scholarly journals Hepatocellular Carcinoma Automatic Diagnosis within CEUS and B-Mode Ultrasound Images Using Advanced Machine Learning Methods

Sensors ◽  
2021 ◽  
Vol 21 (6) ◽  
pp. 2202
Author(s):  
Delia Mitrea ◽  
Radu Badea ◽  
Paulina Mitrea ◽  
Stelian Brad ◽  
Sergiu Nedevschi
Keyword(s):  
Machine Learning ◽  
Hepatocellular Carcinoma ◽  
Recognition Performance ◽  
Kernel Principal Component Analysis ◽  
Ultrasound Images ◽  
Learning Methods ◽  
Malignant Liver Tumor ◽  
Automatic Diagnosis ◽  
Machine Learning Methods ◽  
Combination Methods

Hepatocellular Carcinoma (HCC) is the most common malignant liver tumor, being present in 70% of liver cancer cases. It usually evolves on the top of the cirrhotic parenchyma. The most reliable method for HCC diagnosis is the needle biopsy, which is an invasive, dangerous method. In our research, specific techniques for non-invasive, computerized HCC diagnosis are developed, by exploiting the information from ultrasound images. In this work, the possibility of performing the automatic diagnosis of HCC within B-mode ultrasound and Contrast-Enhanced Ultrasound (CEUS) images, using advanced machine learning methods based on Convolutional Neural Networks (CNN), was assessed. The recognition performance was evaluated separately on B-mode ultrasound images and on CEUS images, respectively, as well as on combined B-mode ultrasound and CEUS images. For this purpose, we considered the possibility of combining the input images directly, performing feature level fusion, then providing the resulted data at the entrances of representative CNN classifiers. In addition, several multimodal combined classifiers were experimented, resulted by the fusion, at classifier, respectively, at the decision levels of two different branches based on the same CNN architecture, as well as on different CNN architectures. Various combination methods, and also the dimensionality reduction method of Kernel Principal Component Analysis (KPCA), were involved in this process. These results were compared with those obtained on the same dataset, when employing advanced texture analysis techniques in conjunction with conventional classification methods and also with equivalent state-of-the-art approaches. An accuracy above 97% was achieved when our new methodology was applied.

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.

scholarly journals Evaluation of machine learning methods with Fourier Transform features for classifying ovarian tumors based on ultrasound images

PLoS ONE ◽  
2019 ◽  
Vol 14 (7) ◽  
pp. e0219388 ◽  
Author(s):  
José Martínez-Más ◽  
Andrés Bueno-Crespo ◽  
Shan Khazendar ◽  
Manuel Remezal-Solano ◽  
Juan-Pedro Martínez-Cendán ◽  
...  
Keyword(s):  
Machine Learning ◽  
Fourier Transform ◽  
Ovarian Tumors ◽  
Ultrasound Images ◽  
Learning Methods ◽  
Machine Learning Methods

scholarly journals Day Ahead Hourly Global Horizontal Irradiance Forecasting—Application to South African Data

Energies ◽  
2019 ◽  
Vol 12 (18) ◽  
pp. 3569 ◽  
Author(s):  
Phathutshedzo Mpfumali ◽  
Caston Sigauke ◽  
Alphonce Bere ◽  
Sophie Mulaudzi
Keyword(s):  
Machine Learning ◽  
Solar Power ◽  
Prediction Interval ◽  
Combination Method ◽  
Support Vector ◽  
Forecast Combination ◽  
Learning Methods ◽  
Machine Learning Methods ◽  
Stochastic Gradient Boosting ◽  
Combination Methods

Due to its variability, solar power generation poses challenges to grid energy management. In order to ensure an economic operation of a national grid, including its stability, it is important to have accurate forecasts of solar power. The current paper discusses probabilistic forecasting of twenty-four hours ahead of global horizontal irradiance (GHI) using data from the Tellerie radiometric station in South Africa for the period August 2009 to April 2010. Variables are selected using a least absolute shrinkage and selection operator (Lasso) via hierarchical interactions and the parameters of the developed models are estimated using the Barrodale and Roberts’s algorithm. Two forecast combination methods are used in this study. The first is a convex forecast combination algorithm where the average loss suffered by the models is based on the pinball loss function. A second forecast combination method, which is quantile regression averaging (QRA), is also used. The best set of forecasts is selected based on the prediction interval coverage probability (PICP), prediction interval normalised average width (PINAW) and prediction interval normalised average deviation (PINAD). The results demonstrate that QRA gives more robust prediction intervals than the other models. A comparative analysis is done with two machine learning methods—stochastic gradient boosting and support vector regression—which are used as benchmark models. Empirical results show that the QRA model yields the most accurate forecasts compared to the machine learning methods based on the probabilistic error measures. Results on combining prediction interval limits show that the PMis the best prediction limits combination method as it gives a hit rate of 0.955 which is very close to the target of 0.95. This modelling approach is expected to help in optimising the integration of solar power in the national grid.

