Automated location of dysplastic fields in colorectal histology using image texture analysis

Colon Cancer Diagnosis Based on Machine Learning and Deep Learning: Modalities and Analysis Techniques

The treatment and diagnosis of colon cancer are considered to be social and economic challenges due to the high mortality rates. Every year, around the world, almost half a million people contract cancer, including colon cancer. Determining the grade of colon cancer mainly depends on analyzing the gland's structure by tissue region, which has led to the existence of various tests for screening that can be utilized to investigate polyp images and colorectal cancer. This article presents a comprehensive survey on the diagnosis of colon cancer. This covers many aspects related to colon cancer, such as its symptoms and grades as well as the available imaging modalities (particularly, histopathology images used for analysis) in addition to common diagnosis systems. Furthermore, the most widely used datasets and performance evaluation metrics are discussed. We provide a comprehensive review of the current studies on colon cancer, classified into deep-learning (DL) and machine-learning (ML) techniques, and we identify their main strengths and limitations. These techniques provide extensive support for identifying the early stages of cancer that lead to early treatment of the disease and produce a lower mortality rate compared with the rate produced after symptoms develop. In addition, these methods can help to prevent colorectal cancer from progressing through the removal of pre-malignant polyps, which can be achieved using screening tests to make the disease easier to diagnose. Finally, the existing challenges and future research directions that open the way for future work in this field are presented.

Stain transfer using Generative Adversarial Networks and disentangled features

With the digitization of histopathology, machine learning algorithms have been developed to help pathologists. Color variation in histopathology images degrades the performance of these algorithms. Many models have been proposed to resolve the impact of color variation and transfer histopathology images to a single stain style. Major shortcomings include manual feature extraction, bias on a reference image, being limited to one style to one style transfer, dependence on style labels for source and target domains, and information loss. We propose two models, considering these shortcomings. Our main novelty is using Generative Adversarial Networks (GANs) along with feature disentanglement. The models extract color-related and structural features with neural networks; thus, features are not hand-crafted. Extracting features helps our models do many-to-one stain transformations and require only target-style labels. Our models also do not require a reference image by exploiting GAN. Our first model has one network per stain style transformation, while the second model uses only one network for many-to-many stain style transformations. We compare our models with six state-of-the-art models on the Mitosis-Atypia Dataset. Both proposed models achieved good results, but our second model outperforms other models based on the Histogram Intersection Score (HIS). Our proposed models were applied to three datasets to test their performance. The efficacy of our models was also evaluated on a classification task. Our second model obtained the best results in all the experiments with HIS of 0.88, 0.85, 0.75 for L-channel, a-channel, and b-channel, using the Mitosis-Atypia Dataset and accuracy of 90.3% for classification.

Deep learning in digital pathology image analysis: a survey

Deep learning (DL) has achieved state-of-the-art performance in many digital pathology analysis tasks. Traditional methods usually require hand-crafted domain-specific features, and DL methods can learn representations without manually designed features. In terms of feature extraction, DL approaches are less labor intensive compared with conventional machine learning methods. In this paper, we comprehensively summarize recent DL-based image analysis studies in histopathology, including different tasks (e.g., classification, semantic segmentation, detection, and instance segmentation) and various applications (e.g., stain normalization, cell/gland/region structure analysis). DL methods can provide consistent and accurate outcomes. DL is a promising tool to assist pathologists in clinical diagnosis.

Unsupervised Domain Adaptation for Classification of Histopathology Whole-Slide Images

Computational image analysis is one means for evaluating digitized histopathology specimens that can increase the reproducibility and reliability with which cancer diagnoses are rendered while simultaneously providing insight as to the underlying mechanisms of disease onset and progression. A major challenge that is confronted when analyzing samples that have been prepared at disparate laboratories and institutions is that the algorithms used to assess the digitized specimens often exhibit heterogeneous staining characteristics because of slight differences in incubation times and the protocols used to prepare the samples. Unfortunately, such variations can render a prediction model learned from one batch of specimens ineffective for characterizing an ensemble originating from another site. In this work, we propose to adopt unsupervised domain adaptation to effectively transfer the discriminative knowledge obtained from any given source domain to the target domain without requiring any additional labeling or annotation of images at the target site. In this paper, our team investigates the use of two approaches for performing the adaptation: (1) color normalization and (2) adversarial training. The adversarial training strategy is implemented through the use of convolutional neural networks to find an invariant feature space and Siamese architecture within the target domain to add a regularization that is appropriate for the entire set of whole-slide images. The adversarial adaptation results in significant classification improvement compared with the baseline models under a wide range of experimental settings.

