Histopathology of thymectomy specimens from the MGTX-trial: Entropy analysis as strategy to quantify spatial heterogeneity of lymphoid follicle and fat distribution.

The thymectomy specimens from the "thymectomy trial in non-thymomatous myasthenia gravis patients receiving prednisone therapy" (MGTX) underwent rigid and comprehensive work-up, which permits analysis of the spatial distribution of histological and immunohistological features. This analysis revealed strong intra- and inter-case variability. While many histological features (e.g. median percent fat content among different specimens) can easily be correlated with clinical parameters, intra-case spatial variability of histological features has yet defied quantification and statistical evaluation. To overcome this gap in digital pathology, we here propose intra-case entropy of measured histological features in all available slides of a given thymectomy specimen as a quantitative marker of spatial histological heterogeneity. Calculation of entropy led to one value per specimen and histological feature. Through these 'entropy values' the so far neglected degree of spatial histological heterogeneity could be fed into statistical analyses, extending the scope of clinico-pathological correlations.

Merging carbohydrate chemistry with lectin histochemistry to study inhibition of lectin binding by glycoclusters in the natural tissue context.

Recognition of glycans by lectins leads to cell adhesion and growth regulation. The specificity and selectivity of this process are determined by carbohydrate structure (sequence and shape) and topology of its presentation. The synthesis of (neo)glycoconjugates with bi- to oligo-valency (glycoclusters) affords tools to delineate structure-activity relationships by blocking lectin binding to an artificial matrix, often a glycoprotein, or cultured cell lines. The drawback of these assays is that glycan presentation is different from that in tissues. In order to approach the natural context, we here introduce lectin histochemistry on fixed tissue sections to determine the susceptibility of binding of two plant lectins, i.e., GSA-II and WGA, to a series of 10 glycoclusters. Besides valency, this panel covers changes in the anomeric position (α/ß) and the atom at the glycosidic linkage (O/S). Flanked by cell and solid-phase assays with human tumor lines and two mucins, respectively, staining (intensity and profile) was analyzed in sections of murine jejunum, stomach and epididymis as a function of glycocluster presence. The marked and differential sensitivity of signal generation to structural aspects of the glycoclusters proves the applicability of this method. This enables comparisons between data sets obtained by using (neo)glycoconjugates, cells and the tissue context as platforms. The special advantage of processing tissue sections is the monitoring of interference with lectin association at sites that are relevant for functionality. Testing glycoclusters in lectin histochemistry will especially be attractive in cases of multi-target recognition (glycans, proteins and lipids) by a tissue lectin.

Comparative study between quantitative digital image analysis and fluorescence in situ hybridization of breast cancer equivocal human epidermal growth factor receptors 2 score 2(+) cases.

BACKGROUND: Optimization of workflow for breast cancer samples with equivocal human epidermal growth factor receptors 2 (HER2)/neu score 2(+) results in routine practice, remains to be a central focus of the on-going efforts to assess HER2 status. According to the College of American Pathologists/American Society of Clinical Oncology guidelines equivocal HER2/neu score 2(+) cases are subject for further testing, usually by fluorescence in situ hybridization (FISH) investigations. It still remains on open question, whether quantitative digital image analysis of HER2 immunohistochemistry (IHC) stained slides can assist in further refining the HER2 score 2(+). AIM OF THIS WORK: To assess utility of quantitative digital analysis of IHC stained slides and compare its performance to FISH in cases of breast cancer with equivocal HER2 score 2(+). MATERIALS AND METHODS: Fifteen specimens (previously diagnosed as breast cancer and was evaluated as HER 2(-) score 2(+)) represented the study population. Contemporary new cuts were prepared for re-evaluation of HER2 immunohistochemical studies and FISH examination. All the cases were digitally scanned by iScan (Produced by BioImagene [Now Roche-Ventana]). The IHC signals of HER2 were measured using an automated image analyzing system (MECES, www.Diagnomx.eu/meces). Finally, a comparative study was done between the results of the FISH and the quantitative analysis of the virtual slides. RESULTS: Three out of the 15 cases with equivocal HER2 score 2(+), turned out to be positive (3(+)) by quantitative digital analysis, and 12 were found to be negative in FISH too. Two of these three positive cases proved to be positive with FISH, and only one was negative. CONCLUSIONS: Quantitative digital analysis is highly sensitive and relatively specific when compared to FISH in detecting HER2/neu overexpression. Therefore, it represents a potential reliable substitute for FISH in breast cancer cases, which desire further refinement of equivocal IHC results.

