Layer-Wise Tumor Segmentation of Breast Images Using Convolutional Neural Networks

2021 ◽  
pp. 70-84
Author(s):  
Nishanth Krishnaraj ◽  
A. Mary Mekala ◽  
Bhaskar M. ◽  
Ruban Nersisson ◽  
Alex Noel Joseph Raj
Keyword(s):  
Breast Cancer ◽  
Neural Network ◽  
Network Architecture ◽  
Breast Imaging ◽  
Breast Tissue ◽  
Imaging Techniques ◽  
Tumor Segmentation ◽  
Cancer Type ◽  
The Neural Network ◽  
Life Threatening

Early prediction of cancer type has become very crucial. Breast cancer is common to women and it leads to life threatening. Several imaging techniques have been suggested for timely detection and treatment of breast cancer. More research findings have been done to accurately detect the breast cancer. Automated whole breast ultrasound (AWBUS) is a new breast imaging technology that can render the entire breast anatomy in 3-D volume. The tissue layers in the breast are segmented and the type of lesion in the breast tissue can be identified which is essential for cancer detection. In this chapter, a u-net convolutional neural network architecture is used to implement the segmentation of breast tissues from AWBUS images into the different layers, that is, epidermis, subcutaneous, and muscular layer. The architecture was trained and tested with the AWBUS dataset images. The performance of the proposed scheme was based on accuracy, loss and the F1 score of the neural network that was calculated for each layer of the breast tissue.

scholarly journals Enhancement of Multimodal Microwave-Ultrasound Breast Imaging Using a Deep-Learning Technique

Sensors ◽  
2019 ◽  
Vol 19 (18) ◽  
pp. 4050 ◽  
Author(s):  
Vahab Khoshdel ◽  
Ahmed Ashraf ◽  
Joe LoVetri
Keyword(s):  
Neural Network ◽  
Deep Learning ◽  
Breast Imaging ◽  
Reconstruction Error ◽  
Tumor Segmentation ◽  
Source Inversion ◽  
The Neural Network ◽  
Contrast Source Inversion ◽  
Imaging Artifacts ◽  
Complex Valued

We present a deep learning method used in conjunction with dual-modal microwave-ultrasound imaging to produce tomographic reconstructions of the complex-valued permittivity of numerical breast phantoms. We also assess tumor segmentation performance using the reconstructed permittivity as a feature. The contrast source inversion (CSI) technique is used to create the complex-permittivity images of the breast with ultrasound-derived tissue regions utilized as prior information. However, imaging artifacts make the detection of tumors difficult. To overcome this issue we train a convolutional neural network (CNN) that takes in, as input, the dual-modal CSI reconstruction and attempts to produce the true image of the complex tissue permittivity. The neural network consists of successive convolutional and downsampling layers, followed by successive deconvolutional and upsampling layers based on the U-Net architecture. To train the neural network, the input-output pairs consist of CSI’s dual-modal reconstructions, along with the true numerical phantom images from which the microwave scattered field was synthetically generated. The reconstructed permittivity images produced by the CNN show that the network is not only able to remove the artifacts that are typical of CSI reconstructions, but can also improve the detectability of tumors. The performance of the CNN is assessed using a four-fold cross-validation on our dataset that shows improvement over CSI both in terms of reconstruction error and tumor segmentation performance.

SCORING MODELING BASED ON NEURAL NETWORKS FOR DETERMINING A BANK BORROWER'S RATING

2020 ◽  
Vol 2020 (10) ◽  
pp. 54-62
Author(s):  
Oleksii VASYLIEV ◽  
Keyword(s):  
Neural Network ◽  
Neural Networks ◽  
Network Architecture ◽  
Statistical Data ◽  
Activation Function ◽  
Decision Making Process ◽  
Neural Network Architecture ◽  
Acceptable Accuracy ◽  
The Neural Network ◽  
Sigmoid Activation Function

The problem of applying neural networks to calculate ratings used in banking in the decision-making process on granting or not granting loans to borrowers is considered. The task is to determine the rating function of the borrower based on a set of statistical data on the effectiveness of loans provided by the bank. When constructing a regression model to calculate the rating function, it is necessary to know its general form. If so, the task is to calculate the parameters that are included in the expression for the rating function. In contrast to this approach, in the case of using neural networks, there is no need to specify the general form for the rating function. Instead, certain neural network architecture is chosen and parameters are calculated for it on the basis of statistical data. Importantly, the same neural network architecture can be used to process different sets of statistical data. The disadvantages of using neural networks include the need to calculate a large number of parameters. There is also no universal algorithm that would determine the optimal neural network architecture. As an example of the use of neural networks to determine the borrower's rating, a model system is considered, in which the borrower's rating is determined by a known non-analytical rating function. A neural network with two inner layers, which contain, respectively, three and two neurons and have a sigmoid activation function, is used for modeling. It is shown that the use of the neural network allows restoring the borrower's rating function with quite acceptable accuracy.

