Recent developments and present status of telepathology.

Telepathology which is the diagnostic work of a pathologist at a distance has been developed to routine application within the last ten years. It can be classified in relation to application, technical solutions, or performance conditions. Diagnostic pathology performance distinguishes primary diagnosis (for example, frozen section statement) from secondary diagnosis (for example, expert consultation) and quality assurance (diagnostic accuracy, continuous education and training). Applications comprise (a) frozen section service; (b) expert consultations; (c) remote control measurements; and (d) education and training. The technical solutions distinguish active (remote control, live imaging) systems from passive (conventional microscope handling, static imaging), and the performance systems with interactive (on-line, live imaging) use from those with passive (offline, static imaging) practice. Intra-operative frozen section service is mainly performed with remote control systems; whereas expert consultations and education/training are commonly based upon Internet connections with static imaging in an off-line mode. The image quality, transfer rates, and screen resolution of active and passive telepathology systems are sufficient for an additional or primary judgment of histological slides and cytological smears. From the technical point of view, remote control telepathology requires a fast transfer and at least near on-line judgement of images, i.e., image acquisition, transfer and presentation can be considered one performance function. Thus, image size, line transfer rate and screen resolution define the practicability of the system. In expert consultation, the pixel resolution of images and natural color presentation are the main factors for diagnostic support, whereas the line transfer rate is of minor importance. These conditions define the technical compartments, especially size and resolution of camera and screen. The performance of commercially available systems has reached a high quality standard. Pathologists can be trained in a short time and use the systems in a routine manner. Several telepathology systems have been implemented in large Institutes of Pathology which serve for frozen section diagnosis in small hospitals located in the local area. In contrast, expert consultation is mainly performed with international connections. There is a remarkable increase of expert consultations by telepathology according to the experiences of the Armed Forces Institute of Pathology or the Department of Pathology, Thoraxklinik, Heidelberg. In expansion of these experiences, a "globalization" of telepathology can be expected. Telepathology can be used to shrink the period necessary for final diagnosis by request for diagnostic assistance to colleagues working in appropriate related time zones. Telepathology is, therefore, not a substitute of conventional diagnostic procedures but a real improvement in the world of pathology.     

The PARTICLE expert system for tumor grading by automated image analysis

While automated microscopic image analysis of histologic sections has been helpful in objectivizing histologic tumor grading and investigating the relationships between grading and prognosis, expert systems have the potential of linking image analysis and other data for statistical analysis and application to a wider range of tumors. One such expert system is PARTICLE, whose development was based on many years of experience in resolving histologic problems by image analysis. This paper discusses the philosophy of expert system for tumor grading and describes its implementation in the PARTICLE system. The system's structure, operations and applications are briefly presented. PARTICLE is essentially based on the evaluation of karyometric data.     

Expert consultation for cervical carcinoma smears. Reliability of selected-field videomicroscopy

OBJECTIVE: To evaluate the diagnostic accuracy of videomicroscopy image selection for expert consultation in cervical cytology. STUDY DESIGN: One hundred diagnostically difficult cervical cytologic smears were selected and rescreened by a general pathologist who chose, from each slide, four or five fields featuring abnormal cells. Video images were digitized and stored on a 512 x 512-pixel matrix using an image acquisition and transmission system. Five experts each reviewed 20 of the 100 cases, and a sixth reviewed all 100 cases. Diagnoses based on selected digitized images were compared to those based on conventional examination of whole slides. RESULTS: Intraobserver agreement was fair to excellent for all six experts (kappa value: 0.47-0.81); it was complete or acceptable in 68.4-85% of cases. Compared to the reference diagnosis, interobserver agreement was not significantly different whether cases were examined by screening the entire slide or by videomicroscopy of selected fields. The marked discordance in four cases concerned very small cells the significance of which was misinterpreted on videomicroscopy because of poor image quality due to lack of focus setting. CONCLUSION: This exploratory study showed that selection of videomicroscopy images seems as reliable as conventional examination of slides for expert consultation on diagnostically difficult cervical cytologic smear cases.     

Machine learning in quantitative histopathology

The role of expert systems functioning as process controllers in learning image understanding systems is discussed. Numeric learning systems already have found a number of applications in cytologic and histopathologic diagnosis. Depending on the required capabilities, systems of increasing complexity are needed. Expert systems to guide scene segmentation in histopathologic imagery require model-based reasoning. Diagnostic image interpretation with learning capability demands a full model of the human expert's competence, including a considerable variety of knowledge representation schemes and inference strategies, coordinated by a meta-process controller.     

