@misc{Viswanath2008,
   abstract = {Current techniques for localization of prostatic adenocarcinoma (CaP) via blinded trans-rectal ultrasound biopsy are associated with a high false negative detection rate. While high resolution endorectal in vivo Magnetic Resonance (MR) prostate imaging has been shown to have improved contrast and resolution for CaP detection over ultrasound, similarity in intensity characteristics between benign and cancerous regions on MR images contribute to a high false positive detection rate. In this paper, we present a novel unsupervised segmentation method that employs manifold learning via consensus schemes for detection of cancerous regions from high resolution 1.5 Tesla (T) endorectal in vivo prostate MRI. A significant contribution of this paper is a method to combine multiple weak, lower-dimensional representations of high dimensional feature data in a way analogous to classifier ensemble schemes, and hence create a stable and accurate reduced dimensional representation. After correcting for MR image intensity artifacts, such as bias field inhomogeneity and intensity non-standardness, our algorithm extracts over 350 3D texture features at every spatial location in the MR scene at multiple scales and orientations. Non-linear dimensionality reduction schemes such as Locally Linear Embedding (LLE) and Graph Embedding (GE) are employed to create multiple low dimensional data representations of this high dimensional texture feature space. Our novel consensus embedding method is used to average object adjacencies from within the multiple low dimensional projections so that class relationships are preserved. Unsupervised consensus clustering is then used to partition the objects in this consensus embedding space into distinct classes. Quantitative evaluation on 18 1.5 T prostate MR data against corresponding histology obtained from the multisite ACRIN trials show a sensitivity of 92.65% and a specificity of 82.06%, which suggests that our method is successfully able to detect suspicious regions in the prostate.},
   author = {Satish E. Viswanath and M.A. Rosen and A. Madabhushi},
   doi = {10.1117/12.770868},
   isbn = {9780819470997},
   issn = {16057422},
   journal = {Progress in Biomedical Optics and Imaging - Proceedings of SPIE},
   keywords = {1.5 Tesla,Computer-aided diagnosis,Consensus clustering,Consensus embedding,In vivo,MRI,Manifold learning,Prostate cancer,Segmentation},
   title = {A consensus embedding approach for segmentation of high resolution in vivo prostate magnetic resonance imagery},
   volume = {6915},
   year = {2008},
}

{"_id":"v984zX6Ju9xApx3RT","bibbaseid":"viswanath-rosen-madabhushi-aconsensusembeddingapproachforsegmentationofhighresolutioninvivoprostatemagneticresonanceimagery-2008","authorIDs":["4Bygm8ju5EJL5ymrQ","6QhxQnZANogYLvQK3","95yz33vzsQF4xkftF","9XZAWfqroLnhv8Yvi","FNZqkqoLDpk7PuWdD","MFZedjHxD2knXtEDJ","QcPeEw2JciXtbZFYv","h2B3dsR3oRk42DaEg","ikoetnssERNBFB49Z","kEjtqmTXpJD7idBiM","mKXojsM3x8movswn3","mTxR5EmKaPZT4FPRw","wqGyw5WWC92w63FBr","zmtHQr2MyDkT4KaPS","zy5Yt2FBfMrjEQLRW"],"author_short":["Viswanath, S. E.","Rosen, M.","Madabhushi, A."],"bibdata":{"bibtype":"misc","type":"misc","abstract":"Current techniques for localization of prostatic adenocarcinoma (CaP) via blinded trans-rectal ultrasound biopsy are associated with a high false negative detection rate. While high resolution endorectal in vivo Magnetic Resonance (MR) prostate imaging has been shown to have improved contrast and resolution for CaP detection over ultrasound, similarity in intensity characteristics between benign and cancerous regions on MR images contribute to a high false positive detection rate. In this paper, we present a novel unsupervised segmentation method that employs manifold learning via consensus schemes for detection of cancerous regions from high resolution 1.5 Tesla (T) endorectal in vivo prostate MRI. A significant contribution of this paper is a method to combine multiple weak, lower-dimensional representations of high dimensional feature data in a way analogous to classifier ensemble schemes, and hence create a stable and accurate reduced dimensional representation. After correcting for MR image intensity artifacts, such as bias field inhomogeneity and intensity non-standardness, our algorithm extracts over 350 3D texture features at every spatial location in the MR scene at multiple scales and orientations. Non-linear dimensionality reduction schemes such as Locally Linear Embedding (LLE) and Graph Embedding (GE) are employed to create multiple low dimensional data representations of this high dimensional texture feature space. Our novel consensus embedding method is used to average object adjacencies from within the multiple low dimensional projections so that class relationships are preserved. Unsupervised consensus clustering is then used to partition the objects in this consensus embedding space into distinct