TY - GEN
T1 - Quaternion neural networks applied to prostate cancer gleason grading
AU - Greenblatt, Aaron
AU - Mosquera-Lopez, Clara
AU - Agaian, Sos
N1 - Copyright:
Copyright 2014 Elsevier B.V., All rights reserved.
PY - 2013
Y1 - 2013
N2 - Diagnosis of prostate cancer currently involves visual examination of samples for the assignment of Gleason grades using a microscope, a time-consuming and subjective process. Computer-aided diagnosis (CAD) of histopathology images has become an important research area in diagnostic pathology. This paper presents a scheme to improve the accuracy of existing CAD systems for Gleason grading on digital biopsy slides by combining color and multi-scale information using quaternion algebra. The distinguishing features of presented algorithm are: 1) use of the quaternion wavelet transform and modified local binary patterns for the analysis of image texture in regions of interest; 2) A two-stage classification method: (a) a quaternion neural network with a new high-speed learning algorithm used for multiclass classification, and (b) several binary Support Vector Machine (SVM) classifiers used for classification refinement. In order to evaluate performance, hold-one-out cross validation is applied to a data set of 71 images of prostatic carcinomas belonging to Gleason grades 3, 4 and 5. The developed system assigns the correct Gleason grade in 98.87% of test cases and outperforms other published automatic Gleason grading systems. Moreover, averaged over all the classes, testing of the proposed method shows a specificity rate of 0.990 and a sensitivity rate of 0.967. Experimental results demonstrate the proposed scheme can help pathologists and radiologists diagnose prostate cancer more efficiently and with better reproducability.
AB - Diagnosis of prostate cancer currently involves visual examination of samples for the assignment of Gleason grades using a microscope, a time-consuming and subjective process. Computer-aided diagnosis (CAD) of histopathology images has become an important research area in diagnostic pathology. This paper presents a scheme to improve the accuracy of existing CAD systems for Gleason grading on digital biopsy slides by combining color and multi-scale information using quaternion algebra. The distinguishing features of presented algorithm are: 1) use of the quaternion wavelet transform and modified local binary patterns for the analysis of image texture in regions of interest; 2) A two-stage classification method: (a) a quaternion neural network with a new high-speed learning algorithm used for multiclass classification, and (b) several binary Support Vector Machine (SVM) classifiers used for classification refinement. In order to evaluate performance, hold-one-out cross validation is applied to a data set of 71 images of prostatic carcinomas belonging to Gleason grades 3, 4 and 5. The developed system assigns the correct Gleason grade in 98.87% of test cases and outperforms other published automatic Gleason grading systems. Moreover, averaged over all the classes, testing of the proposed method shows a specificity rate of 0.990 and a sensitivity rate of 0.967. Experimental results demonstrate the proposed scheme can help pathologists and radiologists diagnose prostate cancer more efficiently and with better reproducability.
KW - Automated gleason grading
KW - Neural network
KW - Prostate cancer
KW - Quaternion
KW - Wavelet transform
UR - http://www.scopus.com/inward/record.url?scp=84893535596&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=84893535596&partnerID=8YFLogxK
U2 - 10.1109/SMC.2013.199
DO - 10.1109/SMC.2013.199
M3 - Conference contribution
AN - SCOPUS:84893535596
SN - 9780769551548
T3 - Proceedings - 2013 IEEE International Conference on Systems, Man, and Cybernetics, SMC 2013
SP - 1144
EP - 1149
BT - Proceedings - 2013 IEEE International Conference on Systems, Man, and Cybernetics, SMC 2013
T2 - 2013 IEEE International Conference on Systems, Man, and Cybernetics, SMC 2013
Y2 - 13 October 2013 through 16 October 2013
ER -