JNM
HOME HELP FEEDBACK SUBSCRIPTIONS ARCHIVE SEARCH RSS TABLE OF CONTENTS
QUICK SEARCH:   [advanced]


     

This Article
Right arrow Full Text (PDF)
Right arrow Alert me when this article is cited
Right arrow Alert me if a correction is posted
Services
Right arrow Email this article to a friend
Right arrow Similar articles in this journal
Right arrow Similar articles in PubMed
Right arrow Alert me to new issues of the journal
Right arrow Download to citation manager
Right arrow reprints & permissions
Citing Articles
Right arrow Citing Articles via Google Scholar
Google Scholar
Right arrow Articles by Wallis, J. W.
Right arrow Search for Related Content
PubMed
Right arrow PubMed Citation
Right arrow Articles by Wallis, J. W.
Journal of Nuclear Medicine Vol. 42 No. 8 1192-1194
© 2001 by Society of Nuclear Medicine

INVITED COMMENTARY

Use of Artificial Intelligence in Cardiac Imaging

Jerold W. Wallis

Mallinckrodt Institute of Radiology


   INTRODUCTION
TOP
 INTRODUCTION
Expert Systems
 Neural Networks
 The Future
 References
 
There has been a trend over the past few decades toward increasing use of quantitation in cardiac perfusion imaging, initially for planar imaging (1–3) and subsequently for SPECT imaging (4–8). Such quantitation may assist the novice reader, thereby increasing the accuracy of the interpretation. Even in the setting of relatively expert readers, quantitation provides the opinion of a second experienced observer, possibly alerting the reader to defects that may have been overlooked. Artificial intelligence has the potential to further improve the quality of this second computer-observer through the use of expert systems or neural networks.


   Expert Systems
TOP
 INTRODUCTION
 Expert Systems
Neural Networks
 The Future
 References
 
The study presented by Garcia et al. (9) in this issue of The Journal of Nuclear Medicine takes quantitation to this next step, creating an expert system (PERFEX; Syntermed, Atlanta, GA) to analyze the results of the image quantitation and generate an interpretation of the examination. An expert system is a rule-based reasoning program, which uses a series of "if/then" rules in sequence to arrive at a conclusion. For example, one rule might be, "If a mild defect is present in the anterior wall, and the defect is nonreversible, and the patient is female, then it can be concluded with high certainty that the defect is artifactual." Such rule-based systems have been shown to function reasonably well, even when dealing with uncertain data (i.e., possible rather than definite abnormalities). The degree of certainty can be propagated through the reasoning system to arrive at appropriate conclusions. Creation of such a set of rules requires lengthy interviews between the programmer and an expert reader, and subsequent refining of the rule set using sample cases. However, once the set of rules is created, the result is an expert system that is portable and available any time of day, bringing an "expert" to settings where the local expertise may be quite limited.

As noted by Datz et al. (10), care must be taken in validating the portability of computer diagnostic systems to assess the effect of differences in tracers, cameras, and acquisition techniques. Interestingly, the article by Garcia et al. (9) dealt with a mixture of protocols, including thallium stress-redistribution, same-day low-dose/high-dose sestamibi studies, and dual-isotope examinations, with a variety of stress techniques. However, because the inputs to the expert system for each study were the 32-segment quantitative bull’s-eye scores (expressed in SD units), such variation was likely accounted for by use of the appropriate reference database for each type of examination.

Several aspects of the article by Garcia et al. (9) deserve special attention. If the right coronary artery and circumflex artery territories are combined (which resolves certain problems arising from computer vs. human scoring), the sensitivity and specificity values are nearly identical for both the human and the computer readers when compared with an angiography gold standard (Table 1), which is an impressive result.


View this table:
[in this window]
[in a new window]
  		TABLE 1 Sensitivity/Specificity for Data of Garcia et al. (9) When RCA and LCX Are Combined

 
However, a concern with these results is the low specificity of the interpretations (21%–29% for presence of coronary artery disease, when operating at an approximately 85% sensitivity level). Whereas it is well known that referral bias can significantly drop the apparent specificity of a test (11), especially in the setting of an imperfect gold standard, these specificity values are lower than those of comparable quantitative and semiquantitative trials. For example, sensitivity and specificity were, respectively, 97% and 44% (12), 83% and 82% (13), 92% and 85% (14), and 93% and 78% (15) in other studies during which patients underwent both cardiac catheterization and perfusion imaging. It would be useful to assess the performance of the PERFEX expert system in a set of patients with a low probability of disease (sometimes referred to as the normalcy rate) to better measure its diagnostic accuracy. Given the extensive work of the authors in this area and the flexibility of the program with regard to exact imaging protocol, it is likely that they have an appropriate patient database available for this evaluation.

