Professional Documents
Culture Documents
1 s2.0 S0720048X15301947
1 s2.0 S0720048X15301947
a r t i c l e i n f o a b s t r a c t
Article history: Purpose: To determine the ability of texture analyses of contrast-enhanced CT images for distinguishing
Received 1 September 2015 between varying degrees of hepatic fibrosis in patients with chronic liver disease using histopathology
Received in revised form 2 December 2015 as the reference standard.
Accepted 13 December 2015
Materials and methods: Following IRB approval, 83 patients who underwent contrast enhanced 64-MDCT
of the abdomen and pelvis in the portal venous phase between 12/2005 and 01/2013 and who had a
Keywords:
liver biopsy within 6 months of the CT were included. An in-house developed, MATLAB-based texture
Image post processing
analysis program was employed to extract 41 texture features from each of 5 axial segmented volumes
Texture analysis
Liver
of liver. Using the Ishak fibrosis staging scale, histopathologic grades of hepatic fibrosis were correlated
Cirrhosis with texture parameters after stratifying patients into three analysis groups, comparing Ishak scales 0–2
Computed tomography with 3–6, 0–3 with 4–6, and 0–4 with 5–6. To assess the utility of texture features, receiver operating
characteristic (ROC) curves were constructed and the area under the curve (AUC) was used to determine
the performance of each feature in distinguishing between normal/low and higher grades of hepatic
fibrosis.
Results: A total of 19 different texture features with 7 histogram features, one grey level co-occurrence
matrix, 6 gray level run length, 1 Laws feature, and 4 gray level gradient matrix demonstrated statistically
significant differences for discriminating between fibrosis groupings. The highest AUC values fell in the
range of fair performance for distinguishing between different fibrosis groupings.
Conclusion: These findings suggest that texture-based analyses of contrast-enhanced CT images offer a
potential avenue toward the non-invasive assessment of liver fibrosis.
© 2016 Published by Elsevier Ireland Ltd.
http://dx.doi.org/10.1016/j.ejrad.2015.12.009
0720-048X/© 2016 Published by Elsevier Ireland Ltd.
Descargado para Anonymous User (n/a) en Hosp Italiano Buenos Aires - JCon de ClinicalKey.es por Elsevier en enero 11, 2019.
Para uso personal exclusivamente. No se permiten otros usos sin autorización. Copyright ©2019. Elsevier Inc. Todos los derechos reservados.
512 N. Daginawala et al. / European Journal of Radiology 85 (2016) 511–517
Descargado para Anonymous User (n/a) en Hosp Italiano Buenos Aires - JCon de ClinicalKey.es por Elsevier en enero 11, 2019.
Para uso personal exclusivamente. No se permiten otros usos sin autorización. Copyright ©2019. Elsevier Inc. Todos los derechos reservados.
N. Daginawala et al. / European Journal of Radiology 85 (2016) 511–517 513
deviation, 5-neighborhood std, 9-neighborhood std, 4th moment, due to alcohol and fatty liver disease (n = 2), autoimmune hepatitis
IQR, and entropy), five gray level co-occurrence matrix (GLCM) fea- (n = 1), drug hypersensitivity (n = 2), primary biliary cirrhosis (n = 2),
tures (entropy, contrast, correlation, energy, homogeneity), eleven hemochromatosis (n = 1), Budd–Chiari syndrome (n = 1), crypto-
gray-level run-length (GLRL) features (short run emphasis (SRE), genic cirrhosis (n = 2). The remaining nine patients underwent liver
long run emphasis (LRE), gray-level non-uniformity (GLN), run- biopsy to evaluate for abnormal liver function tests with no specific
length non-uniformity (RLN), run percentage (RP), low gray-level etiology of liver disease identified.
run emphasis (LGRE), high gray-level run emphasis (HGRE), short
run low gray-level emphasis (SRLGE), short run high gray-level 3.2. Histopathology
emphasis (SRHGE), long run low gray-level emphasis (LRLGE),
and long run high gray-level emphasis (LRHGE)), four gray level The distribution of the Ishak hepatic fibrosis staging scores in
gradient matrix (GLGM) features (mean, variance, skewness, and the 83 patients was the following: 16 patients (19%) with a score
kurtosis), and nine Laws features were computed and averaged over of 0, 18 patients (22%) with a score of 1, 15 patients (18%) with a
the 5 axial images segmented for each patient, similar to our prior score of 2, 11 patients (13%) with a score of 3, 2 patients (2%) with
work [19]. a score of 4, and 5 patients (6%) with a score of 5, and 16 patients
(19%) with a score of 6.
