On the interplay of machine learning and background knowledge in image interpretation by Bayesian networks

https://doi.org/10.1016/j.artmed.2012.12.004Get rights and content

Abstract

Objectives

To obtain a balanced view on the role and place of expert knowledge and learning methods in building Bayesian networks for medical image interpretation.

Methods and materials

The interpretation of mammograms was selected as the example medical image interpretation problem. Medical image interpretation has its own common standards and procedures. The impact of these on two complementary methods for Bayesian network construction was explored. Firstly, methods for the discretisation of continuous features were investigated, yielding multinomial distributions that were compared to the original Gaussian probabilistic parameters of the network. Secondly, the structure of a manually constructed Bayesian network was tested by structure learning from image data. The image data used for the research came from screening mammographic examinations of 795 patients, of whom 344 were cancerous.

Results

The experimental results show that there is an interesting interplay of machine learning results and background knowledge in medical image interpretation. Networks with discretised data lead to better classification performance (increase in the detected cancers of up to 11.7%), easier interpretation, and a better fit to the data in comparison to the expert-based Bayesian network with Gaussian probabilistic parameters. Gaussian probability distributions are often used in medical image interpretation because of the continuous nature of many of the image features. The structures learnt supported many of the expert-originated relationships but also revealed some novel relationships between the mammographic features. Using discretised features and performing structure learning on the mammographic data has further improved the cancer detection performance of up to 17% compared to the manually constructed Bayesian network model.

Conclusion

Finding the right balance between expert knowledge and data-derived knowledge, both at the level of network structure and parameters, is key to using Bayesian networks for medical image interpretation. A balanced approach to building Bayesian networks for image interpretation yields more accurate and understandable Bayesian network models.

Introduction

Bayesian networks have become the state-of-the-art for the representation of and reasoning with uncertain knowledge of a clinical problem. They have a sound statistical basis, yet allow exploiting available background knowledge in a way superior to many other formalisms for statistical machine learning. Even when no data at all are available, it is often still possible to develop a Bayesian network, guided by a mixture of expert knowledge and information from literature. If data are available, one can also learn the network structure and parameters from data. As this holds for any medical domain, it also holds for medical imaging. However, medical imaging has its own characteristics: methods are applied, ranging from image segmentation via region detection to lesion determination, as part of the image processing pipeline. At the very end of this pipeline we find image interpretation; methods for image interpretation are, thus, clearly dependent on the previous processing steps. Some of the characteristics of the image processing steps, such as that image features are continuous, have particular implications for image interpretation that has a foundation in medical knowledge of the structure—histology and anatomy—and function—physiology. As in the end, medical images need to tell something about the patient, medical knowledge offers a natural start for computer-aided detection. However, exploiting explicit representations of medical knowledge into medical image interpretation has so far met with significant challenges.

These challenges bring us back to the relationship between manual construction and learning from data of Bayesian network, a topic discussed repeatedly in the past, without giving rise to scientific consensus. New in this paper is that we address this issue from the point of view of image interpretation. We critically exam the assumptions made in the expert-knowledge-guided development of a Bayesian network for medical image interpretation by the use of image data. Both the assumptions made in choosing the probabilistic parameters and in designing the graphical structure are studied.

The research was carried out in a concrete clinical setting: the interpretation of breast-cancer screening mammograms. Breast-cancer detection is a hard medical image interpretation task. With the digitisation of medical images in the last decade, there has been considerable progress in computer-aided interpretation of mammograms where most of the improvement have come from the development of new pattern-recognition techniques to better detect potentially suspicious breast regions. However, existing systems still exhibit limitations in attaining the required clinical accuracy, i.e. with respect to presence or absence of cancer in the patient. The major reason for this is their failure to explicitly represent the working principles and knowledge of human experts; expert radiologists normally compare image parts and different images of the breasts to each other, i.e. they interpret potentially suspicious regions of the breasts in the context of all other available image information. It is only recently that researchers have started to study ways to incorporate such principles into computer-aided detection (CAD) systems [1], [2].

As part of the research we constructed a Bayesian network that incorporated the most important image features and their relationships as used by radiologists to interpret mammograms. Thus, the resulting Bayesian network can be looked upon as a knowledge representation of mammogram interpretation in terms of breast tissue architecture and signs of abnormality. As image features are continuous variables, we used Gaussian distribution to model their uncertainty.

In a well-cited paper by Pradhan et al., published in 1996, it was experimentally established that the network structure is the single most important factor determining the Bayesian network's performance [3]. In time, this insight has become general wisdom underlying much of Bayesian network modelling. The results of this paper were in particular compelling as they were based on an extensive study of a variety of large, real-world networks. In our paper, we challenge the conclusions from the paper by Pradhan et al. and aim at offering a more balanced view on this important problem. It is also the right time to reexamine this problem, as considerable progress has been made in Bayesian network technology since 1996. Other recent research [4] also suggests that the problem of the sensitivity of Bayesian networks to imprecision in their parameters is domain-dependent and requires more careful investigation.

We emphasise that the problem of medical image interpretation we tackle in this paper is particularly challenging as the input to the network is based on image features automatically extracted by a CAD system through image processing, which in itself is a complex task and ongoing research. Even though the continuous nature of the features obtained in this way is understandable from a physical point of view, their relationships to the clinical abnormalities detected in the image are not straightforward from the radiologist's point of view. In contrast, the features provided by radiologists after visual inspection and interpretation are discrete; they have a specific semantics, although prone to subjective variation [5], [6]. Furthermore, the manual network contained two features obtained from the CAD system's output, that are assumed to have direct causal relationships with the variable that indicates whether or not an abnormality is present. Again, the inclusion of such variables is novel in comparison to available benchmark datasets for breast cancer and their relationships have not been studied before.