Human osteoarthritic knee cartilage: fingerprinting of adhesion/growth-regulatory galectins in vitro and in situ indicates differential upregulation in severe degeneration.

The apparent connection of galectin-3 to chondrocyte survival and osteoarthritis-like cartilage modifications in animal models provided incentive for the mapping of seven members of this family of adhesion/growth-regulatory proteins in human cartilage specimens. Starting with work in vitro, RT-qPCR analyses and immunocytochemistry revealed gene transcription and protein presence in cultured OA chondrocytes, especially for galectin-1, galectin-3 and galectin-8. Immunohistochemistry in clinical specimens with mild and severe cartilage degeneration detected galectins in chondrocytes-with upregulation, especially of galectin-1 in areas of severe degeneration-accompanied by α2,6-sialylation in the pericellular matrix. Given the possibility for additive/antagonistic activities between galectins, these results direct further research toward examining cellular effects of (1) these proteins (alone or in combination) on chondrocytes and (2) remodeling of the chondrocyte glycophenotype.

Introduction to glycopathology: the concept, the tools and the perspectives.

Analyzing the flow of biological information is a fundamental challenge for basic sciences. The emerging results will then lend themselves to the development of new approaches for medical applications. Toward this end, the products of protein/lipid glycosylation deserve special attention. The covalent attachment of sugars to these carriers means much more than just a change of the carriers' physicochemical properties. In principle, the ubiquitous presence of glycoconjugates and the close inspection of the particular structural 'talents' of carbohydrates provide suggestive evidence for information coding by sugars. In fact, the theoretical number of 'words' (oligomers) formed by 'letters' (monosaccharides) is by far higher than by using nucleotides or amino acids. In other words, glycans harbor an unsurpassed coding capacity. The cyto- and histochemical detection of dynamic changes in the profile of cellular glycans (glycome, the equivalent of the proteome) by sugar receptors such as antibodies used as tools underscores the suitability of carbohydrates for such a task. The resulting staining patterns can be likened to a molecular fingerprint. By acting as ligand (counterreceptor) for endogenous receptors (tissue lectins), glycan epitopes become partners in a specific recognition pair, and the sugar-encoded information can then be translated into effects, e.g. in growth regulation. Of note, expression of both sides of such a pair, i.e. lectin and cognate glycan, can physiologically be orchestrated for optimal efficiency. Indeed, examples how to prevent autoimmune diseases by regulatory T cells and restrict carcinoma growth by a tumor suppressor attest occurrence of co-regulation. In consequence, these glycans have potential to establish a new class of functional biomarkers, and mapping presence of their receptors is warranted. In this review, the cyto- and histochemical methods, which contribute to explore information storage and transfer within the sugar code, are described. This introduction to the toolbox is flanked by illustrating the application of each type of tool in histopathology, with focus on adhesion/growth-regulating galectins. Together with an introduction to fundamental principles of the sugar code, the review is designed to guide into this field and to inspire respective research efforts. VIRTUAL SLIDES: The virtual slides for this article can be found here: http://www.diagnosticpathology.diagnomx.eu/vs/1670639891114983.

Diagnostic pathology in 2013: facts, thoughts, and perspectives.

Herein we analyze the development of the open access, peer reviewed journal Diagnostic Pathology (http://www.diagnosticpathology.org) during the past year and try to forecast its perspectives in 2014. VIRTUAL SLIDES: The virtual slide(s) for this article can be found here: http://www.diagnosticpathology.diagnomx.eu/vs/1562693099114452.

The history of pathology informatics: A global perspective.

Pathology informatics has evolved to varying levels around the world. The history of pathology informatics in different countries is a tale with many dimensions. At first glance, it is the familiar story of individuals solving problems that arise in their clinical practice to enhance efficiency, better manage (e.g., digitize) laboratory information, as well as exploit emerging information technologies. Under the surface, however, lie powerful resource, regulatory, and societal forces that helped shape our discipline into what it is today. In this monograph, for the first time in the history of our discipline, we collectively perform a global review of the field of pathology informatics. In doing so, we illustrate how general far-reaching trends such as the advent of computers, the Internet and digital imaging have affected pathology informatics in the world at large. Major drivers in the field included the need for pathologists to comply with national standards for health information technology and telepathology applications to meet the scarcity of pathology services and trained people in certain countries. Following trials by a multitude of investigators, not all of them successful, it is apparent that innovation alone did not assure the success of many informatics tools and solutions. Common, ongoing barriers to the widespread adoption of informatics devices include poor information technology infrastructure in undeveloped areas, the cost of technology, and regulatory issues. This review offers a deeper understanding of how pathology informatics historically developed and provides insights into what the promising future might hold.

