Global acetylation and methylation changes predict papillary urothelial neoplasia of low malignant potential recurrence: a quantitative analysis.

Papillary urothelial neoplasia of low malignant potential (PUNLMP) recurs in approximately 35% of patients. Conventional histopathological assessment does not distinguish non-recurrent from recurrent PUNLMP. The aim of this study is to explore the differences in global histone acetylation and global DNA methylation between non-recurrent and recurrent PUNLMP. Acetylated histone H3 lysine 9 (AcH3K9) and 5-methylcytosine (5MeC) were investigated by immunohistochemistry (IHC) in 20 PUNLMP cases (10 non-recurrent and 10 recurrent), in 5 cases of normal urothelium (NU) and in 5 cases of muscle invasive pT2 urothelial carcinoma (UC). The total optical density of the nuclear staining was measured photometrically in at least 40 nuclei separately for the basal, intermediate and luminal positions in each case. Concerning the total optical density values for both acetylation and methylation, a decrease in staining is observed from non-recurrent PUNLMP to recurrent PUNLMP, at all nuclear locations. For acetylation the mean value in non-recurrent PUNLMP, intermediate between NU and UC, is closer to the former than to latter. The mean value in recurrent PUNLMP is closer to UC than to NU. In NU, non-recurrent and recurrent PUNLMP, the acetylation to methylation ratio decreased from the nuclei in basal position to those in the surface, the average for the above groups being 1.491, 1.611 and 1.746, respectively. Setting the observed values for NU at each sampling location to unity, acetylation shows a steady decrease, the percentages of changes in this nuclear location compared to NU being -5% in non-recurrent PUNLMP, -15% in recurrent PUNLMP and -24% in UC. Concerning methylation, there is a slight increase in non-recurrent PUNLMP (+5%), a decrease in recurrent PUNLMP (-19%) followed by a sharp rise for the UC (+61%). In conclusion, there are differences in global histone acetylation and DNA methylation patterns between non-recurrent and recurrent PUNLMP. Further studies are needed to elucidate the complex interplay between chromatin structure, its modifications and recurrence of PUNLMP.

Karyometric marker features in normal-appearing glands adjacent to human colonic adenocarcinoma.

The expression of nuclear marker features in normal-appearing tissue adjacent to colonic adenocarcinoma was investigated. Formalin-fixed, paraffin-embedded tissue sections of colon from 9 patients with adenocarcinoma and from 9 normal controls were cut 4 microns thick, Feulgen stained, and measured by a cell image analysis system using a Matrox MVP-AT/NP imaging board. Thirty nuclei in the tumor region, 30 nuclei 2 mm into the histologically normal-appearing distal margin, and the same number at 5, 10, 20, and 50 mm into the margin were measured for each patient. An additional 30 nuclei were recorded from 9 patients each free from colonic disease. Nuclear features were selected to discriminate between tumor nuclei and nuclei from normal control subjects and between nuclei measured in the histologically normal-appearing margin next to the tumor and control nuclei. Eight micromorphometric measures were found to be statistically significantly different in nuclei measured in the margin site, including features describing staining density (total absorbance, average absorbance 20% below mean, average absorbance 20% above mean) chromatin texture (cooccurrence matrix, run length, and peripheral tendency) and nuclear area. The category differences are statistically highly significant.

Karyometry in the early detection and chemoprevention of intraepithelial lesions.

The ideal chemopreventive agent targets pre-neoplastic changes and intraepithelial neoplasia, preventing progression over time without notable side effects. Assessment of success of chemopreventive intervention in the short and medium term remains a challenge, and in this review the suggestion is investigated that karyometric measurements constitute suitable markers of chemopreventive efficacy. Karyometry provides the sensitivity required to detect small differences amidst relatively high biological variability. It can help establish progression curves of intraepithelial neoplasia (IEN) to invasive cancer, and thus detect chemopreventive effects. Such effects can be observed in two ways, at the group level (intervention vs. placebo), and at the case (or patient) level. The latter is more difficult to establish, necessitating the development of specialised statistical methods. Analysis of between-case and within-case heterogeneity can reveal useful information about cancer progression and prevention. We suggest that karyometry can objectively quantify IEN progression, providing a framework for statistically securing chemopreventive effects. It can act as an integrating biomarker by detecting chemopreventive activity even when the mechanism for a given progression pathway is unknown, or when multiple pathways exist. The sensitivity of karyometric detection can help optimise the design of clinical trials of novel chemopreventive agents by decreasing trial duration and/or sample size.