Spatial Variability Aware Deep Neural Networks (SVANN): A General Approach

2021 ◽  
Vol 12 (6) ◽  
pp. 1-21
Author(s):  
Jayant Gupta ◽  
Carl Molnar ◽  
Yiqun Xie ◽  
Joe Knight ◽  
Shashi Shekhar
Keyword(s):  
Neural Network ◽  
Spatial Variability ◽  
Network Architecture ◽  
Network Models ◽  
Neural Network Architecture ◽  
Neural Network Models ◽  
Climatic Zones ◽  
The Neural Network ◽  
Plant Hardiness ◽  
Interpretation Model

Spatial variability is a prominent feature of various geographic phenomena such as climatic zones, USDA plant hardiness zones, and terrestrial habitat types (e.g., forest, grasslands, wetlands, and deserts). However, current deep learning methods follow a spatial-one-size-fits-all (OSFA) approach to train single deep neural network models that do not account for spatial variability. Quantification of spatial variability can be challenging due to the influence of many geophysical factors. In preliminary work, we proposed a spatial variability aware neural network (SVANN-I, formerly called SVANN ) approach where weights are a function of location but the neural network architecture is location independent. In this work, we explore a more flexible SVANN-E approach where neural network architecture varies across geographic locations. In addition, we provide a taxonomy of SVANN types and a physics inspired interpretation model. Experiments with aerial imagery based wetland mapping show that SVANN-I outperforms OSFA and SVANN-E performs the best of all.

AUTOMATIC SEGMENTATION OF BREAST TISSUE THERMAL IMAGES

2018 ◽  
Vol 30 (03) ◽  
pp. 1850024 ◽  
Author(s):  
Zeinab Heidari ◽  
Mehrdad Dadgostar ◽  
Zahra Einalou
Keyword(s):  
Breast Cancer ◽  
Image Processing ◽  
Breast Imaging ◽  
Breast Tissue ◽  
Early Stage ◽  
Automatic Segmentation ◽  
Image Data ◽  
Thermal Images ◽  
Early Stages ◽  
Invasive Method

Breast cancer is one of the main causes of women’s death. Thermal breast imaging is one the non-invasive method for cancer at early stage diagnosis. In contrast to mammography this method is cheap and painless and it can be used during pregnancy while ionized beams are not used. Specialists are seeking new ways to diagnose the cancer in early stages. Segmentation of the breast tissue is one of the most indispensable stages in most of the cancer diagnosis methods. By the advancement of infrared precise cameras, new and fast computers and nouvelle image processing approaches, it is feasible to use thermal imaging for diagnosis of breast cancer at early stages. Since the breast form is different in individuals, image segmentation is a hard task and semi-automatic or manual methods are usual in investigations. In this research the image data base of DMR-IR has been utilized and a now automatic approach has been proposed which does not need learning. Data were included 159 gray images used by dynamic protocol (132 healthy and 27 patients). In this study, by combination of different image processing methods, the segmentation of thermal images of the breast tissues have been completed automatically and results show the proper performance of recommended method.

An artificial neural network approach to discrete-event simulation

1995 ◽  
Vol 9 (1) ◽  
pp. 37-49 ◽  
Author(s):  
Ian Flood ◽  
Kenneth Worley
Keyword(s):  
Neural Network ◽  
Discrete Event Simulation ◽  
Network Architecture ◽  
Discrete Event ◽  
Network Approach ◽  
Neural Network Approach ◽  
Event Simulation ◽  
The Neural Network ◽  
Component Processes ◽  
And Performance

