scholarly journals Breast Tumour Classification Using Ultrasound Elastography with Machine Learning: A Systematic Scoping Review

Cancers ◽  
2022 ◽  
Vol 14 (2) ◽  
pp. 367
Author(s):  
Ye-Jiao Mao ◽  
Hyo-Jung Lim ◽  
Ming Ni ◽  
Wai-Hin Yan ◽  
Duo Wai-Chi Wong ◽  
...  
Keyword(s):  
Machine Learning ◽  
Computer Vision ◽  
Deep Learning ◽  
Shear Wave ◽  
Shear Wave Elastography ◽  
Breast Tumour ◽  
Learning Model ◽  
Ultrasound Elastography ◽  
Tumour Classification ◽  
Strain Elastography

Ultrasound elastography can quantify stiffness distribution of tissue lesions and complements conventional B-mode ultrasound for breast cancer screening. Recently, the development of computer-aided diagnosis has improved the reliability of the system, whilst the inception of machine learning, such as deep learning, has further extended its power by facilitating automated segmentation and tumour classification. The objective of this review was to summarize application of the machine learning model to ultrasound elastography systems for breast tumour classification. Review databases included PubMed, Web of Science, CINAHL, and EMBASE. Thirteen (n = 13) articles were eligible for review. Shear-wave elastography was investigated in six articles, whereas seven studies focused on strain elastography (5 freehand and 2 Acoustic Radiation Force). Traditional computer vision workflow was common in strain elastography with separated image segmentation, feature extraction, and classifier functions using different algorithm-based methods, neural networks or support vector machines (SVM). Shear-wave elastography often adopts the deep learning model, convolutional neural network (CNN), that integrates functional tasks. All of the reviewed articles achieved sensitivity ³ 80%, while only half of them attained acceptable specificity ³ 95%. Deep learning models did not necessarily perform better than traditional computer vision workflow. Nevertheless, there were inconsistencies and insufficiencies in reporting and calculation, such as the testing dataset, cross-validation, and methods to avoid overfitting. Most of the studies did not report loss or hyperparameters. Future studies may consider using the deep network with an attention layer to locate the targeted object automatically and online training to facilitate efficient re-training for sequential data.

scholarly journals Strain Elastography - How To Do It?

2017 ◽  
Vol 03 (04) ◽  
pp. E137-E149 ◽  
Author(s):  
Christoph Dietrich ◽  
Richard Barr ◽  
André Farrokh ◽  
Manjiri Dighe ◽  
Michael Hocke ◽  
...  
Keyword(s):  
Shear Wave ◽  
Wave Speed ◽  
Shear Wave Elastography ◽  
Ultrasound Elastography ◽  
Tissue Stiffness ◽  
Shear Wave Speed ◽  
Strain Elastography ◽  
Advantages And Disadvantages ◽  
Similar Information ◽  
Qualitative Technique

AbstractTissue stiffness assessed by palpation for diagnosing pathology has been used for thousands of years. Ultrasound elastography has been developed more recently to display similar information on tissue stiffness as an image. There are two main types of ultrasound elastography, strain and shear wave. Strain elastography is a qualitative technique and provides information on the relative stiffness between one tissue and another. Shear wave elastography is a quantitative method and provides an estimated value of the tissue stiffness that can be expressed in either the shear wave speed through the tissues in meters/second, or converted to the Young’s modulus making some assumptions and expressed in kPa. Each technique has its advantages and disadvantages and they are often complimentary to each other in clinical practice. This article reviews the principles, technique, and interpretation of strain elastography in various organs. It describes how to optimize technique, while pitfalls and artifacts are also discussed.

scholarly journals A Study of incremental Learning model using deep neural network

2021 ◽  
Vol 10 (2) ◽  
pp. 658-663
Keyword(s):  
Neural Network ◽  
Machine Learning ◽  
Computer Vision ◽  
Deep Learning ◽  
Supervised Learning ◽  
Incremental Learning ◽  
Deep Neural Network ◽  
Learning Model