Quantitative morphology of late renal radiation injury.

Late radiation injury manifests itself in all morphologic compartments of the kidney, but loss of cell mass is most significant in the proximal convoluted tubules. Development of an end stage or nonfunctional kidney requires 12 or more months after single fraction X ray exposures of about 12 Gy (2, 5, 13) and is associated with marked morphologic alterations of renal tubules. Radiation induced changes were studied at 6 months after irradiation, a time interval when histological alterations appear minor, but in previous studies were shown to correlate with the later end stage alterations (5, 8, 9). Renal alterations were graded objectively based on renal weight, variation in size of tubule cell nuclei, and glomerular nuclear volume fraction. Irradiation was associated with loss of renal weight, increased variability of tubule nuclear size, and previously unappreciated changes in glomerular nuclear volume fraction. A classification index derived from a weighted combination of renal weight ratio and tubule cell nuclear variability correlates with radiation dose and with previously established subjective histologic grading of renal damage, and allows objective comparisons of various fractionation schedules.

Ultrafast laser scanner microscope.

Advances in monolayer deposition of cervical cells have removed one of the last serious obstacles to the design of high-resolution automated diagnostic assessment systems. In this article, we describe the design considerations for a system that is capable of acquiring, within 60 sec, a 0.5 micron digitized image of a 4 cm2 area on a standard glass slide. The most feasible approach is found to be a system using a rotating polygon to sweep the focused spot from a laser across a 2-mm scan line while the slide is uniformly translated perpendicular to the scan direction the use of laser sources (a helium-neon laser at 632 nm and a krypton ion laser at 568 and/or 476 nm) as compared to the incoherent light sources used in conventional microscope systems alleviates many of the optical design problems and provides the proper wavelengths needed for recognition of Papanicolaou stained cells. We also find that focus control of the scanning spot should be achievable using a technique involving a holographic grating. Other relevant considerations such as sample heating problems, multiphoton absorption by the sample, detector signal-to-noise ratios, laser amplitude noise control, and the digitization and buffering of the data stream are also discussed.

Computer analysis of defined populations of lymphocytes irradiated in vitro. III. Evaluation of human T and B cells of peripheral blood origin.

The radiosensitivities of lymphocytes of peripheral blood origin obtained from two healthy 45 year old male donors were studied simultaneously at yearly intervals over a three year period. Hypaque-Ficoll purified cells were exposed in vitro to 0, 5, 50, and 500 rads and then evaluated serially for viability of T and B cells, responsiveness to PHA and Con A, and morphologic evidence of injury as documented by standard light microscopy and computer assisted morphometric analysis. The results showed that T cells in both subjects were less radiosensitive than B cells. Differences between the two subjects also existed in the radiosensitivity of these two subpopulations of lymphocytes, differences that remained constant over the three years period of observation. The differences correlated with similar discrepancies in mitogenic responsiveness and are thought to relate to variations in the relative proportions of subpopulations of T and B cells. In the mouse, T and B cell subpopulations differ in radiosensitivity. The data reported herein are consistent with a similar situation in man.

Atypical adenomatous hyperplasia (adenosis) of the prostate: development of a Bayesian belief network for its distinction from well-differentiated adenocarcinoma.

The diagnosis of atypical adenomatous hyperplasia (AAH) of the prostate and its distinction from well-differentiated prostatic adenocarcinoma with small acinar pattern (PACsmac; Gleason primary grades 1 or 2) are affected by uncertainties that arise from the fact that the knowledge of AAH histopathology is expressed in descriptive linguistic terms, words, and concepts. A Bayesian belief network (BBN) was used to reduce the problem of uncertainty in diagnostic clue assessment, while still considering the dependencies between elements in the reasoning sequence. A shallow network was designed and developed with an open-tree topology, consisting of a root node containing two diagnostic alternatives (eg, AAH v PACsmac) and 12 first-level descendant nodes for the diagnostic features. Eight of these nodes were based on cell features, three on the type of gland lumen contents and one on the gland shape. The results obtained with prototypes of relative likelihood ratios showed that belief for the diagnostic alternatives is high and that the network can differentiate AAH from PACsmac with certainty. The features that best contributed to the highest belief were those concerning the nucleolar size, frequency, and location. In particular, after the analysis of five nucleolar features (prominent nucleoli, inconspicuous nucleoli, nucleoli with diameter greater than 2.5 micron, nucleolar margination, and nuclei with multiple nucleoli), the belief for AAH was 1.0, being already close to 1.0 when three were evaluated (the value range is 0.0 to 1.0; the closer to 1.0, the greater the belief). The contribution of the three features concerning the gland lumen contents (mucinous material, corpora amylacea, and crystalloids) was such that the final belief did not exceed 0.8. Results with the group of remaining features (eg, basal cell recognition, gland shape variation, cytoplasm appearance, and nuclear size variation) were slightly better. These features allowed a substantial accumulation of belief that was already greater than 0.9 when three were polled. However, the maximum belief value was never obtained. In conclusion, a BBN for AAH diagnosis offers a descriptive classifier that is readily implemented, and allows the use of linguistic, fuzzy variables, and the accumulation of evidence presented by diagnostic clues.

