Ultrasonic images of the kidney and of the liver are subjected to a multiscale analysis in a generalized Hermite pyramid framework. The gradient images of the multiscale decompositions of the images of healthy and sick kidneys, and of the intraoperative and conventionally imaged livers, exhibit differences, in the structures of gray level regions, which can be interpreted by a medical doctor. These are used as inputs to an unsupervised classifier to automatically classify the images into homogeneous groups, which are found, in the case of the ultrasonic images examined, to correspond to the different physical characteristics of tissues of the organs under study. The main contribution of the paper is believed to be the multiscale tissue characterization along with its display in a manner that has utility as a diagnostic aid to the clinician.
WagnerR. F.InsanaM. F.BrownD. G., Unified approach to the detection and classification of speckle texture in diagnostic ultrasound, Opt. Engng.25, 738–742 (1986).
2.
InsanaM. F.WagnerR. F.GarraS.BrownD. G.ShawkerT. H., Analysis of ultrasound image texture via generalized Rician statistics, Opt. Engng.25, 743–748 (1986).
3.
WagnerR. F.InsanaM. F.BrownD. G., Statistical properties of radio-frequency and envelope-detected signals with applications to medical ultrasound, J. Opt. Soc. Am. A4, 910–922 (1987).
4.
InsanaM. F.WagnerR. F.GarraS.BrownD. G.ShawkerT. H., A Statistical Approach to an Expert Diagnostic Ultrasonic System, in Applications of Optical Instrumentation in Medicine XIV: Medical Imaging, Processing, and Display, SchneiderR. H.DwyerS. J.III, Eds., pp. 24–29, (Proc. SPIE 626, 1986).
5.
InsanaM. F.WagnerR. F.GarraB. S.MomenanR.ShawerT. H., Pattern recognition methods for optimizing tissue signatures in diagnostic ultrasound, Ultrasonic Imaging, 8, 165–180 (1986).
6.
NicholasD.NassiriD. K.CarbuttP.HillC. R., Tissue characterization from Ultrasound B-scan data, Ultrasound Med. Biol., 12, 135–143 (1986).
7.
RaethU.SchlapsD.LimbergB.ZunaI.LorenzA.Van KaickG.LorenzW. J.KommerrelB., Diagnostic accuracy of computerized b-scan texture analysis conventional ultrasonography in diffuse parenchymal and malignant liver disease, J. Clin. Ultrasound, 13, 87–99 (1985).
8.
FinetteS.BleierA.SwindellW., Breast tissue classification using diagnostic ultrasound and pattern recognition techniques, I: Methods of pattern recognition, Ultrasonic Imaging, 5, 55–70 (1983).
9.
FinetteS.BleierA.SwindellW.HarberK., Breast tissue classification using diagnostic ultrasound and pattern recognition techniques, II: Experimental results, Ultrasonic Imaging, 5, 71–86 (1983).
10.
MomenanR.WagnerR. F.GarraB. S.LoadM. H.InsanaM. F., Image staining and differential diagnosis of ultrasound scans on the Mahalanobis distance, IEEE Transactions on Medical Imaging, 13, 37–47 (1994).
11.
MomenanR.InsanaM. F.WagnerR. F.GarraB. S.LoewM. H., Application of cluster analysis and unsupervised learning to multi-variate tissue characterization, J. Clinical Eng., 455–461 (1988).
12.
InsanaM. F.WagnerR. F.GarraS.MomenanR.ShawkerT. H., Supervised pattern recognition techniques in quantitative diagnostic ultrasound, J. Clinical Eng., 447–454 (1988).
13.
GarraB. S.InsanaM. F.ShawkerT. H.WagnerR. F.BradfordM.RussellM., Quantitative ultrasonic detection and classification of diffuse liver disease comparison with human observer performance, Invest. Radiology, 24, 196–203 (1989).
14.
MarrD., Vision (FreemanSan Francisco, CA, 1982).
15.
PelegS.NaorJ.HartleyR.AvnirD., Multiple resolution texture analysis and classification, IEEE Trans. Pattern Analysis and Machine Intelligence, 6, pp 110–117 (1984).
16.
GreinerT.LoizouCh.PanditM.MauruschatJ.AlbertR. W., Speckle reduction in Ultrasonic Imaging for medical applications, in Proc. ICASSP 91—International Conf. on Acoustics, Speech and Signal Processing, pp. 2993–2996, M12.22 (1991).
17.
GreinerT.MettlachH.PanditM.KumaresanR., Multiresolution Texture Analysis—Tissue Characterization Based on Ultrasonic Images, in Signal Processing VI: Theories and Applications, VandewalleJ.BoiteR.MoonenM.OosterlinckA., Eds. (Elsevier Science Publishers B.V.1992).
18.
MandelbrotB. B., The Fractal Geometry of Nature (FreemanSan Francisco, CA, 1982).
19.
ChangC. C.DaponteJ. S.FoxM. D., Fractal feature analysis and classification in medical imaging, IEEE Trans. on Medical Imaging, 8, 133–142 (1989).
20.
HoeferS., Die statistische Analyse medizinischer Ultraschallbilder unter Beruecksichtigung der physikalischen Effekte der Ultrascahllbildgebung sowie der fraktalen Struktur der abgebildeten Organe, Dr.-Ing Thesis (Universitaet KaiserslauternKaiserslautern, Germany, 1994).
21.
HuangQ.LorchJ. R.DubesR. C., Can the fractal dimension of an image be measured?Pattern Recognition, 27, 339–349 (1994).
22.
GaborD., Theory of Communication, J. Inst. Elec. Eng. (London), 93, 429–457 (1946).
23.
BastiaansM. J., Gabor's signal expansion and degrees of freedom of a signal, Proc. IEEE, 68, 538–539 (1980).
24.
MallatS., (a) Multiresolution approximation and wavelet orthonormal bases of L2, Trans. Amer. Math. Soc., 3–15, 69–87 (1989); (b) Multifrequency channel decompositions of images and wavelet models, IEEE Trans. ASSP 37, 2091–2110 (1989).
25.
DaubechiesI., (a) The Wavelet Transform, time-frequency localization and signal analysis, IEEE Trans. Information Theory, 36, 961–1004 (1990); (b) Orthonormal basis of compactly supported wavelets, Comm. Pure & Applied Math. 41, 909–996 (1988).
26.
HealyD. M.Jr.WeaverJ. B., Two applications of wavelet transforms in magnetic resonance imaging, IEEE Trans. Information Theory, 38, 840–860 (1992).
27.
GreinerT., Methoden der Digitalen Bildverarbeitung zur computergestuetzen Gewebecharakerisierung mit Ultraschall unter besonderer Beruecksichtigung der hierarchischen Texturanalyse, Dr.-Ing Thesis, (Universitaet KaiserslauternKaiserslautern, Germany, 1993).
28.
WatsonA. B., The Cortex transform: Rapid computation of simulated neural images, Computer Vision, Graphics, and Image Processing, 39, 311–327 (1987).
29.
BurtP. J.AdelsonE. H., The Laplacian pyramid as a compact image code, IEEE Trans. Commun.31, 532–540 (1983).
30.
SlepianD., On bandwidth, Proc. IEEE64, 292–300 (1976).
31.
VenkateshY. V.RamaniK.NandiniR., Hermite sieve as a wavelet-like array for 1D and 2D signal decomposition, IEE Proc., Vision, Image Signal Proc.141, 348–356 (1994).
32.
HigginsJ. R., Completeness and Basis Properties of Sets of Special Functions, (Cambridge University PressCambridge, Great Britain, 1977).
