Ultrasonic multifeature tissue characterization for prostate diagnostics.

A new system for prostate diagnostics based on multifeature tissue characterization is proposed. Radiofrequency (RF) ultrasonic echo data are acquired during the standard transrectal ultrasound (US) imaging examination. Nine spectral, texture, first order and morphologic parameters are calculated and fed into two adaptive neuro-fuzzy inference systems (FIS) working in parallel. The outputs of the FISs are fed into a postprocessing procedure evaluating contextual information before being combined to form a malignancy map in which areas of high cancer probability are marked in red. The malignancy map is presented to the physician during the examination to improve the early detection of prostate cancer. The system has been evaluated on 100 patients undergoing radical prostatectomy. The ROC curve area using leave-one-out cross-validation over patients is A(Z) = 0.86 when distinguishing between hyperechoic and hypoechoic tumors and normal tissue and A(Z) = 0.84 when distinguishing between isoechoic tumors and healthy tissue, respectively. Tumors that are not visible in the conventional B-mode image can be located. Diagnosis of the prostate carcinoma using multifeature tissue characterization in combination with US imaging allows the detection of tumors at an early stage. Also, biopsy guidance and therapy planning can be improved.

[1]  E. Feleppa,et al.  Statistical framework for ultrasonic spectral parameter imaging. , 1997, Ultrasound in medicine & biology.

[2]  H. Barrett,et al.  Objective comparison of quantitative imaging modalities without the use of a gold standard , 2002, IEEE Transactions on Medical Imaging.

[3]  H. Ermert,et al.  Tissue-characterization of the prostate using radio frequency ultrasonic signals , 1999, IEEE Transactions on Ultrasonics, Ferroelectrics and Frequency Control.

[4]  R. L. Romijn,et al.  Ultrasound attenuation and texture analysis of diffuse liver disease: methods and preliminary results. , 1991, Physics in medicine and biology.

[5]  V. Reuter,et al.  Typing of prostate tissue by ultrasonic spectrum analysis , 1996, IEEE Transactions on Ultrasonics, Ferroelectrics and Frequency Control.

[6]  C W Piccoli,et al.  Tissue classification with generalized spectrum parameters. , 2001, Ultrasound in medicine & biology.

[7]  R G Aarnink,et al.  Computer analysis of transrectal ultrasound images of the prostate for the detection of carcinoma: a prospective study in radical prostatectomy specimens. , 1995, The Journal of urology.

[8]  L. Huang,et al.  Duct Detection and Wall Spacing Estimation in Breast Tissue , 2000, Ultrasonic imaging.

[9]  Lotfi A. Zadeh,et al.  Outline of a New Approach to the Analysis of Complex Systems and Decision Processes , 1973, IEEE Trans. Syst. Man Cybern..

[10]  E J Feleppa,et al.  Spectrum-Analysis and Neural Networks for Imaging to Detect and Treat Prostate Cancer , 2001, Ultrasonic imaging.

[11]  Ernest J. Feleppa,et al.  Ultrasonic spectral‐parameter imaging of the prostate , 1997 .

[12]  S. Delorme,et al.  Ad multos annos , 2000 .

[13]  Nancy A. Obuchowski,et al.  Classification of atherosclerotic plaque composition by spectral analysis of intravascular ultrasound data , 2001, 2001 IEEE Ultrasonics Symposium. Proceedings. An International Symposium (Cat. No.01CH37263).

[14]  H Ermert,et al.  In vivo study of online liver tissue classification based on envelope power spectrum analysis. , 1994, Ultrasonic imaging.

[15]  Chuen-Tsai Sun,et al.  Neuro-fuzzy modeling and control , 1995, Proc. IEEE.

[16]  J. Mendel.  Fuzzy logic systems for engineering: a tutorial , 1995, Proc. IEEE.

[17]  Helmut Ermert,et al.  In vivo study of on-line liver tissue classification based on envelope power spectrum analysis , 1990, IEEE Symposium on Ultrasonics.

[18]  Chuen-Chien Lee.  FUZZY LOGIC CONTROL SYSTEMS: FUZZY LOGIC CONTROLLER - PART I , 1990 .