Computerized diagnostic decision support system for the classification of preinvasive cervical squamous lesions.

Previous studies have revealed considerable interobserver and intraobserver variation in the histological classification of preinvasive cervical squamous lesions. The aim of the present study was to develop a decision support system (DSS) for the histological interpretation of these lesions. Knowledge and uncertainty were represented in the form of a Bayesian belief network that permitted the storage of diagnostic knowledge and, for a given case, the collection of evidence in a cumulative manner that provided a final probability for the possible diagnostic outcomes. The network comprised 8 diagnostic histological features (evidence nodes) that were each independently linked to the diagnosis (decision node) by a conditional probability matrix. Diagnostic outcomes comprised normal; koilocytosis; and cervical intraepithelial neoplasia (CIN) I, CIN II, and CIN III. For each evidence feature, a set of images was recorded that represented the full spectrum of change for that feature. The system was designed to be interactive in that the histopathologist was prompted to enter evidence into the network via a specifically designed graphical user interface (i-Path Diagnostics, Belfast, Northern Ireland). Membership functions were used to derive the relative likelihoods for the alternative feature outcomes, the likelihood vector was entered into the network, and the updated diagnostic belief was computed for the diagnostic outcomes and displayed. A cumulative probability graph was generated throughout the diagnostic process and presented on screen. The network was tested on 50 cervical colposcopic biopsy specimens, comprising 10 cases each of normal, koilocytosis, CIN I, CIN II, and CIN III. These had been preselected by a consultant gynecological pathologist. Using conventional morphological assessment, the cases were classified on 2 separate occasions by 2 consultant and 2 junior pathologists. The cases were also then classified using the DSS on 2 occasions by the 4 pathologists and by 2 medical students with no experience in cervical histology. Interobserver and intraobserver agreement using morphology and using the DSS was calculated with kappa statistics. Intraobserver reproducibility using conventional unaided diagnosis was reasonably good (kappa range, 0.688 to 0.861), but interobserver agreement was poor (kappa range, 0.347 to 0.747). Using the DSS improved overall reproducibility between individuals. Using the DSS, however, did not enhance the diagnostic performance of junior pathologists when comparing their DSS-based diagnosis against an experienced consultant. However, the generation of a cumulative probability graph also allowed a comparison of individual performance, how individual features were assessed in the same case, and how this contributed to diagnostic disagreement between individuals. Diagnostic features such as nuclear pleomorphism were shown to be particularly problematic and poorly reproducible. DSSs such as this therefore not only have a role to play in enhancing decision making but also in the study of diagnostic protocol, education, self-assessment, and quality control.

The diagnostic pattern in histopathology.

Defining in precise detail the diagnostic clues used by histopathologists to arrive at a diagnosis is a difficult process; however, better analytic understanding of this process is a prerequisite for the design of diagnostic expert systems. Such systems offer the potential for consistency and setting standards in the diagnostic evaluation of difficult situations. Diagnostic clues as offered by the image represent two-dimensional information. Their description is entered into the knowledge base of an aspect system, however, in the form of a description, which is one-dimensional. Preserving all of the two-dimensional dependence structure in this conversion is a fundamental problem. Use of the description to generate simulated imagery tests whether or not the two-dimensional dependence structure of a given tissue architecture has been adequately represented in the analytic description. This analytic description would then be entered into the knowledge base of an expert system.

Automated image analysis in clinical pathology.

The applications of automated cell image analyses are primarily in cytopathology, hematology, and cellular immunology. This paper presents data evaluation technics and statistical methods for automated cell analysis.

