Neural Network Ensemble Based CAD System for Focal Liver Lesions from B-Mode Ultrasound

Abstract

A neural network ensemble (NNE) based computeraided diagnostic (CAD) system to assist radiologists in differential diagnosis between focal liver lesions (FLLs), including (1) typical and atypical cases of Cyst, hemangioma (HEM) and metastatic carcinoma (MET) lesions, (2) small and large hepatocellular carcinoma (HCC) lesions, along with (3) normal (NOR) liver tissue is proposed in the present work. Expert radiologists, visualize the textural characteristics of regions inside and outside the lesions to differentiate between different FLLs, accordingly texture features computed from inside lesion regions of interest (IROIs) and texture ratio features computed from IROIs and surrounding lesion regions of interests (SROIs) are taken as input. Principal component analysis (PCA) is used for reducing the dimensionality of the feature space before classifier design. The first step of classification module consists of a five class PCA-NN based primary classifier which yields probability outputs for five liver image classes. The second step of classification module consists of ten binary PCA-NN based secondary classifiers for NOR/Cyst, NOR/HEM, NOR/HCC, NOR/MET, Cyst/HEM, Cyst/HCC, Cyst/MET, HEM/HCC, HEM/MET and HCC/MET classes. The probability outputs of five class PCA-NN based primary classifier is used to determine the first two most probable classes for a test instance, based on which it is directed to the corresponding binary PCA-NN based secondary classifier for crisp classification between two classes. By including the second step of the classification module, classification accuracy increases from 88.7 % to 95 %. The promising results obtained by the proposed system indicate its usefulness to assist radiologists in differential diagnosis of FLLs.

Three-way decision support for diagnosis on focal liver lesions

“…Finally, the FLLs are judged as benign or cancerous using classification algorithms. The most commonly used classification algorithms include Neural Networks (NN) [44,58,52], k-Nearest Neighbors (KNN) [38,11], Support Vector Machine (SVM) [55,56,5], Decision Trees [1,18] and the combination of multiple classification algorithms [57,26].…”

A CAD system for B-mode fatty liver ultrasound images using texture features

“…Run-length matrix (RLM) features: Eleven RLM features, i.e. Short run emphasis, Long run emphasis, Greylevel non-uniformity, Run-length non-uniformity, Run percentage, Low grey-level run emphasis, High greylevel rum emphasis, Short run low grey-level emphasis, Short run high grey-level emphasis, Long run low greylevel emphasis and Long run high grey-level emphasis [28,29] [28,32]. Texture rotational invariance images are obtained as per the procedure described in Virmani et al [33].…”

Reduction of speckle noise from medical images using principal component analysis image fusion

“…Out of all the imaging modalities the use of ultrasound (US) imaging modality is gaining importance because of its noninvasive, no-ionizing and real time imaging capabilities [1][2][3][4][5][6]. However, the ultrasound images are often degraded by speckle which also contains diagnostic information.…”