Expert systems in medicine

The emergence of the artificial intelligence (AI) in computer technology and its application in the medical field enables the researchers to carry out such intelligent activities like image processing, medical reasoning systems, clinical decision supporting and natural language understanding, etc. A gastroenterological expert system application is briefly demonstrated in this paper. Similar expert systems can be seen to be useful in the research of gastrointestinal cytoprotection, including the plan of different compounds with cytoprotective effect, experimental and clinical medical research.     

An expert system for the early detection of melanoma using knowledge-based image analysis

Melanoma is the most lethal skin cancer; however, nearly all patients can be saved and cured by early detection and prompt surgical treatment. It has been demonstrated that the major diagnostic and prognostic parameters of melanoma are the vertical thickness, three-dimensional (3D) size and shape, and color of the lesion. The other characteristic features of early melanoma are irregularities in the boundary of the lesion and the appearance of nonuniform pigmentation (with a variety of color). During early stages of development of the melanoma, the changes in these parameters are very difficult to assess since no good tool exists for measuring them in situ and analyzing them for malignancy. A novel optical instrument called the "Nevoscope" has been developed to obtain multiple views of the transilluminated skin lesion from several angles. These views have been used to measure the thickness and 3D size of the skin lesion without excision. A knowledge-based image analysis and interpretation system is being developed to analyze images of the skin lesion for a set of diagnostic and prognostic features: thickness, 3D size, color and margin, boundary and surface characteristics. This analysis combined with the patient's history, such as occurrence of melanoma or dysplastic nevi in the family, life style, skin type, etc., is used by the knowledge-based expert system to detect early or potentially malignant lesions. The diagnostic and prognostic knowledge bases for the early detection of melanoma are being developed with the help of expert dermatologists and published case studies.     

Telepathology: a tool to aid in diagnosis and quality assurance in cervicovaginal cytology

Telepathology: a tool to aid in diagnosis and quality assurance in cenicovaginal cytology
The purpose of this study is to evaluate the use of a Teletransmission System with regard to quality of diagnosis and screening so as to establish its potential role in gynaecological cytology. Three aspects of its use in cytopathology have been considered: diagnosis, training, and quality control. The circumstances in which the system may be used for diagnosis, together with its advantages and disadvantages, are examined and discussed. In general, the costbenefit in diagnostic use related to the experience of both the expert and the peripheral pathologist. The system may also contribute to training and quality assessment, particularly if combined with other automated services, such as an image data bank.     

Basic aspects of and recent developments in telepathology in Europe, with specific emphasis on quality assurance

Telepathology is the diagnostic work of a pathologist from a distance and includes all specific fields of diagnostic pathology, such as frozen section services, expert consultation, cytometric and histometric measurement, and continuous education. For about 15 years experience has been collected at several universities in the United States and Europe based upon analog telephone lines (9.2 kbaud), digitized lines (ISDN, 64 kbaud), broad band connections (1.5 Mbaud) and the World Wide Web (28 kbaud). Potential use can be expected in the application of telepresentation, remote slide preparation, remote central diagnostics and telediscussion. The transfer of still images is well developed; that of live images is used in only a few institutions for frozen section services. The image quality and spatial resolution as well as the transfer speed are sufficient for expert consultations, morphometric measurements, quality assurance and education. All applications focus on discontinuous work flow. Although the European Community focuses on user needs and standardization aspects of telepathology by sponsoring a widespread telepathology project (Europath), implementation of telepathology into routine application in the continuous work flow has still to be developed. The technical equipment has still to be adjusted to the labor flow charts in routine pathologic diagnostic procedures. Telepathology seems to be the appropriate technique to offer both improvement in diagnostic quality and inclusion of the "control institution" into diagnostic responsibility.     

Colonic lesion expert system. Performance evaluation

A computer-based expert system for diagnosing colonic sections as normal, adenoma or adenocarcinoma is described, along with an evaluation of its performance. On the basis of its knowledge base, consisting of the values of diagnostic clues and their associated certainty factors for the possible diagnoses, the system will suggest the diagnosis for new cases presented to it. Using the data provided for 16 diagnostic clues, the system arrived at correct diagnoses for all cases of normal colon, for 49 of 50 cases of adenoma and for 48 of 49 cases of adenocarcinoma. Sample outputs from the expert system are presented and discussed, and the effects of possible alterations in the data base are considered.     

