Computer-aided diagnosis system outperforms scoring analysis in myocardial perfusion imaging

Lena Johansson, Lars Edenbrandt, Kenichi Nakajima, Milan Lomsky, Sven-Eric Svensson, Elin Trägårdh

Research output: Contribution to journalArticlepeer-review

11 Citations (SciVal)


The aim of this myocardial perfusion imaging (MPI) study was to compare the diagnostic performance of two computer-aided diagnosis (CAD) systems, EXINI Heart(TM) (EXINI), and PERFEXTM (PERFEX) Emory Cardiac Toolbox (ECT), and the summed stress score (SSS) values from both software packages. We studied 1,052 consecutive patients who underwent 2-day stress/rest Tc-99m-sestamibi MPI studies. The reference standard classifications for the MPI studies were obtained from three experienced physicians who separately classified all cases regarding the presence or absence of ischemia and/or infarction. Automatic processing was carried out using EXINI and PERFEX to obtain CAD results and SSS values based on the 17-segment model. The three experts' classifications showed ischemia in 257 patients and abnormal studies, i.e., either ischemia or infarction or both, in 318 patients. Accuracy was significantly higher in EXINI than in PERFEX, regarding both the detection of ischemia (87.4 vs 77.6%; P < 0.0001) and the detection of abnormal studies (91.6 vs 67.9%; P < 0.0001). EXINI's CAD system showed a higher specificity than its SSS values (86.8 vs 73.6%; P < 0.0001) at the same level of sensitivity. EXINI demonstrated greater diagnostic accuracy for detection of ischemia and abnormal studies than did PERFEX. EXINI CAD also outperformed its SSS analysis.
Original languageEnglish
Pages (from-to)416-423
JournalJournal of Nuclear Cardiology
Issue number3
Publication statusPublished - 2014

Subject classification (UKÄ)

  • Radiology, Nuclear Medicine and Medical Imaging


  • Ischemic heart disease
  • myocardial perfusion imaging
  • automatic
  • quantification
  • software


Dive into the research topics of 'Computer-aided diagnosis system outperforms scoring analysis in myocardial perfusion imaging'. Together they form a unique fingerprint.

Cite this