Computer-aided image analysis of focal hepatic lesions in ultrasonography: preliminary results
Tóm tắt
To develop a computer-aided image analysis (CAIA) algorithm for analyzing US features of focal hepatic lesions and to correlate the feature values of CAIA with radiologists’ grading. Two abdominal radiologists, blinded to the final diagnosis, independently evaluated sonographic images of 51 focal hepatic lesions in 47 patients: hemangiomas (n = 19), hepatic simple cysts or cystic lesions (n = 14), hepatocellular carcinoma (n = 11), metastases (n = 6), and focal fat deposition (n = 1). All images were graded using a 3- to 5-point scale, in terms of border (roundness, sharpness, and the presence of peripheral rim), texture (echogenicity, homogeneity, and internal artifact), posterior enhancement, and lesion conspicuity. Using a CAIA, texture and morphological parameters representing radiologists’ subjective evaluations were extracted. Correlations between the radiologists and the CAIA for assessing parameters in corresponding categories were computed by means of weighted κ statistics and Spearman correlation test. A good agreement was achieved between CAIA and radiologists for grading echogenicity (weighted κ = 0.675) and the presence of hyper- or hypoechoic rim (weighted κ = 0.743). Several CAIA-derived features representing homogeneity of the lesions showed good correlations (correlation coefficient (γ) = 0.603∼0.641) with radiologists’ grading (P < 0.05). For internal artifact (γ = 0.469–0.490) and posterior enhancement (γ = −0.516) of the cyst and lesion conspicuity (γ = 0.410), a fair correlation between CAIA and radiologists was obtained (P < 0.05). However, parameters representing lesions’ border such as sharpness (γ = 0.252–0.299) and roundness (γ = −0.134–0.163) showed no significant correlation (P > 0.05). As a preliminary step in US computer-aided diagnosis for focal hepatic lesions, a CAIA algorithm was constructed with a good agreement and correlation with human observers in most US features. In addition, these features should be weighted highly when a computer-aided diagnosis for characterizing focal liver lesions on US is designed and developed.
Tài liệu tham khảo
Chen DR, Chang RF, Kuo WJ, et al. (2002) Diagnosis of breast tumors with sonographic texture analysis using wavelet transform and neural networks. Ultrasound Med Biol 28:1301–1310
Chen DR, Chang RF, Huang YL (1999) Computer-aided diagnosis applied to US of solid breast nodules by using neural networks. Radiology 213:407–412
Kim KG, Cho SW, Min SJ, et al. (2005) Computerized scheme for assessing ultrasonographic features of breast masses. Acad Radiol 12:58–66
Chen EL, Chung PC, Chen CL, et al. (1998) An automatic diagnostic system for CT liver image classification. IEEE Trans Biomed Eng 45:783–794
Bleck JS, Gebel M, Hebel R, et al. (1994) Tissue characterization using intelligent adaptive filter in the diagnosis of diffuse and focal liver disease. Ultrasound Med Biol 20:521–528
Lee WL, Chen YC, Hsieh KS (2003) Ultrasonic liver tissues classification by fractal feature vector based on M-band wavelet transform. IEEE Trans Med Imaging 22:382–392
Pavlopoulos S, Kyriacou E, Koutsouris D, et al. (2000) Fuzzy neural network-based texture analysis of ultrasonic images. IEEE Eng Med Biol Mag 19:39–47
Kim SH, Lee JM, Kim JH, et al. (2005) Appropriateness of a donor liver with respect to macrosteatosis: application of artificial neural networks to US images–initial experience. Radiology 234:793–803
Kyriacou E, Pavlopoulos S, Koutsouris D, et al. (1997) Computer assisted characterization of liver tissue using image texture analysis techniques on B-scan images. In: IEEE/EMBS 19th international conference proceedings, pp 806–809
Choi BI, Kim AY, Lee JY, et al. (2002) Hepatocellular carcinoma: contrast enhancement with Levovist. J Ultrasound Med 21:77–84
Prando A, Wallace S, Bernardino ME, et al. (1979) Computed tomographic arteriography of the liver. Radiology 130:697–701
Matsui O, Kadoya M, Suzuki M, et al. (1983) Work in progress: dynamic sequential computed tomography during arterial portography in the detection of hepatic neoplasms. Radiology 146:721–727
Ohishi H, Uchida H, Yoshimura H, et al. (1985) Hepatocellular carcinoma detected by iodized oil. Use of anticancer agents. Radiology 154:25–29
Leslie DF, Johnson CD, Johnson CM, et al. (1995) Distinction between cavernous hemangiomas of the liver and hepatic metastases on CT: value of contrast enhancement patterns. AJR Am J Roentgenol 164:625–629
Yoshida H, Itai Y, Ohtomo K, et al. (1989) Small hepatocellular carcinoma and cavernous hemangioma: differentiation with dynamic FLASH MR imaging with Gd-DTPA. Radiology 171:339–342
Kim KG, Kim JH, Min BG (2002) Classification of malignant and benign tumors using boundary characteristics in breast ultrasonograms. J Digit Imaging 15(Suppl 1):224–227
Landis JR, Koch GG (1977) The measurement of observer agreement for categorical data. Biometrics 33:159–174
Yoshida H, Keserci B, David CD, et al. (1998) Segmentation of liver tumors in ultrasound images based on scale-space analysis of the continuous wavelet transform. In: IEEE ultrasonic symposium, pp 1713–1716
Bilello M, Gokturk SB, Desser T, et al. (2004) Automatic detection and classification of hypodense hepatic lesions on contrast-enhanced venous-phase CT. Med Phys 31:2584–2593
Huang YL, Chen JH, Shen WC (2006) Diagnosis of hepatic tumors with texture analysis in nonenhanced computed tomography images. Acad Radiol 13:713–720
Klein HM, Eisele T, Klose KC, et al. (1996) Pattern recognition system for focal liver lesions using “crisp” and “fuzzy” classifiers. Invest Radiol 31:6–10
Gletsos M, Mougiakakou SG, Matsopoulos GK, et al. (2003) A computer-aided diagnostic system to characterize CT focal liver lesions: design and optimization of a neural network classifier. IEEE Trans Inf Technol Biomed 7:153–162
Williams DM, Bland P, Liu L, et al. (1989) Liver-tumor boundary detection: human observer vs computer edge detection. Invest Radiol 24:768–775