利用GIS对吉林针阔混交林TM遥感图像分类方法的初探

为提高林区TM遥感图像自动分类识别精度,在GIS技术辅助下,以吉林省汪清林业局针阔混交林TM遥感图像为例,对研究区DEM、坡向等地理因子和土壤类型等环境因子与森林植被分布之间的内在规律进行了定量分析,并结合对遥感图像预分类的定性分析,形成分类知识库,建立了适用于针阔混交林的自动分类识别专家系统.分类试验证明,该系统能比较明显地削弱混合像元和地形阴影的影响,分类精度较无监督分类法提高了14.22%,Kappa指数为0.7556,达到区别森林类型的分类目的.将GIS数据引入专家系统,应用先验知识建立推理机制,可以解决遥感图像中云区和云阴影区由于不能接收到正确的光谱值而无法进行分类的问题.     

An interactive microcomputer-based system for the quantitative analysis of stratified tissue sections

This paper describes a microcomputer-based system that allows diagnostically relevant properties of stratified tissue sections to be objectively measured. The results of detailed nuclear image analyses are examined in the broader context of the position of nuclei within the tissue section and relative to histologic structures and each other. Quantitative measures are obtained for important morphometric and densitometric properties of individual nuclei and mitotic figures and especially for their distribution and orientation within the tissue section relative to the stratum germinativum and each other. Recorded karyometric and histometric parameters include measures of nuclear DNA content (based on optical density measurements), size, roundness, texture, shape, distance to the basal layer, angle with the stratum germinativum, epithelial height and proximate nuclear distance. Statistics generated describe normalized mitotic density as a function of depth in the epithelium, and a composite mitotic index is produced based upon weighting of these densities relative to their distance from the stratum germinativum. These properties and derived statistics may be examined as a function of epithelial depth and nuclear type and may be plotted as a function of other diagnostic features in addition to the observed stratum. The system is one part of microTICAS-STRATEX, an expert diagnostic system for the clinical evaluation of stratified tissue sections, now under development as an outgrowth of the microTICAS system. Results of measurements made with this system will be compared with site-specific and diagnosis-specific reference profiles and used in conjunction with clinical data derived from a data base at the University of Chicago of over 1.5 million patients to generate diagnostic and prognostic evaluations.     

The utility of deformable image registration for small artery visualisation in contrast-enhanced whole body MR angiography

PurposeAn investigation was carried out into the effect of three image registration techniques on the diagnostic image quality of contrast-enhanced magnetic resonance angiography (CE-MRA) images.MethodsWhole-body CE-MRA data from the lower legs of 27 patients recruited onto a study of asymptomatic atherosclerosis were processed using three deformable image registration algorithms. The resultant diagnostic image quality was evaluated qualitatively in a clinical evaluation by four expert observers, and quantitatively by measuring contrast-to-noise ratios and volumes of blood vessels, and assessing the techniques' ability to correct for varying degrees of motion.ResultsThe first registration algorithm (‘AIR’) introduced significant stenosis-mimicking artefacts into the blood vessels' appearance, observed both qualitatively (clinical evaluation) and quantitatively (vessel volume measurements). The two other algorithms (‘Slicer’ and ‘SEMI’), based on the normalised mutual information (NMI) concept and designed specifically to deal with variations in signal intensity as found in contrast-enhanced image data, did not suffer from this serious issue but were rather found to significantly improve the diagnostic image quality both qualitatively and quantitatively, and demonstrated a significantly improved ability to deal with the common problem of patient motion.ConclusionsThis work highlights both the significant benefits to be gained through the use of suitable registration algorithms and the deleterious effects of an inappropriate choice of algorithm for contrast-enhanced MRI data. The maximum benefit was found in the lower legs, where the small arterial vessel diameters and propensity for leg movement during image acquisitions posed considerable problems in making accurate diagnoses from the un-registered images.     

Colonic lesion expert system. Evaluation of sensitivity

In a previous study, an expert system using visually assessed diagnostic clues for diagnosing colonic tissue as normal, adenoma or adenocarcinoma arrived at diagnoses agreeing with the evaluation by pathologists ("correct diagnoses") for all 49 cases of normal colon, for 49 of 50 cases of adenoma and for 48 of 49 cases of adenocarcinoma. The present study examined the robustness and sensitivity of the expert system to changes in the knowledge base, to changes in criteria specified by the user and to missing information. Alternative rules for combining certainty factors are discussed.     

Image processing for accurate cell recognition and count on histologic slides

OBJECTIVE: To design an automatic system for recognition and count of two different cell families on histologic slides. STUDY DESIGN: The segmentation strategy uses color information on the image. The morphologic operations and Support Vector Machine approaches are used for each color to obtain precise segmentation of the image into separate cells for recognition. RESULTS: A large set of histologic slides of bone marrow was assessed byour system and the results compared to the score of a human expert. The results are in good agreement. The difference is within acceptable limits (below 10%). CONCLUSION: The automatic system of cell recognition and extraction is accurate and provides a useful tool for cell recognition and count on histologic slides.     