Haralick's texture features for the prediction of response to therapy in colorectal cancer: a preliminary study

PURPOSE

Haralick features Texture analysis is a recent oncologic imaging biomarker used to assess quantitatively the heterogeneity within a tumor. The aim of this study is to evaluate which Haralick's features are the most feasible in predicting tumor response to neoadjuvant chemoradiotherapy (CRT) in colorectal cancer.

MATERIALS AND METHODS

After MRI and histological assessment, eight patients were enrolled and divided into two groups based on response to neoadjuvant CRT in complete responders (CR) and non-responders (NR). Oblique Axial T2-weighted MRI sequences before CRT were analyzed by two radiologists in consensus drawing a ROI around the tumor. 14 over 192 Haralick's features were extrapolated from normalized gray-level co-occurrence matrix in four different directions. A dedicated statistical analysis was performed to evaluate distribution of the extracted Haralick's features computing mean and standard deviation.

RESULTS

Pretreatment MRI examination showed significant value (p < 0.05) of 5 over 14 computed Haralick texture. In particular, the significant features are the following: concerning energy, contrast, correlation, entropy and inverse difference moment.

CONCLUSIONS

Five Haralick's features showed significant relevance in the prediction of response to therapy in colorectal cancer and might be used as additional imaging biomarker in the oncologic management of colorectal patients.

Automated tumor analysis for molecular profiling in lung cancer

The discovery and clinical application of molecular biomarkers in solid tumors, increasingly relies on nucleic acid extraction from FFPE tissue sections and subsequent molecular profiling. This in turn requires the pathological review of haematoxylin & eosin (H&E) stained slides, to ensure sample quality, tumor DNA sufficiency by visually estimating the percentage tumor nuclei and tumor annotation for manual macrodissection. In this study on NSCLC, we demonstrate considerable variation in tumor nuclei percentage between pathologists, potentially undermining the precision of NSCLC molecular evaluation and emphasising the need for quantitative tumor evaluation. We subsequently describe the development and validation of a system called TissueMark for automated tumor annotation and percentage tumor nuclei measurement in NSCLC using computerized image analysis. Evaluation of 245 NSCLC slides showed precise automated tumor annotation of cases using Tissuemark, strong concordance with manually drawn boundaries and identical EGFR mutational status, following manual macrodissection from the image analysis generated tumor boundaries. Automated analysis of cell counts for % tumor measurements by Tissuemark showed reduced variability and significant correlation (p < 0.001) with benchmark tumor cell counts. This study demonstrates a robust image analysis technology that can facilitate the automated quantitative analysis of tissue samples for molecular profiling in discovery and diagnostics.

ARTIFICIAL INTELLIGENT SYSTEMS APPLICATION IN CERVICAL CANCER PATHOLOGICAL CELL IMAGE CLASSIFICATION SYSTEMS — A REVIEW

Cervical cancer cell images play an important part in diagnosing the cancer among the females worldwide. Existing noises, overlapping cells, mucus, blood and air artifacts in cervical cancer cell images makes their classification a hard task. It makes it difficult for both pathologists and intelligent systems to segment and classify them into normal, pre-cancerous and cancerous cells. However, true cell segmentation is needed for pathologists to make for accurate diagnosis. In this paper, a review of algorithms used for cervical cancer cell image classification is presented. This includes pre-processing steps (noise reduction and cell segmentation/without segmentation), feature extraction, and intelligent diagnosis systems and their evaluations. Finally, future research trends on cervical cell classification to achieve complete accuracy are described.

Stain Normalization using Sparse AutoEncoders (StaNoSA): Application to digital pathology

Digital histopathology slides have many sources of variance, and while pathologists typically do not struggle with them, computer aided diagnostic algorithms can perform erratically. This manuscript presents Stain Normalization using Sparse AutoEncoders (StaNoSA) for use in standardizing the color distributions of a test image to that of a single template image. We show how sparse autoencoders can be leveraged to partition images into tissue sub-types, so that color standardization for each can be performed independently. StaNoSA was validated on three experiments and compared against five other color standardization approaches and shown to have either comparable or superior results.

Multimodal nonlinear microscopy of head and neck carcinoma - toward surgery assisting frozen section analysis

BACKGROUND

Treatment of early cancer stages is deeply connected to a good prognosis, a moderate reduction of the quality of life, and comparably low treatment costs.

METHODS

Head and neck squamous cell carcinomas were investigated using the multimodal combination of coherent anti-Stokes Raman scattering (CARS), two-photon excited fluorescence (TPEF), and second-harmonic generation (SHG) microscopy.