A diagnostic expert system for colonic lesions.

The diagnostic expert system for colonic lesions (DESCL) was designed to discriminate colonic adenoma and adenocarcinoma from normal colonic tissue. Although it was originally developed for use in conjunction with a machine vision analytic system, the DESCL has evolved into a teaching tool and a model for conceptual machine learning. The expert system is table driven and consists of a shell and a knowledge base. The latter comprises a series of architectural and cytologic observations and a quantitative estimate of diagnostic importance relating these observations to diagnostic outcome. In a validation study of 100 colonic lesions, the expert system achieved a success rate of 98%. It has the flexibility to allow individual pathologists to "customize" the knowledge base to suit their diagnostic criteria.

DNA ploidy profiles as prognostic indicators in CIN lesions.

The prognostic significance of DNA ploidy measurements in cervical tissues was examined. Microphotometric measurements of 302 Feulgen-stained tissue sections (91 normal squamous epithelia, 14 condylomata, 29 cervical intraepithelial neoplasia (CIN) I, 78 CIN II, and 90 CIN III) were performed with a personal computer (PC)-based video microphotometry system. Analysis of these data shows that the DNA profile provides significant prognostic information: CINs with a polyploid DNA profile are more likely to return to normal than are those exhibiting an aneuploid pattern. Of 211 abnormal cases, 38% had polyploid DNA profiles and 62% were aneuploid. Eight-six percent of the cases that regressed were polyploid and 14% were aneuploid. Of the 130 aneuploid DNA cases, 95% remained static or progressed and only 5% regressed. Of these nonregressing aneuploid lesions, 90 remained static and 34 progressed, whereas within the nonregressing polyploid group 37 remained static and only 6 progressed. This result holds across diagnostic categories. Several other ploidy-related descriptors also showed prognostic significance (including mean ploidy, the 5N exceeding rate and 2N deviation index, and discriminant functions derived from order statistic analysis of the cumulative DNA histograms), but not to the degree or with the consistency of expression as the DNA profile categorization. These results indicate that important information about the prognosis of CIN lesions may be obtained by the DNA profile on Feulgen-stained tissue specimens. The data were acquired by a cytophotometry system of relatively modest cost consisting of readily available hardware components.

Differentiation by TICAS analysis of cell populations of tracheal aspirates from hamsters with squamous-cell carcinoma.

Individual cells from the tracheal aspirates of hamsters exposed to benzo-a-pyrene were scanned at .5 mum in three colors. Features relating to size, shape, and color were extracted and calculated by computer. The single cells were then classified by these features into separate populations with varying degrees of atypia, extending up to frank cancer cells. A high degree of accuracy was attained in classification by these methods.

Expert system support using Bayesian belief networks in the diagnosis of fine needle aspiration biopsy specimens of the breast.

AIM: To develop an expert system model for the diagnosis of fine needle aspiration cytology (FNAC) of the breast. METHODS: Knowledge and uncertainty were represented in the form of a Bayesian belief network which permitted the combination of diagnostic evidence in a cumulative manner and provided a final probability for the possible diagnostic outcomes. The network comprised 10 cytological features (evidence nodes), each independently linked to the diagnosis (decision node) by a conditional probability matrix. The system was designed to be interactive in that the cytopathologist entered evidence into the network in the form of likelihood ratios for the outcomes at each evidence node. RESULTS: The efficiency of the network was tested on a series of 40 breast FNAC specimens. The highest diagnostic probability provided by the network agreed with the cytopathologists' diagnosis in 100% of cases for the assessment of discrete, benign, and malignant aspirates. Atypical probably benign cases were given probabilities in favour of a benign diagnosis. Suspicious cases tended to have similar probabilities for both diagnostic outcomes and so, correctly, could not be assigned as benign or malignant. A closer examination of cumulative belief graphs for the diagnostic sequence of each case provided insight into the diagnostic process, and quantitative data which improved the identification of suspicious cases. CONCLUSION: The further development of such a system will have three important roles in breast cytodiagnosis: (1) to aid the cytologist in making a more consistent and objective diagnosis; (2) to provide a teaching tool on breast cytological diagnosis for the non-expert; and (3) it is the first stage in the development of a system capable of automated diagnosis through the use of expert system machine vision.

Diagnostic distance of high grade prostatic intraepithelial neoplasia from normal prostate and adenocarcinoma.

