Classification of Hepatocellular Carcinoma and Liver Abscess by Applying Neural Network to Ultrasound Images

Abstract Background: The rapid development of artificial intelligence technology has improved the capability of automatic breast cancer diagnosis, compared to traditional machine learning methods. Convolutional Neural Network (CNN) can automatically select high-efficiency features, which helps to improve the level of computer-aided diagnosis (CAD). It can improve the performance of distinguishing benign and malignant breast ultrasound (BUS) tumor images and makes rapid breast tumor screening possible. Results: The classification model was evaluated by using BUS tumor images without training. Evaluation indicators include accuracy, sensitivity, specificity, and Area Under Curve (AUC) value. The results in the Fus2Net model had an accuracy of 92%, the sensitivity reached 95.65%, the specificity reached 88.89%, and the AUC value reached 0.97 for classifying BUS tumor images. Conclusions: The experiment compared the existing CNN categorized architecture, and the Fus2Net architecture we customed has more advantages in a comprehensive performance. The obtained results demonstrated that the Fus2Net classification method we proposed can better assist radiologists in the diagnosis of benign and malignant BUS tumor images. Methods: The existing public datasets are small and the amount of data suffer from the balance issue. In this paper, we provide a relatively larger dataset with a total of 1052 ultrasound images, including 696 benign images and 356 malignant images, which were collected from a local hospital. We proposed a novel CNN named Fus2Net for the benign and malignant classification of BUS tumor images and it contains two self-designed feature extraction modules. To evaluate how the classifier generalizes on the experimental dataset, 10-fold cross validation was employed. Meanwhile, to solve the balance of the dataset, the training data was augmented before being fed into the Fus2Net. In the experiment, we used hyperparameter fine-tuning and regularization technology to make the Fus2Net convergence.

Download Full-text

Ovarian Tumor Texture Classification Based on Sparse Auto-Encoder Network Combined with Multi-Feature Fusion and Random Forest in Ultrasound Image

Journal of Medical Imaging and Health Informatics ◽

10.1166/jmihi.2021.3298 ◽

2021 ◽

Vol 11 (2) ◽

pp. 424-431

Author(s):

Yingxin Wang ◽

Qianqian Zeng

Keyword(s):

Neural Network ◽

Feature Fusion ◽

Texture Classification ◽

Ultrasound Image ◽

Texture Features ◽

Recall Rate ◽

Svm Classifier ◽

Ultrasound Images ◽

Feature Extraction Method

Texture analysis has always been active areas of ultrasound image processing research. Using texture features to classify the ultrasound images is the focus of researchers' attention. How to extract representative texture features is an important part of successful texture description. The research goal of this paper is to apply the deep neural network into the ultrasound classification of ovarian tumors, and design a novel type of ovarian cancer diagnosis system. The improved HOG feature extraction method and the gray-level concurrence matrix of LBP image are firstly adopted to extract low-level features; Then, these features are cascaded into a new feature vector, and are input into the auto-encoder neural network to learn the high-level feature. Finally, the SVM classifier is used to achieve the classification of ovarian lesion. A large number of qualitative and quantitative experiments show that the improved method has more performance than the comparisons algorithms for ovarian ultrasound lesion, and it can significantly improve the classification performance while ensuring the accuracy rate and recall rate.

Download Full-text