RESULTS

An increased median TPEF to CARS contrast was found comparing cancerous and healthy squamous epithelium with a p value of 1.8·10(-10) . A following comprehensive image analysis was able to predict the diagnosis of imaged tissue sections with an overall accuracy of 90% for a 4-class model.

CONCLUSION

Nonlinear multimodal imaging is verified objectively as a valuable diagnostic tool that complements conventional staining protocols and can serve as filter in future clinical routine reducing the pathologist's workload. © 2016 Wiley Periodicals, Inc. Head Neck 38: First-1552, 2016.

Assessment of tumour viability in human lung cancer xenografts with texture-based image analysis

Aims

To build and evaluate an automated method for assessing tumour viability in histological tissue samples using texture features and supervised learning.

Methods

H&E-stained sections (n=56) of human non-small cell lung adenocarcinoma xenografts were digitised with a whole-slide scanner. A novel image analysis method based on local binary patterns and a support vector machine classifier was trained with a set of sample regions (n=177) extracted from the whole-slide images and tested with another set of images (n=494). The extracted regions, or single-tissue entity images, were chosen to represent as pure as possible examples of three morphological tissue entities: viable tumour tissue, non-viable tumour tissue and mouse host tissue.

Results

An agreement of 94.5% (area under the curve=0.995, kappa=0.90) was achieved to classify the single-tissue entity images in the test set (n=494) into the viable tumour and non-viable tumour tissue categories. The algorithm assigned 250 of the 252 non-viable and 219 of the 242 of viable sample regions to the correct categories, respectively. This corresponds to a sensitivity of 90.5% and specificity of 99.2%.

Conclusions

The proposed image analysis-based tumour viability assessment resulted in a high agreement with expert annotations. By providing extraction of detailed information of the tumour microenvironment, the automated method can be used in preclinical research settings. The method could also have implications in cancer diagnostics, cancer outcome prognostics and prediction.

A nonlinear mapping approach to stain normalization in digital histopathology images using image-specific color deconvolution

Histopathology diagnosis is based on visual examination of the morphology of histological sections under a microscope. With the increasing popularity of digital slide scanners, decision support systems based on the analysis of digital pathology images are in high demand. However, computerized decision support systems are fraught with problems that stem from color variations in tissue appearance due to variation in tissue preparation, variation in stain reactivity from different manufacturers/batches, user or protocol variation, and the use of scanners from different manufacturers. In this paper, we present a novel approach to stain normalization in histopathology images. The method is based on nonlinear mapping of a source image to a target image using a representation derived from color deconvolution. Color deconvolution is a method to obtain stain concentration values when the stain matrix, describing how the color is affected by the stain concentration, is given. Rather than relying on standard stain matrices, which may be inappropriate for a given image, we propose the use of a color-based classifier that incorporates a novel stain color descriptor to calculate image-specific stain matrix. In order to demonstrate the efficacy of the proposed stain matrix estimation and stain normalization methods, they are applied to the problem of tumor segmentation in breast histopathology images. The experimental results suggest that the paradigm of color normalization, as a preprocessing step, can significantly help histological image analysis algorithms to demonstrate stable performance which is insensitive to imaging conditions in general and scanner variations in particular.

Methods for nuclei detection, segmentation, and classification in digital histopathology: a review-current status and future potential

Digital pathology represents one of the major evolutions in modern medicine. Pathological examinations constitute the gold standard in many medical protocols, and also play a critical and legal role in the diagnosis process. In the conventional cancer diagnosis, pathologists analyze biopsies to make diagnostic and prognostic assessments, mainly based on the cell morphology and architecture distribution. Recently, computerized methods have been rapidly evolving in the area of digital pathology, with growing applications related to nuclei detection, segmentation, and classification. In cancer research, these approaches have played, and will continue to play a key (often bottleneck) role in minimizing human intervention, consolidating pertinent second opinions, and providing traceable clinical information. Pathological studies have been conducted for numerous cancer detection and grading applications, including brain, breast, cervix, lung, and prostate cancer grading. Our study presents, discusses, and extracts the major trends from an exhaustive overview of various nuclei detection, segmentation, feature computation, and classification techniques used in histopathology imagery, specifically in hematoxylin-eosin and immunohistochemical staining protocols. This study also enables us to measure the challenges that remain, in order to reach robust analysis of whole slide images, essential high content imaging with diagnostic biomarkers and prognosis support in digital pathology.

