Hepatocellular Carcinoma Recognition from Ultrasound Images Using Combinations of Conventional and Deep Learning Techniques

Abstract

Hepatocellular Carcinoma (HCC) is the most frequent malignant liver tumor and the third cause of cancer-related deaths worldwide. For many years, the golden standard for HCC diagnosis has been the needle biopsy, which is invasive and carries risks. Computerized methods are due to achieve a noninvasive, accurate HCC detection process based on medical images. We developed image analysis and recognition methods to perform automatic and computer-aided diagnosis of HCC. Conventional approaches that combined advanced texture analysis, mainly based on Generalized Co-occurrence Matrices (GCM) with traditional classifiers, as well as deep learning approaches based on Convolutional Neural Networks (CNN) and Stacked Denoising Autoencoders (SAE), were involved in our research. The best accuracy of 91% was achieved for B-mode ultrasound images through CNN by our research group. In this work, we combined the classical approaches with CNN techniques, within B-mode ultrasound images. The combination was performed at the classifier level. The CNN features obtained at the output of various convolution layers were combined with powerful textural features, then supervised classifiers were employed. The experiments were conducted on two datasets, acquired with different ultrasound machines. The best performance, above 98%, overpassed our previous results, as well as representative state-of-the-art results.

Deep Learning Techniques for Liver Tumor Recognition in Ultrasound Images

“…We also employed advanced, original textural attributes, conceived by the authors, as for example the edge orientation variability [5], or those derived from superior order GCMs, defined by (1) and computed as described in [5].…”

“…Superior order Generalized Cooccurrence Matrices (GCM), in the form of the Gray Level Cooccurrence Matrix (GLCM) of superior order, respectively Textual Microstructures Cooccurrence Matrices (TMCM) of second and third order [3], combined with highly performant conventional classifiers, such as the Support Vector Machines (SVM), the Multilayer Perceptron (MLP), Random Forest (RF), respectively AdaBoost in conjunction with Decision Trees (J48) were involved in this phase. Recently, taking advantage of the spectacular development of deep learning methods, various types of such techniques were considered for employment and assessment within ultrasound images for HCC recognition [4][5][6]. In the current approach, we focus on those deep learning techniques that led to the best classification performance in our research, also on the combinations among these techniques, as well as on their combinations with the Conventional Machine Learning (CML) methods, at both classifier and decision level.…”

Malignancy diagnosis of liver lesion in contrast enhanced ultrasound using an end-to-end method based on deep learning

“…DL algorithms developed based on B-mode data typically only use static images as data sources. As such, only spatial information is taking into account and the developednetworks are primarily VGG-type 2D CNN, DenseNet 2D CNN, and ResNet-type 2D CNN [11][12][13][14][15]. Unlike B-mode, CEUS provides dynamic perfusion information on the tissue in real-time.…”

Imaging Investigation of Hepatocellular Carcinoma Progress via Monitoring γ-Glutamyltranspeptidase Level with a Near-Infrared Fluorescence/Photoacoustic Bimodal Probe

“…Ultrasonography was the first imaging method utilized in screening HCC, but its low resolution limited the differentiation capability at the tissue level. 27 The above-mentioned methods such as MRI and CT showed higher spatial resolution, but they were still not well-prepared for the nodules of HCC. These methods all required experienced operators and precise apparatus.…”

“…For the signal output and graphics presentation, several imaging techniques were applied for the diagnosis of HCC. Ultrasonography was the first imaging method utilized in screening HCC, but its low resolution limited the differentiation capability at the tissue level . The above-mentioned methods such as MRI and CT showed higher spatial resolution, but they were still not well-prepared for the nodules of HCC.…”