2.3. Reference standard
3.3. Texture analysis: histogram features
The pathology reports of the 83 patients meeting the inclusion
criteria were queried in our institutional electronic medical record
ROC curve analysis results comparing histogram texture fea-
to identify the results of each individual’s ultrasound-guided percu-
tures and histopathologic analysis of fibrosis are reported in
taneous liver biopsy. The degree of fibrosis which had been reported
Table 1. For the comparison of fibrosis scores 0–2 with 3–6, statis-
for each patient, graded on a scale from 0 to 6 and based on the
tically significant AUC values were found for the mean (AUC = 0.68,
Ishak fibrosis scoring sytem (0 = no fibrosis, 1 = fibrous expansion
p = 0.005), median (AUC = 0.69, p = 0.004), STD (AUC = 0.64, p = 0.03),
of some portal areas with or without short fibrous septa, 2 = fibrous
and 4th moment (AUC = 0.66, p = 0.01) features. For the compar-
expansion of most portal areas with or without short fibrous septa,
ison of fibrosis scores of 0–3 with 4–6, statistically significant
3 = fibrous expansion of most portal areas with occasional por-
AUC values were found for the mean (AUC = 0.68, p = 0.01), median
tal to portal bridging, 4 = fibrous expansion of most portal areas
(AUC = 0.69, p = 0.009), STD9 (AUC = 0.65, p = 0.03), 4th moment
with marked portal to portal bridging as well as portal to central
(AUC = 0.64, p = 0.04), IQR (AUC = 0.66, p = 0.02), and entropy
bridging, 5 = marked bridging with occasional nodules (incomplete
(AUC = 0.67, p = 0.02) features. For the comparison of fibrosis scores
cirrhosis), 6 = cirrhosis, probable or definite) was recorded for each
of 0–4 with 5–6, statistically significant AUC values were found
patient.
for the mean (AUC = 0.69, p = 0.009), median (AUC = 0.69, p = 0.009),
STD9 (AUC = 0.65, p = 0.04), IQR (AUC = 0.66, p = 0.03), and entropy
2.4. Statistical analysis
(AUC = 0.66, p = 0.03) features. The texture feature that was best
correlated with fibrosis score for all three stratifications was the
Based on the patients’ histopathological results, the Ishak fibro-
median noting that the aforementioned histogram texture features
sis staging scale was used to stratify the patient cohort into the
with the highest AUC values remained within the range of poor ROC
following three different categorizations of normal/low and higher
curve results.
grade hepatic fibrosis: (1) scores 0–2 vs. 3–6, (2) scores 0–3 vs. 4–6,
and (3) scores 0–4 vs. 5–6. To assess the potential clinical utility
of texture features, receiver operating characteristic (ROC) curves 3.4. Texture analysis: gray-level co-occurrence matrix features
were constructed to determine the performance of each feature in
distinguishing between the three different categorizations of nor- ROC curve analysis results comparing GLCM texture features
mal/low and higher degrees of hepatic fibrosis. The area under the and histopathologic analysis of fibrosis are reported in Table 2. Only
ROC curve (AUC) was used to assess the predicted validity of each the entropy texture feature was found to be statistically significant
texture feature. The closer the AUC value is to 1.0, the more predic- for the comparison of fibrosis scores 0–3 with 4–6 with an AUC of
tive the features were with respect to high grade hepatic fibrosis. 0.64 (p = 0.05), within the range of poor ROC curve results.
