Expert system support using a Bayesian belief network for the classification of endometrial hyperplasia

Application of Bayesian network modeling to pathology informatics

BACKGROUND

In the era of extensive data collection, there is a growing need for a large scale data analysis with tools that can handle many variables in one modeling framework. In this article, we present our recent applications of Bayesian network modeling to pathology informatics.

METHODS

Bayesian networks (BNs) are probabilistic graphical models that represent domain knowledge and allow investigators to process this knowledge following sound rules of probability theory. BNs can be built based on expert opinion as well as learned from accumulating data sets. BN modeling is now recognized as a suitable approach for knowledge representation and reasoning under uncertainty. Over the last two decades BN have been successfully applied to many studies on medical prognosis and diagnosis.

RESULTS

Based on data and expert knowledge, we have constructed several BN models to assess patient risk for subsequent specific histopathologic diagnoses and their related prognosis in gynecological cytopathology and breast pathology. These models include the Pittsburgh Cervical Cancer Screening Model assessing risk for histopathologic diagnoses of cervical precancer and cervical cancer, modeling of the significance of benign-appearing endometrial cells in Pap tests, diagnostic modeling to determine whether adenocarcinoma in tissue specimens is of endometrial or endocervical origin, and models to assess risk for recurrence of invasive breast carcinoma and ductal carcinoma in situ.

CONCLUSIONS

Bayesian network models can be used as powerful and flexible risk assessment tools on large clinical datasets and can quantitatively identify variables that are of greatest significance in predicting specific histopathologic diagnoses and their related prognosis. Resulting BN models are able to provide individualized quantitative risk assessments and prognostication for specific abnormal findings commonly reported in gynecological cytopathology and breast pathology.

Virtual microscopy and digital pathology in training and education

Traditionally, education and training in pathology has been delivered using textbooks, glass slides and conventional microscopy. Over the last two decades, the number of web-based pathology resources has expanded dramatically with centralized pathological resources being delivered to many students simultaneously. Recently, whole slide imaging technology allows glass slides to be scanned and viewed on a computer screen via dedicated software. This technology is referred to as virtual microscopy and has created enormous opportunities in pathological training and education. Students are able to learn key histopathological skills, e.g. to identify areas of diagnostic relevance from an entire slide, via a web-based computer environment. Students no longer need to be in the same room as the slides. New human-computer interfaces are also being developed using more natural touch technology to enhance the manipulation of digitized slides. Several major initiatives are also underway introducing online competency and diagnostic decision analysis using virtual microscopy and have important future roles in accreditation and recertification. Finally, researchers are investigating how pathological decision-making is achieved using virtual microscopy and modern eye-tracking devices. Virtual microscopy and digital pathology will continue to improve how pathology training and education is delivered.

Decision support systems for morphology-based diagnosis and prognosis of prostate neoplasms: a methodological approach

Recent advances in computer and information technologies have allowed the integration of both numeric and non-numeric data, that is, descriptive, linguistic terms. This has led at 1 end of the spectrum of technology development to machine vision based on image understanding and, at the other, to decision support systems. This has had a significant impact on our capability to derive diagnostic and prognostic information from histopathological material with prostate neoplasms. Cancer 2009;115(13 suppl):3068-77. (c) 2009 American Cancer Society.

Do we see what we think we see? The complexities of morphological assessment

Reliable pathological interpretation is vital to so many aspects of tissue-based research as well as being central to patient care. Understanding the complex processes involved in decision-making is the starting point to improve both diagnostic reproducibility and the definition of diagnostic groups that underpin our experiments. Unfortunately, there is a paucity of research in this field and it is encouraging to see The Journal of Pathology publishing work in this area. This review attempts to highlight the opportunities that exist in this field and the technologies that are now available to support this type of research. Key amongst these are the use of decision analysis tools such as inference networks, and virtual microscopy that allows us to simulate diagnostic decision-making. These tools have roles, not only in studying the subtleties of diagnostic decision-making, but also in delivering new methods of training and proficiency testing. Research which helps us to better understand what we see, why we see it, and standardizing interpretative reasoning in pathological classification is essential for improving the wide range of activities that pathologists support, including clinical diagnosis, teaching, training, and experimental research.

