Ultrasonic Evaluation of Liver Fibrosis Using the Homodyned K Distribution with an Artificial Neural Network Estimator

Gao, Anna H.; Wu, Shuicai; Tai, Dar‐In; Zhou, Zhuhuang; Tsui, Po-Hsiang

doi:10.1109/ius52206.2021.9593684

Cited by 4 publications

(4 citation statements)

References 15 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The iANN estimator was based on a four-layer feed-forward backpropagation network, which had an input layer of eight neuros corresponding to the eight features; 2 hidden layers of 10 and 4 neurons, respectively; and an output layer of two neurons corresponding to log 10 ( α ) and k . The iANN estimator 22 outperformed the original one. 21 Thus, it was used in this study for estimating α and k .…”

Section: Theoretical Backgroundmentioning

confidence: 95%

“…The ANN estimator is flexible, accurate, fast, and easy to implement. 21 In Gao et al, 22 we introduced the iANN estimator, using eight features from RSK and XU: R 0.72 , S 0.72 , K 0.72 , R 0.88 , S 0.88 , K 0.88 , X, and U. The iANN estimator was based on a four-layer feed-forward backpropagation network, which had an input layer of eight neuros corresponding to the eight features; 2 hidden layers of 10 and 4 neurons, respectively; and an output layer of two neurons corresponding to log 10 (α) and k. The iANN estimator 22 outperformed the original one.…”

Section: The Ann and Iann Estimatorsmentioning

confidence: 99%

“…21 In Gao et al, 22 we introduced the iANN estimator, using eight features from RSK and XU: R 0.72 , S 0.72 , K 0.72 , R 0.88 , S 0.88 , K 0.88 , X, and U. The iANN estimator was based on a four-layer feed-forward backpropagation network, which had an input layer of eight neuros corresponding to the eight features; 2 hidden layers of 10 and 4 neurons, respectively; and an output layer of two neurons corresponding to log 10 (α) and k. The iANN estimator 22 outperformed the original one. 21 Thus, it was used in this study for estimating α and k. The estimates were used for constructing parametric images of α and k, which is termed iANN-based ultrasound homodyned-K imaging.…”

Section: The Ann and Iann Estimatorsmentioning

confidence: 99%

“…21 Further, we introduced an improved ANN (iANN) estimator for homodyned-K distribution. 22 Radiomics is an emerging medical image analysis method proposed in recent years, which usually refers to extracting high-dimensional features that are difficult to quantitatively describe in human vision from medical images, analyzing the potential information of the obtained images, 23,24 and correlating it with clinical pathology. Radiomics is widely used in the diagnosis of breast cancer, lung cancer, gastrointestinal cancer, and other cancers as well as cardiovascular diseases, 23 and has high clinical application value.…”

Section: Introductionmentioning

confidence: 99%

See 3 more Smart Citations

Liver Fibrosis Assessment Using Radiomics of Ultrasound Homodyned-K imaging Based on the Artificial Neural Network Estimator

et al. 2022

Self Cite

View full text Add to dashboard Cite

The homodyned-K distribution is an important ultrasound backscatter envelope statistics model of physical meaning, and the parametric imaging of the model parameters has been explored for quantitative ultrasound tissue characterization. In this paper, we proposed a new method for liver fibrosis characterization by using radiomics of ultrasound backscatter homodyned-K imaging based on an improved artificial neural network (iANN) estimator. The iANN estimator was used to estimate the ultrasound homodyned-K distribution parameters k and α from the backscattered radiofrequency (RF) signals of clinical liver fibrosis ( n = 237), collected with a 3-MHz convex array transducer. The RF data were divided into two groups: Group I corresponded to liver fibrosis with no hepatic steatosis ( n = 94), and Group II corresponded to liver fibrosis with mild to severe hepatic steatosis ( n = 143). The estimated homodyned-K parameter values were then used to construct k and α parametric images using the sliding window technique. Radiomics features of k and α parametric images were extracted, and feature selection was conducted. Logistic regression classification models based on the selected radiomics features were built for staging liver fibrosis. Experimental results showed that the proposed method is overall superior to the radiomics method of uncompressed envelope images when assessing liver fibrosis. Regardless of hepatic steatosis, the proposed method achieved the best performance in staging liver fibrosis ≥ F1, ≥ F4, and the area under the receiver operating characteristic curve was 0.88, 0.85 (Group I), and 0.85, 0.86 (Group II), respectively. Radiomics has improved the ability of ultrasound backscatter statistical parametric imaging to assess liver fibrosis, and is expected to become a new quantitative ultrasound method for liver fibrosis characterization.

show abstract

Section: Theoretical Backgroundmentioning

confidence: 95%