Quantitative pathology in virtual microscopy: history, applications, perspectives.

With the emerging success of commercially available personal computers and the rapid progress in the development of information technologies, morphometric analyses of static histological images have been introduced to improve our understanding of the biology of diseases such as cancer. First applications have been quantifications of immunohistochemical expression patterns. In addition to object counting and feature extraction, laws of thermodynamics have been applied in morphometric calculations termed syntactic structure analysis. Here, one has to consider that the information of an image can be calculated for separate hierarchical layers such as single pixels, cluster of pixels, segmented small objects, clusters of small objects, objects of higher order composed of several small objects. Using syntactic structure analysis in histological images, functional states can be extracted and efficiency of labor in tissues can be quantified. Image standardization procedures, such as shading correction and color normalization, can overcome artifacts blurring clear thresholds. Morphometric techniques are not only useful to learn more about biological features of growth patterns, they can also be helpful in routine diagnostic pathology. In such cases, entropy calculations are applied in analogy to theoretical considerations concerning information content. Thus, regions with high information content can automatically be highlighted. Analysis of the "regions of high diagnostic value" can deliver in the context of clinical information, site of involvement and patient data (e.g. age, sex), support in histopathological differential diagnoses. It can be expected that quantitative virtual microscopy will open new possibilities for automated histological support. Automated integrated quantification of histological slides also serves for quality assurance. The development and theoretical background of morphometric analyses in histopathology are reviewed, as well as their application and potential future implementation in virtual microscopy.

Diagnostic pathology in 2012: development of digital pathology in an open access journal.

Herein we describe and interpret the digital world of diagnostic surgical pathology, and take the in Pathology leading Open Access Journal Diagnostic Pathology as example. VIRTUAL SLIDE: http://www.diagnosticpathology.diagnomx.eu/vs/1944221953867351.

Introduction of virtual microscopy in routine surgical pathology--a hypothesis and personal view from Europe.

The technology of whole image acquisition from histological glass slides (Virtual slides, (VS)) and its associated software such as image storage, viewers, and virtual microscopy (VM), has matured in the recent years. There is an ongoing discussion whether to introduce VM into routine diagnostic surgical pathology (tissue-based diagnosis) or not, and if these are to be introduced how best to do this. The discussion also centres around how to substantially define the mandatory standards and working conditions related to introducing VM. This article briefly describes some hypotheses alongside our perspective and that of several of our European colleagues who have experienced VS and VM either in research or routine praxis. After consideration of the different opinions and published data the following statements can be derived: 1. Experiences from static and remote telepathology as well as from daily routine diagnoses, confirm that VM is a diagnostic tool that can be handled with the same diagnostic accuracy as conventional microscopy; at least no statistically significant differences (p > 0.05) exist. 2. VM possesses several practical advantages in comparison to conventional microscopy; such as digital image storage and retrieval and contemporary display of multiple images (acquired from different stains, and/or different cases). 3. VM enables fast and efficient feedback between the pathologist and the laboratory in terms of ordered additional stains, automated access to the latest research for references, and fast consultation with outstanding telepathology experts. 4. Industry has already invested "big money" into this technology which certainly will be of influence in its future development. The main constraints against VM include the questionable reimbursement of the initial investment, the missing direct and short term financial benefit, and the loss of potential biological identity between the patient and the examined tissue. This article tries to analyze and evaluate the factors that influence the implementation of VM into routine tissue-based diagnosis, for example in combination with predictive diagnosis. It focuses on describing the advantages of modern and innovative electronically based communication technology. VIRTUAL SLIDES: The virtual slide(s) for this article can be found here: http://www.diagnosticpathology.diagnomx.eu/vs/1245603103708547.

How to introduce virtual microscopy (VM) in routine diagnostic pathology: constraints, ideas, and solutions.