The area under the ROC curve (AUC) results were considered excel-
lent for AUC values between 0.9–1, good for AUC values between 3.5. Texture analysis: gray-level run-length features
0.8–0.9, fair for AUC values between 0.7–0.8, poor for AUC val-
ues between 0.6–0.7 and failed for AUC values between 0.5–0.6 ROC curve analysis results comparing GLRL texture features
[20,21]. A two-sided hypothesis was used for all tests, and a proba- and histopathologic analysis of fibrosis is reported in Table 3. For
bility value of less than 0.05 was considered statistically significant. the comparison of fibrosis scores 0–2 with 3–6, statistically sig-
Statistical computations were performed using SAS 9.1.3 software nificant AUC values were found for the RP (AUC = 0.64, p = 0.04),
(SAS Institute, Cary, NC) and GraphPad prism software (version 3.0, LGRE (AUC = 0.63, p = 0.04), and SRLGE (AUC = 0.63, p = 0.04) tex-
GraphPad Software). ture features. For the comparison of fibrosis scores of 0–3 with
4–6, statistically significant AUC values were found for the
3. Results LGRE (AUC = 0.65, p = 0.04), SRLGE (AUC = 0.65, p = 0.04), SRHGE
(AUC = 0.75, p = 0.0004), LRLGE (AUC = 0.71, p = 0.004), and LRHGE
3.1. Patient population (AUC = 0.70, p = 0.006) texture features. For the comparison of fibro-
sis scores of 0–4 with 5–6, statistically significant AUC values were
A total of 83 patients (49 males, 34 females) aged 22–75 years found for the SRHGE (AUC = 0.76, p = 0.0004), LRLGE (AUC = 0.71,
(mean age, 50 years) fulfilled the criteria for inclusion. The eti- p = 0.004), and LRHGE (AUC = 0.71, p = 0.005) texture features. Of
ologies of liver disease in the included patients were chronic note, the texture features with the highest AUC values fall within
hepatitis C (n = 48), chronic hepatitis B (n = 5), cytomegalovirus the range of fair ROC curve results. The texture feature which
induced hepatitis (n = 1), Epstein–Barr virus induced hepatitis demonstrated the highest AUC values for comparisons of both the
(n = 1), nonalcoholic steatohepatitis (NASH) (n = 8), steatohepatitis 0–3 with the 4–6 groups as well as the 0–4 with the 5–6 groups was
Descargado para Anonymous User (n/a) en Hosp Italiano Buenos Aires - JCon de ClinicalKey.es por Elsevier en enero 11, 2019.
Para uso personal exclusivamente. No se permiten otros usos sin autorización. Copyright ©2019. Elsevier Inc. Todos los derechos reservados.
514 N. Daginawala et al. / European Journal of Radiology 85 (2016) 511–517
Table 1
Texture histogram features differentiating between hepatic fibrosis grades.
Grade 0–2 vs. 3–6 Grade 0–3 vs. 4–6 Grade 0–4 vs. 5–6
Abbreviations: AUC—area under curve; CI—confidence interval; STD—standard deviation; STD5—5-neighborhood standard deviation; STD9—9-neighborhood standard devi-
ation; IQR—inter quartile range.
*
p-value < 0.05 indicates AUC is significantly different from 0.5 and there is evidence that the texture parameter has ability to distinguish between the two groups.
Table 2
Texture GLCM features differentiating between hepatic fibrosis grades.
Grade 0–2 vs. 3–6 Grade 0–3 vs. 4–6 Grade 0–4 vs. 5–6
Abbreviations: GLCM—gray level co-occurrence matrix; AUC—area under curve; CI—confidence interval.
*
p-value is less than 0.05 which indicates AUC is significantly different from 0.5 and there is evidence that the texture parameter has ability to distinguish between the
two groups.
Table 3
Texture GLRL features differentiating between hepatic fibrosis grades.
