Invariant delineation of nuclear architecture in glioblastoma multiforme for clinical and molecular association

Stacked Predictive Sparse Decomposition for Classification of Histology Sections

Image-based classification of histology sections, in terms of distinct components (e.g., tumor, stroma, normal), provides a series of indices for histology composition (e.g., the percentage of each distinct components in histology sections), and enables the study of nuclear properties within each component. Furthermore, the study of these indices, constructed from each whole slide image in a large cohort, has the potential to provide predictive models of clinical outcome. For example, correlations can be established between the constructed indices and the patients' survival information at cohort level, which is a fundamental step towards personalized medicine. However, performance of the existing techniques is hindered as a result of large technical variations (e.g., variations of color/textures in tissue images due to non-standard experimental protocols) and biological heterogeneities (e.g., cell type, cell state) that are always present in a large cohort. We propose a system that automatically learns a series of dictionary elements for representing the underlying spatial distribution using stacked predictive sparse decomposition. The learned representation is then fed into the spatial pyramid matching framework with a linear support vector machine classifier. The system has been evaluated for classification of distinct histological components for two cohorts of tumor types. Throughput has been increased by using of graphical processing unit (GPU), and evaluation indicates a superior performance results, compared with previous research.

Segmentation of cytoplasm and nuclei of abnormal cells in cervical cytology using global and local graph cuts

Automation-assisted reading (AAR) techniques have the potential to reduce errors and increase productivity in cervical cancer screening. The sensitivity of AAR relies heavily on automated segmentation of abnormal cervical cells, which is handled poorly by current segmentation algorithms. In this paper, a global and local scheme based on graph cut approach is proposed to segment cervical cells in images with a mix of healthy and abnormal cells. For cytoplasm segmentation, the multi-way graph cut is performed globally on the a* channel enhanced image, which can be effective when the image histogram presents a non-bimodal distribution. For segmentation of nuclei, especially when they are abnormal, we propose to use graph cut adaptively and locally, which allows the combination of intensity, texture, boundary and region information. Two concave points-based approaches are integrated to split the touching-nuclei. As part of an ongoing clinical trial, preliminary validation results obtained from 21 cervical cell images with non-ideal imaging condition and pathology show that our segmentation method achieved 93% accuracy for cytoplasm, and 88.4% F-measure for abnormal nuclei, outperforming state of the art methods in terms of accuracy. Our method has the potential to improve the sensitivity of AAR in screening for cervical cancer.

Automation-assisted cervical cancer screening in manual liquid-based cytology with hematoxylin and eosin staining

Current automation-assisted technologies for screening cervical cancer mainly rely on automated liquid-based cytology slides with proprietary stain. This is not a cost-efficient approach to be utilized in developing countries. In this article, we propose the first automation-assisted system to screen cervical cancer in manual liquid-based cytology (MLBC) slides with hematoxylin and eosin (H&E) stain, which is inexpensive and more applicable in developing countries. This system consists of three main modules: image acquisition, cell segmentation, and cell classification. First, an autofocusing scheme is proposed to find the global maximum of the focus curve by iteratively comparing image qualities of specific locations. On the autofocused images, the multiway graph cut (GC) is performed globally on the a* channel enhanced image to obtain cytoplasm segmentation. The nuclei, especially abnormal nuclei, are robustly segmented by using GC adaptively and locally. Two concave-based approaches are integrated to split the touching nuclei. To classify the segmented cells, features are selected and preprocessed to improve the sensitivity, and contextual and cytoplasm information are introduced to improve the specificity. Experiments on 26 consecutive image stacks demonstrated that the dynamic autofocusing accuracy was 2.06 μm. On 21 cervical cell images with nonideal imaging condition and pathology, our segmentation method achieved a 93% accuracy for cytoplasm, and a 87.3% F-measure for nuclei, both outperformed state of the art works in terms of accuracy. Additional clinical trials showed that both the sensitivity (88.1%) and the specificity (100%) of our system are satisfyingly high. These results proved the feasibility of automation-assisted cervical cancer screening in MLBC slides with H&E stain, which is highly desirable in community health centers and small hospitals.