CONTEXT: Virtual microscopy which is the diagnostic work with digitized microscopic images in tissue - based diagnosis is in its childhood in being implemented in routine diagnosis. Until today, only a few pathology institutions take use of this new technology, although it is available since several years. Why? DESIGN: Virtual microscopy requires a new workflow organisation in the pathologist's diagnostic procedure. At a first view, the laboratory workflow seems to remain untouched to a high degree. However, the used laboratory information system (LIS), which is commonly built in a hierarchic order, has to be adjusted at its highest levels, i.e., diagnosis statement, quality evaluation, submission to the clinician (hospital information system), and feedback to the laboratory. Therefore, the laboratory's workflow is involved at all levels too, and the LIS has to be changed or adjusted to the requirements of VM. VM systems are usually equipped with a viewer that mimics the viewing of a conventional microscope, and do not offer access to sensitive nodes of the LIS. Similar, LIS are usually closed and fixed systems because of data security and certification demands. Thus, VM systems have to possess communication access at different LIS levels together with steering commands for the LIS in close association with the diagnostic quality and efficiency (for example demands for additional stains, immunohistochemical or quantitative image methods, etc.), as well as expert consultation, or panel discussion. OUTCOME: An implementation of an open and active LIS - VM management system could significantly promote the introduction of VM into routine diagnostic surgical pathology. The management system has to coordinate and translate the demands of VM to LIS (and vice versa), and to assure the communication with HIS. Mandatory features include streaming of the laboratory workflow, feedback commands to LIS, as well as regulation of temporary priority levels. CONCLUSION: A successful implementation of VM systems in routine tissue-based diagnosis requires communicative management systems as long as VM is considered to be a "stand alone system" that just mimics a conventional microscope.

Virtual slides in peer reviewed, open access medical publication.

BACKGROUND: Application of virtual slides (VS), the digitalization of complete glass slides, is in its infancy to be implemented in routine diagnostic surgical pathology and to issues that are related to tissue-based diagnosis, such as education and scientific publication. APPROACH: Electronic publication in Pathology offers new features of scientific communication in pathology that cannot be obtained by conventional paper based journals. Most of these features are based upon completely open or partly directed interaction between the reader and the system that distributes the article. One of these interactions can be applied to microscopic images allowing the reader to navigate and magnify the presented images. VS and interactive Virtual Microscopy (VM) are a tool to increase the scientific value of microscopic images. TECHNOLOGY AND PERFORMANCE: The open access journal Diagnostic Pathology http://www.diagnosticpathology.org has existed for about five years. It is a peer reviewed journal that publishes all types of scientific contributions, including original scientific work, case reports and review articles. In addition to digitized still images the authors of appropriate articles are requested to submit the underlying glass slides to an institution (DiagnomX.eu, and Leica.com) for digitalization and documentation. The images are stored in a separate image data bank which is adequately linked to the article. The normal review process is not involved. Both processes (peer review and VS acquisition) are performed contemporaneously in order to minimize a potential publication delay. VS are not provided with a DOI index (digital object identifier). The first articles that include VS were published in March 2011. RESULTS AND PERSPECTIVES: Several logistic constraints had to be overcome until the first articles including VS could be published. Step by step an automated acquisition and distribution system had to be implemented to the corresponding article. The acceptance of VS by the reader is high as well as by the authors. Of specific value are the increased confidence to and reputation of authors as well as the presented information to the reader. Additional associated functions such as access to author-owned related image collections, reader-controlled automated image measurements and image transformations are in preparation. VIRTUAL SLIDES: The virtual slide(s) for this article can be found here: http://www.diagnosticpathology.diagnomx.eu/vs/1232133347629819.

History and structures of telecommunication in pathology, focusing on open access platforms.

