@article{RN169,
   author = {Matulewicz, L. and Jansen, J. F. and Bokacheva, L. and Vargas, H. A. and Akin, O. and Fine, S. W. and Shukla-Dave, A. and Eastham, J. A. and Hricak, H. and Koutcher, J. A. and Zakian, K. L.},
   title = {Anatomic segmentation improves prostate cancer detection with artificial neural networks analysis of 1H magnetic resonance spectroscopic imaging},
   journal = {J Magn Reson Imaging},
   volume = {40},
   number = {6},
   pages = {1414-21},
   note = {Matulewicz, Lukasz
Jansen, Jacobus F A
Bokacheva, Louisa
Vargas, Hebert Alberto
Akin, Oguz
Fine, Samson W
Shukla-Dave, Amita
Eastham, James A
Hricak, Hedvig
Koutcher, Jason A
Zakian, Kristen L
eng
R01 CA076423/CA/NCI NIH HHS/
R01 CA76423/CA/NCI NIH HHS/
Evaluation Study
Research Support, N.I.H., Extramural
2013/11/19 06:00
J Magn Reson Imaging. 2014 Dec;40(6):1414-21. doi: 10.1002/jmri.24487. Epub 2013 Nov 15.},
   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 (1)H-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
Aged
Algorithms
Biomarkers, Tumor/*analysis
Humans
Image Enhancement/methods
Magnetic Resonance Imaging/*methods
Male
Middle Aged
*Neural Networks, Computer
Pattern Recognition, Automated/*methods
Prostatic Neoplasms/*chemistry/*diagnosis
Proton Magnetic Resonance Spectroscopy/*methods
Reproducibility of Results
Sensitivity and Specificity
computer-aided diagnosis
magnetic resonance spectroscopic imaging
neural networks
pattern recognition
prostate cancer},
   ISSN = {1522-2586 (Electronic)
1053-1807 (Linking)},
   DOI = {10.1002/jmri.24487},
   url = {http://www.ncbi.nlm.nih.gov/pubmed/24243554
https://www.ncbi.nlm.nih.gov/pmc/articles/PMC4306557/pdf/nihms532784.pdf},
   year = {2014},
   type = {Journal Article}
}

{"_id":"RQCoQnWodjAhmT6Jv","bibbaseid":"matulewicz-jansen-bokacheva-vargas-akin-fine-shukladave-eastham-etal-anatomicsegmentationimprovesprostatecancerdetectionwithartificialneuralnetworksanalysisof1hmagneticresonancespectroscopicimaging-2014","downloads":0,"creationDate":"2017-09-02T18:10:13.493Z","title":"Anatomic segmentation improves prostate cancer detection with artificial neural networks analysis of 1H magnetic resonance spectroscopic imaging","author_short":["Matulewicz, L.","Jansen, J. F.","Bokacheva, L.","Vargas, H. A.","Akin, O.","Fine, S. W.","Shukla-Dave, A.","Eastham, J. A.","Hricak, H.","Koutcher, J. A.","Zakian, K. L."],"year":2014,"bibtype":"article","biburl":"https://raw.githubusercontent.com/jansenjfa1/bibbase.github.io/master/jansenjfa.bib","bibdata":{"bibtype":"article","type":"Journal Article","author":[{"propositions":[],"lastnames":["Matulewicz"],"firstnames":["L."],"suffixes":[]},{"propositions":[],"lastnames":["Jansen"],"firstnames":["J.","F."],"suffixes":[]},{"propositions":[],"lastnames":["Bokacheva"],"firstnames":["L."],"suffixes":[]},{"propositions":[],"lastnames":["Vargas"],"firstnames":["H.","A."],"suffixes":[]},{"propositions":[],"lastnames":["Akin"],"firstnames":["O."],"suffixes":[]},{"propositions":[],"lastnames":["Fine"],"firstnames":["S.","W."],"suffixes":[]},{"propositions":[],"lastnames":["Shukla-Dave"],"firstnames":["A."],"suffixes":[]},{"propositions":[],"lastnames":["Eastham"],"firstnames":["J.","A."],"suffixes":[]},{"propositions":[],"lastnames":["Hricak"],"firstnames":["H."],"suffixes":[]},{"propositions":[],"lastnames":["Koutcher"],"firstnames":["J.","A."],"suffixes":[]},{"propositions":[],"lastnames":["Zakian"],"firstnames":["K.","L."],"suffixes":[]}],"title":"Anatomic segmentation improves prostate cancer detection with artificial neural networks analysis of 1H magnetic resonance spectroscopic imaging","journal":"J Magn Reson Imaging","volume":"40","number":"6","pages":"1414-21","note":"Matulewicz, Lukasz Jansen, Jacobus F A Bokacheva, Louisa Vargas, Hebert Alberto Akin, Oguz Fine, Samson W Shukla-Dave, Amita Eastham, James A Hricak, Hedvig Koutcher, Jason A Zakian, Kristen L eng R01 CA076423/CA/NCI NIH HHS/ R01 CA76423/CA/NCI NIH HHS/ Evaluation Study Research Support, N.I.H., Extramural 2013/11/19 06:00 J Magn Reson Imaging. 