Grade 0–2 vs. 3–6 Grade 0–3 vs. 4–6 Grade 0–4 vs. 5–6
Abbreviations: GLRL—gray level run length; AUC—area under curve; CI—confidence interval; SRE—short run emphasis; LRE—long run emphasis; GLN—gray-level non-
uniformity; RLN—run-length non-uniformity; RP—run percentage; LGRE—low gray-level run emphasis; HGRE—high gray-level run emphasis; SRLGE—short run low gray-level
emphasis; SRHGE—short run high gray-level emphasis; LRLGE—long run low gray-level emphasis; LRHGE—long run high gray-level emphasis.
*
p-value is less than 0.05 which indicates AUC is significantly different from 0.5 and there is evidence that the texture parameter has ability to distinguish between the
two groups.
SRHGE; as an illustrative example, the ROC curve for SRHGE for the texture GLGM texture features were found to have statistically sig-
0–4 vs. 5–6 categorization is graphically represented in Fig. 2. nificant AUC values. For comparison of fibrosis levels of 0–2 with
3–6, AUC values ranged from 0.64 to 0.67, with p-values ranging
3.6. Texture analysis: laws features from 0.008 to 0.027. For comparison of fibrosis levels of 0–3 with
4–6, AUC values ranged from 0.72 to 0.74, with p-values ranging
ROC curve analysis results comparing Laws texture features and from 0.001 to 0.003. For comparison of fibrosis levels of 0–4 with
histopathologic analyses of fibrosis are reported in Table 4. Laws 5–6, AUC values ranged from 0.71 to 0.74, with p-values ranging
feature 1 was found to have a statistically significant AUC when from 0.001 to 0.005. Of note, the GLGM texture features with the
comparing fibrosis scores of 0–3 with 4–6 (AUC = 0.67, p = 0.02) and highest AUC values fall within the range of fair ROC curve results.
0–4 with 5–6 (AUC = 0.66, p = 0.03), both within the range of poor The texture feature which demonstrated the highest AUC values
ROC curve results. for comparisons of both the 0–3 with the 4–6 groups as well as the
0–4 with the 5–6 group categorizations was MGR.
3.7. Texture analysis: GLGM features
Descargado para Anonymous User (n/a) en Hosp Italiano Buenos Aires - JCon de ClinicalKey.es por Elsevier en enero 11, 2019.
Para uso personal exclusivamente. No se permiten otros usos sin autorización. Copyright ©2019. Elsevier Inc. Todos los derechos reservados.
N. Daginawala et al. / European Journal of Radiology 85 (2016) 511–517 515
Table 4
Texture laws features differentiating between hepatic fibrosis grades.
Grade 0–2 vs. 3–6 Grade 0–3 vs. 4–6 Grade 0–4 vs. 5–6
Table 5
Texture GLGM features differentiating between hepatic fibrosis grades.
Grade 0–2 vs. 3–6 Grade 0–3 vs. 4–6 Grade 0–4 vs. 5–6
Abbreviations: GLGM—gray level gradient matrix; AUC—area under curve; CI—confidence interval; MGR—mean gradient; VGR—variance gradient.
*
p-value is less than 0.05 which indicates AUC is significantly different from 0.5 and there is evidence that the texture parameter has ability to distinguish between the
two groups.
Descargado para Anonymous User (n/a) en Hosp Italiano Buenos Aires - JCon de ClinicalKey.es por Elsevier en enero 11, 2019.
Para uso personal exclusivamente. No se permiten otros usos sin autorización. Copyright ©2019. Elsevier Inc. Todos los derechos reservados.
516 N. Daginawala et al. / European Journal of Radiology 85 (2016) 511–517
liver images, a strength of our study includes that we identified above, given that our results demonstrate fair performance in spite
a relatively large number of texture features (19 total) across dif- of this potential confounding limitation, this further supports the
ferent categories of features with statistical significance in their robust nature of these analyses. Another limitation to consider is
capacity to discriminate between fibrosis stage groupings. No one the fact that, given that there were only two patients in our dataset
modality has yet shown an adequate sensitivity and specificity with an Ishak fibrosis score of 4, our ability to categorize patients
for staging liver fibrosis and therefore non-invasive methods for with this level of fibrosis may be limited. This fact may, in part,
assessing fibrosis remain an active area of investigation. explain why the AUC values reported above for the various texture
CT may find integration into the clinical evaluation of patients features are similar when comparing fibrosis scores of 0–3 with 4–6
with chronic liver disease for a variety of reasons. A major con- and 0–4 with 5–6.
