Anatomic segmentation improves prostate cancer detection with artificial neural networks analysis of 1H magnetic resonance spectroscopic imaging Journal Article


Authors: Matulewicz, L.; Jansen, J. F. A.; Bokacheva, L.; Vargas, H. A.; Akin, O.; Fine, S. W.; Shukla-Dave, A.; Eastham, J. A.; Hricak, H.; Koutcher, J. A.; Zakian, K. L.
Article Title: Anatomic segmentation improves prostate cancer detection with artificial neural networks analysis of 1H magnetic resonance spectroscopic imaging
Abstract: Purpose: To assess whether an artificial neural network (ANN) model is a useful tool for automatic detection of cancerous voxels in the prostate from 1H-MRSI datasets and whether the addition of information about anatomical segmentation improves the detection of cancer. Materials and Methods: The Institutional Review Board approved this HIPAA-compliant study and waived informed consent. Eighteen men with prostate cancer (median age, 55 years; range, 36-71 years) who underwent endorectal MRI/MRSI before radical prostatectomy were included in this study. These patients had at least one cancer area on whole-mount histopathological map and at least one matching MRSI voxel suspicious for cancer detected. Two ANN models for automatic classification of MRSI voxels in the prostate were implemented and compared: model 1, which used only spectra as input, and model 2, which used the spectra plus information from anatomical segmentation. The models were trained, tested and validated using spectra from voxels that the spectroscopist had designated as cancer and that were verified on histopathological maps. Results: At ROC analysis, model 2 (AUC = 0.968) provided significantly better (P = 0.03) classification of cancerous voxels than did model 1 (AUC = 0.949). Conclusion: Automatic analysis of prostate MRSI to detect cancer using ANN model is feasible. Application of anatomical segmentation from MRI as an additional input to ANN improves the accuracy of detecting cancerous voxels from MRSI.
Keywords: adult; clinical article; human tissue; aged; cancer surgery; histopathology; cancer patient; cancer diagnosis; retrospective study; prostate cancer; feasibility study; prostatectomy; magnetic resonance spectroscopic imaging; proton nuclear magnetic resonance; artificial neural network; nuclear magnetic resonance scanner; pattern recognition; computer-aided diagnosis; autoanalysis; neural networks; human; male; article
Journal Title: Journal of Magnetic Resonance Imaging
Volume: 40
Issue: 6
ISSN: 1053-1807
Publisher: Wiley Blackwell  
Date Published: 2014-12-01
Start Page: 1414
End Page: 1421
Language: English
DOI: 10.1002/jmri.24487
PROVIDER: scopus
PUBMED: 24243554
PMCID: PMC4306557
DOI/URL:
Notes: Export Date: 1 December 2014 -- Source: Scopus
Altmetric Score
MSK Authors
  1. Hedvig Hricak
    330 Hricak
  2. James Eastham
    426 Eastham
  3. Amita Dave
    80 Dave
  4. Kristen L Zakian
    74 Zakian
  5. Jason A Koutcher
    234 Koutcher
  6. Samson W Fine
    316 Fine
  7. Oguz Akin
    177 Akin