[19]  J. Thijssen,et al.  Characterization of echographic image texture by cooccurrence matrix parameters. , 1997, Ultrasound in medicine & biology.

[20]  J. Thijssen,et al.  Correlations between acoustic and texture parameters from RF and B-mode liver echograms. , 1993, Ultrasound in medicine & biology.

[21]  Helmut Ermert,et al.  Color-Coded Tissue Characterization Images of the Prostate , 1996 .

[22]  Theo M. de Reijke,et al.  Transrectal Ultrasound in the Diagnosis of Prostate Cancer: State of the Art and Perspectives , 2001, European Urology.

[23]  Donald H. Foley.  Considerations of sample and feature size , 1972, IEEE Trans. Inf. Theory.

[24]  Jyh-Shing Roger Jang,et al.  Fuzzy Modeling Using Generalized Neural Networks and Kalman Filter Algorithm , 1991, AAAI.

[25]  A. Pesavento,et al.  System for real-time elastography , 1999 .

[26]  H. Ermert,et al.  Ultrasonic multifeature tissue characterization for the early detection of prostate cancer , 2001, 2001 IEEE Ultrasonics Symposium. Proceedings. An International Symposium (Cat. No.01CH37263).

[27]  E. Feleppa,et al.  Statistics of ultrasonic spectral parameters for prostate and liver examinations , 1997, IEEE Transactions on Ultrasonics, Ferroelectrics and Frequency Control.

[28]  J.M. Thijssen,et al.  Calibrated Parametric Medical Ultrasound Imaging , 2000, Ultrasonic imaging.

[29]  H. Ermert,et al.  Diagnosis of prostate carcinoma using multicompression strain imaging: data acquisition and first in vivo results , 1998, 1998 IEEE Ultrasonics Symposium. Proceedings (Cat. No. 98CH36102).

[30]  H. Ermert,et al.  Ultrasonic tissue characterization-assessment of prostate tissue malignancy in vivo using a conventional classifier based tissue classification approach and elastographic imaging , 2000, 2000 IEEE Ultrasonics Symposium. Proceedings. An International Symposium (Cat. No.00CH37121).

[31]  W. Ellis,et al.  The significance of isoechoic prostatic carcinoma. , 1994, The Journal of urology.

[32]  T. Furuhashi,et al.  Fusion of fuzzy/neuro/evolutionary computing for knowledge acquisition , 2001, Proc. IEEE.

[33]  Georg Schmitz,et al.  Fortschritte der endoskopischen Prostatasonographie , 2001 .

[34]  Robert M. Haralick,et al.  Textural Features for Image Classification , 1973, IEEE Trans. Syst. Man Cybern..

[35]  M. Stöckle,et al.  Weiterentwicklung des transrektalen Ultraschalls Artifizielle neuronale Netzwerkanalyse (ANNA) in der Erkennung und Stadieneinteilung des Prostatakarzinoms , 2000, Der Urologe A.

[36]  L. A. Zedeh.  Knowledge representation in fuzzy logic , 1989 .

[37]  P. Scardino,et al.  Early detection of prostate cancer. , 1989, The Urologic clinics of North America.

[38]  C. Bangma,et al.  Prostate-specific antigen as a screening test. The Netherlands experience. , 1997, The Urologic clinics of North America.

[39]  Ernest J. Feleppa,et al.  Advanced ultrasonic tissue-typing and imaging based on radio-frequency spectrum analysis and neural-network classification for guidance of therapy and biopsy procedures , 2001, CARS.

[40]  H. Ermert,et al.  A time-efficient and accurate strain estimation concept for ultrasonic elastography using iterative phase zero estimation , 1999, IEEE Transactions on Ultrasonics, Ferroelectrics and Frequency Control.

[41]  J M Thijssen.  Spectroscopy and image texture analysis. , 2000, Ultrasound in medicine & biology.

[42]  O Basset,et al.  Texture analysis of ultrasonic images of the prostate by means of co-occurrence matrices. , 1993, Ultrasonic imaging.

[43]  H. Ermert,et al.  Comparison of different Neuro-Fuzzy classification systems for the detection of prostate cancer in ultrasonic images , 1997, 1997 IEEE Ultrasonics Symposium Proceedings. An International Symposium (Cat. No.97CH36118).