sideration is in the routine screening of patients undergoing In conclusion, the promising results reported herein strongly
abdominopelvic CT imaging, for a variety of indications, in the support further inquiry into and refinements of these tech-
Emergency Department. In this case, a practical, accurate CT-based niques, possibly through the development of multi-parametric
tool may be employed to effectively screen and identify patients approaches leveraging numerous individual texture features. The
with hepatic fibrosis, thereby triaging this subset of patients to reported findings related to texture analysis of contrast-enhanced
receive the appropriate care of their liver disease. In addition, as CT datasets offer a potential avenue toward the noninvasive eval-
CT is often employed in the imaging evaluation of patients with uation of degrees of liver fibrosis.
suspected or known hepatocellular carcinoma or liver metastases,
the added benefit of a liver fibrosis assessment at this time offers Conflicts of interest
the potential for providing clinically relevant information prior to
direct therapeutic interventions (surgical resection, ablation, etc.) None.
[12]. Finally, in those patients in whom advanced MRI and ultra-
sound technology is unavailable, a robust, CT-based tool may be Grant support
employed in select cases for assessment of fibrosis, being mindful
of the ionizing radiation exposure. None.
In the case of CT, a variety of techniques, dual-energy imag-
ing, quantitative morphologic analyses, as well as multiphasic, References
contrast-enhanced imaging have been applied to the evaluation of
hepatic fibrosis [25–29]. While fair performance of texture analysis [1] G. Menghini, One-second needle biopsy of the liver, Gastroenterology 35
(1958) 190–199.
of portal venous phase, contrast-enhanced CT imaging is reported
[2] P. Thampanitchawong, T. Piratvisuth, Liver biopsy: complications and risk
herein, several facets of the study design must be considered when factors, World J. Gastroenterol. 5 (1999) 301–304.
judging the potential utility of this technique. Firstly, all patients [3] A. Regev, M. Berho, L.J. Jeffers, C. Milikowski, E.G. Molina, N.T. Pyrsopoulos,
included in this study exhibited some degree of liver dysfunction, et al., Sampling error and intraobserver variation in liver biopsy in patients
with chronic HCV infection, Am. J. Gastroenterol. 97 (2002) 2614–2618.
thereby necessitating the need for a percutaneous liver biopsy. As [4] V. Ratziu, F. Charlotte, A. Heurtier, S. Gombert, P. Giral, E. Bruckert, et al.,
no true control group without any active liver disease was analyzed, Sampling variability of liver biopsy in nonalcoholic fatty liver disease,
this introduces potentially confounding effects related to hepatic Gastroenterology 128 (2005) 1898–1906.
[5] M. Friedrich-Rust, K. Wunder, S. Kriener, F. Sotoudeh, S. Richter, J. Bojunga,
parenchymal abnormalities such as inflammation or edema, even et al., Liver fibrosis in viral hepatitis: noninvasive assessment with acoustic
in the absence of hepatic fibrosis (Ishak score 0). Furthermore, as radiation force impulse imaging versus transient elastography, Radiology 252
patients with a variety of etiologies of liver disease are included, (2) (2009) 595–604.
[6] S.H. Park, C.H. Kim, D.J. Kim, K.T. Suk, J.Y. Cheong, S.W. Cho, et al., Usefulness
similar confounding effects may be introduced such as, for exam- of multiple biomarkers for the prediction of significant fibrosis in chronic
ple, differing degrees of steatosis between patients with NASH vs. hepatitis B, J. Clin. Gastroenterol. 45 (4) (2011) 361–365.
those with chronic viral hepatitis, among others. Finally, the acqui- [7] S.W. Anderson, H. Jara, A. Ozonoff, M. O’Brien, J.A. Hamilton, J.A. Soto, The
effect of disease progression on liver ADC and T2 values in a murine model of
sition of portal venous phase images using a range of injection rates
hepatic fibrosis at 11.7T MRI, J. Magn. Reson. Imaging 35 (2012) 140–146.
