Classification of focal liver lesions on ultrasound images by extracting hybrid textural features and using an artificial neural network

Hwang, Yoo Na; Lee, Ju Hwan; Kim, Ga Young; Jiang, Yuan; Kim, Sung Min

doi:10.3233/bme-151459

Cited by 44 publications

(42 citation statements)

References 25 publications

(29 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Among different machine learning algorithms, artificial neural networks (ANNs) are commonly applied for pattern recognition and classification . Moreover, ANNs have proven to pose a promising alternative to ordinary LSR with good resilience to noise and outliers …”

Section: Introductionmentioning

confidence: 99%

Diffusion parameter mapping with the combined intravoxel incoherent motion and kurtosis model using artificial neural networks at 3 T

et al. 2017

View full text Add to dashboard Cite

Artificial neural networks (ANNs) were used for voxel-wise parameter estimation with the combined intravoxel incoherent motion (IVIM) and kurtosis model facilitating robust diffusion parameter mapping in the human brain. The proposed ANN approach was compared with conventional least-squares regression (LSR) and state-of-the-art multi-step fitting (LSR-MS) in Monte-Carlo simulations and in vivo in terms of estimation accuracy and precision, number of outliers and sensitivity in the distinction between grey (GM) and white (WM) matter. Both the proposed ANN approach and LSR-MS yielded visually increased parameter map quality. Estimations of all parameters (perfusion fraction f, diffusion coefficient D, pseudo-diffusion coefficient D*, kurtosis K) were in good agreement with the literature using ANN, whereas LSR-MS resulted in D* overestimation and LSR yielded increased values for f and D*, as well as decreased values for K. Using ANN, outliers were reduced for the parameters f (ANN, 1%; LSR-MS, 19%; LSR, 8%), D* (ANN, 21%; LSR-MS, 25%; LSR, 23%) and K (ANN, 0%; LSR-MS, 0%; LSR, 15%). Moreover, ANN enabled significant distinction between GM and WM based on all parameters, whereas LSR facilitated this distinction only based on D and LSR-MS on f, D and K. Overall, the proposed ANN approach was found to be superior to conventional LSR, posing a powerful alternative to the state-of-the-art method LSR-MS with several advantages in the estimation of IVIM-kurtosis parameters, which might facilitate increased applicability of enhanced diffusion models at clinical scan times.

show abstract

Section: Introductionmentioning

confidence: 99%

Diffusion parameter mapping with the combined intravoxel incoherent motion and kurtosis model using artificial neural networks at 3 T

et al. 2017

View full text Add to dashboard Cite

show abstract

“…Secondly, in order to obtain estimates to a Spectral component using the Nyström extension. Using these approaches, the author demonstrates that this universal filter can be achieved efficient fairly small fraction of the pixel in this figure [1]. Deepa Parasar proposed segmentation of foetus ultrasound image, (10).The research method drawback is that they have not used CPNN which is the fastest network also our accuracy determined is effective and efficiency is enhanced…”

Section: Related Workmentioning

confidence: 96%

“…Hwanga et al [1] , presented the diagnostic accuracy of focal liver lesions by evaluating key features of hemangiomas and cancerous lesions in ultrasound images. Focal liver lesions were divided into 29, 37 and 33 with severe hemangiomas.…”

Section: Related Workmentioning

confidence: 99%

Classification of Biomedical Images using Counter Propagation Neural Network

Sangita¹,

Vijay²

2018

IJCA

View full text Add to dashboard Cite

In this paper, method for the segmentation, feature extraction & classification for ultrasonic biomedical images are proposed The method has been applied & implemented Some sets of descriptors corresponding to texture measurements and geometrical features is extracted for each segmented object and applied to a classifier. The paper reports comparative results of classification of ultrasound images; research experimentation has been implemented on various ultrasound images from the standard datasets. The present experimental study is aimed at comparing the evaluation of image processing algorithms and classification techniques applied on the ultrasound images. Different image segmentation techniques have been proposed here for feature extraction. Currently, there is a large amount of research work going on in the field of automated system for inspection, analysis of ultrasound enhancement, feature extraction and classification. Comparison of other classification methods and application of image processing on the ultrasound images of are aimed to categorize the US images for medical diagnosis purpose to make accept/reject decisions as per the international biomedical standards. The diagnosis scheme includes three steps: Preprocessing, feature extraction and classification. Finally experimental results are reported for three different classifiers (Support Vector Machine, ANFIS,CPNN).

show abstract

“…The classification of liver tumors images has become important in recent years. Many studies have been done with conventional image processing methods [26,27,28,29]. Many of the studies, like ours, used custom datasets.…”

Section: Related Workmentioning

confidence: 99%

A Novel Method for Classifying Liver and Brain Tumors Using Convolutional Neural Networks, Discrete Wavelet Transform and Long Short-Term Memory Networks

Kutlu

Avcı

2019

Sensors

View full text Add to dashboard Cite

Rapid classification of tumors that are detected in the medical images is of great importance in the early diagnosis of the disease. In this paper, a new liver and brain tumor classification method is proposed by using the power of convolutional neural network (CNN) in feature extraction, the power of discrete wavelet transform (DWT) in signal processing, and the power of long short-term memory (LSTM) in signal classification. A CNN–DWT–LSTM method is proposed to classify the computed tomography (CT) images of livers with tumors and to classify the magnetic resonance (MR) images of brains with tumors. The proposed method classifies liver tumors images as benign or malignant and then classifies brain tumor images as meningioma, glioma, and pituitary. In the hybrid CNN–DWT–LSTM method, the feature vector of the images is obtained from pre-trained AlexNet CNN architecture. The feature vector is reduced but strengthened by applying the single-level one-dimensional discrete wavelet transform (1-D DWT), and it is classified by training with an LSTM network. Under the scope of the study, images of 56 benign and 56 malignant liver tumors that were obtained from Fırat University Research Hospital were used and a publicly available brain tumor dataset were used. The experimental results show that the proposed method had higher performance than classifiers, such as K-nearest neighbors (KNN) and support vector machine (SVM). By using the CNN–DWT–LSTM hybrid method, an accuracy rate of 99.1% was achieved in the liver tumor classification and accuracy rate of 98.6% was achieved in the brain tumor classification. We used two different datasets to demonstrate the performance of the proposed method. Performance measurements show that the proposed method has a satisfactory accuracy rate at the liver tumor and brain tumor classifying.

show abstract

Classification of focal liver lesions on ultrasound images by extracting hybrid textural features and using an artificial neural network

Cited by 44 publications

References 25 publications

Diffusion parameter mapping with the combined intravoxel incoherent motion and kurtosis model using artificial neural networks at 3 T

Diffusion parameter mapping with the combined intravoxel incoherent motion and kurtosis model using artificial neural networks at 3 T

Classification of Biomedical Images using Counter Propagation Neural Network

A Novel Method for Classifying Liver and Brain Tumors Using Convolutional Neural Networks, Discrete Wavelet Transform and Long Short-Term Memory Networks

Contact Info

Product

Resources

About