An entirely automated method to score DSS-induced colitis in mice by digital image analysis of pathology slides

The DSS (dextran sulfate sodium) model of colitis is a mouse model of inflammatory bowel disease. Microscopic symptoms include loss of crypt cells from the gut lining and infiltration of inflammatory cells into the colon. An experienced pathologist requires several hours per study to score histological changes in selected regions of the mouse gut. In order to increase the efficiency of scoring, Definiens Developer software was used to devise an entirely automated method to quantify histological changes in the whole H&E slide. When the algorithm was applied to slides from historical drug-discovery studies, automated scores classified 88% of drug candidates in the same way as pathologists' scores. In addition, another automated image analysis method was developed to quantify colon-infiltrating macrophages, neutrophils, B cells and T cells in immunohistochemical stains of serial sections of the H&E slides. The timing of neutrophil and macrophage infiltration had the highest correlation to pathological changes, whereas T and B cell infiltration occurred later. Thus, automated image analysis enables quantitative comparisons between tissue morphology changes and cell-infiltration dynamics.

A recent survey on colon cancer detection techniques

Colon cancer causes deaths of about half a million people every year. Common method of its detection is histopathological tissue analysis, which, though leads to vital diagnosis, is significantly correlated to the tiredness, experience, and workload of the pathologist. Researchers have been working since decades to get rid of manual inspection, and to develop trustworthy systems for detecting colon cancer. Several techniques, based on spectral/spatial analysis of colon biopsy images, and serum and gene analysis of colon samples, have been proposed in this regard. Due to rapid evolution of colon cancer detection techniques, a latest review of recent research in this field is highly desirable. The aim of this paper is to discuss various colon cancer detection techniques. In this survey, we categorize the techniques on the basis of the adopted methodology and underlying data set, and provide detailed description of techniques in each category. Additionally, this study provides an extensive comparison of various colon cancer detection categories, and of multiple techniques within each category. Further, most of the techniques have been evaluated on similar data set to provide a fair performance comparison. Analysis reveals that neither of the techniques is perfect; however, research community is progressively inching toward the finest possible solution.

Coupled analysis of in vitro and histology tissue samples to quantify structure-function relationship

The structure/function relationship is fundamental to our understanding of biological systems at all levels, and drives most, if not all, techniques for detecting, diagnosing, and treating disease. However, at the tissue level of biological complexity we encounter a gap in the structure/function relationship: having accumulated an extraordinary amount of detailed information about biological tissues at the cellular and subcellular level, we cannot assemble it in a way that explains the correspondingly complex biological functions these structures perform. To help close this information gap we define here several quantitative temperospatial features that link tissue structure to its corresponding biological function. Both histological images of human tissue samples and fluorescence images of three-dimensional cultures of human cells are used to compare the accuracy of in vitro culture models with their corresponding human tissues. To the best of our knowledge, there is no prior work on a quantitative comparison of histology and in vitro samples. Features are calculated from graph theoretical representations of tissue structures and the data are analyzed in the form of matrices and higher-order tensors using matrix and tensor factorization methods, with a goal of differentiating between cancerous and healthy states of brain, breast, and bone tissues. We also show that our techniques can differentiate between the structural organization of native tissues and their corresponding in vitro engineered cell culture models.

Identification of tumor epithelium and stroma in tissue microarrays using texture analysis

Background

The aim of the study was to assess whether texture analysis is feasible for automated identification of epithelium and stroma in digitized tumor tissue microarrays (TMAs). Texture analysis based on local binary patterns (LBP) has previously been used successfully in applications such as face recognition and industrial machine vision. TMAs with tissue samples from 643 patients with colorectal cancer were digitized using a whole slide scanner and areas representing epithelium and stroma were annotated in the images. Well-defined images of epithelium (n = 41) and stroma (n = 39) were used for training a support vector machine (SVM) classifier with LBP texture features and a contrast measure C (LBP/C) as input. We optimized the classifier on a validation set (n = 576) and then assessed its performance on an independent test set of images (n = 720). Finally, the performance of the LBP/C classifier was evaluated against classifiers based on Haralick texture features and Gabor filtered images.

Results

The proposed approach using LPB/C texture features was able to correctly differentiate epithelium from stroma according to texture: the agreement between the classifier and the human observer was 97 per cent (kappa value = 0.934, P < 0.0001) and the accuracy (area under the ROC curve) of the LBP/C classifier was 0.995 (CI95% 0.991-0.998). The accuracy of the corresponding classifiers based on Haralick features and Gabor-filter images were 0.976 and 0.981 respectively.

Conclusions

The method illustrates the capability of automated segmentation of epithelial and stromal tissue in TMAs based on texture features and an SVM classifier. Applications include tissue specific assessment of gene and protein expression, as well as computerized analysis of the tumor microenvironment.

