Prostate Cancer Localization with Endorectal MR Imaging and MR Spectroscopic Imaging: Effect of Clinical Data on Reader Accuracy

Rajpal Dhingsa, Aliya Qayyum, Fergus V. Coakley, Ying Lu, Kirk D. Jones, Mark G. Swanson, Peter R. Carroll, Hedvig Hricak, John Kurhanewicz

Research output: Contribution to journalArticle

80 Scopus citations

Abstract

PURPOSE: To determine the effect of digital rectal examination findings, sextant biopsy results, and prostate-specific antigen (PSA) levels on reader accuracy in the localization of prostate cancer with endorectal magnetic resonance (MR) imaging and MR spectroscopic imaging. MATERIALS AND METHODS: This was a retrospective study of 37 patients (mean age, 57 years) with biopsy-proved prostate cancer. Transverse T1-weighted, transverse high-spatial-resolution, and coronal T2-weighted MR images and MR spectroscopic images were obtained. Two independent readers, unaware of clinical data, recorded the size and location of suspicious peripheral zone tumor nodules on a standardized diagram of the prostate. Readers also recorded their degree of diagnostic confidence for each nodule on a five-point scale. Both readers repeated this interpretation with knowledge of rectal examination findings, sextant biopsy results, and PSA level. Step-section histopathologic findings were the reference standard. Logistic regression analysis with generalized estimating equations was used to correlate tumor detection with clinical data, and alternative free-response receiver operating characteristic (AFROC) curve analysis was used to examine the overall effect of clinical data on all positive results. RESULTS: Fifty-one peripheral zone tumor nodules were identified at histopathologic evaluation. Logistic regression analysis showed awareness of clinical data significantly improved tumor detection rate (P < .02) from 15 to 19 nodules for reader 1 and from 13 to 19 nodules for reader 2 (27%-37% overall) by using both size and location criteria. AFROC analysis showed no significant change in overall reader performance because there was an associated increase in the number of false-positive findings with awareness of clinical data, from 11 to 21 for reader 1 and from 16 to 25 for reader 2. CONCLUSION: Awareness of clinical data significantly improves reader detection of prostate cancer nodules with endorectal MR imaging and MR spectroscopic imaging, but there is no overall change in reader accuracy, because of an associated increase in false-positive findings. A stricter definition of a true-positive result is associated with reduced sensitivity for prostate cancer nodule detection.

Original languageEnglish (US)
Pages (from-to)215-220
Number of pages6
JournalRADIOLOGY
Volume230
Issue number1
DOIs
StatePublished - Jan 1 2004

Keywords

  • Diagnostic radiology, observer performance
  • Magnetic resonance (MR), spectroscopy
  • Prostate neoplasms
  • Prostate neoplasms, MR

ASJC Scopus subject areas

  • Radiology Nuclear Medicine and imaging

Fingerprint Dive into the research topics of 'Prostate Cancer Localization with Endorectal MR Imaging and MR Spectroscopic Imaging: Effect of Clinical Data on Reader Accuracy'. Together they form a unique fingerprint.

  • Cite this

    Dhingsa, R., Qayyum, A., Coakley, F. V., Lu, Y., Jones, K. D., Swanson, M. G., Carroll, P. R., Hricak, H., & Kurhanewicz, J. (2004). Prostate Cancer Localization with Endorectal MR Imaging and MR Spectroscopic Imaging: Effect of Clinical Data on Reader Accuracy. RADIOLOGY, 230(1), 215-220. https://doi.org/10.1148/radiol.2301021562