[44]  T. Senge,et al.  ULTRASCHALL-GEWEBECHARAKTERISIERUNG FÜR DIE PROSTATADIAGNOSTIK , 2001 .

[45]  H. Ermert,et al.  A new system for the acquisition of ultrasonic multicompression strain images of the human prostate in vivo , 1999, IEEE Transactions on Ultrasonics, Ferroelectrics and Frequency Control.

[46]  Helmut Ermert,et al.  Tissue characterization of the prostate using Kohonen-maps , 1994, 1994 Proceedings of IEEE Ultrasonics Symposium.

[47]  Sun-Yuan Kung,et al.  Decision-based neural networks with signal/image classification applications , 1995, IEEE Trans. Neural Networks.

[48]  U. Cobet,et al.  Tissue characterization by imaging the local frequency dependent relative backscatter coefficient , 2000, Medical Imaging.

[49]  Jyh-Shing Roger Jang,et al.  ANFIS: adaptive-network-based fuzzy inference system , 1993, IEEE Trans. Syst. Man Cybern..

[50]  W. Catalona,et al.  Artificial neural networks in the diagnosis and prognosis of prostate cancer: a pilot study. , 1994, The Journal of urology.

[51]  A. Pesavento,et al.  Real time strain imaging and in-vivo applications in prostate cancer , 2001, 2001 IEEE Ultrasonics Symposium. Proceedings. An International Symposium (Cat. No.01CH37263).

[52]  M. Stöckle,et al.  Artificial neural network analysis (ANNA) of prostatic transrectal ultrasound , 1999, The Prostate.

[53]  U. Cobet,et al.  System independent tissue typing of human testis and prostate , 1999, 1999 IEEE Ultrasonics Symposium. Proceedings. International Symposium (Cat. No.99CH37027).

[54]  R G Aarnink,et al.  Analysis of ultrasonographic prostate images for the detection of prostatic carcinoma: the automated urologic diagnostic expert system. , 1994, Ultrasound in medicine & biology.

[55]  N. Obuchowski,et al.  Assessing spectral algorithms to predict atherosclerotic plaque composition with normalized and raw intravascular ultrasound data. , 2001, Ultrasound in medicine & biology.

[56]  J M Thijssen,et al.  Precision and accuracy of acoustospectrographic parameters. , 1996, Ultrasound in medicine & biology.

[57]  Thijssen Jm,et al.  Ultrasonic tissue characterization and echographic imaging. , 1987 .

[58]  F. Lizzi.  Ultrasound Imaging , 1991, Proceedings Technology Requirements for Biomedical Imaging.

[59]  Michio Sugeno,et al.  A fuzzy-logic-based approach to qualitative modeling , 1993, IEEE Trans. Fuzzy Syst..

[60]  Jacek M. Zurada,et al.  Classification algorithms for quantitative tissue characterization of diffuse liver disease from ultrasound images , 1996, IEEE Trans. Medical Imaging.

[61]  Berkman Sahiner,et al.  Effects of sample size on classifier design: quadratic and neural network classifiers , 1997, Medical Imaging.

[62]  J. Thijssen.  Ultrasonic tissue characterisation and echographic imaging. , 1989, Physics in medicine and biology.

[63]  Dimitar Filev,et al.  Generation of Fuzzy Rules by Mountain Clustering , 1994, J. Intell. Fuzzy Syst..

[64]  P Renty,et al.  Value of transrectal prostatic echography, prostate-specific antigen and rectal examination in the diagnosis of prostate cancer. Relationship with the result of prostatic biopsies. , 1996, Acta urologica Belgica.

[65]  M. Cloostermans,et al.  A Beam Corrected Estimation of the Frequency Dependent Attenuation of Biological Tissues from Backscattered Ultrasound , 1983 .

[66]  Stephen L. Chiu,et al.  Fuzzy Model Identification Based on Cluster Estimation , 1994, J. Intell. Fuzzy Syst..

[67]  N A Obuchowski,et al.  Nonparametric analysis of clustered ROC curve data. , 1997, Biometrics.

[68]  J. Fukushima,et al.  Colour Doppler ultrasound: a new index improves the diagnosis of renal artery stenosis. , 2000, Ultrasound in medicine & biology.