Automatic diagnosis of vocal fold paresis by employing phonovibrogram features and machine learning methods

2010 ◽  
Vol 99 (3) ◽  
pp. 275-288 ◽  
Author(s):  
Daniel Voigt ◽  
Michael Döllinger ◽  
Anxiong Yang ◽  
Ulrich Eysholdt ◽  
Jörg Lohscheller
Keyword(s):  
Machine Learning ◽  
Vocal Fold ◽  
Learning Methods ◽  
Vocal Fold Paresis ◽  
Automatic Diagnosis ◽  
Machine Learning Methods

scholarly journals Automatic diagnosis of melanoma using machine learning methods on a spectroscopic system

2014 ◽  
Vol 14 (1) ◽  
Author(s):  
Lin Li ◽  
Qizhi Zhang ◽  
Yihua Ding ◽  
Huabei Jiang ◽  
Bruce H Thiers ◽  
...  
Keyword(s):  
Machine Learning ◽  
Learning Methods ◽  
Automatic Diagnosis ◽  
Machine Learning Methods

Automatic Fault Detection for Wind Turbines Using Single-Class Machine Learning Methods

2011 ◽  
Vol 58-60 ◽  
pp. 2602-2607
Author(s):  
Yi Hung Liu ◽  
Wei Zhi Lin ◽  
Jui Yiao Su ◽  
Yan Chen Liu
Keyword(s):  
Machine Learning ◽  
Fault Detection ◽  
Wind Turbine ◽  
Principal Component ◽  
Kernel Principal Component Analysis ◽  
Support Vector ◽  
Support Vector Data Description ◽  
Learning Methods ◽  
Single Class ◽  
Machine Learning Methods

This work adopts data related to the rotor efficiency of wind turbine to estimate the performance of wind turbine. To achieve this goal, two novel machine learning methods are adopted to build models for wind-turbine fault detection: one is the support vector data description (SVDD) and the other is the kernel principal component analysis (KPCA). The data collected from a normally-operating wind turbine are used to train models. In addition, we also build a health index using the KPCA reconstruction error, which can be used to predict the performance of a wind turbine when it operates online. The data used in our experiments were collected from a real wind turbine in Taiwan. Experiments results show that the model based on KPCA performs better than the one based on SVDD. The highest fault detection rate for KPCA model is higher than 98%. The results also indicate the validity of using rotor efficacy to predict the overall performance of a wind turbine.

Preventing Model Overfitting and Underfitting in Convolutional Neural Networks

2018 ◽  
Vol 10 (4) ◽  
pp. 19-28 ◽  
Author(s):  
Andrei Dmitri Gavrilov ◽  
Alex Jordache ◽  
Maya Vasdani ◽  
Jack Deng
Keyword(s):  
Machine Learning ◽  
Image Recognition ◽  
Recognition Performance ◽  
Square Lattice ◽  
Training Set ◽  
Learning Methods ◽  
Theoretical Understanding ◽  
The Past ◽  
Machine Learning Methods ◽  
The Impact

The current discourse in the machine learning domain converges to the agreement that machine learning methods emerged as some of the most prominent learning and classification approaches over the past decade. The CNN became one of most actively researched and broadly-applied deep machine learning methods. However, the training set has a large influence on the accuracy of a network and it is paramount to create an architecture that supports its maximum training and recognition performance. The problem considered in this article is how to prevent overfitting and underfitting. The deficiencies are addressed by comparing the statistics of CNN image recognition algorithms to the Ising model. Using a two-dimensional square-lattice array, the impact that the learning rate and regularization rate parameters have on the adaptability of CNNs for image classification are evaluated. The obtained results contribute to a better theoretical understanding of a CNN and provide concrete guidance on preventing model overfitting and underfitting when a CNN is applied for image recognition tasks.

Sign in / Sign up

Export Citation Format

Share Document