ULTRASONIC TISSUE CHARACTERIZATION FOR THE CLASSIFICATION OF PROSTATE TISSUE

Radio‐frequency ultrasound echo data of the prostate are captured during routine examinations with standard ultrasound equipment. The data are directly transmitted to a PC and subdivided into numerous regions of interest. Several parameters describing the histological characteristics of the underlying tissue are calculated from the frequency spectrum and from the demodulated signal of the underlying echo data. Parameters are fed into two adaptive network‐based fuzzy inference systems working in parallel. One system is used to classify hypo‐ and hyperechoic tumors, the other system is used to detect isoechoic tumors within the normal prostate tissue. Subsequent morphological analysis combines clusters to mark areas of similar tissue characteristics. Classification results are presented as two‐dimensional malignancy maps and as volumetric reconstructions of the whole organ. Radio‐frequency ultrasonic echo data of 100 patients have been recorded. Tissue samples following radical prostatectomies are used as t...

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

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

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

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

[5]  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).

[6]  J. Thijssen.  Ultrasonic tissue characterization and echographic imaging. , 1987, Medical progress through technology.

[7]  J M Thijssen,et al.  A beam corrected estimation of the frequency dependent attenuation of biological tissues from backscattered ultrasound. , 1983, Ultrasonic imaging.

[8]  J M Thijssen,et al.  Precision and accuracy of acoustospectrographic parameters. , 1996, Ultrasound in Medicine and Biology.

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

[10]  Helmut Ermert,et al.  Ultrasonic multifeature tissue characterization for prostate diagnostics. , 2003, Ultrasound in medicine & biology.

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

[12]  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).

[13]  I.E. Magnin,et al.  Processing radio frequency ultrasound images: a robust method for local spectral features estimation by a spatially constrained parametric approach , 2002, IEEE Transactions on Ultrasonics, Ferroelectrics and Frequency Control.

[14]  H. Ermert,et al.  Neuro-fuzzy inference system for ultrasonic multifeature tissue characterization for prostate diagnostics , 2002, 2002 IEEE Ultrasonics Symposium, 2002. Proceedings..