OBJECTIVE: To develop a distance measure based methodology to support the morphological evaluation of high grade prostatic intraepithelial neoplasia (PIN), a direct precursor of prostate cancer. METHODS: Eight morphological and cellular features were analysed in 20 cases of high grade PIN found in radical prostatectomy specimens from patients with adenocarcinoma. The diagnostic distance was evaluated to measure the extent to which the feature outcomes of the individual high grade PIN cases differed from the expected outcome profile of normal prostate, low and high grade PIN, and cribriform and large acinar adenocarcinoma. The belief value for high grade PIN was evaluated with a Bayesian belief network (BBN). RESULTS: Complete separation existed between the cumulative absolute diagnostic distances of these 20 cases from the prototype feature outcomes of high grade PIN and normal prostate the values for which were < or = 3 (range 0 to 3) and > or = 9 (range 9 to 15), respectively. The distances from low grade PIN (range 3 to 9), cribriform adenocarcinoma (range 2 to 8), and large acinar adenocarcinoma (range 5 to 10) were intermediate and showed overlap in their distribution. When taking into consideration whether the severity of feature changes was increasing or decreasing in comparison with the category prototype outcomes, the cumulative directional diagnostic distances from high grade PIN ranged from -3 to +3. Positive distance values were seen relative to low grade PIN (range +3 to +9) and relative to normal prostate (range +9 to +15). Negative values were found relative to cribriform adenocarcinoma (range -8 to +2). The distance values from large acinar adenocarcinoma ranged from -2 to +4 and partly overlapped with those from the high grade PIN category. A bivariate scattergram derived from both diagnostic distance measures showed excellent separation between the groups' distances. BBN analysis confirmed the morphology based diagnosis. The distance evaluation resulted in 18 cases whose belief value for high grade PIN ranged from 0.60 to 0.87. In the remaining two cases the results of the BBN analysis showed a belief value of 0.50 and 0.57 for low grade PIN and of 0.49 and 0.38 for high grade PIN, respectively. CONCLUSIONS: Distance measure based methodology represents a useful diagnostic decision support tool for the accurate evaluation of high grade PIN.

Karyometry detects subvisual differences in chromatin organisation state between non-recurrent and recurrent papillary urothelial neoplasms of low malignant potential.

AIM: To analyse nuclear chromatin texture in non-recurrent and recurrent papillary urothelial neoplasms of low malignant potential (PUNLMPs). MATERIALS: Ninety three karyometric features were analysed on haematoxylin and eosin stained sections from 20 PUNLMP cases: 10 from patients with a solitary PUNLMP lesion, who were disease free during at least eight years' follow up, and 10 from patients with unifocal PUNLMP, one or more recurrences being seen during follow up. RESULTS: Kruskal-Wallis analysis was used to search for features showing significant differences between recurrent and non-recurrent cases. Significance was better than p<0.005 for more than 20 features. Based on significance, six texture features were selected for discriminant analysis. Stepwise linear discriminant analysis reduced Wilk's lambda to 0.87, indicating a highly significant difference between the two multivariate data sets, but only modest ability to discriminate (70% correct case classification). A box sequential classifier was used based on data derived from discriminant analysis. The classifier took three classification steps and classified 19 of the 20 cases correctly (95% correct case classification). To determine whether significant case grouping could also be obtained based on an objective criterion, the merged data sets of non-recurrent and recurrent cases were submitted to the unsupervised learning algorithm P-index. Two clusters were formed with significant differences. The subsequent application of a Cooley/Lohnes classifier resulted in an overall correct case classification rate of 85%. CONCLUSIONS: Karyometry and multivariate analyses detect subvisual differences in chromatin organisation state between non-recurrent and recurrent PUNLMPs, thus allowing identification of lesions that do or do not recur.

Immunohistochemical expression of pi class glutathione S-transferase in the basal cell layer of benign prostate tissue following chronic treatment with finasteride.