A Bayesian derived network of breast pathology co-occurrence

In this paper, we present the validation and verification of a machine-learning based Bayesian network of breast pathology co-occurrence. The present/not present occurrences of 29 common breast pathologies from 1631 pathology reports were used to build the network. All pathology reports were developed by a single pathologist. The resulting network has 25 diagnosis nodes interconnected by 40 arcs. Each arc represents a predicted co-occurrence or null co-occurrence. Model verification involved assessing the robustness of the original network structure after random exclusion of 25%, 50%, and 75% of the pathology report dataset. The structure of the network appears stable as random removal of 75% of the records in the original dataset leaves 81% of the original network intact. Model validation was primarily assessed by review of the breast pathology literature for each arc in the network. Almost all network identified co-occurrences (95%) have been published in the breast pathology literature or were verified by expert opinion. In conclusion, the Bayesian network of breast pathology co-occurrence presented here is both robust with respect to incomplete data and validated by consistency with the breast pathology literature and by expert opinion. Further, the ability to utilize a specific pathology observation to predict multiple co-current pathologies enables exploration of pathology co-occurrence patterns in an intuitive manner that may have broader application in both the breast pathologist clinical community and the breast cancer research community.

Computer-aided diagnosis with potential application to rapid detection of disease outbreaks

Our objectives are to quickly interpret symptoms of emergency patients to identify likely syndromes and to improve population-wide disease outbreak detection. We constructed a database of 248 syndromes, each syndrome having an estimated probability of producing any of 85 symptoms, with some two-way, three-way, and five-way probabilities reflecting correlations among symptoms. Using these multi-way probabilities in conjunction with an iterative proportional fitting algorithm allows estimation of full conditional probabilities. Combining these conditional probabilities with misdiagnosis error rates and incidence rates via Bayes theorem, the probability of each syndrome is estimated. We tested a prototype of computer-aided differential diagnosis (CADDY) on simulated data and on more than 100 real cases, including West Nile Virus, Q fever, SARS, anthrax, plague, tularaemia and toxic shock cases. We conclude that: (1) it is important to determine whether the unrecorded positive status of a symptom means that the status is negative or that the status is unknown; (2) inclusion of misdiagnosis error rates produces more realistic results; (3) the naive Bayes classifier, which assumes all symptoms behave independently, is slightly outperformed by CADDY, which includes available multi-symptom information on correlations; as more information regarding symptom correlations becomes available, the advantage of CADDY over the naive Bayes classifier should increase; (4) overlooking low-probability, high-consequence events is less likely if the standard output summary is augmented with a list of rare syndromes that are consistent with observed symptoms, and (5) accumulating patient-level probabilities across a larger population can aid in biosurveillance for disease outbreaks.

Grid technology in tissue-based diagnosis: fundamentals and potential developments

Tissue-based diagnosis still remains the most reliable and specific diagnostic medical procedure. It is involved in all technological developments in medicine and biology and incorporates tools of quite different applications. These range from molecular genetics to image acquisition and recognition algorithms (for image analysis), or from tissue culture to electronic communication services. Grid technology seems to possess all features to efficiently target specific constellations of an individual patient in order to obtain a detailed and accurate diagnosis in providing all relevant information and references. Grid technology can be briefly explained by so-called nodes that are linked together and share certain communication rules in using open standards. The number of nodes can vary as well as their functionality, depending on the needs of a specific user at a given point in time. In the beginning of grid technology, the nodes were used as supercomputers in combining and enhancing the computation power. At present, at least five different Grid functions can be distinguished, that comprise 1) computation services, 2) data services, 3) application services, 4) information services, and 5) knowledge services. The general structures and functions of a Grid are described, and their potential implementation into virtual tissue-based diagnosis is analyzed. As a result Grid technology offers a new dimension to access distributed information and knowledge and to improving the quality in tissue-based diagnosis and therefore improving the medical quality.

A multi-layered application for the gross description using Semantic Web technology

OBJECTIVE

Development of a Semantic Web technology based system for the formalization of the gross description.

METHOD

A system is developed using the Java-2 platform. It is based on a light-weight version of the Galen top level ontology. Web technologies like XML, SAX en DOM have been used.

RESULT

Three system components have been developed to support the semantic, the object and the syntax layers of the PathOnt architecture.

CONCLUSION

The PathOnt approach provides a tool for the communication among clinicians and technicians involved in pathology examinations. This tool also provides a foundation for linking the specimen-specific data with the controlled medical ontology so that the stored information can be used in different circumstances.

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.

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.