classes. Quantitative evaluation on 18 1.5 T prostate MR data against corresponding histology obtained from the multisite ACRIN trials show a sensitivity of 92.65% and a specificity of 82.06%, which suggests that our method is successfully able to detect suspicious regions in the prostate.","author":[{"firstnames":["Satish","E."],"propositions":[],"lastnames":["Viswanath"],"suffixes":[]},{"firstnames":["M.A."],"propositions":[],"lastnames":["Rosen"],"suffixes":[]},{"firstnames":["A."],"propositions":[],"lastnames":["Madabhushi"],"suffixes":[]}],"doi":"10.1117/12.770868","isbn":"9780819470997","issn":"16057422","journal":"Progress in Biomedical Optics and Imaging - Proceedings of SPIE","keywords":"1.5 Tesla,Computer-aided diagnosis,Consensus clustering,Consensus embedding,In vivo,MRI,Manifold learning,Prostate cancer,Segmentation","title":"A consensus embedding approach for segmentation of high resolution in vivo prostate magnetic resonance imagery","volume":"6915","year":"2008","bibtex":"@misc{Viswanath2008,\n abstract = {Current techniques for localization of prostatic adenocarcinoma (CaP) via blinded trans-rectal ultrasound biopsy are associated with a high false negative detection rate. While high resolution endorectal in vivo Magnetic Resonance (MR) prostate imaging has been shown to have improved contrast and resolution for CaP detection over ultrasound, similarity in intensity characteristics between benign and cancerous regions on MR images contribute to a high false positive detection rate. In this paper, we present a novel unsupervised segmentation method that employs manifold learning via consensus schemes for detection of cancerous regions from high resolution 1.5 Tesla (T) endorectal in vivo prostate MRI. A significant contribution of this paper is a method to combine multiple weak, lower-dimensional representations of high dimensional feature data in a way analogous to classifier ensemble schemes, and hence create a stable and accurate reduced dimensional representation. After correcting for MR image intensity artifacts, such as bias field inhomogeneity and intensity non-standardness, our algorithm extracts over 350 3D texture features at every spatial location in the MR scene at multiple scales and orientations. Non-linear dimensionality reduction schemes such as Locally Linear Embedding (LLE) and Graph Embedding (GE) are employed to create multiple low dimensional data representations of this high dimensional texture feature space. Our novel consensus embedding method is used to average object adjacencies from within the multiple low dimensional projections so that class relationships are preserved. Unsupervised consensus clustering is then used to partition the objects in this consensus embedding space into distinct classes. Quantitative evaluation on 18 1.5 T prostate MR data against corresponding histology obtained from the multisite ACRIN trials show a sensitivity of 92.65% and a specificity of 82.06%, which suggests that our method is successfully able to detect suspicious regions in the prostate.},\n author = {Satish E. Viswanath and M.A. Rosen and A. Madabhushi},\n doi = {10.1117/12.770868},\n isbn = {9780819470997},\n issn = {16057422},\n journal = {Progress in Biomedical Optics and Imaging - Proceedings of SPIE},\n keywords = {1.5 Tesla,Computer-aided diagnosis,Consensus clustering,Consensus embedding,In vivo,MRI,Manifold learning,Prostate cancer,Segmentation},\n title = {A consensus embedding approach for segmentation of high resolution in vivo prostate magnetic resonance imagery},\n volume = {6915},\n year = {2008},\n}\n","author_short":["Viswanath, S. E.","Rosen, M.","Madabhushi, A."],"key":"Viswanath2008-1","id":"Viswanath2008-1","bibbaseid":"viswanath-rosen-madabhushi-aconsensusembeddingapproachforsegmentationofhighresolutioninvivoprostatemagneticresonanceimagery-2008","role":"author","urls":{},"keyword":["1.5 Tesla","Computer-aided diagnosis","Consensus clustering","Consensus embedding","In vivo","MRI","Manifold learning","Prostate cancer","Segmentation"],"metadata":{"authorlinks":{"viswanath, s":"https://bibbase.org/service/mendeley/eaba325f-653b-3ee2-b960-0abd5146933e","viswanath, s":"https://case.edu/engineering/labs/invent/publications"}},"downloads":0},"bibtype":"misc","creationDate":"2020-04-20T04:32:18.575Z","downloads":0,"keywords":["1.5 tesla","computer-aided diagnosis","consensus clustering","consensus embedding","in vivo","mri","manifold learning","prostate cancer","segmentation"],"search_terms":["consensus","embedding","approach","segmentation","high","resolution","vivo","prostate","magnetic","resonance","imagery","viswanath","rosen","madabhushi"],"title":"A consensus embedding approach for segmentation of high resolution in vivo prostate magnetic resonance imagery","year":2008,"biburl":"https://bibbase.org/f/w8Gpb3sdkT5KfcMbC/export.bib","dataSources":["EqsrWP7MGiqJ6MAPy","ya2CyA73rpZseyrZ8","MFTLffJ4nzQec8k8n","2252seNhipfTmjEBQ","xGcAuoNZfYSSjMypc"]}