Deep learning has arrived with a great number of advances in the research of machine learning and its models. Due to the advancements recently in the field of deep learning and its models especially in the fields like NLP and Computer Vision in supervised learning for which we have to pre-definably decide a dataset and train our model completely on it and make predictions but in case if we have any new samples of data on which we want our model to be predicted then we have to completely retrain the model, which is computationally costly therefore to avoid re-training the model, we add the new samples on the previously learnt features from the pre- trained model called Incremental Learning. In the paper we proposed the system to overcome the process of catastrophic forgetting we introduced the concept of building on pre-trained model.

scholarly journals General advice in ultrasound based elastography of pediatric patients

2019 ◽  
Vol 21 (3) ◽  
pp. 315 ◽  
Author(s):  
Christoph F. Dietrich ◽  
Giovanna Ferraioli ◽  
Roxana Sirli ◽  
Alina Popescu ◽  
Ioan Sporea ◽  
...  
Keyword(s):  
Gastrointestinal Tract ◽  
Shear Wave ◽  
Pediatric Patients ◽  
Transient Elastography ◽  
Three Dimensional ◽  
Shear Wave Elastography ◽  
Ultrasound Elastography ◽  
Strain Elastography ◽  
Initial Results ◽  
Current Report

Ultrasound elastography including transient elastography (TE), point shear wave elastography, (pSWE) and two (three)- dimensional shear wave elastography (2D-SWE) have been introduced mainly for the evaluation of the liver. All the techniques are also feasible for the examination of spleen, whereas pSWE and 2D-SWE can be used for the assessment of the pancreas, kidney, gastrointestinal tract and other organs. Strain elastography also plays a role for non-liver applications. The aim of the current report is to highlight unique features and techniques for the elastographic examinations in children and to report initial results in non-liver applications

scholarly journals Non-invasive cuff-less blood pressure estimation using a hybrid deep learning model

2021 ◽  
Vol 53 (2) ◽  
Author(s):  
Sen Yang ◽  
Yaping Zhang ◽  
Siu-Yeung Cho ◽  
Ricardo Correia ◽  
Stephen P. Morgan
Keyword(s):  
Machine Learning ◽  
Blood Pressure ◽  
Deep Learning ◽  
Absolute Error ◽  
Learning Model ◽  
Physiological Measurement ◽  
British Hypertension Society ◽  
Non Invasive ◽  
Blood Pressure Estimation ◽  
Deep Learning Model

AbstractConventional blood pressure (BP) measurement methods have different drawbacks such as being invasive, cuff-based or requiring manual operations. There is significant interest in the development of non-invasive, cuff-less and continual BP measurement based on physiological measurement. However, in these methods, extracting features from signals is challenging in the presence of noise or signal distortion. When using machine learning, errors in feature extraction result in errors in BP estimation, therefore, this study explores the use of raw signals as a direct input to a deep learning model. To enable comparison with the traditional machine learning models which use features from the photoplethysmogram and electrocardiogram, a hybrid deep learning model that utilises both raw signals and physical characteristics (age, height, weight and gender) is developed. This hybrid model performs best in terms of both diastolic BP (DBP) and systolic BP (SBP) with the mean absolute error being 3.23 ± 4.75 mmHg and 4.43 ± 6.09 mmHg respectively. DBP and SBP meet the Grade A and Grade B performance requirements of the British Hypertension Society respectively.

scholarly journals Semantic segmentation of PolSAR image data using advanced deep learning model

2021 ◽  
Vol 11 (1) ◽  
Author(s):  
Rajat Garg ◽  
Anil Kumar ◽  
Nikunj Bansal ◽  
Manish Prateek ◽  
Shashi Kumar
Keyword(s):  
Machine Learning ◽  
Remote Sensing ◽  
Deep Learning ◽  
Urban Area ◽  
Urban Areas ◽  
Learning Algorithms ◽  
Semantic Segmentation ◽  
Learning Model ◽  
Machine Learning Algorithms ◽  
Deep Learning Model

