Elsevier

Medical Image Analysis

Volume 3, Issue 4, December 1999, Pages 321-337
Medical Image Analysis

The development and evaluation of CADMIUM: a prototype system to assist in the interpretation of mammograms

https://doi.org/10.1016/S1361-8415(99)80027-9Get rights and content

Abstract

We have developed CADMIUM, a novel approach for the design of systems to assist in the interpretation of medical images. CADMIUM uses symbolic reasoning to relate information obtained from image processing to the decisions radiologists take. The approach is based on a symbolic decision procedure which has already been used successfully in a variety of non-imaging clinical decision systems. In CADMIUM this decision procedure is extended with models of three generic image interpretation tasks: detection, measurement and classification of image features. The extended procedure is used to construct the lines of reasoning needed in each task and to control the acquisition of information by image processing. CADMIUM has been evaluated as an aid to the differential diagnosis of microcalcifications on mammographic images. Radiographers who had been trained to interpret images performed better when using the advice provided by the system.

References (48)

  • D. Betal et al.

    Segmentation and numerical analysis of microcalcifications on mammograms using mathematical morphology

    Brit. J. Radiol.

    (1997)
  • D.S. Brettle et al.

    Automatic microcalcifications localisation using matched Fourier filtering

  • E. Cernadas et al.

    Detection of mammographic microcalcifications using a statistical model

  • H.-P. Chan et al.

    Computer-aided detection of microcalcifications in mammograms: methodology and preliminary clinical study

    Invest. Radiol.

    (1988)
  • H.-P. Chan et al.

    Computer-aided detection of mammographic microcalcifications: pattern recognition with an artificial neural network

    Med. Phys.

    (1995)
  • Y. Chitre et al.

    Classification of mammographic microcalcifications using image structure and cluster features

  • H.M. Cook et al.

    Application of expert systems to mammographic image analysis

    Am. J. Physiol. Imag.

    (1989)
  • D.H. Davies et al.

    Automatic detection of microcalcifications in digital mammograms

    Brit. J. Radiol.

    (1989)
  • C.J. D'Orsi et al.

    Reading and decision aids for improved accuracy and standardization of mammographic diagnosis

    Radiology

    (1992)
  • G.A. Dunn et al.

    Alignment of fibroblasts on grooved surfaces described by a simple geometric transform

    J. Cell Sci.

    (1986)
  • J. Fox et al.

    A unified framework for hypothetical and practical reasoning (2): lessons from medical applications

    Proc. 1st Int. Conf. on Formal and Applied Practical Reasoning

    (1996)
  • J. Fox et al.

    Decision support and disease management a logic engineering approach

    IEEE Trans. Inform. Technol. Biomed.

    (1998)
  • M. Le Gal et al.

    Conduite a tenir devant une mammographie revelatrice de microcalcifications groupees sans tumeur palpable

    Nouv. Presse Med.

    (1973)
  • R.C. Gonzalez et al.
    (1992)
  • Cited by (29)

    • Cognitive systems at the point of care: The CREDO program

      2017, Journal of Biomedical Informatics
      Citation Excerpt :

      The earliest trialed PROforma applications were decision support systems for general practitioners in making routine medication decisions [21,46], genetic risk assessments [10,7] and when deciding whether patients require urgent referral to cancer specialists (see Appendix, Fig. A1). Trials in specialist care included radiological image interpretation [44]; treatment of leukemia in children [4] and diagnosis and treatment of breast cancer [36,37], Thyroid disease [40] and colon cancer [33]. All trials to date have shown improvements in clinical decision making, and in some cases major improvements over unaided human judgment.

    • OpenClinical.net: A platform for creating and sharing knowledge and promoting best practice in healthcare

      2015, Computers in Industry
      Citation Excerpt :

      Early PROforma applications were developed for prescribing medications, genetic risk assessments and decisions about whether patients required urgent referral to cancer specialists, and were very promising [17–19]. Later applications focused on specialist care, particularly cancer care, including radiological image interpretation; treatment of leukaemia in children and diagnosis and treatment of breast cancer [20–23]. All these applications have demonstrated significant improvements in quality of decision-making, and in some cases dramatic improvements over unaided human judgment.

    • A kernel-based approach to categorizing laryngeal images

      2007, Computerized Medical Imaging and Graphics
      Citation Excerpt :

      In such a situation, a decision support system for automated analysis and interpretation of medical data is of great value. Recent developments in this area have shown that physicians benefit from the advise of decision support systems in terms of increased reliability of the analysis, decreased intra- and inter-observer variability [1–4]. This paper, is concerned with an approach to automated analysis of vocal fold – laryngeal – images aiming to categorize diseases of vocal folds.

    • Towards a computer-aided diagnosis system for vocal cord diseases

      2006, Artificial Intelligence in Medicine
      Citation Excerpt :

      In such a situation, a decision support system for an automated analysis and interpretation of medical data is of great value. Recent developments in this area have shown that physicians benefit from the advise of decision support systems in terms of increased reliability of the analysis, decreased intra- and inter-observer variability [1–4]. In this paper, we propose an approach to an automated analysis of vocal cord images aiming to categorize diseases of vocal cords.

    View all citing articles on Scopus
    View full text