Virtual slides

The virtual slide(s) for this article can be found here: http://www.diagnosticpathology.diagnomx.eu/vs/4123422336534537

Whole slide images for primary diagnostics of gastrointestinal tract pathology: a feasibility study

During the last decade, whole slide images have been used in many areas of pathology such as teaching, research, digital archiving, teleconsultation, and quality assurance testing. However, whole slide images have as yet not much been used for up-front diagnostics because of the lack of validation studies. The aim of this study was, therefore, to test the feasibility of whole slide images for diagnosis of gastrointestinal tract specimens, one of the largest areas of diagnostic pathology. One hundred gastrointestinal tract biopsies and resections that had been diagnosed using light microscopy 1 year before were rediagnosed on whole slide images scanned at ×20 magnification by 5 pathologists (all reassessing their own cases), having the original clinical information available but blinded to their original light microscopy diagnoses. The original light microscopy and whole slide image-based diagnoses were compared and classified as concordant, slightly discordant (without clinical consequences), and discordant. The diagnoses based on light microscopy and the whole slide image-based rediagnoses were concordant in 95% of the cases. Light microscopy and whole slide image diagnosis in the remaining 5% of cases were slightly discordant, none of these were with clinical or prognostic implications. Up-front histopathologic diagnosis of gastrointestinal biopsies and resections can be done on whole slide images.

SHIRAZ: an automated histology image annotation system for zebrafish phenomics

Histological characterization is used in clinical and research contexts as a highly sensitive method for detecting the morphological features of disease and abnormal gene function. Histology has recently been accepted as a phenotyping method for the forthcoming Zebrafish Phenome Project, a large-scale community effort to characterize the morphological, physiological, and behavioral phenotypes resulting from the mutations in all known genes in the zebrafish genome. In support of this project, we present a novel content-based image retrieval system for the automated annotation of images containing histological abnormalities in the developing eye of the larval zebrafish.

ECM-Aware Cell-Graph Mining for Bone Tissue Modeling and Classification

Pathological examination of a biopsy is the most reliable and widely used technique to diagnose bone cancer. However, it suffers from both inter- and intra- observer subjectivity. Techniques for automated tissue modeling and classification can reduce this subjectivity and increases the accuracy of bone cancer diagnosis. This paper presents a graph theoretical method, called extracellular matrix (ECM)-aware cell-graph mining, that combines the ECM formation with the distribution of cells in hematoxylin and eosin (H&E) stained histopathological images of bone tissues samples. This method can identify different types of cells that coexist in the same tissue as a result of its functional state. Thus, it models the structure-function relationships more precisely and classifies bone tissue samples accurately for cancer diagnosis. The tissue images are segmented, using the eigenvalues of the Hessian matrix, to compute spatial coordinates of cell nuclei as the nodes of corresponding cell-graph. Upon segmentation a color code is assigned to each node based on the composition of its surrounding ECM. An edge is hypothesized (and established) between a pair of nodes if the corresponding cell membranes are in physical contact and if they share the same color. Hence, multiple colored-cell-graphs coexist in a tissue each modeling a different cell-type organization. Both topological and spectral features of ECM-aware cell-graphs are computed to quantify the structural properties of tissue samples and classify their different functional states as healthy, fractured, or cancerous using support vector machines. Classification accuracy comparison to related work shows that ECM-aware cell-graph approach yields 90.0% whereas Delaunay triangulation and simple cell-graph approach achieves 75.0% and 81.1% accuracy, respectively.

Fluorescent stains for quantification of DNA by confocal laser scanning microscopy in 3-D

Confocal microscopy requires the use of fluorophores to visualize structures of interest within a specimen. To perform reliable measurements of the intensity of fluorescence, the stain should be specific, penetrate well into tissue sections, and bind stoichiometrically. Furthermore, emission must be linear with respect to DNA content and brightness, and fluorescence should be stable. Confocal microscopy is used to determine DNA ploidy and to analyze texture of nuclei, which is accomplished in three dimensions, because nuclei can be measured within the original tissue context. For this purpose the sample must be stained with a DNA binding fluorophore with the properties described above. Stains with different properties have been developed for different applications. We review here the advantages and disadvantages of these different stains for analyzing DNA ploidy and nuclear texture using three-dimensional microscopy. We conclude that SYBR green I and TO-PRO-3 are the most suitable stains for this purpose at present.

