PURPOSE: To develop an image-based technique capable of detection and grading of prostate cancer, which combines features extracted from multiparametric MRI into a single parameter map of cancer probability. MATERIALS AND METHODS: A combination of features extracted from diffusion tensor MRI and dynamic contrast enhanced MRI was used to characterize biopsy samples from 29 patients. Support vector machines were used to separate the cancerous samples from normal biopsy samples and to compute a measure of cancer probability, presented in the form of a cancer colormap. The classification results were compared with the biopsy results and the classifier was tuned to provide the largest area under the receiver operating characteristic (ROC) curve. Based solely on the tuning of the classifier on the biopsy data, cancer colormaps were also created for whole-mount histopathology slices from four radical prostatectomy patients. RESULTS: An area under ROC curve of 0.96 was obtained on the biopsy dataset and was validated by a "leave-one-patient-out" procedure. The proposed measure of cancer probability shows a positive correlation with Gleason score. The cancer colormaps created for the histopathology patients do display the dominant tumors. The colormap accuracy increases with measured tumor area and Gleason score. CONCLUSION: Dynamic contrast enhanced imaging and diffusion tensor imaging, when used within the framework of supervised classification, can play a role in characterizing prostate cancer.
PURPOSE: To develop an image-based technique capable of detection and grading of prostate cancer, which combines features extracted from multiparametric MRI into a single parameter map of cancer probability. MATERIALS AND METHODS: A combination of features extracted from diffusion tensor MRI and dynamic contrast enhanced MRI was used to characterize biopsy samples from 29 patients. Support vector machines were used to separate the cancerous samples from normal biopsy samples and to compute a measure of cancer probability, presented in the form of a cancer colormap. The classification results were compared with the biopsy results and the classifier was tuned to provide the largest area under the receiver operating characteristic (ROC) curve. Based solely on the tuning of the classifier on the biopsy data, cancer colormaps were also created for whole-mount histopathology slices from four radical prostatectomy patients. RESULTS: An area under ROC curve of 0.96 was obtained on the biopsy dataset and was validated by a "leave-one-patient-out" procedure. The proposed measure of cancer probability shows a positive correlation with Gleason score. The cancer colormaps created for the histopathology patients do display the dominant tumors. The colormap accuracy increases with measured tumor area and Gleason score. CONCLUSION: Dynamic contrast enhanced imaging and diffusion tensor imaging, when used within the framework of supervised classification, can play a role in characterizing prostate cancer.
Authors: B Nicolas Bloch; Neil M Rofsky; Ronaldo H Baroni; Robert P Marquis; Ivan Pedrosa; Robert E Lenkinski Journal: Acad Radiol Date: 2004-08 Impact factor: 3.173
Authors: Piotr Kozlowski; Silvia D Chang; Ran Meng; Burkhard Mädler; Robert Bell; Edward C Jones; S Larry Goldenberg Journal: Magn Reson Imaging Date: 2010-04-13 Impact factor: 2.546
Authors: Sedat Ozer; Deanna L Langer; Xin Liu; Masoom A Haider; Theodorus H van der Kwast; Andrew J Evans; Yongyi Yang; Miles N Wernick; Imam S Yetik Journal: Med Phys Date: 2010-04 Impact factor: 4.071
Authors: Gautam Jayram; Guarionex J Decastro; Michael C Large; Aria Razmaria; Gregory P Zagaja; Arieh L Shalhav; Charles B Brendler Journal: J Endourol Date: 2011-01-15 Impact factor: 2.942
Authors: David L Buckley; Caleb Roberts; Geoff J M Parker; John P Logue; Charles E Hutchinson Journal: Radiology Date: 2004-10-21 Impact factor: 11.105
Authors: Geoff J M Parker; Caleb Roberts; Andrew Macdonald; Giovanni A Buonaccorsi; Sue Cheung; David L Buckley; Alan Jackson; Yvonne Watson; Karen Davies; Gordon C Jayson Journal: Magn Reson Med Date: 2006-11 Impact factor: 4.668
Authors: Nandinee Fariah Haq; Piotr Kozlowski; Edward C Jones; Silvia D Chang; S Larry Goldenberg; Mehdi Moradi Journal: Comput Med Imaging Graph Date: 2014-07-05 Impact factor: 4.790
Authors: Jin Tae Kwak; Sheng Xu; Bradford J Wood; Baris Turkbey; Peter L Choyke; Peter A Pinto; Shijun Wang; Ronald M Summers Journal: Med Phys Date: 2015-05 Impact factor: 4.071
Authors: K Pinker; H Bickel; T H Helbich; S Gruber; P Dubsky; U Pluschnig; M Rudas; Z Bago-Horvath; M Weber; S Trattnig; W Bogner Journal: Eur Radiol Date: 2013-03-16 Impact factor: 5.315
Authors: Alpay Özcan; Barış Türkbey; Peter L Choyke; Oguz Akin; Ömer Aras; Seong K Mun Journal: Magn Reson Imaging Date: 2015-04-11 Impact factor: 2.546
Authors: Duc Fehr; Harini Veeraraghavan; Andreas Wibmer; Tatsuo Gondo; Kazuhiro Matsumoto; Herbert Alberto Vargas; Evis Sala; Hedvig Hricak; Joseph O Deasy Journal: Proc Natl Acad Sci U S A Date: 2015-11-02 Impact factor: 11.205
Authors: Wenya Linda Bi; Ahmed Hosny; Matthew B Schabath; Maryellen L Giger; Nicolai J Birkbak; Alireza Mehrtash; Tavis Allison; Omar Arnaout; Christopher Abbosh; Ian F Dunn; Raymond H Mak; Rulla M Tamimi; Clare M Tempany; Charles Swanton; Udo Hoffmann; Lawrence H Schwartz; Robert J Gillies; Raymond Y Huang; Hugo J W L Aerts Journal: CA Cancer J Clin Date: 2019-02-05 Impact factor: 508.702