scholarly journals Automatic Recognition of the Hepatocellular Carcinoma from Ultrasound Images using Complex Textural Microstructure Co-Occurrence Matrices (CTMCM)

2018 ◽  
Author(s):  
Delia Mitrea ◽  
Sergiu Nedevschi ◽  
Radu Badea
Keyword(s):  
Hepatocellular Carcinoma ◽  
Automatic Recognition ◽  
Ultrasound Images

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

2020 ◽  
Vol 32 (8) ◽  
pp. 2659
Author(s):  
Sendren Sheng-Dong Xu ◽  
Chun-Chao Chang ◽  
Chien-Tien Su ◽  
Pham Quoc Phu ◽  
Tifany Inne Halim ◽  
...  
Keyword(s):  
Neural Network ◽  
Hepatocellular Carcinoma ◽  
Liver Abscess ◽  
Ultrasound Images

scholarly journals Treatment of hepatocellular carcinoma using the Smart Fusion needle navigation system: conversion from real-time 4D-echo data

2021 ◽  
pp. 46
Author(s):  
Keyword(s):  
Hepatocellular Carcinoma ◽  
Magnetic Resonance ◽  
Real Time ◽  
Navigation System ◽  
Magnetic Resonance Images ◽  
The Body ◽  
Target Point ◽  
Ultrasound Images ◽  
Volume Data ◽  
Needle Position

Advances in ultrasound systems have improved the accuracy of hepatocellular carcinoma (HCC) diagnosis and treatment. We have been treating HCC using real-time 4D and Live 3D-echo technologies. However, these treatment methods have drawbacks such as vibrations during puncture and a limited angle of needle insertion. To overcome these problems, systems that can display ultrasound images simultaneously with computed tomography (CT) and magnetic resonance images in a real-time manner for reference purposes have been reported. These systems have recently been equipped with a needle tip navigation system, making it possible to reliably visualize tumors and determine the needle tip position in a tumor. These developments have enabled the safe treatment of HCC. Treatment using needle navigation is performed as follows: A Canon APLIO800 ultrasound system is used with a conventional convex probe (PVT-375BT) and a micro-convex probe (PVT-382BT). The system function is known as Smart Fusion. Ultrasound images can be displayed with volume data from other modalities, such as CT and magnetic resonance imaging (MRI), in relation to the positional information using a magnetic sensor. This enables the use of CT/MRI data as reference for accurate puncture and treatment of lesions that are difficult to identify by ultrasound alone. Axis alignment is also completed by displaying the xiphoid process on a CT image and having the system learn the orientation of the probe placed perpendicular to the body axis. Then, landmark alignment is performed and fine-adjusted by aligning a target point near the lesion with the same point as displayed on CT (Fig. 1). Case presentation A 7x-year-old woman was found to have elevated tumor markers and a liver tumor identified by regular blood testing and CT performed in August 20xx and was admitted to our hospital for treatment. Abdominal ultrasonography showed a hypoechoic lesion measuring approximately 3 cm in diameter in liver S6, which led to a diagnosis of HCC. For treatment, microwave therapy was selected at the patient’s request. Microwaves were delivered using a Medtronic Emprint ablation system with a 3.0-cm needle for ablation. During treatment, the needle position was confirmed by needle navigation before ablation (Fig. 2) because the tumor needed to be ablated in an overlapping manner (Fig. 3).

scholarly journals Hepatocellular carcinoma associated with pregnancy about 2 cases at the gynecological and obstetrical clinic of the Aristide Le Dantec hospital, Dakar, Senegal

2020 ◽  
Vol 10 (1) ◽  
pp. 353
Author(s):  
Abdoulaye Diakhate ◽  
Omar Gassama ◽  
Mohamed Diadhiou ◽  
Simon B. Ndour ◽  
Mouhamadou Wade ◽  
...  
Keyword(s):  
Hepatocellular Carcinoma ◽  
Caesarean Section ◽  
Liver Cancer ◽  
Hepatitis B ◽  
Incidental Finding ◽  
Clinical Signs ◽  
Ultrasound Images ◽  
Third Trimester ◽  
Hepatic Cytolysis

The objective of our study was to report 2 cases of hepatocellular carcinomas associated with pregnancy followed in our structure and to review the literature. Our patients were 30 and 37-year-old multi-gesture females with chronic unattended viral hepatitis B in whom the diagnosis of hepatocellular carcinoma was made in the third trimester of pregnancy at 31 weeks of amenorrhea and 4 days and at 32 weeks of amenorrhea after the incidental finding of tumor hepatomegaly on abdominal-pelvic ultrasound. The main clinical signs were jaundice and hepatomegaly and paraclinical signs were dominated by hepatic cytolysis and anemia in addition to ultrasound images. Follow-up of pregnancies revealed no particularities. A caesarean section was scheduled at 32 weeks of amenorrhea and 32 weeks of amenorrhea and 3 days allowing the birth of two preterm newborns weighing 1210 and 1500 gm with Apgar scores of 8-10/10 and 7-9/10 respectively at the fifth minute. The immediate post-operative follow-up was simple. However, the maternal-fetal prognosis was poor with the death of both patients in a multi-visceral failure table occurring respectively at 6 weeks and 3 weeks after caesarean section. The newborns had died 8 days after birth. Although rare, these two cases challenge any obstetrician to think about liver cancer in pregnant women, especially those with chronic hepatitis B. Ultrasound examination of the liver, or even better, the MRI, which is more efficient, in order to suspect early on a possible liver cancer. Indeed, early diagnosis and a thorough medical approach are essential for the treatment of HCC in pregnant patients.