BACKGROUND: Telecommunication has matured to a broadly applied tool in diagnostic pathology. TECHNOLOGY AND SYSTEMS: Contemporary with the development of fast electronic communication lines (Integrated digital network services (ISDN), broad band connections, and fibre optics, as well as the digital imaging technology (digital camera), telecommunication in tissue--based diagnosis (telepathology) has matured. Open access (internet) and server--based communication have induced the development of specific medical information platforms, such as iPATH, UICC-TPCC (telepathology consultation centre of the Union International against Cancer), or the Armed Forces Institute of Pathology (AFIP) teleconsultation system. They have been closed, and are subject to be replaced by specific open access forums (Medical Electronic Expert Communication System (MECES) with embedded virtual slide (VS) technology). MECES uses php language, data base driven mySqL architecture, X/L-AMPP infrastructure, and browser friendly W3C conform standards. EXPERIENCES: The server--based medical communication systems (AFIP, iPATH, UICC-TPCC) have been reported to be a useful and easy to handle tool for expert consultation. Correct sampling and evaluation of transmitted still images by experts reported revealed no or only minor differences to the original images and good practice of the involved experts. ß tests with the new generation medical expert consultation systems (MECES) revealed superior results in terms of performance, still image viewing, and system handling, especially as this is closely related to the use of so--called social forums (facebook, youtube, etc.). BENEFITS AND EXPECTATIONS: In addition to the acknowledged advantages of the former established systems (assistance of pathologists working in developing countries, diagnosis confirmation, international information exchange, etc.), the new generation offers additional benefits such as acoustic information transfer, assistance in image screening, VS technology, and teaching in diagnostic sampling, judgement, and verification.

To be at the right place at the right time.

AIM: To analyze the hypothesis of events or neighborhood interactions that is based upon recognizable structures of systems which possess a surface in a four dimensional space-time constellation {x, y, z, t}. To include the theory of hierarchic order of structures and aspects of thermodynamically open systems, especially entropy, structural entropy and entropy flow. HYPOTHESIS: Any structure is a space-time constellation that occupies a unique space in its environment. The environment can be a system too, and is assumed to be (nearly) constant. Structures can interact in their environment and create a new structure at a higher order level. Interacting structures that create a surface are called a system. Starting from the bottom, such a system is characterized by its inner structures, its surface function, and its neighborhood. Interaction with a neighboring system is called an event. An event can alter a system, create new systems or induce the decay of a system, dependent upon the surrounding lower level system (background). RESULTS: The hypothesis results in a uniform theory about matter, life, diseases, or behavior. Concrete applications permit the estimation of duration of life in man, for example the effect of solid cancer in man, or appearance of protozoans in sexual or asexual reduplication. In addition, it can successfully describe the development of the universe (small exceed of matter above antimatter at the big bang), or the increase of structures (and systems) with increasing time (development of intelligent systems). The three dimensional space possesses the lowest number of mandatory dimensions to implement such a system.

Grid computing in image analysis.

Diagnostic surgical pathology or tissue­based diagnosis still remains the most reliable and specific diagnostic medical procedure. The development of whole slide scanners permits the creation of virtual slides and to work on so-called virtual microscopes. In addition to interactive work on virtual slides approaches have been reported that introduce automated virtual microscopy, which is composed of several tools focusing on quite different tasks. These include evaluation of image quality and image standardization, analysis of potential useful thresholds for object detection and identification (segmentation), dynamic segmentation procedures, adjustable magnification to optimize feature extraction, and texture analysis including image transformation and evaluation of elementary primitives. Grid technology seems to possess all features to efficiently target and control the specific tasks of image information and detection in order to obtain a detailed and accurate diagnosis. Grid technology is based upon so-called nodes that are linked together and share certain communication rules in using open standards. Their number and functionality can vary according to the needs of a specific user at a given point in time. When implementing automated virtual microscopy with Grid technology, all of the five different Grid functions have to be taken into account, namely 1) computation services, 2) data services, 3) application services, 4) information services, and 5) knowledge services. Although all mandatory tools of automated virtual microscopy can be implemented in a closed or standardized open system, Grid technology offers a new dimension to acquire, detect, classify, and distribute medical image information, and to assure quality in tissue­based diagnosis.

Interactive and automated application of virtual microscopy.

Virtual microscopy can be applied in an interactive and an automated manner. Interactive application is performed in close association to conventional microscopy. It includes image standardization suitable to the performance of an individual pathologist such as image colorization, white color balance, or individual adjusted brightness. The steering commands have to include selection of wanted magnification, easy navigation, notification, and simple measurements (distances, areas). The display of the histological image should be adjusted to the physical limits of the human eye, which are determined by a view angle of approximately 35 seconds. A more sophisticated performance should include acoustic commands that replace the corresponding visual commands. Automated virtual microscopy includes so-called microscopy assistants which can be defined similar to the developed assistants in computer based editing systems (Microsoft Word, etc.). These include an automated image standardization and correction algorithms that excludes images of poor quality (for example uni-colored or out-of-focus images), an automated selection of the most appropriate field of view, an automated selection of the best magnification, and finally proposals of the most probable diagnosis. A quality control of the final diagnosis, and feedback to the laboratory determine the proposed system. The already developed tools of such a system are described in detail, as well as the results of first trials. In order to enhance the speed of such a system, and to allow further user-independent development a distributed implementation probably based upon Grid technology seems to be appropriate. The advantages of such a system as well as the present pathology environment and its expectations will be discussed in detail.