Hence, the novelty of our research lies in the thorough investigation of both the quantitative part (probability distribution) and the qualitative part (structure) of the manual network to obtain insight into the appropriateness of the assumptions made in developing a Bayesian network for a highly complex task: medical image interpretation. The selected task of mammogram interpretation is sufficiently similar to other complex medical image interpretation tasks to act as an example problem for the research. As breast cancer is a major disorder that is associated with enormous research efforts, techniques for the automated detection of breast cancer reflect the state of the arts of the field of CAD.

In this study in particular, we build upon our results from the work presented in [7], where we discretised the continuous mammographic features automatically extracted from the CAD system to check whether the probabilistic parameters in the initial expert network were optimal and correctly reflecting reality. It was shown that the parameters play an essential role in the network's performance. Therefore, after preliminary investigations [8], in the current study we provide an extensive and thorough investigation of learning Bayesian network structures, both restricted and unrestricted, from the discretised image data to gain detailed insight into the feature dependencies and independencies assumed in the manual model. The performance of the learned networks is compared with that of the manual network in terms of classification accuracy and knowledge representation.

The structure of the paper is as follows. We start with a review of the theory of Bayesian networks and related work in the areas of discretisation and structure learning in Section 2. Next, in Section 3, some background is provided on mammogram interpretation, the Bayesian network for mammogram interpretation that was developed by hand is presented, and we describe the data used for the experimental part in the research. Our previous work that examines the assumptions about the probabilistic parameters of the Bayesian network is shortly summarised in Section 4. This is done to provide the reader with a good understanding of the choices made about the discretisation of the data used for the research study on structure learning presented in Section 5. Finally, in Section 6 we return to the questions from which the research started and summarise what has been achieved.

Section snippets

Bayesian networks

A Bayesian network (BN) is defined as a pair B=(G,P), where G is a directed acyclic graph (DAG) G = (V, E) and P is a joint probability distribution of the random variables XV [9], [10], [11]. There exists a 1-1 correspondence between the nodes vV and the random variables XvXV; the (directed) edges, or arcs, E  (V × V) correspond to direct causal relationships between the variables: a node is a parent of a child, if there is an arc from the former to the latter. We say that G is an I-map of P if

Mammography, the Bayesian network model and data

We start by reviewing the problem domain of screening mammography and describe in detail the Bayesian network that was constructed for the purpose of mammogram interpretation.

Reappraisal of the probabilistic parameters

As most of the variables modelled by the manual Bayesian network were continuous features, they were represented using conditional Gaussian distributions. A limitation of Gaussian distributions is that they are symmetric, which will not allow capturing asymmetries available in the data. Rather than using other continuous probability distributions, that would allow representing asymmetries, however again with particular assumptions, discretisation of the continuous data offers a way to fit the

Network structure reappraisal by learning

In this section we investigate the structures learnt from various algorithms and compare them with the continuous baseline network. For this purpose, we used the discretised data obtained from the best performing FI method as reported in the previous section.

Discussion and conclusions

Our aim was to obtain insight into the validity of the modelling assumptions made when developing a BN for complex medical image interpretation problems based on expert knowledge, with the interpretation of mammograms as a real-world example. Where in other problem domains it might be easier to construct such manual models using knowledge engineering methods, in the domain of image interpretation it is not unlikely that modelling mistakes are made. We carried out this study to find out whether

Acknowledgements

We would like to thank Saskia Robben and Niels Radstake for conducting the initial experiments and providing the preliminary results on discretisation and structure learning. We also thank the reviewers for their useful comments that help improve this paper. This work has been funded by the Netherlands Organization for Scientific Research under BRICKS/FOCUS Grant Number 642.066.605.

References (47)

  • M.J. Druzdzel et al.

    Are Bayesian networks sensitive to precision of their parameters?

  • E.A. Fischer et al.

    Bayesian networks of BI-RADS descriptors for breast lesion classification

  • E.S. Burnside et al.

    Bayesian network to predict breast cancer risk of mammographic microcalcifications and reduce number of benign biopsy results

    Journal of Radiology

    (2006)
  • S. Robben et al.

    Discretisation does affect the performance of Bayesian networks.

  • N. Radstake et al.

    Critiquing knowledge representation in medical image interpretation using structure learning

    Lecture Notes in Artificial Intelligence

    (2011)
  • R.G. Cowell et al.

    Probabilistic networks and expert systems

    (1999)
  • F.V. Jensen et al.

    Bayesian networks and decision graphs

    (2007)
  • D. Koller et al.

    Probabilistic graphical models: principles and techniques.

    (2009)
  • U. Fayyad et al.

    Multi-interval discretization of continuous-valued attributes for classification learning

  • P. Geurts et al.

    Investigation and reduction of discretization variance in decision tree induction

    Lecture Notes in Computer Science

    (2000)
  • J.L. Flores et al.

    Wrapper discretization by means of estimation of distribution algorithms

    Intelligent Data Analysis

    (2007)
  • M. Mizianty et al.

    Comparative analysis of the impact of discretization on the classification with naïve Bayes and semi-naïve Bayes classifiers

  • R. Abraham et al.

    A comparative analysis of discretization methods for medical datamining with naïve Bayesian classifier

  • Cited by (0)

    View full text