A self-tuning vision system for monitoring biotechnological processes: I. Application to production of pullulan by Aureobasidium pullulans

A prototype of a self-tuning vision system (STVS) has been developed to monitor cell population in fermentations. The STVS combines classical image processing techniques, neural networks and fuzzy logic technologies. By combining these technologies the STVS is able to analyze sampled images of the culture. The proposed system can be "tailored" with minimum effort by an expert who can "teach" the system to recognize cells by showing examples of different morphologies. After adaptation, the STVS is able to capture images, isolate the different cells, classify them according to the expert's criteria, and provide the profile of the cell's population. The system was applied to the classification and analysis of Aureobasidium pullulans. The importance of understanding the changes of population distribution during the fermentation and its effect in the production of pullulan are emphasized. The STVS can be used for monitoring and control of the cell population in small research fermentors or in large-scale production.     

Quantitative microscopy and artificial intelligence: some philosophical reflections

The interdisciplinary field of quantitative microscopy (computer-aided microscopy) and artificial image understanding systems is explored, with an emphasis on the philosophical aspects of pathology and artificial intelligence. Three methodological problems of traditional diagnostic pathology are identified: those of validity, variability and organisation. Quantitative microscopy is a potential research strategy for solving these problems. In practice, however, the quantitative microscopy program is handicapped by the difficulty of building artificial image-understanding systems. We discuss the segmentation problem in image understanding, and four general strategies, three cognitivistic and one connectionistic, are reviewed.     

Expert systems in histopathology. II. Knowledge representation and rule-based systems

Two aspects of expert systems for use in diagnostic histopathology and cytopathology are examined: knowledge representation and the structure and operation of rule-based systems. Knowledge may be represented, e.g., in semantic networks, frames, multiple contexts and model-based structures; the choice of structure should be matched to the type of information to create an efficient and logically adequate expert system. In a rule-based system, knowledge is represented as "rules," often in the form of "IF (condition)-THEN (conclusion)" rules. The anatomy of such rules and their operation is explored via the use of examples. Uncertainty in rules is briefly addressed, and their processing by the symbolic reasoning of the "inference engine" of the expert system is described, including both "forward-chaining" ("data-driven") operations and "backward-chaining" ("goal-driven") operations.     

The use of inference strategies in the differential diagnosis of microcytic anemia

A new expert system developed on a Macintosh personal computer using a commercially available artificial intelligence shell was compared with four different discriminant functions (DFs) for the differentiation of microcytic anemia into etiologic categories. Several databases were used with a different composition but all contained at least some samples from thalassemic individuals and from patients with iron deficiency anemia. The DFs analyzed were those proposed by England and Fraser, Green and colleagues, Mentzer, and by Shine and Lal. None of the databases performed satisfactorily when used singly, whereas very high false-positive rates were obtained by one of them. The diagnostic efficiency was somewhat improved by combining several DFs. An expert system using an artificial intelligence "shell" with an "interference engine" was developed using cluster analysis and a set of learning examples. The input necessary for the system to achieve a conclusion consists of MCV, RBC, and RDW as well as a statement as to whether the patient has anemia. Based upon the values of these parameters, the expert system will give an "advice" regarding the probabilities for thalassemia, iron deficiency, and/or other probabilities such as previous transfusions, anemia of chronic disease, laboratory error, etc. In a prospective trial, the system functioned with an accuracy of better than 85%.     

Color image analysis for quantifying renal tumor angiogenesis

OBJECTIVE: To segment and quantify microvessels in renal tumor angiogenesis based on a color image analysis method and to improve the accuracy and reproducibility of quantifying microvessel density. STUDY DESIGN: The segmentation task was based on a supervised learning scheme. First, 12 color features (RGB, HSI, I1I2I3 and L*a*b*) were extracted from a training set. The feature selection procedure selected I2L*S features as the best color feature vector. Then we segmented microvessels using the discriminant function made using the minimum error rate classification rule of Bayesian decision theory. In the quantification step, after applying a connected component-labeling algorithm, microvessels with discontinuities were connected and touching microvessels separated. We tested the proposed method on 23 images. RESULTS: The results were evaluated by comparing them with manual quantification of the same images. The comparison revealed that our computerized microvessel counting correlated highly with manual counting by an expert (r = 0.95754). The association between the number of microvessels after the initial segmentation and manual quantification was also assessed using Pearson's correlation coefficient (r = 0.71187). The results indicate that our method is better than conventional computerized image analysis methods. CONCLUSION: Our method correlated highly with quantification by an expert and could become a way to improve the accuracy, feasibility and reproducibility of quantifying microvessel density. We anticipate that it will become a useful diagnostic tool for angiogenesis studies.