Temporal stability assessment in shear wave elasticity images validated by deep learning neural network for chronic liver disease fibrosis stage assessment

Abstract Purpose To assess the performance of two-dimensional shear wave elastography (2D-SWE) on the GE LOGIQ E9 ultrasound system in a cohort of healthy subjects and to investigate its accuracy in the staging of liver fibrosis in patients with chronic liver disease (CLD) using liver biopsy as a reference standard. Materials and Methods From October 2014 to June 2016, 54 healthy subjects and 174 patients with CLD were consecutively enrolled. Liver fibrosis stage was assessed by the METAVIR scoring system. 18 (10.3 %) and 17 (9.8 %) patients had advanced fibrosis and cirrhosis, respectively. The correlation of liver stiffness measurement (LSM) and continuous variable was assessed using the Spearman rank correlation. The accuracy of 2D-SWE was evaluated with areas under the receiver operating characteristics curves (AUROC). Results Reliable LSMs were obtained in all subjects. The interobserver agreement ICC was excellent: 0.847. In healthy subjects, gender, but not anthropometric and biochemical data, were correlated with LSM. In patients with CLD, LSM had a strong positive correlation with fibrosis stage (rho = 0.628; p > 0.001). The AUROC was 0.724 for mild fibrosis (F≥ 1), 0.857 for moderate fibrosis (F≥ 2), 0.946 for severe fibrosis (F≥ 3), and 0.935 for cirrhosis (F4). Likewise, good accuracy was observed in the HCV subgroup. The optimal cut-off value in differentiating healthy subjects from CLD patients with any fibrosis was 5.47 kPa with an AUROC of 0.875. Conclusion 2D-SWE is a reliable and reproducible method to assess LSM with good diagnostic accuracy to assess liver fibrosis in patients with CLD.

Download Full-text

The assessment of liver fibrosis stage by two-dimensional shear wave ultrasound and transient elastography in patients with chronic liver disease

Journal of Hepatology ◽

10.1016/s0168-8278(17)31814-7 ◽

2017 ◽

Vol 66 (1) ◽

pp. S672

Author(s):

S.G. Kim ◽

B. Lee ◽

J.J. Yoo ◽

Y.S. Kim ◽

S.W. Jeong ◽

...

Keyword(s):

Liver Disease ◽

Liver Fibrosis ◽

Chronic Liver Disease ◽

Shear Wave ◽

Transient Elastography ◽

Chronic Liver ◽

Fibrosis Stage ◽

Two Dimensional

Download Full-text

Deep learning networks on chronic liver disease assessment with fine-tuning of shear wave elastography image sequences

Physics in Medicine and Biology ◽

10.1088/1361-6560/abae06 ◽

2020 ◽

Vol 65 (21) ◽

pp. 215027

Author(s):

George C Kagadis ◽

Petros Drazinos ◽

Ilias Gatos ◽

Stavros Tsantis ◽

Panagiotis Papadimitroulas ◽

...

Keyword(s):

Deep Learning ◽

Liver Disease ◽

Chronic Liver Disease ◽

Shear Wave ◽

Shear Wave Elastography ◽

Image Sequences ◽

Chronic Liver ◽

Fine Tuning ◽

Disease Assessment ◽

Learning Networks

Download Full-text

Comparison between shear wave elastography and serological findings for the evaluation of fibrosis in chronic liver disease

Journal of Ultrasonography ◽

10.15557/jou.2021.0030 ◽

2021 ◽

Vol 21 (86) ◽

pp. e186-e193

Author(s):

Mahjabeen Liaqat ◽

◽

Kashif Siddique ◽

Imran Yousaf ◽

Raham Bacha ◽

...

Keyword(s):