(3–4 mL/s) and a fixed scan delay introduces potential confound- [8] L. Huwart, C. Sempoux, E. Vicaut, N. Salameh, L. Annet, E. Danse, et al.,
ing effects of slight differences in hepatic parenchymal contrast Magnetic resonance elastography for the non invasive staging of liver fibrosis,
Gastroenterology 135 (1) (2015) 32–40.
kinetics as a function of injection rate and physiology. Overall, the
[9] M. Romero-Gómez, E. Gómez-González, A. Madrazo, M. Vera-Valencia, L.
fact that numerous texture parameters achieved fair performance Rodrigo, R. Pérez-Alvarez, et al., Optical analysis of computed tomography
based on ROC analyses potentially speaks to the robust nature of images of the liver predicts fibrosis stage and distribution in chronic hepatitis
texture analyses in the assessment of liver fibrosis, regardless of C, Hepatology 47 (3) (2008) 810–816.
[10] O. Kayaaltı, B.H. Aksebzeci, I.O. Karahan, K. Deniz, M. Öztürk, B. Yılmaz, S.
etiology or the presence of confounding histopathological features Kara, et al., Liver fibrosis staging using CT image texture analysis and soft
(varying degrees of steatosis or tissue inflammation, for exam- computing, Appl. Soft Comput. 25 (2014) 399–413.
ple). The results reported herein strongly support future inquiry [11] X. Zhang, X. Gao, B.J. Liu, K. Ma, W. Yan, L. Liling, et al., Effective staging of
fibrosis by the selected texture features of liver: which one is better, CT or MR
in which such potential confounding effects are more strictly con- imaging? Comput. Med. Imaging Graph. 46 (2015) 227–236.
trolled, such as analyzing a patients affected by a single etiology [12] A.L. Simpson, L.B. Adams, P.J. Allen, M.I. D’Angelica, R.P. DeMatteo, Y. Fong,
of liver disease. With regards to CT acquisition techniques, strictly et al., Texture analysis of preoperative CT images for prediction of
postoperative hepatic insufficiency: a preliminary study, J. Am. Coll. Surg. 220
fixed injection rates and automated bolus tracking approaches may (3) (2015) 339–346.
be employed to mitigate potential confounders related to the acqui- [13] G. Castellano, L. Bonilha, L.M. Li, F. Cendes, Texture analysis of medical images,
sition of the portal venous phase datasets. Clin. Radiol. 59 (2004) 1061–1069.
[14] O. Yu, Y. Mauss, G. Zollner, I.J. Namer, J. Chambron, Distinct patterns of active
There are a few additional limitations to our study to consider.
and non-active plaques using texture analysis on brain NMR images in
Given that there were up to 6-month intervals between the imaging multiple sclerosis patients: preliminary results, Magn. Reson. Imaging 17
studies and the percutaneous liver biopsies, it is possible that the (1999) 1261–1267.
[15] F. Risse, J. Pesic, S. Young, L.E. Olsson, A texture analysis approach to quantify
level of liver fibrosis differed in the intervening time between the
ventilation changes in hyperpolarised 3He MRI of the rat lung in an asthma
biopsy and CT study. In addition, it has been previously reported model, NMR Biomed. 25 (1) (2012) 131–141.
that differences in noise indices affect texture analysis [30]. Even if [16] A. Skoch, D. Jirák, P. Vyhnanovská, M. Dezortová, P. Fendrych, E. Rolencová,
automated, attenuation-based dose modulation is employed, as in et al., Classification of calf muscle MR images by texture analysis, Magn.
Reson. Mater. Phys. 16 (6) (2004) 259–267.
this study (fixed noise indices), noise will nevertheless be expected [17] G. Bahl, I. Cruite, T. Wolfson, A.C. Gamst, J.M. Collins, A.D. Chavez, et al.,
to vary, especially at the extremes of body habitus. However, as Noninvasive classification of hepatic fibrosis based on texture parameters
Descargado para Anonymous User (n/a) en Hosp Italiano Buenos Aires - JCon de ClinicalKey.es por Elsevier en enero 11, 2019.