Automated classification of inflammation in colon histological sections based on digital microscopy and advanced image analysis

Automated and quantitative histological analysis can improve diagnostic efficacy in colon sections. Our objective was to develop a parameter set for automated classification of aspecific colitis, ulcerative colitis, and Crohn's disease using digital slides, tissue cytometric parameters, and virtual microscopy. Routinely processed hematoxylin-and-eosin-stained histological sections from specimens that showed normal mucosa (24 cases), aspecific colitis (11 cases), ulcerative colitis (25 cases), and Crohn's disease (9 cases) diagnosed by conventional optical microscopy were scanned and digitized in high resolution (0.24 mum/pixel). Thirty-eight cytometric parameters based on morphometry were determined on cells, glands, and superficial epithelium. Fourteen tissue cytometric parameters based on ratios of tissue compartments were counted as well. Leave-one-out discriminant analysis was used for classification of the samples groups. Cellular morphometric features showed no significant differences in these benign colon alterations. However, gland related morphological differences (Gland Shape) for normal mucosa, ulcerative colitis, and aspecific colitis were found (P < 0.01). Eight of the 14 tissue cytometric related parameters showed significant differences (P < 0.01). The most discriminatory parameters were the ratio of cell number in glands and in the whole slide, biopsy/gland surface ratio. These differences resulted in 88% overall accuracy in the classification. Crohn's disease could be discriminated only in 56%. Automated virtual microscopy can be used to classify colon mucosa as normal, ulcerative colitis, and aspecific colitis with reasonable accuracy. Further developments of dedicated parameters are necessary to identify Crohn's disease on digital slides.

Mathematical modeling of the malignancy of cancer using graph evolution

We report a novel computational method based on graph evolution process to model the malignancy of brain cancer called glioma. In this work, we analyze the phases that a graph passes through during its evolution and demonstrate strong relation between the malignancy of cancer and the phase of its graph. From the photomicrographs of tissues, which are diagnosed as normal, low-grade cancerous and high-grade cancerous, we construct cell-graphs based on the locations of cells; we probabilistically generate an edge between every pair of cells depending on the Euclidean distance between them. For a cell-graph, we extract connectivity information including the properties of its connected components in order to analyze the phase of the cell-graph. Working with brain tissue samples surgically removed from 12 patients, we demonstrate that cell-graphs generated for different tissue types evolve differently and that they exhibit different phase properties, which distinguish a tissue type from another.

Automated virtual microscopy of gastric biopsies

BACKGROUND

Automated virtual microscopy of specimens from gastrointestinal biopsies is based on cytometric parameters of digitized histological sections. To our knowledge, cytometric parameters of gastritis and of adenocarcinoma have yet to be fully characterized. Our objective was to classify gastritis and adenocarcinoma based on cytometric parameters. We hypothesized that automated virtual microscopy using this novel classification can reliably diagnose gastritis and adenocarcinoma.

METHODS

Routinely processed hematoxylin-and-eosin-stained histological sections from specimens that showed normal mucosa (14 cases), gastritis (35 cases), and adenocarcinoma (30 cases) diagnosed by conventional optical microscopy were scanned and digitized at high resolution. Thirty-eight cytometric parameters based on density and morphometry were applied to glands and superficial epithelium. Twelve cytometric parameters based on cytologic detail were applied to individual cells.

RESULTS

Statistically significant differences in cytometric parameters for normal mucosa, gastritis, and adenocarcinoma were found. The most discriminatory parameter was the ratio of the total number of cells to the number of interstitial cells. These differences correctly classified adenocarcinoma at 100% accuracy and overall correctness was 86%.

CONCLUSIONS

We describe a novel method of analyzing gastric mucosal histology based on cytometric parameters. Automated virtual microscopy can be used to classify gastric mucosa as normal, gastritis, or adenocarcinoma with reasonable accuracy. Further research is necessary to determine whether automated virtual microscopy can subclassify gastric mucosal histology in greater detail.

Towards an automated virtual slide screening: theoretical considerations and practical experiences of automated tissue-based virtual diagnosis to be implemented in the Internet

Aims

To develop and implement an automated virtual slide screening system that distinguishes normal histological findings and several tissue – based crude (texture – based) diagnoses.

Theoretical considerations

Virtual slide technology has to handle and transfer images of GB Bytes in size. The performance of tissue based diagnosis can be separated into a) a sampling procedure to allocate the slide area containing the most significant diagnostic information, and b) the evaluation of the diagnosis obtained from the information present in the selected area. Nyquist's theorem that is broadly applied in acoustics, can also serve for quality assurance in image information analysis, especially to preset the accuracy of sampling. Texture – based diagnosis can be performed with recursive formulas that do not require a detailed segmentation procedure. The obtained results will then be transferred into a "self-learning" discrimination system that adjusts itself to changes of image parameters such as brightness, shading, or contrast.