Stacked Predictive Sparse Coding for Classification of Distinct Regions of Tumor Histopathology

Image-based classification of tissue histology, in terms of distinct histopathology (e.g., tumor or necrosis regions), provides a series of indices for tumor composition. Furthermore, aggregation of these indices from each whole slide image (WSI) in a large cohort can provide predictive models of clinical outcome. However, the performance of the existing techniques is hindered as a result of large technical variations (e.g., fixation, staining) and biological heterogeneities (e.g., cell type, cell state) that are always present in a large cohort. We suggest that, compared with human engineered features widely adopted in existing systems, unsupervised feature learning is more tolerant to batch effect (e.g., technical variations associated with sample preparation) and pertinent features can be learned without user intervention. This leads to a novel approach for classification of tissue histology based on unsupervised feature learning and spatial pyramid matching (SPM), which utilize sparse tissue morphometric signatures at various locations and scales. This approach has been evaluated on two distinct datasets consisting of different tumor types collected from The Cancer Genome Atlas (TCGA), and the experimental results indicate that the proposed approach is (i) extensible to different tumor types; (ii) robust in the presence of wide technical variations and biological heterogeneities; and (iii) scalable with varying training sample sizes.

Analyzing huge pathology images with open source software

BACKGROUND

Digital pathology images are increasingly used both for diagnosis and research, because slide scanners are nowadays broadly available and because the quantitative study of these images yields new insights in systems biology. However, such virtual slides build up a technical challenge since the images occupy often several gigabytes and cannot be fully opened in a computer's memory. Moreover, there is no standard format. Therefore, most common open source tools such as ImageJ fail at treating them, and the others require expensive hardware while still being prohibitively slow.

RESULTS

We have developed several cross-platform open source software tools to overcome these limitations. The NDPITools provide a way to transform microscopy images initially in the loosely supported NDPI format into one or several standard TIFF files, and to create mosaics (division of huge images into small ones, with or without overlap) in various TIFF and JPEG formats. They can be driven through ImageJ plugins. The LargeTIFFTools achieve similar functionality for huge TIFF images which do not fit into RAM. We test the performance of these tools on several digital slides and compare them, when applicable, to standard software. A statistical study of the cells in a tissue sample from an oligodendroglioma was performed on an average laptop computer to demonstrate the efficiency of the tools.

CONCLUSIONS

Our open source software enables dealing with huge images with standard software on average computers. They are cross-platform, independent of proprietary libraries and very modular, allowing them to be used in other open source projects. They have excellent performance in terms of execution speed and RAM requirements. They open promising perspectives both to the clinician who wants to study a single slide and to the research team or data centre who do image analysis of many slides on a computer cluster.

VIRTUAL SLIDES

The virtual slide(s) for this article can be found here:http://www.diagnosticpathology.diagnomx.eu/vs/5955513929846272.

CLASSIFICATION OF TUMOR HISTOPATHOLOGY VIA SPARSE FEATURE LEARNING

Our goal is to decompose whole slide images (WSI) of histology sections into distinct patches (e.g., viable tumor, necrosis) so that statistics of distinct histopathology can be linked with the outcome. Such an analysis requires a large cohort of histology sections that may originate from different laboratories, which may not use the same protocol in sample preparation. We have evaluated a method based on a variation of the restricted Boltzmann machine (RBM) that learns intrinsic features of the image signature in an unsupervised fashion. Computed code, from the learned representation, is then utilized to classify patches from a curated library of images. The system has been evaluated against a dataset of small image blocks of 1k-by-1k that have been extracted from glioblastoma multiforme (GBM) and clear cell kidney carcinoma (KIRC) from the cancer genome atlas (TCGA) archive. The learned model is then projected on each whole slide image (e.g., of size 20k-by-20k pixels or larger) for characterizing and visualizing tumor architecture. In the case of GBM, each WSI is decomposed into necrotic, transition into necrosis, and viable. In the case of the KIRC, each WSI is decomposed into tumor types, stroma, normal, and others. Evaluation of 1400 and 2500 samples of GBM and KIRC indicates a performance of 84% and 81%, respectively.

Characterization of tissue histopathology via predictive sparse decomposition and spatial pyramid matching

Image-based classification of tissue histology, in terms of different components (e.g., subtypes of aberrant phenotypic signatures), provides a set of indices for tumor composition. Subsequently, integration of these indices in whole slide images (WSI), from a large cohort, can provide predictive models of the clinical outcome. However, the performance of the existing histology-based classification techniques is hindered as a result of large technical and biological variations that are always present in a large cohort. In this paper, we propose an algorithm for classification of tissue histology based on predictive sparse decomposition (PSD) and spatial pyramid matching (SPM), which utilize sparse tissue morphometric signatures at various locations and scales. The method has been evaluated on two distinct datasets of different tumor types collected from The Cancer Genome Atlas (TCGA). The novelties of our approach are: (i) extensibility to different tumor types; (ii) robustness in the presence of wide technical and biological variations; and (iii) scalability with varying training sample size.