Liver Disease ◽

Liver Fibrosis ◽

Diagnostic Accuracy ◽

Chronic Liver Disease ◽

Shear Wave ◽

Shear Wave Elastography ◽

Chronic Liver ◽

Optimal Cutoff ◽

Cutoff Value ◽

Cutoff Values

Aim: In this study, we sought to examine the optimal cutoff values for predicting different stages of liver fibrosis, and to determine the level of agreement between shear wave elastography and aspartate aminotransferase to platelet ratio index (APRI) and fibrosis-4 index (FIB-4) scores in patients with chronic liver disease. Methodology: A descriptive, cross-sectional study was performed at the Radiology Department of Shaukat Khanum Memorial Hospital Lahore from 1 Jun 2019 until 1 June 2020. FIB-4 and APRI scores were determined by the following formula: FIB-4 = (age × AST) ÷ (platelet count × (√ (ALT)) and APRI = (AST÷AST upper limit of normal) ÷ platelet × 100. Data was analyzed with the help of SPSS version 24.0 and Microsoft Excel 2013. Results: Eighty individuals were conveniently selected, of which 62.5% were men and 37.5% were women. The mean age of the subjects was 43.47 SD ± 13.85 years. APRI and FIB-4 scores predicted F4 patients using the cutoff values of 0.47 (Sn. 72%, Sp. 70%) and 1.27 (Sn. 78%, Sp. 73%), respectively. The cutoff values of 0.46 for APRI and 1.27 for FIB-4 predicted F3–F4 patients (Sn. 74% and 77%; Sp. 76% and 76%), respectively. To predict F1–F4 compared to F0, the cutoff value was 0.34 (Sn. 68%, Sp. 75%) for APRI, while the cutoff value for FIB was 0.87 (Sn. 72%, Sp. 75%). The findings suggest that FIB-4 shows better diagnostic accuracy than APRI. Conclusion: This study provides optimal cutoff values for different groups of fibrosis patients for both serum markers. Also, the diagnostic accuracy of FIB-4 for predicting liver fibrosis was found to be superior to APRI in all disease stages.

Download Full-text

Elast q - 2D shear wave liver elastography correlates well with vibration controlled transcient elastography in patients with different etiologies of chronic liver disease

Journal of Hepatology ◽

10.1016/s0168-8278(20)31996-6 ◽

2020 ◽

Vol 73 ◽

pp. S774-S775

Author(s):

David JM Bauer ◽

Annalisa De Silvestri ◽

Dr. Laura Maiocchi ◽

Ruxandra Mare ◽

Ioan Sporea ◽

...

Keyword(s):

Liver Disease ◽

Chronic Liver Disease ◽

Shear Wave ◽

Chronic Liver ◽

Liver Elastography

Download Full-text

Liver Stiffness Assessed by Ultrasound Shear Wave Elastography from General Electric Accurately Predicts Clinically Significant Portal Hypertension in Patients with Advanced Chronic Liver Disease

Ultraschall in der Medizin - European Journal of Ultrasound ◽

10.1055/a-0965-0745 ◽

2019 ◽

Vol 41 (05) ◽

pp. 526-533

Author(s):

Horia Stefanescu ◽

Corina Rusu ◽

Monica Lupsor-Platon ◽

Oana Nicoara Farcau ◽

Petra Fischer ◽

...

Keyword(s):

Portal Hypertension ◽

Liver Disease ◽

Diagnostic Accuracy ◽

Chronic Liver Disease ◽

Shear Wave ◽

Liver Stiffness ◽

Shear Wave Elastography ◽

Chronic Liver ◽

General Electric ◽

Clinically Significant

Abstract Purpose Clinically significant portal hypertension (CSPH) is responsible for most of the complications in patients with cirrhosis. Liver stiffness (LS) measurement by vibration-controlled transient elastography (VCTE) is currently used to evaluate CSPH. Bi-dimensional shear wave elastography from General Electric (2D-SWE.GE) has not yet been validated for the diagnosis of PHT. Our aims were to test whether 2D-SWE.GE-LS is able to evaluate CSPH, to determine the reliability criteria of the method and to compare its accuracy with that of VCTE-LS in this clinical setting. Materials and Methods Patients with chronic liver disease referred to hepatic catheterization (HVPG) were consecutively enrolled. HVPG and LS by both VCTE and 2D-SWE.GE were performed on the same day. The diagnostic performance of each LS method was compared against HVPG and between each other. Results 2D-SWE.GE-LS was possible in 123/127 (96.90 %) patients. The ability to record at least 5 LS measurements by 2D-SWE.GE and IQR < 30 % were the only features associated with reliable results. 2D-SWE.GE-LS was highly correlated with HVPG (r = 0.704; p < 0.0001), especially if HVPG < 10 mmHg and was significantly higher in patients with CSPH (15.52 vs. 8.14 kPa; p < 0.0001). For a cut-off value of 11.3 kPa, the AUROC of 2D-SWE.GE-LS to detect CSPH was 0.91, which was not inferior to VCTE-LS (0.92; p = 0.79). The diagnostic accuracy of LS by 2D-SWE.GE-LS to detect CSPH was similar with the one of VCTE-LS (83.74 % vs. 85.37 %; p = 0.238). The diagnostic accuracy was not enhanced by using different cut-off values which enhanced the sensitivity or the specificity. However, in the subgroup of compensated patients with alcoholic liver disease, 2D-SWE.GE-LS classified CSPH better than VCTE-LS (93.33 % vs. 85.71 %, p = 0.039). Conclusion 2D-SWE.GE-LS has good accuracy, not inferior to VCTE-LS, for the diagnosis of CSPH.

Download Full-text