Preoperative prediction of microvascular invasion (MVI) in hepatocellular carcinoma based on kupffer phase radiomic features of sonazoid contrast-enhanced ultrasound (SCEUS): A prospective study

2022 ◽  
pp. 1-11
Author(s):  
Yi Dong ◽  
Dan Zuo ◽  
Yi-Jie Qiu ◽  
Jia-Ying Cao ◽  
Han-Zhang Wang ◽  
...  
Keyword(s):  
Hepatocellular Carcinoma ◽  
Receiver Operating Characteristic ◽  
Operating Characteristic ◽  
Microvascular Invasion ◽  
Ultrasound Images ◽  
Contrast Enhanced Ultrasound ◽  
Model Based ◽  
Preoperative Prediction ◽  
Contrast Enhanced ◽  
Receiver Operating

OBJECTIVES: To establish and evaluate a machine learning radiomics model based on grayscale and Sonazoid contrast enhanced ultrasound images for the preoperative prediction of microvascular invasion (MVI) in hepatocellular carcinoma (HCC) patients. METHODS: 100 cases of histopathological confirmed HCC lesions were prospectively included. Regions of interest were segmented on both grayscale and Kupffer phase of Sonazoid contrast enhanced (CEUS) images. Radiomic features were extracted from tumor region and region containing 5 mm of peritumoral liver tissues. Maximum relevance minimum redundancy (MRMR) and Least Absolute Shrinkage and Selection Operator (LASSO) were used for feature selection and Support Vector Machine (SVM) classifier was trained for radiomic signature calculation. Radiomic signatures were incorporated with clinical variables using univariate-multivariate logistic regression for the final prediction of MVI. Receiver operating characteristic curves, calibration curves and decision curve analysis were used to evaluate model’s predictive performance of MVI. RESULTS: Age were the only clinical variable significantly associated with MVI. Radiomic signature derived from Kupffer phase images of peritumoral liver tissues (kupfferPT) displayed a significantly better performance with an area under the receiver operating characteristic curve (AUROC) of 0.800 (95% confidence interval: 0.667, 0.834), the final prediction model using Age and kupfferPT achieved an AUROC of 0.804 (95% CI: 0.723, 0.878), accuracy of 75.0%, sensitivity of 87.5% and specificity of 69.1%. CONCLUSIONS: Radiomic model based on Kupffer phase ultrasound images of tissue adjacent to HCC lesions showed an observable better predictive value compared to grayscale images and has potential value to facilitate preoperative identification of HCC patients at higher risk of MVI.

scholarly journals Comparison of Deep-Learning and Conventional Machine-Learning Methods for the Automatic Recognition of the Hepatocellular Carcinoma Areas from Ultrasound Images

Sensors ◽  
2020 ◽  
Vol 20 (11) ◽  
pp. 3085 ◽  
Author(s):  
Raluca Brehar ◽  
Delia-Alexandrina Mitrea ◽  
Flaviu Vancea ◽  
Tiberiu Marita ◽  
Sergiu Nedevschi ◽  
...  
Keyword(s):  
Machine Learning ◽  
Hepatocellular Carcinoma ◽  
Deep Learning ◽  
Binary Classification ◽  
Classification Performance ◽  
Ultrasound Images ◽  
Learning Methods ◽  
Machine Learning Methods ◽  
Segmentation Accuracy ◽  
Conventional Machine

The emergence of deep-learning methods in different computer vision tasks has proved to offer increased detection, recognition or segmentation accuracy when large annotated image datasets are available. In the case of medical image processing and computer-aided diagnosis within ultrasound images, where the amount of available annotated data is smaller, a natural question arises: are deep-learning methods better than conventional machine-learning methods? How do the conventional machine-learning methods behave in comparison with deep-learning methods on the same dataset? Based on the study of various deep-learning architectures, a lightweight multi-resolution Convolutional Neural Network (CNN) architecture is proposed. It is suitable for differentiating, within ultrasound images, between the Hepatocellular Carcinoma (HCC), respectively the cirrhotic parenchyma (PAR) on which HCC had evolved. The proposed deep-learning model is compared with other CNN architectures that have been adapted by transfer learning for the ultrasound binary classification task, but also with conventional machine-learning (ML) solutions trained on textural features. The achieved results show that the deep-learning approach overcomes classical machine-learning solutions, by providing a higher classification performance.

Sign in / Sign up

Export Citation Format

Share Document