Methods

Non-overlapping compartments of the original virtual slide (image) will be chosen at random and according to Nyquist's theorem (predefined error-rate). The compartments will be standardized by local filter operations, and are subject for texture analysis. The texture analysis is performed on the basis of a recursive formula that computes the median gray value and the local noise distribution. The computations will be performed at different magnifications that are adjusted to the most frequently used objectives (*2, *4.5, *10, *20, *40). The obtained data are statistically analyzed in a hierarchical sequence, and in relation to the clinical significance of the diagnosis.

Results

The system has been tested with a total of 896 lung cancer cases that include the diagnoses groups: cohort (1) normal lung – cancer; cancer subdivided: cohort (2) small cell lung cancer – non small cell lung cancer; non small cell lung cancer subdivided: cohort (3) squamous cell carcinoma – adenocarcinoma – large cell carcinoma. The system can classify all diagnoses of the cohorts (1) and (2) correctly in 100%, those of cohort (3) in more than 95%. The percentage of the selected area can be limited to only 10% of the original image without any increased error rate.

Conclusion

The developed system is a fast and reliable procedure to fulfill all requirements for an automated "pre-screening" of virtual slides in lung pathology.

Learning the topological properties of brain tumors

This work presents a graph-based representation (a.k.a., cell-graph) of histopathological images for automated cancer diagnosis by probabilistically assigning a link between a pair of cells (or cell clusters). Since the node set of a cell-graph can include a cluster of cells as well as individual ones, it enables working with low-cost, low-magnification photomicrographs. The contributions of this work are twofold. First, it is shown that without establishing a pairwise spatial relation between the cells (i.e., the edges of a cell-graph), neither the spatial distribution of the cells nor the texture analysis of the images yields accurate results for tissue level diagnosis of brain cancer called malignant glioma. Second, this work defines a set of global metrics by processing the entire cell-graph to capture tissue level information coded into the histopathological images. In this work, the results are obtained on the photomicrographs of 646 archival brain biopsy samples of 60 different patients. It is shown that the global metrics of cell-graphs distinguish cancerous tissues from noncancerous ones with high accuracy (at least 99 percent accuracy for healthy tissues with lower cellular density level, and at least 92 percent accuracy for benign tissues with similar high cellular density level such as nonneoplastic reactive/inflammatory conditions).

The use of morphological characteristics and texture analysis in the identification of tissue composition in prostatic neoplasia

Quantitative examination of prostate histology offers clues in the diagnostic classification of lesions and in the prediction of response to treatment and prognosis. To facilitate the collection of quantitative data, the development of machine vision systems is necessary. This study explored the use of imaging for identifying tissue abnormalities in prostate histology. Medium-power histological scenes were recorded from whole-mount radical prostatectomy sections at x 40 objective magnification and assessed by a pathologist as exhibiting stroma, normal tissue (nonneoplastic epithelial component), or prostatic carcinoma (PCa). A machine vision system was developed that divided the scenes into subregions of 100 x 100 pixels and subjected each to image-processing techniques. Analysis of morphological characteristics allowed the identification of normal tissue. Analysis of image texture demonstrated that Haralick feature 4 was the most suitable for discriminating stroma from PCa. Using these morphological and texture measurements, it was possible to define a classification scheme for each subregion. The machine vision system is designed to integrate these classification rules and generate digital maps of tissue composition from the classification of subregions; 79.3% of subregions were correctly classified. Established classification rates have demonstrated the validity of the methodology on small scenes; a logical extension was to apply the methodology to whole slide images via scanning technology. The machine vision system is capable of classifying these images. The machine vision system developed in this project facilitates the exploration of morphological and texture characteristics in quantifying tissue composition. It also illustrates the potential of quantitative methods to provide highly discriminatory information in the automated identification of prostatic lesions using computer vision.

Digital imaging in pathology: theoretical and practical considerations, and applications

Digital imaging is rapidly replacing photographic prints and Kodachromes for pathology reporting and conference purposes. Advanced systems linked to computers allow greater versatility and speed of turn-around as well as lower costs, allowing the incorporation of macroscopic and microscopic pictures into routine pathology reports and publications. Digital images allow transmission to remote sites via the Internet for primary diagnosis, consultation, quality assurance and educational purposes and can be stored and disseminated in CD-ROMs. Total slide digitisation is now a reality and has the potential to replace glass slides to a large extent. There are extensive applications of digital images in education and research, allowing more objective and automated quantitation of a variety of morphological and immunohistological parameters. Three-dimensional images of gross specimens can be developed and posted on websites for interactive educational programs and preliminary reports indicate that medical vision systems are a reality and can provide for automated computer generated histopathological diagnosis and quality assurance.

