Knowledge-Based Medical Image Analysis and Representation for Integrating Content Definition with the Radiological Report

C. A. Kulikowski; L. Gong; R. S. Mezrich

doi:10.1055/s-0038-1634572

Methods of Information in Medicine, Table of Contents

Methods Inf Med 1995; 34(01/02): 96-103
DOI: 10.1055/s-0038-1634572

Original article

Schattauer GmbH

Knowledge-Based Medical Image Analysis and Representation for Integrating Content Definition with the Radiological Report

C. A. Kulikowski

¹Department of Computer Science Rutgers University, New Brunswick, NJ, USA

,

L. Gong

¹Department of Computer Science Rutgers University, New Brunswick, NJ, USA

,

R. S. Mezrich

²Laurie Imaging Center, Robert Wood Johnson School of Medicine – UMDNJ, and Radiology Group of New Brunswick, New Brunswick, NJ, USA

› Author Affiliations

Abstract

Abstract:

Technology breakthroughs in high-speed, high-capacity, and high performance desk-top computers and workstations make the possibility of integrating multimedia medical data to better support clinical decision making, computer-aided education, and research not only attractive, but feasible. To systematically evaluate results from increasingly automated image segmentation it is necessary to correlate them with the expert judgments of radiologists and other clinical specialists interpreting the images. These are contained in increasingly computerized radiological reports and other related clinical records. But to make automated comparison feasible it is necessary to first ensure compatibility of the knowledge content of images with the descriptions contained in these records. Enough common vocabulary, language, and knowledge representation components must be represented on the computer, followed by automated extraction of image-content descriptions from the text, which can then be matched to the results of automated image segmentation. A knowledge-based approach to image segmentation is essential to obtain the structured image descriptions needed for matching against the expert’s descriptions. We have developed a new approach to medical image analysis which helps generate such descriptions: a knowledge-based object-centered hierarchical planning method for automatically composing the image analysis processes. The problem-solving steps of specialists are represented at the knowledge level in terms of goals, tasks, and domain objects and concepts separately from the implementation level for specific representations of different image types, and generic analysis methods. This system can serve as a major functional component in incrementally building and updating a structured and integrated hybrid information system of patient data. This approach has been tested for magnetic resonance image interpretation, and has achieved promising results.

Keywords:

Knowledge-based Imaging - Image Segmentation - Medical Image Databases - Radiological Reports - Integration