Para uso personal exclusivamente. No se permiten otros usos sin autorización. Copyright ©2019. Elsevier Inc. Todos los derechos reservados.
N. Daginawala et al. / European Journal of Radiology 85 (2016) 511–517 517
from double contrast-enhanced magnetic resonance images, J Magn. Reson. [25] J.H. Yoon, J.M. Lee, E. Klotz, J.H. Jeon, K.B. Lee, J.K. Han, et al., Estimation of
Imaging 36 (November (5)) (2012) 1154–1161. hepatic extracellular volume fraction using multiphasic liver computed
[18] B. Barry, K. Buch, J.A. Soto, H. Jara, A. Nakhmani, S.W. Anderson, Quantifying tomography for hepatic fibrosis grading, Invest. Radiol. 50 (4) (2015) 290–296.
liver fibrosis through the application of texture analysis to diffusion weighted [26] P. Lamb, D.V. Sahani, J.M. Fuentes-Orrego, M. Patino, A. Ghosh, P.R. Mendonça,
imaging, Magn. Reson. Imaging 32 (1) (2014) 84–90. Stratification of patients with liver fibrosis using dual-energy CT, IEEE Trans.
[19] H. Yu, K. Buch, B. Li, M. O’Brien, J. Soto, H. Jara, S.W. Anderson, Utility of Med. Imaging 34 (3) (2015) 807–815.
texture analysis for quantifying hepatic fibrosis on proton density MRI, J. [27] Y.W. Chen, J. Luo, C. Dong, X. Han, T. Tateyama, A. Furukawa, et al.,
Magn. Reson. Imaging 42 (5) (2015) 1259–1265. Computer-aided diagnosis and quantification of cirrhotic livers based on
[20] N.A. Obuchowski, Receiver operating characteristic curves and their use in morphological analysis and machine learning, Comput. Math. Methods Med.
radiology, Radiology 229 (2003) 3–8. 2013 (2013), 264809.
[21] C.E. Metz, Basic principles of ROC analysis, Semin. Nucl. Med. 8 (1978) [28] M. Hori, T. Okada, K. Higashiura, Y. Sato, Y.W. Chen, T. Kim, et al., Quantitative
283–298. imaging: quantification of liver shape on CT using the statistical shape model
[22] M. Friedrich-Rust, M.F. Ong, S. Martens, C. Sarrazin, J. Bojunga, S. Zeuzem, to evaluate hepatic fibrosis, Acad. Radiol. 22 (3) (2015) 303–309.
et al., Performance of transient elastography for the staging of liver fibrosis: a [29] S. Guan, W.D. Zhao, K.R. Zhou, W.J. Peng, J. Mao, F. Tang, CT perfusion at early
meta-analysis, Gastroenterology 134 (2008) 960. stage of hepatic diffuse disease, World J. Gastroenterol. 11 (22) (2005)
[23] L. Castéra, J. Foucher, P.H. Bernard, F. Carvalho, D. Allaix, W. Merrouche, et al., 3465–3467.
Pitfalls of liver stiffness measurement: a 5-year prospective study of 13,369 [30] O.S. Al-Kadi, Assessment of texture measures susceptibility to noise in
examinations, Hepatology 51 (2010) 828. conventional and contrast enhanced computed tomography lung tumour
[24] M.H. Hsiao, P. Chen, J. Jao, Y. Huang, C. Lee, S. Chao, et al., Quantifying liver images, Comput. Med. Imaging Graph. 34 (6) (2010) 494–503.
cirrhosis by extracting significant features from MRI T2 image, Sci. World J.
2012 (2012) 343847.
Descargado para Anonymous User (n/a) en Hosp Italiano Buenos Aires - JCon de ClinicalKey.es por Elsevier en enero 11, 2019.
Para uso personal exclusivamente. No se permiten otros usos sin autorización. Copyright ©2019. Elsevier Inc. Todos los derechos reservados.