A survey on histological image analysis-based assessment of three major biological factors influencing radiotherapy: proliferation, hypoxia and vasculature

Image analysis is a rapidly evolving field with growing applications in science and engineering. In cancer research, it has played a key role in advancing techniques of major diagnostic importance, minimising human intervention and providing vital clinical information. Especially in the field of tissue microscopy, the use of computers for the automated analysis of histological sections is becoming increasingly important. This paper presents an overview of various image analysis methodologies and summarises developments in this field, with great emphasis given on the assessment of three major biological factors known to influence the outcome of radiotherapy: proliferation, vasculature and hypoxia. A brief introduction followed by a survey is provided in each of these areas.

Histological image retrieval based on semantic content analysis

The demand for automatically recognizing and retrieving medical images for screening, reference, and management is growing faster than ever. In this paper, we present an intelligent content-based image retrieval system called I-Browse, which integrates both iconic and semantic content for histological image analysis. The I-Browse system combines low-level image processing technology with high-level semantic analysis of medical image content through different processing modules in the proposed system architecture. Similarity measures are proposed and their performance is evaluated. Furthermore, as a byproduct of semantic analysis, I-Browse allows textual annotations to be generated for unknown images. As an image browser, apart from retrieving images by image example, it also supports query by natural language.

Digital imaging applications in anatomic pathology

Digital imaging has progressed at a rapid rate and is likely to eventually replace chemical photography in most areas of professional and amateur digital image acquisition. In pathology, digital microscopy has implications beyond that of taking a photograph. The arguments for adopting this new medium are compelling, and given similar developments in other areas of pathology and radiologic imaging, acceptance of the digital medium should be viewed as a component of the technological evolution of the laboratory. A digital image may be stored, replicated, catalogued, employed for educational purposes, transmitted for further interpretation (telepathology), analyzed for salient features (medical vision/image analysis), or form part of a wider digital healthcare strategy. Despite advances in digital camera technology, good image acquisition still requires good microscope optics and the correct calibration of all system components, something which many neglect. The future of digital imaging in pathology is very promising and new applications in the fields of automated quantification and interpretation are likely to have profound long-term influence on the practice of anatomic pathology. This paper discusses the state of the art of digital imaging in anatomic pathology.

Fractal analysis in the detection of colonic cancer images

The aim of this study was to investigate the value of fractal dimension in separating normal and cancerous images, and to examine the relationship between fractal dimension and traditional texture analysis features. Forty-four normal images and 58 cancer images from sections of the colon were analyzed. A "leave-one-out" analysis approach was used to classify the samples into each group. With fractal analysis there was a highly significant difference between groups (p < 0.0001). Correlation and entropy features showed greater differences between the groups (p < 0.0001). Nevertheless, the addition of fractal analysis to the feature analysis improved the sensitivity from 90% to 95% and specificity from 86% to 93%.

Texture analysis of fluorescence microscopic images of colonic tissue sections

The aim of this study was to assess the potential of texture analysis for the characterization of fluorescence images from colonic tissue sections stained with a novel and selective fluoroprobe, Rhodamine B-phenylboronic acid. Fluorescence microscopy images of colonic healthy mucosa (n = 35) and adenocarcinomas (n = 35) were digitally captured and subjected to image texture analysis. Textural features derived from the grey level co-occurrence matrix were calculated. A modified version of the multiple discriminant analysis criterion was used to choose an appropriate subset of features. A minimum Mahalanobis distance, linear discriminant classifier and a simple evaluation 'score' method were used to classify image feature data into the two categories. A subset of four textural features was selected and used for the description and classification of each image field. They were found appropriate to correctly classify 95% of the images into the two classes, using two different classifiers. These features contained information about local homogeneity and grey level linear dependencies of the image. This study demonstrated that texture analysis techniques could provide valuable diagnostic decision support in a complex domain such as colorectal tissue.

Microscopic image analysis for quantitative measurement and feature identification of normal and cancerous colonic mucosa

The development of an automated algorithm for the categorization of normal and cancerous colon mucosa is reported. Six features based on texture analysis were studied. They were derived using the co-occurrence matrix and were angular second moment, entropy, contrast, inverse difference moment, dissimilarity, and correlation. Optical density was also studied. Forty-four normal images and 58 cancerous images from sections of the colon were analyzed. These two groups were split equally into two subgroups: one set was used for supervised training and the other to test the classification algorithm. A stepwise selection procedure showed that correlation and entropy were the features that discriminated most strongly between normal and cancerous tissue (P < 0.0001). A parametric linear-discriminate function was used to determine the classification rule. For the training set, a sensitivity and specificity of 93.1% and 81.8%, respectively, were achieved, with an overall accuracy of 88.2%. These results were confirmed with the test set, with a sensitivity and specificity of 93.1% and 86.4%, respectively, and an overall accuracy of 90.2%.