E-education in pathology including certification of e-institutions.

E-education or electronically transferred continuous education in pathology is one major application of virtual microscopy. The basic conditions and properties of acoustic and visual information transfer, of teaching and learning processes, as well as of knowledge and competence, influence its implementation to a high degree. Educational programs and structures can be judged by access to the basic conditions, by description of the teaching resources, methods, and its program, as well as by identification of competences, and development of an appropriate evaluation system. Classic teaching and learning methods present a constant, usually non-reversible information flow. They are subject to personal circumstances of both teacher and student. The methods of information presentation need to be distinguished between static and dynamic, between acoustic and visual ones. Electronic tools in education include local manually assisted tools (language assistants, computer-assisted design, etc.), local passive tools (slides, movies, sounds, music), open access tools (internet), and specific tools such as Webinars. From the medical point of view information content can be divided into constant (gross and microscopic anatomy) and variable (disease related) items. Most open access available medical courses teach constant information such as anatomy or physiology. Mandatory teaching resources are image archives with user-controlled navigation and labelling, student-oriented user manuals, discussion forums, and expert consultation. A classic undergraduate electronic educational system is WebMic which presents with histology lectures. An example designed for postgraduate teaching is the digital lung pathology system. It includes a description of diagnostic and therapeutic features of 60 rare and common lung diseases, partly in multimedia presentation. Combining multimedia features with the organization structures of a virtual pathology institution will result in a virtual pathology education institution (VPEI), which can develop to a partly automated distant learning faculty in medicine.

How to measure diagnosis-associated information in virtual slides.

The distribution of diagnosis-associated information in histological slides is often spatial dependent. A reliable selection of the slide areas containing the most significant information to deriving the associated diagnosis is a major task in virtual microscopy. Three different algorithms can be used to select the appropriate fields of view: 1) Object dependent segmentation combined with graph theory; 2) time series associated texture analysis; and 3) geometrical statistics based upon geometrical primitives. These methods can be applied by sliding technique (i.e., field of view selection with fixed frames), and by cluster analysis. The implementation of these methods requires a standardization of images in terms of vignette correction and gray value distribution as well as determination of appropriate magnification (method 1 only). A principle component analysis of the color space can significantly reduce the necessary computation time. Method 3 is based upon gray value dependent segmentation followed by graph theory application using the construction of (associated) minimum spanning tree and Voronoi's neighbourhood condition. The three methods have been applied on large sets of histological images comprising different organs (colon, lung, pleura, stomach, thyroid) and different magnifications, The trials resulted in a reproducible and correct selection of fields of view in all three methods. The different algorithms can be combined to a basic technique of field of view selection, and a general theory of "image information" can be derived. The advantages and constraints of the applied methods will be discussed.

Quantification of virtual slides: Approaches to analysis of content-based image information.

Virtual microscopy, which is the diagnostic work on completely digitized histological and cytological slides as well as blood smears, is at the stage to be implemented in routine diagnostic surgical pathology (tissue-based diagnosis) in the near future, once it has been accepted by the US Food and Drug Administration. The principle of content-based image information, its mandatory prerequisites to obtain reproducible and stable image information as well as the different compartments that contribute to image information are described in detail. Automated extraction of content-based image information requires shading correction, constant maximum of grey values, and standardized grey value histograms. The different compartments to evaluate image information include objects, structure, and texture. Identification of objects and derived structure depend on segmentation accuracy and applied procedures; textures contain pixel-based image information only. All together, these image compartments posses the discrimination power to distinguish between object space and background, and, in addition, to reproducibly define regions of interest (ROIs). ROIs are image areas which display the information that is of preferable interest to the viewing pathologist. They contribute to the derived diagnosis to a higher level when compared with other image areas. The implementation of content-based image information algorithms to be applied for predictive tissue-based diagnoses is described in detail.