Also worthy of consideration is whether the expert system adds significant value when quantitation is already being used. There is fairly extensive literature on the sensitivity and specificity of the various cardiac perfusion quantitation programs, using simple thresholds for the number of abnormal pixels in each vessel territory (when compared with the appropriate sex-matched database). Using these thresholds is roughly comparable with creating an expert system with only 3–4 rules (e.g., "If the number of abnormal pixels in the right coronary artery territory exceeds the threshold, then the study is abnormal and suggests right coronary artery disease," with similar rules for the other vessels and for the study overall). The expert system used by Garcia et al. (9) used 253 rules, and it would be interesting to assess the added value of the additional rules compared with the (simpler) standard quantitation. It might be possible for Garcia et al. to perform this comparison relatively easily, because no additional human interpretation of the studies would be required and because standard quantitation was already performed as an input to the expert system.


   Neural Networks
TOP
 INTRODUCTION
 Expert Systems
 Neural Networks
The Future
 References
 
Neural networks provide an alternative use of artificial intelligence in interpretation of myocardial perfusion studies. In a neural network, the programmer does not create explicit rules for interpretation but instead gathers a large collection of sample cases for training. To reduce the number of cases required for training and accelerate learning, a processed image may be used as the input for the system in place of the raw slice data or full bull’s-eye images. Authors have used coarser segmented bull’s-eye images (with only 8–16 "pixels"), Fourier derivatives of the bull’s-eye image reduced to 30 values, and segmented blackout maps (from standard quantitation) as inputs to the neural networks (16–22). The output nodes (diagnoses) are connected to the input nodes through a layer of "hidden" nodes to increase the flexibility of the reasoning system. Weighting functions connect the layers of the network; these functions are derived from repeated presentation of case examples ("training") rather than being programmed into the system by an expert reader. Results of applications of these systems toward the diagnosis of coronary artery disease have been encouraging, with recent sensitivity and specificity values comparable with standard quantitation programs (16).

A potential disadvantage of neural networks is that once they are created, their method of function is difficult to describe in a way that can be comprehended by humans, making it impossible for the user to figure out how the program arrived at a given conclusion. Given that their exact function is obscure, great care must be taken in moving neural networks from one site to another, for fear that a trivial difference in procedure or processing technique may significantly alter the resulting interpretation. Despite this, a multicenter trial of a cardiac neural network system yielded good results even when differences in technique were known to be present (16).

Case-based reasoning programs are similar to neural networks in that they use a large set of examples with known diagnoses to arrive at a conclusion. However, they omit the neural network "training" step and instead give a diagnosis by finding the most similar case in their database of known examples. Khorsand et al. (23) report results similar to standard cardiac quantitation using this method.


   The Future
TOP
 INTRODUCTION
 Expert Systems
 Neural Networks
 The Future
References
 
Regardless of its exact nature, a validated computer interpretation assistant is likely to improve the quality of cardiac study interpretation. Lindahl et al. (18) compared physician interpretation of bull’s-eye images with and without such decision support, which in this case was provided by a neural network system. That study showed that intraobserver variability dropped by 10%, with a similar improvement in interobserver variability, and noted a significant improvement in diagnostic accuracy when compared with results of cardiac catheterization.

Although quantitative aids and artificial intelligence systems are valuable in an adjunct capacity, human readers will remain essential, with a superior ability to identify image artifacts and processing errors, compensate for variation in patient body size, and discuss examinations with referring physicians.

Washington University School of Medicine

St. Louis, Missouri


   FOOTNOTES
 
Received Apr. 4, 2001; accepted Apr. 9, 2001.

For correspondence or reprints contact: Jerold W. Wallis, MD, Radiology–Nuclear Medicine, Campus Box 8223, 510 S. Kingshighway, St. Louis, MO 63110-1076.


   References
TOP
 INTRODUCTION
 Expert Systems
 Neural Networks
 The Future
 References
 