Full Text

References

References
1 Ackerman MJ. The visible human project. In: Proceedings of Medicine Meets Virtual Reality Conference II. San Diego, CA: 1994
2 Udupa JK, Herman GT. eds. 3D Imaging in Medicine. Boca Raton FL: CRC Press; 1991
3 Allen L, Frieder O. Exploiting database technology in the medical arena. IEEE Biomed Eng 1992; 11: 42-9.
4 Sawyer G, Mason DC, Hindley N. et al. MuSIP multi-sensor image processing system. Image Vision Comput 1992; 10: 589-609.
5 Pavlidis T. Why progress in machine vision is so slow. Pattern Recognition Letters 1992; 13: 221-5.
6 Robb RA, Hanson DP. A software system for interactive and quantitative visualization of biomedical images. Sci Med 1991; 1 (14) 1.
7 Udupa JK, Hung HM, Odhner D, Goncalves RJ, Samarasekera S. 3DVIEWNIX: a data-, machine-, and application-independent software system for multidimensional data visualization and analysis. SPIE Proceedings 1992; 1653: 185-91.
8 Ligier Y, Funk M, Ratib O. et al. Object oriented design of a portable platform for medical image manipulation. In: MEDINFO 92. Amsterdam: North Holland Publ; 1992: 26-32.
9 Hoffman EA, Gnanaprakasam D, Gupta KB. et al. VIDA: An environment for multidimensional image display and analysis. SPIE Proc Biomed Image Processing and 3-D Microscopy 1992; 1660: 1-18.
10 Jolesz F, Shtem F. The operating room of the future. Investigative Radiology 1992; 27: 326-8.
11 Kokinis R, Gleason PL, Jolesz F. Surgical planning using computer assisted 3-D reconstruction. In: Taylor R, Lavalle S, Burdea G, Mosges R. eds. Computer Integrated Surgery. Cambridge MA: MIT Press; 1995. (in press).
12 Kaltenborn K-F, Rienhoff O. Virtual reality in medicine. Meth Inform Med 1993; 32: 407-17.
13 Canny JF. A computational approach to edge detection. IEEE Trans Pattern Anal Mach Intelli 1986; 8: 679-98.
14 Udupa JK. Computer aspect of 3D imaging in medicine: a tutorial. In: Udupa JK, Herman GT. eds. 3D Imaging in Medicine. Boca Raton FL: CRC Press; 1991: 2-69.
15 Udupa JK, Raya SP. Sphere-based interpolation of multidimensional objects. IEEE Trans Med Imag 1990; 9: 32-79.
16 Goshtasby A, Turner DA, Ackerman LV. Matching of tomographic slices for interpolation. IEEE Trans Med Imag. 1992; 11: 507-16.
17 Pelizzari CA, Tan KK, Levin DN, Chen GT, Bolter J. Interactive 3-D patient-image registration. In: Colchester ACF, Hawkes DJ. eds. Information Processing in Medical Imaging. Berlin: Springer-Verlag; 1991: 132-41.
18 Brown LG. A survey of image registration techniques. ACM Comput Surv 1992; 24: 325-76.
19 Vannier MW, Butterfield RL, Rickman DL. et al. Multispectral magnetic resonance image analysis. CRC Critical Rev Biomed Engin 1987; 15: 117-44.
20 Soltanian-Zadeh H, Winham JP, Peck DJ, Yagle AE. Comparative analysis of several tranformations for enhancement and segmentation of magnetic resonance image scene sequences. IEEE Trans Med Imag 1992; 11: 302-18.
21 Wiederhold G. Mediators in the architecture of future information systems. Computer 1992; 25: 38-47.
22 Friedman C. The UMLS coverage of clinical radiology. In: Clayton PD. ed. Proceedings 16th Annual Symposium on Computer Applications in Medical Care. New York: McGraw Hill; 1991: 199-203.
23 Côté R, Rothwell DJ. eds. Systematized Nomenclature of Medicine (3rd ed). Chicago IL: College of American Pathologists; 1992
24 INDEX for Radiological Diagnoses (4th ed). Reston, VA: American College of Radiology; 1992
25 Rector AL, Nowlan W A, Kay S. Foundations for an electronic medical record. Meth Inform Med 1991; 30: 179-86.
26 Lindberg DAB, Humphreys BL, McCray AT. The unified medical language system. In: van Bemmel JH, McCray AT. eds. Yearbook of Medical Informatics 93. Stuttgart: Schattauer Verlag; 1993: 41-51.
27 Breant CM, Taira RK, Huang HK. Interfacing aspects between the picture archiving communication systems, radiology information systems, and hospital information systems. J Digit Imag 1993; 6: 88-94.
28 Dayhoff RE, Maloney DL. An integrated multidepartmental hospital imaging system: usage of data across specialties. In: Symposium Computer Application in Medical Care. New York: McGraw Hill; 1993: 30-9.
29 Ratib O, Ligier Y, Funk M. et al. Distributed architecture for image archival in a hospitalwide PACS. SPIE Conference Proceedings on PACS Design and Evaluation 1992; 1654.
30 Wiltgen M, Gell G, Graif E. et al. An integrated picture archiving and communication system – radiology information system in a radiological department. J Digit Imag 1993; 6: 16-24.
31 Bell OS, Pattison-Gordon E, Greenes RA. Experiments in concept modeling for radiographic image reports. JAMIA 1994; 1: 249-62.
32 Campbell KE, Das AK, Musen MA. A logical foundation for representation of clinical data. JAMIA 1994; 3: 218-32.
33 Friedman C, Cimino JJ, Johnson SB. A schema for representing medical language applied to clinical radiology. JAMIA 1994; 3: 233-48.
34 Apte C, Damerau F, Weiss S. automated learning of decision rules for text categorization. IBM Tech Report: RC18879. ACM Trans Office Info Sys 1994; 12: 233-51.
35 Baud RH, Rassinoux A-M, Scherrer J-R. Natural language processing and semantical representation of medical texts. Meth Inform Med 1992; 31: 117-25.
36 Bloom FE. Databases of brain information. In: Toga A W. ed. Three-Dimensional Neuroimaging. New York: Raven Press; 1990: 273-306.
37 Swanson LW. Brain Maps: Structure of the Rat Brain. New York: Elsevier; 1992
38 Bloom FE, Yong W. Brain Browser. New York: Academic Press; 1992
39 Brinkley JF, Eno K, Sundsten JW. Knowledge-based client-server approach to structural information retrieval: the digital anatomist browser. Comp Meth Progr Biomed 1993; 40: 131-45.
40 Matsuyama T. Expert systems for image processing: knowledge-based composition of image analysis processes. Comput Vision Graph Imag Process 1989; 48: 22-49.
41 Gong L, Kulikowski CA, Mezrich R. Knowledge-based experimental design for planning biomedical image analysis. In: MEDINFO-92. Amsterdam: North Holland Publ; 1992: 628-34.
42 Gong L. Composition of image analysis processes through object-centered hierarchical planning, Technical Report LCSR-TR-180. (PhD. Thesis). Rutgers University; New Brunswick: 1992
43 Tagare HD, Gindi GR, Duncan JS, Jaffe CC. A geometric indexing scheme for an image library. In: Proceedings of the International Symposium, CAR’91. Berlin: Springer-Verlag; 1991: 513-8.
44 Udupa JK, Odhner D. Shell rendering: fast volume rendering and analysis of fuzzy surfaces. SPIE Proceedings 1992; 1653: 35-43.
45 Brinkley JF, Prothero JS, Prothero JW, Rosse C. A framework for the design of knowledge-based systems in structural biology. In: Proc Symposium on Computer Applications in Medical Care. New York: IEEE Comp Soc Press; 1989. 13 61-5.