Detection and grading of prostate cancer using temporal enhanced ultrasound: combining deep neural networks and tissue mimicking simulations

被引:39
作者
Azizi, Shekoofeh [1 ]
Bayat, Sharareh [1 ]
Yan, Pingkun [2 ]
Tahmasebi, Amir [2 ]
Nir, Guy [1 ]
Kwak, Jin Tae [3 ]
Xu, Sheng [6 ]
Wilson, Storey [4 ]
Iczkowski, Kenneth A. [4 ]
Lucia, M. Scott [4 ]
Goldenberg, Larry [5 ]
Salcudean, Septimiu E. [1 ]
Pinto, Peter A. [6 ]
Wood, Bradford [6 ]
Abolmaesumi, Purang [1 ]
Mousavi, Parvin [7 ]
机构
[1] Univ British Columbia, Vancouver, BC, Canada
[2] Philips Res North Amer, Cambridge, MA USA
[3] Sejong Univ, Seoul, South Korea
[4] Univ Colorado, Denver, CO 80202 USA
[5] Vancouver Prostate Ctr, Vancouver, BC, Canada
[6] NIH, Bethesda, MD 20892 USA
[7] Queens Univ, Kingston, ON, Canada
基金
加拿大健康研究院; 加拿大自然科学与工程研究理事会;
关键词
Temporal enhanced ultrasound; Deep learning; Deep belief network; Cancer grading; Prostate cancer; BIOPSY; FUSION; MRI; ELASTOGRAPHY; DIAGNOSIS; GUIDANCE; CELLS;
D O I
10.1007/s11548-017-1627-0
中图分类号
R318 [生物医学工程];
学科分类号
0831 ;
摘要
Purpose Temporal Enhanced Ultrasound (TeUS) has been proposed as a newparadigm for tissue characterization based on a sequence of ultrasound radio frequency (RF) data. We previously used TeUS to successfully address the problem of prostate cancer detection in the fusion biopsies. Methods In this paper, we use TeUS to address the problem of grading prostate cancer in a clinical study of 197 biopsy cores from 132 patients. Our method involves capturing high-level latent features of TeUS with a deep learning approach followed by distribution learning to cluster aggressive cancer in a biopsy core. In this hypothesis-generating study, we utilize deep learning based feature visualization as a means to obtain insight into the physical phenomenon governing the interaction of temporal ultrasound with tissue. Results Based on the evidence derived from our feature visualization, and the structure of tissue from digital pathology, we build a simulation framework for studying the physical phenomenon underlying TeUS-based tissue characterization. Conclusion Results from simulation and feature visualization corroborated with the hypothesis that micro-vibrations of tissue microstructure, captured by low-frequency spectral features of TeUS, can be used for detection of prostate cancer.
引用
收藏
页码:1293 / 1305
页数:13
相关论文
共 33 条
[1]  
[Anonymous], RECENT ADV ULTRASONI
[2]  
[Anonymous], SPIE MED IMAGING
[3]  
[Anonymous], SPIE MED IMAGING
[4]  
[Anonymous], PATTERN RECOGN LETT
[5]  
[Anonymous], SPIE MED IMAGING
[6]  
Azizi Shekoofeh, 2016, Medical Image Computing and Computer-Assisted Intervention - MICCAI 2016. 19th International Conference. Proceedings: LNCS 9900, P653, DOI 10.1007/978-3-319-46720-7_76
[7]   Detection of prostate cancer using temporal sequences of ultrasound data: a large clinical feasibility study [J].
Azizi, Shekoofeh ;
Imani, Farhad ;
Ghavidel, Sahar ;
Tahmasebi, Amir ;
Kwak, Jin Tae ;
Xu, Sheng ;
Turkbey, Baris ;
Choyke, Peter ;
Pinto, Peter ;
Wood, Bradford ;
Mousavi, Parvin ;
Abolmaesumi, Purang .
INTERNATIONAL JOURNAL OF COMPUTER ASSISTED RADIOLOGY AND SURGERY, 2016, 11 (06) :947-956
[8]   Ultrasound-Based Detection of Prostate Cancer Using Automatic Feature Selection with Deep Belief Networks [J].
Azizi, Shekoofeh ;
Imani, Farhad ;
Zhuang, Bo ;
Tahmasebi, Amir ;
Kwak, Jin Tae ;
Xu, Sheng ;
Uniyal, Nishant ;
Turkbey, Baris ;
Choyke, Peter ;
Pinto, Peter ;
Wood, Bradford ;
Moradi, Mehdi ;
Mousavi, Parvin ;
Abolmaesumi, Purang .
MEDICAL IMAGE COMPUTING AND COMPUTER-ASSISTED INTERVENTION - MICCAI 2015, PT II, 2015, 9350 :70-77
[9]   The ''independent components'' of natural scenes are edge filters [J].
Bell, AJ ;
Sejnowski, TJ .
VISION RESEARCH, 1997, 37 (23) :3327-3338
[10]  
Bengio Y., 2007, Advances in neural information processing systems, V19, P153