AbstractUrban area mapping is an important application of remote sensing which aims at both estimation and change in land cover under the urban area. A major challenge being faced while analyzing Synthetic Aperture Radar (SAR) based remote sensing data is that there is a lot of similarity between highly vegetated urban areas and oriented urban targets with that of actual vegetation. This similarity between some urban areas and vegetation leads to misclassification of the urban area into forest cover. The present work is a precursor study for the dual-frequency L and S-band NASA-ISRO Synthetic Aperture Radar (NISAR) mission and aims at minimizing the misclassification of such highly vegetated and oriented urban targets into vegetation class with the help of deep learning. In this study, three machine learning algorithms Random Forest (RF), K-Nearest Neighbour (KNN), and Support Vector Machine (SVM) have been implemented along with a deep learning model DeepLabv3+ for semantic segmentation of Polarimetric SAR (PolSAR) data. It is a general perception that a large dataset is required for the successful implementation of any deep learning model but in the field of SAR based remote sensing, a major issue is the unavailability of a large benchmark labeled dataset for the implementation of deep learning algorithms from scratch. In current work, it has been shown that a pre-trained deep learning model DeepLabv3+ outperforms the machine learning algorithms for land use and land cover (LULC) classification task even with a small dataset using transfer learning. The highest pixel accuracy of 87.78% and overall pixel accuracy of 85.65% have been achieved with DeepLabv3+ and Random Forest performs best among the machine learning algorithms with overall pixel accuracy of 77.91% while SVM and KNN trail with an overall accuracy of 77.01% and 76.47% respectively. The highest precision of 0.9228 is recorded for the urban class for semantic segmentation task with DeepLabv3+ while machine learning algorithms SVM and RF gave comparable results with a precision of 0.8977 and 0.8958 respectively.

scholarly journals Elastic Modulus and Elasticity Ratio of Malignant Breast Lesions with Shear Wave Ultrasound Elastography: Variations with Different Region of Interest and Lesion Size

Diagnostics ◽  
2021 ◽  
Vol 11 (6) ◽  
pp. 1015
Author(s):  
Antonio Bulum ◽  
Gordana Ivanac ◽  
Eugen Divjak ◽  
Iva Biondić Špoljar ◽  
Martina Džoić Dominković ◽  
...  
Keyword(s):  
Elastic Modulus ◽  
Shear Wave ◽  
Large Diameter ◽  
Small Diameter ◽  
Shear Wave Elastography ◽  
Lesion Size ◽  
Ultrasound Elastography ◽  
Breast Lesions ◽  
Malignant Breast ◽  
The Impact

Shear wave elastography (SWE) is a type of ultrasound elastography with which the elastic properties of breast tissues can be quantitatively assessed. The purpose of this study was to determine the impact of different regions of interest (ROI) and lesion size on the performance of SWE in differentiating malignant breast lesions. The study included 150 female patients with histopathologically confirmed malignant breast lesions. Minimal (Emin), mean (Emean), maximal (Emax) elastic modulus and elasticity ratio (e-ratio) values were measured using a circular ROI size of 2, 4 and 6 mm diameters and the lesions were divided into large (diameter ≥ 15 mm) and small (diameter < 15 mm). Highest Emin, Emean and e-ratio values and lowest variability were observed when using the 2 mm ROI. Emax values did not differ between different ROI sizes. Larger lesions had significantly higher Emean and Emax values, but there was no difference in e-ratio values between lesions of different sizes. In conclusion, when measuring the Emin, Emean and e-ratio of malignant breast lesions using SWE the smallest possible ROI size should be used regardless of lesion size. ROI size has no impact on Emax values while lesion size has no impact on e-ratio values.

scholarly journals Implementation of conventional communication system in deep learning

2017 ◽  
Vol 7 (1.1) ◽  
pp. 696
Author(s):  
Satyanarayana P ◽  
Charishma Devi. V ◽  
Sowjanya P ◽  
Satish Babu ◽  
N Syam Kumar ◽  
...  
Keyword(s):  
Machine Learning ◽  
Computer Vision ◽  
Communication Network ◽  
Deep Learning ◽  
Communication System ◽  
Communication Systems ◽  
Physical Layer ◽  
Learning Capacity ◽  
Constrained Learning ◽  
Complex Channel

