain relatively sparse soma distributions. This method involves three steps: (i) deblocking the image with overlap between adjacent sub-stacks; (ii) locating the somas in each small sub-stack using multi-scale morphological close and adaptive thresholds; and (iii) fusion of the repeatedly located somas in all sub-stacks. We also describe a new method for the accurate detection of the surface morphology of somas containing hollowness; this was achieved by improving the classical Rayburst Sampling with a new gradient-based criteria. Three 3D neuron image stacks of different sizes were used to quantitatively validate our methods. For the soma localization algorithm, the average recall and precision were greater than 93% and 96%, respectively. For the soma surface detection algorithm, the overlap of the volumes created by automatic detection of soma surfaces and manually segmenting soma volumes was more than 84% for 89% of all correctly detected somas. Our method for locating somas can reveal the soma distributions in large-scale neural networks more efficiently. The method for soma surface detection will serve as a valuable tool for systematic studies of neuron types based on neuron structure.

An integrated framework for automatic Ki-67 scoring in pancreatic neuroendocrine tumor

The Ki-67 labeling index is a valid and important biomarker to gauge neuroendocrine tumor cell progression. Automatic Ki-67 assessment is very challenging due to complex variations of cell characteristics. In this paper, we propose an integrated learning-based framework for accurate Ki-67 scoring in pancreatic neuroendocrine tumor. The main contributions of our method are: a novel and robust cell detection algorithm is designed to localize both tumor and non-tumor cells; a repulsive deformable model is applied to correct touching cell segmentation; a two stage learning-based scheme combining cellular features and regional structure information is proposed to differentiate tumor from non-tumor cells (such as lymphocytes); an integrated automatic framework is developed to accurately assess the Ki-67 labeling index. The proposed method has been extensively evaluated on 101 tissue microarray (TMA) whole discs, and the cell detection performance is comparable to manual annotations. The automatic Ki-67 score is very accurate compared with pathologists' estimation.

Pathology Imaging Informatics for Clinical Practice and Investigative and Translational Research

Pathologists routinely interpret gross and microscopic specimens to render diagnoses and to engage in a broad spectrum of investigative research. Multiple studies have demonstrated that imaging technologies have progressed to a level at which properly digitized specimens provide sufficient quality comparable to the traditional glass slides examinations. Continued advancements in this area will have a profound impact on the manner in which pathology is conducted from this point on. Several leading institutions have already undertaken ambitious projects directed toward digitally imaging, archiving, and sharing pathology specimens. As a result of these advances, the use of informatics in diagnostic and investigative pathology applications is expanding rapidly. In addition, the advent of novel technologies such as multispectral imaging makes it possible to visualize and analyze imaged specimens using multiple wavelengths simultaneously. As these powerful technologies become increasingly accepted and adopted, the opportunities for gaining new insight into the underlying mechanisms of diseases as well as the potential for discriminating among subtypes of pathologies are growing accordingly.