  1. Wackers FJ, Fetterman RC, Mattera JA, Clements JP. Quantitative planar thallium-201 stress scintigraphy: a critical evaluation of the method. Semin Nucl Med 1985;15:46–66.[Medline]
  2. Maddahi J, Garcia EV, Berman DS, Waxman A, Swan HJ, Forrester J. Improved noninvasive assessment of coronary artery disease by quantitative analysis of regional stress myocardial distribution and washout of thallium-201. Circulation 1981;64:924–935.[Free Full Text]
  3. Berger BC, Watson DD, Taylor GJ, et al. Quantitative thallium-201 exercise scintigraphy for detection of coronary artery disease. J Nucl Med 1981;22:585–593.[Abstract/Free Full Text]
  4. Van Train KF, Maddahi J, Berman DS, et al. Quantitative analysis of tomographic stress thallium-201 myocardial scintigrams: a multicenter trial. J Nucl Med 1990;31:1168–1179.[Abstract/Free Full Text]
  5. DePasquale EE, Nody AC, DePuey EG, et al. Quantitative rotational thallium-201 tomography for identifying and localizing coronary artery disease. Circulation 1988;77:316–327.[Abstract/Free Full Text]
  6. Garcia EV, Van Train K, Maddahi J, et al. Quantification of rotational thallium-201 myocardial tomography. J Nucl Med 1985;26:17–26.[Abstract/Free Full Text]
  7. Maddahi J, Van Train K, Prigent F, et al. Quantitative single photon emission computed thallium-201 tomography for detection and localization of coronary artery disease: optimization and prospective validation of a new technique. J Am Coll Cardiol 1989;14:1689–1699.[Abstract]
  8. Van Train KF, Garcia EV, Cooke CD, Areeda J. Quantitative analysis of SPECT myocardial perfusion. In: DePue EG, Berman DS, Garcia EV, eds. Cardiac SPECT Imaging New York, NY: Raven Press, Ltd.; 1995:49–74.
  9. Garcia EV, Cooke CD, Folks RD, et al. Diagnostic performance of an expert system for the interpretation of myocardial perfusion SPECT studies. J Nucl Med 2001;42:1185–1191.[Abstract/Free Full Text]
  10. Datz FL, Gabor FV, Christian PE, Gullberg GT, Menzel CE, Morton KA. The use of computer-assisted diagnosis in cardiac perfusion nuclear medicine studies: a review (part 2). J Digit Imaging 1993;6:1–15.[Medline]
  11. Rozanski A, Diamond GA, Berman D, Forrester JS, Morris D, Swan HJ. The declining specificity of exercise radionuclide ventriculography. N Engl J Med 1983;309:518–522.[Abstract]
  12. Van Train KF, Areeda J, Garcia EV, et al. Quantitative same-day rest-stress technetium-99m-sestamibi SPECT: definition and validation of stress normal limits and criteria for abnormality. J Nucl Med 1993;34:1494–1502.[Abstract/Free Full Text]
  13. Sharir T, Germano G, Waechter PB, et al. A new algorithm for the quantitation of myocardial perfusion SPECT. II. Validation and diagnostic yield. J Nucl Med 2000;41:720–727.[Abstract/Free Full Text]
  14. Matzer L, Kiat H, Wang FP, et al. Pharmacologic stress dual-isotope myocardial perfusion single-photon emission computed tomography. Am Heart J 1994;128:1067–1076.[Medline]
  15. Amanullah AM, Kiat H, Friedman JD, Berman DS. Adenosine technetium-99m sestamibi myocardial perfusion SPECT in women: diagnostic efficacy in detection of coronary artery disease. J Am Coll Cardiol 1996;27:803–809.[Abstract]
  16. Lindahl D, Toft J, Hesse B, et al. Scandinavian test of artificial neural network for classification of myocardial perfusion images. Clin Physiol 2000;20:253–261.[Medline]
  17. Lindahl D, Palmer J, Edenbrandt L. Myocardial SPET: artificial neural networks describe extent and severity of perfusion defects. Clin Physiol 1999;19:497–503.[Medline]
  18. Lindahl D, Lanke J, Lundin A, Palmer J, Edenbradt L. Improved classifications of myocardial bull’s-eye scintigrams with computer-based decision support system. J Nucl Med 1999;40:96–101.[Abstract/Free Full Text]
  19. Lindahl D, Palmer J, Ohlsson M, Peterson C, Lundin A, Edenbrandt L. Automated interpretation of myocardial SPECT perfusion images using artificial neural networks. J Nucl Med 1997;38:1870–1875.[Abstract/Free Full Text]
  20. Hamilton D, Riley PJ, Miola UJ, Amro AA. A feed forward neural network for classification of bull’s-eye myocardial perfusion images. Euro J Nucl Med 1995;22:108–115.[Medline]
  21. Lindahl D, Palmer J, Pettersson J, White T, Lundin A, Edenbrandt L. Scintigraphic diagnosis of coronary artery disease: myocardial bull’s-eye images contain the important information. Clin Physiol 1998;18:554–561.[Medline]
  22. Fujita H, Katafuchi T, Uehara T, Nishimura T. Application of artificial neural network to computer-aided diagnosis of coronary artery disease in myocardial SPECT bull’s-eye images. J Nucl Med 1992;33:272–276.[Abstract/Free Full Text]
  23. Khorsand A, Haddad M, Graf S, et al. Automated assessment of dipyridamole Tl-302 myocardial SPECT perfusion scintigraphy by case-based reasoning. J Nucl Med 2001;42:189–193.[Abstract/Free Full Text]




This Article
Right arrow Full Text (PDF)
Right arrow Alert me when this article is cited
Right arrow Alert me if a correction is posted
Services
Right arrow Email this article to a friend
Right arrow Similar articles in this journal
Right arrow Similar articles in PubMed
Right arrow Alert me to new issues of the journal
Right arrow Download to citation manager
Right arrow reprints & permissions
Citing Articles
Right arrow Citing Articles via Google Scholar
Google Scholar
Right arrow Articles by Wallis, J. W.
Right arrow Search for Related Content
PubMed
Right arrow PubMed Citation
Right arrow Articles by Wallis, J. W.

HOME HELP FEEDBACK SUBSCRIPTIONS ARCHIVE SEARCH RSS TABLE OF CONTENTS
JOURNAL OF NUCLEAR MEDICINE TECHNOLOGY THE JOURNAL OF NUCLEAR MEDICINE