Machine learning (ML) has been broadly connected to the upper layers of communication systems for different purposes, for example, arrangement of cognitive radio and communication network. Nevertheless, its application to the physical layer is hindered by complex channel conditions and constrained learning capacity of regular ML algorithms. Deep learning (DL) has been as of late connected for some fields, for example, computer vision and normal dialect preparing, given its expressive limit and advantageous enhancement ability. This paper describes about a novel use of DL for the physical layer. By deciphering a communication system as an auto encoder, we build up an essential better approach to consider communication system outline as a conclusion to-end reproduction undertaking that tries to together enhance transmitter and receiver in a solitary procedure. This DL based technique demonstrates promising execution change than traditional communication system.  

scholarly journals A Hybrid Prognostics Deep Learning Model for Remaining Useful Life Prediction

Electronics ◽  
2020 ◽  
Vol 10 (1) ◽  
pp. 39
Author(s):  
Zhiyuan Xie ◽  
Shichang Du ◽  
Jun Lv ◽  
Yafei Deng ◽  
Shiyao Jia
Keyword(s):  
Machine Learning ◽  
Deep Learning ◽  
Learning Model ◽  
Recurrent Network ◽  
Remaining Useful Life ◽  
Support Vector ◽  
Second Phase ◽  
Learning Methods ◽  
Useful Life ◽  
Deep Learning Model

Remaining Useful Life (RUL) prediction is significant in indicating the health status of the sophisticated equipment, and it requires historical data because of its complexity. The number and complexity of such environmental parameters as vibration and temperature can cause non-linear states of data, making prediction tremendously difficult. Conventional machine learning models such as support vector machine (SVM), random forest, and back propagation neural network (BPNN), however, have limited capacity to predict accurately. In this paper, a two-phase deep-learning-model attention-convolutional forget-gate recurrent network (AM-ConvFGRNET) for RUL prediction is proposed. The first phase, forget-gate convolutional recurrent network (ConvFGRNET) is proposed based on a one-dimensional analog long short-term memory (LSTM), which removes all the gates except the forget gate and uses chrono-initialized biases. The second phase is the attention mechanism, which ensures the model to extract more specific features for generating an output, compensating the drawbacks of the FGRNET that it is a black box model and improving the interpretability. The performance and effectiveness of AM-ConvFGRNET for RUL prediction is validated by comparing it with other machine learning methods and deep learning methods on the Commercial Modular Aero-Propulsion System Simulation (C-MAPSS) dataset and a dataset of ball screw experiment.

Deep Learning for the Automated Classification of Functional Brain Networks in fMRI (Preprint)

2021 ◽  
Author(s):  
Lukman Ismael ◽  
Pejman Rasti ◽  
Florian Bernard ◽  
Philippe Menei ◽  
Aram Ter Minassian ◽  
...  
Keyword(s):  
Machine Learning ◽  
Deep Learning ◽  
Learning Algorithms ◽  
Brain Networks ◽  
Learning Model ◽  
Machine Learning Algorithms ◽  
Functional Networks ◽  
Functional Brain ◽  
Functional Brain Networks ◽  
Deep Learning Model

BACKGROUND The functional MRI (fMRI) is an essential tool for the presurgical planning of brain tumor removal, allowing the identification of functional brain networks in order to preserve the patient’s neurological functions. One fMRI technique used to identify the functional brain network is the resting-state-fMRI (rsfMRI). However, this technique is not routinely used because of the necessity to have a expert reviewer to identify manually each functional networks. OBJECTIVE We aimed to automatize the detection of brain functional networks in rsfMRI data using deep learning and machine learning algorithms METHODS We used the rsfMRI data of 82 healthy patients to test the diagnostic performance of our proposed end-to-end deep learning model to the reference functional networks identified manually by 2 expert reviewers. RESULTS Experiment results show the best performance of 86% correct recognition rate obtained from the proposed deep learning architecture which shows its superiority over other machine learning algorithms that were equally tested for this classification task. CONCLUSIONS The proposed end-to-end deep learning model was the most performant machine learning algorithm. The use of this model to automatize the functional networks detection in rsfMRI may allow to broaden the use of the rsfMRI, allowing the presurgical identification of these networks and thus help to preserve the patient’s neurological status. CLINICALTRIAL Comité de protection des personnes Ouest II, decision reference CPP 2012-25)

Sign in / Sign up

Export Citation Format

Share Document