PURPOSE: This paper presents the results of a large study involving fusion prostate biopsies to demonstrate that temporal ultrasound can be used to accurately classify tissue labels identified in multi-parametric magnetic resonance imaging (mp-MRI) as suspicious for cancer. METHODS: We use deep learning to analyze temporal ultrasound data obtained from 255 cancer foci identified in mp-MRI. Each target is sampled in axial and sagittal planes. A deep belief network is trained to automatically learn the high-level latent features of temporal ultrasound data. A support vector machine classifier is then applied to differentiate cancerous versus benign tissue, verified by histopathology. Data from 32 targets are used for the training, while the remaining 223 targets are used for testing. RESULTS: Our results indicate that the distance between the biopsy target and the prostate boundary, and the agreement between axial and sagittal histopathology of each target impact the classification accuracy. In 84 test cores that are 5 mm or farther to the prostate boundary, and have consistent pathology outcomes in axial and sagittal biopsy planes, we achieve an area under the curve of 0.80. In contrast, all of these targets were labeled as moderately suspicious in mp-MR. CONCLUSION: Using temporal ultrasound data in a fusion prostate biopsy study, we achieved a high classification accuracy specifically for moderately scored mp-MRI targets. These targets are clinically common and contribute to the high false-positive rates associated with mp-MRI for prostate cancer detection. Temporal ultrasound data combined with mp-MRI have the potential to reduce the number of unnecessary biopsies in fusion biopsy settings.
PURPOSE: This paper presents the results of a large study involving fusion prostate biopsies to demonstrate that temporal ultrasound can be used to accurately classify tissue labels identified in multi-parametric magnetic resonance imaging (mp-MRI) as suspicious for cancer. METHODS: We use deep learning to analyze temporal ultrasound data obtained from 255 cancer foci identified in mp-MRI. Each target is sampled in axial and sagittal planes. A deep belief network is trained to automatically learn the high-level latent features of temporal ultrasound data. A support vector machine classifier is then applied to differentiate cancerous versus benign tissue, verified by histopathology. Data from 32 targets are used for the training, while the remaining 223 targets are used for testing. RESULTS: Our results indicate that the distance between the biopsy target and the prostate boundary, and the agreement between axial and sagittal histopathology of each target impact the classification accuracy. In 84 test cores that are 5 mm or farther to the prostate boundary, and have consistent pathology outcomes in axial and sagittal biopsy planes, we achieve an area under the curve of 0.80. In contrast, all of these targets were labeled as moderately suspicious in mp-MR. CONCLUSION: Using temporal ultrasound data in a fusion prostate biopsy study, we achieved a high classification accuracy specifically for moderately scored mp-MRI targets. These targets are clinically common and contribute to the high false-positive rates associated with mp-MRI for prostate cancer detection. Temporal ultrasound data combined with mp-MRI have the potential to reduce the number of unnecessary biopsies in fusion biopsy settings.
Entities:
Keywords:
Cancer diagnosis; Deep belief network; Deep learning; Prostate cancer; Temporal ultrasound data
Authors: Farhad Imani; Mahdi Ramezani; Saman Nouranian; Eli Gibson; Amir Khojaste; Mena Gaed; Madeleine Moussa; Jose A Gomez; Cesare Romagnoli; Michael Leveridge; Silvia Chang; Aaron Fenster; D Robert Siemens; Aaron D Ward; Parvin Mousavi; Purang Abolmaesumi Journal: IEEE Trans Biomed Eng Date: 2015-02-16 Impact factor: 4.538
Authors: Mohammad I Daoud; Parvin Mousavi; Farhad Imani; Robert Rohling; Purang Abolmaesumi Journal: IEEE Trans Biomed Eng Date: 2012-10-24 Impact factor: 4.538
Authors: Farhad Imani; Purang Abolmaesumi; Eli Gibson; Amir Khojaste Galesh-Khale; Mena Gaed; Madeleine Moussa; Jose A Gomez; Cesare Romagnoli; D Robert Siemens; Michael Leviridge; Silvia Chang; Aaron Fenster; Aaron D Ward; Parvin Mousavi Journal: Med Image Comput Comput Assist Interv Date: 2013
Authors: Shekoofeh Azizi; Sharareh Bayat; Pingkun Yan; Amir Tahmasebi; Guy Nir; Jin Tae Kwak; Sheng Xu; Storey Wilson; Kenneth A Iczkowski; M Scott Lucia; Larry Goldenberg; Septimiu E Salcudean; Peter A Pinto; Bradford Wood; Purang Abolmaesumi; Parvin Mousavi Journal: Int J Comput Assist Radiol Surg Date: 2017-06-20 Impact factor: 2.924