2014 Dec;40(6):1414-21. doi: 10.1002/jmri.24487. Epub 2013 Nov 15.","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 (1)H-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 Aged Algorithms Biomarkers, Tumor/*analysis Humans Image Enhancement/methods Magnetic Resonance Imaging/*methods Male Middle Aged *Neural Networks, Computer Pattern Recognition, Automated/*methods Prostatic Neoplasms/*chemistry/*diagnosis Proton Magnetic Resonance Spectroscopy/*methods Reproducibility of Results Sensitivity and Specificity computer-aided diagnosis magnetic resonance spectroscopic imaging neural networks pattern recognition prostate cancer","issn":"1522-2586 (Electronic) 1053-1807 (Linking)","doi":"10.1002/jmri.24487","url":"http://www.ncbi.nlm.nih.gov/pubmed/24243554 https://www.ncbi.nlm.nih.gov/pmc/articles/PMC4306557/pdf/nihms532784.pdf","year":"2014","bibtex":"@article{RN169,\n author = {Matulewicz, L. and Jansen, J. F. and Bokacheva, L. and Vargas, H. A. and Akin, O. and Fine, S. W. and Shukla-Dave, A. and Eastham, J. A. and Hricak, H. and Koutcher, J. A. and Zakian, K. L.},\n title = {Anatomic segmentation improves prostate cancer detection with artificial neural networks analysis of 1H magnetic resonance spectroscopic imaging},\n journal = {J Magn Reson Imaging},\n volume = {40},\n number = {6},\n pages = {1414-21},\n note = {Matulewicz, Lukasz\nJansen, Jacobus F A\nBokacheva, Louisa\nVargas, Hebert Alberto\nAkin, Oguz\nFine, Samson W\nShukla-Dave, Amita\nEastham, James A\nHricak, Hedvig\nKoutcher, Jason A\nZakian, Kristen L\neng\nR01 CA076423/CA/NCI NIH HHS/\nR01 CA76423/CA/NCI NIH HHS/\nEvaluation Study\nResearch Support, N.I.H., Extramural\n2013/11/19 06:00\nJ Magn Reson Imaging. 2014 Dec;40(6):1414-21. doi: 10.1002/jmri.24487. Epub 2013 Nov 15.},\n 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 (1)H-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.},\n keywords = {Adult\nAged\nAlgorithms\nBiomarkers, Tumor/*analysis\nHumans\nImage Enhancement/methods\nMagnetic Resonance Imaging/*methods\nMale\nMiddle Aged\n*Neural Networks, Computer\nPattern Recognition, Automated/*methods\nProstatic Neoplasms/*chemistry/*diagnosis\nProton Magnetic Resonance Spectroscopy/*methods\nReproducibility of Results\nSensitivity and Specificity\ncomputer-aided diagnosis\nmagnetic resonance spectroscopic imaging\nneural networks\npattern recognition\nprostate cancer},\n ISSN = {1522-2586 (Electronic)\n1053-1807 (Linking)},\n DOI = {10.1002/jmri.24487},\n url = {http://www.ncbi.nlm.nih.gov/pubmed/24243554\nhttps://www.ncbi.nlm.nih.gov/pmc/articles/PMC4306557/pdf/nihms532784.pdf},\n year = {2014},\n type = {Journal Article}\n}\n\n","author_short":["Matulewicz, L.","Jansen, J. F.","Bokacheva, L.","Vargas, H. A.","Akin, O.","Fine, S. W.","Shukla-Dave, A.","Eastham, J. A.","Hricak, H.","Koutcher, J. A.","Zakian, K. L."],"key":"RN169","id":"RN169","bibbaseid":"matulewicz-jansen-bokacheva-vargas-akin-fine-shukladave-eastham-etal-anatomicsegmentationimprovesprostatecancerdetectionwithartificialneuralnetworksanalysisof1hmagneticresonancespectroscopicimaging-2014","role":"author","urls":{"Paper":"http://www.ncbi.nlm.nih.gov/pubmed/24243554 https://www.ncbi.nlm.nih.gov/pmc/articles/PMC4306557/pdf/nihms532784.pdf"},"keyword":["Adult Aged Algorithms Biomarkers","Tumor/*analysis Humans Image Enhancement/methods Magnetic Resonance Imaging/*methods Male Middle Aged *Neural Networks","Computer Pattern Recognition","Automated/*methods Prostatic Neoplasms/*chemistry/*diagnosis Proton Magnetic Resonance Spectroscopy/*methods Reproducibility of Results Sensitivity and Specificity computer-aided diagnosis magnetic resonance spectroscopic imaging neural networks pattern recognition prostate cancer"],"metadata":{"authorlinks":{"jansen, j":"https://www.jansenjfa.com/publications/"}},"downloads":0,"html":""},"search_terms":["anatomic","segmentation","improves","prostate","cancer","detection","artificial","neural","networks","analysis","magnetic","resonance","spectroscopic","imaging","matulewicz","jansen","bokacheva","vargas","akin","fine","shukla-dave","eastham","hricak","koutcher","zakian"],"keywords":["adult aged algorithms biomarkers","tumor/*analysis humans image enhancement/methods magnetic resonance imaging/*methods male middle aged *neural networks","computer pattern recognition","automated/*methods prostatic neoplasms/*chemistry/*diagnosis proton magnetic resonance spectroscopy/*methods reproducibility of results sensitivity and specificity computer-aided diagnosis magnetic resonance spectroscopic imaging neural networks pattern recognition prostate cancer"],"authorIDs":["TEAWLnKpXtQE8hs6C"],"dataSources":["TCkfRWJAZvbLAZi29"]}