BACKGROUND: Glutathione S-transferases (GST) may prevent carcinogenesis through inactivation of reactive electrophiles by conjugation to reduced glutathione. Treatment directed at the induction or preservation of GST-pi expression in normal epithelium could have a profound impact on the prevention of prostate neoplasia. Finasteride, a 5-alpha-reductase inhibitor, is used as a chemopreventive agent because it blocks the conversion of testosterone to its byproduct which promotes prostate tumour growth. OBJECTIVE: To investigate GST-pi expression immunohistochemically in benign prostate tissue from untreated patients and from patients chronically treated with finasteride. MATERIALS: Immunostaining with anti-GST-pi antibody was performed on 10 (cysto-) prostatectomy, eight simple prostatectomy, and three transurethral prostatectomy specimens. The first set of 10 prostates was from untreated patients operated on for bladder cancer. The other cases were from patients with benign prostatic hyperplasia and chronically treated with finasteride. None of the specimens in either group showed prostatic cancer, prostatic intraepithelial neoplasia, urothelial carcinoma, or chronic prostatitis. Specimens were evaluated for the presence, intensity, and distribution of immunostaining. RESULTS: Diffuse cytoplasmic immunostaining was observed in the basal cell layer of the untreated specimens. Some variability in the expression of GST-pi was seen within each zone and also between the prostate zones. Only a minority of the secretory cells was stained weakly, mainly in the subnuclear region of the cells facing an uninterrupted basal cell layer. Staining was more homogeneously diffuse in the cytoplasm of the luminal cells facing the basement membrane directly. In the benign epithelium of the finasteride treated specimens the circumferential staining of the basal cells appeared to be more continuous than in the untreated cases, the gaps in the stained basal cell layer being fewer, shorter, or even absent in some ducts and acini. There was no variability in the intensity of staining of the basal cell layer, all the cells being intensely stained in a uniform way. The intensity of staining of the secretory cells was not influenced by finasteride treatment. CONCLUSIONS: Following chronic treatment with finasteride the immunohistochemical expression of pi class glutathione S-transferase in the benign prostate ducts and acini is upregulated in relation to an expanded basal cell layer. This could indicate that finasteride acts as a GST-pi inducer.

Transcontinental communication and quantitative digital histopathology via the Internet; with special reference to prostate neoplasia.

OBJECTIVE: To describe practical experiences in the sharing of very large digital data bases of histopathological imagery via the Internet, by investigators working in Europe, North America, and South America. MATERIALS: Experiences derived from medium power (sampling density 2.4 pixels/microm) and high power (6 pixels/microm) imagery of prostatic tissues, skin shave biopsies, breast lesions, endometrial sections, and colonic lesions. Most of the data included in this paper were from prostate. In particular, 1168 histological images of normal prostate, high grade prostatic intraepithelial neoplasia (PIN), and prostate cancer (PCa) were recorded, archived in an image format developed at the Optical Sciences Center (OSC), University of Arizona, and transmitted to Ancona, Italy, as JPEG (joint photographic experts group) files. Images were downloaded for review using the Internet application FTP (file transfer protocol). The images were then sent from Ancona to other laboratories for additional histopathological review and quantitative analyses. They were viewed using Adobe Photoshop, Paint Shop Pro, and Imaging for Windows. For karyometric analysis full resolution imagery was used, whereas histometric analyses were carried out on JPEG imagery also. RESULTS: The three applications of the telecommunication system were remote histopathological assessment, remote data acquisition, and selection of material. Typical data volumes for each project ranged from 120 megabytes to one gigabyte, and transmission times were usually less than one hour. There were only negligible transmission errors, and no problem in efficient communication, although real time communication was an exception, because of the time zone differences. As far as the remote histopathological assessment of the prostate was concerned, agreement between the pathologist's electronic diagnosis and the diagnostic label applied to the images by the recording scientist was present in 96.6% of instances. When these images were forwarded to two pathologists, the level of concordance with the reviewing pathologist who originally downloaded the files from Tucson was as high as 97.2% and 98.0%. Initial results of studies made by researchers belonging to our group but located in others laboratories showed the feasibility of making quantitative analysis on the same images. CONCLUSIONS: These experiences show that diagnostic teleconsultation and quantitative image analyses via the Internet are not only feasible, but practical, and allow a close collaboration between researchers widely separated by geographical distance and analytical resources.

Construction of the knowledge file for an image understanding system.

To enable an image understanding system to provide an automated interpretation of diagnostic imagery it must have access to all of the concepts, procedures and methods used by human experts. The paper describes information elicitation from experts of different domains and the construction of a knowledge file. Uncertainty management is based on Bayesian belief network methods.

Machine vision system for diagnostic histopathology.

In a machine vision system for the diagnostic assessment of histopathologic sections, human diagnostic knowledge and human ability to recognize components in a complex image need to be emulated. This is attempted by three integrated expert systems, supported by a multiprocessor computer with data-driven, dynamically reconfigurable architecture.