AbstractThis paper proposes and evaluates a neural network-based method for simulating manufacturing processes that exhibit both noncontinuous and stochastic behavior processes more conventionally modeled, using discrete-event simulation algorithms. The incentive for developing the technique is its potential for rapid execution of a simulation through parallel processing, and facilitation of the development and improvement of models particularly where there is limited theory describing the dependence between component processes. A brief introduction is provided to a radial-Gaussian neural network architecture and training process, the system adopted for the work presented in this paper. A description of the basic approach proposed for applying this technology to simulation is then described. This involves the use of a modularized neural network approach to model construction and the prediction of the occurrence of events using information retained from several previous states of the simulation. A class of earth-moving systems, comprising a push-dozer and a fleet of scrapers, is used as the basis for assessing the viability and performance of the proposed approach. A series of experiments show the neural network to be capable of both capturing the characteristic behavior and making an accurate prediction of production rates of scraper-based earth-moving systems. The paper concludes with an indication of some areas for further development and evaluation of the technique.

scholarly journals SD-UNet: Stripping down U-Net for Segmentation of Biomedical Images on Platforms with Low Computational Budgets

Diagnostics ◽  
2020 ◽  
Vol 10 (2) ◽  
pp. 110 ◽  
Author(s):  
Pius Kwao Gadosey ◽  
Yujian Li ◽  
Enock Adjei Agyekum ◽  
Ting Zhang ◽  
Zhaoying Liu ◽  
...  
Keyword(s):  
Neural Network ◽  
Network Architecture ◽  
Tumor Segmentation ◽  
Biomedical Data ◽  
Electron Microscopic ◽  
Brain Tumor Segmentation ◽  
Current State ◽  
Expected Performance ◽  
Computational Resources ◽  
Medical Segmentation

During image segmentation tasks in computer vision, achieving high accuracy performance while requiring fewer computations and faster inference is a big challenge. This is especially important in medical imaging tasks but one metric is usually compromised for the other. To address this problem, this paper presents an extremely fast, small and computationally effective deep neural network called Stripped-Down UNet (SD-UNet), designed for the segmentation of biomedical data on devices with limited computational resources. By making use of depthwise separable convolutions in the entire network, we design a lightweight deep convolutional neural network architecture inspired by the widely adapted U-Net model. In order to recover the expected performance degradation in the process, we introduce a weight standardization algorithm with the group normalization method. We demonstrate that SD-UNet has three major advantages including: (i) smaller model size (23x smaller than U-Net); (ii) 8x fewer parameters; and (iii) faster inference time with a computational complexity lower than 8M floating point operations (FLOPs). Experiments on the benchmark dataset of the Internatioanl Symposium on Biomedical Imaging (ISBI) challenge for segmentation of neuronal structures in electron microscopic (EM) stacks and the Medical Segmentation Decathlon (MSD) challenge brain tumor segmentation (BRATs) dataset show that the proposed model achieves comparable and sometimes better results compared to the current state-of-the-art.

scholarly journals ON SOME BOUNDS OF THE MINIMUM EDGE DOMINATING ENERGY OF A GRAPH

2021 ◽  
Vol 12 (4) ◽  
pp. 1285-1296
Author(s):  
Dr. Gauri Ghule , Et. al.
Keyword(s):  
Neural Network ◽  
Network Architecture ◽  
Fuzzy Controller ◽  
Back Propagation ◽  
Back Propagation Neural Network ◽  
Superior Performance ◽  
Fuzzy Classifier ◽  
Manual Intervention ◽  
The Neural Network ◽  
Hidden Neurons

Number of hidden neurons is necessary constant for tuning the neural network to achieve superior performance. These parameters are set manually through experimentation. The performance of the network is evaluated repeatedly to choose the best input parameters.Random selection of hidden neurons may cause underfitting or overfitting of the network. We propose a novel fuzzy controller for finding the optimal value of hidden neurons automatically. The hybrid classifier helps to design competent neural network architecture, eliminating manual intervention for setting the input parameters. The effectiveness of tuning the number of hidden neurons automatically on the convergence of a back-propagation neural network, is verified on speech data. The experimental outcomes demonstrate that the proposed Neuro-Fuzzy classifier can be viably utilized for speech recognition with maximum classification accuracy.

scholarly journals Handheld diffuse optical breast scanner probe for cross-sectional imaging of breast tissue

2019 ◽  
Vol 12 (02) ◽  
pp. 1950008 ◽  
Author(s):  
Majid Shokoufi ◽  
Farid Golnaraghi
Keyword(s):  
Breast Cancer ◽  
Breast Imaging ◽  
Breast Tissue ◽  
Reconstruction Algorithm ◽  
Breast Cancer Diagnosis ◽  
Array Detector ◽  
Light Sources ◽  
Compact Structure ◽  
Cross Sectional

Diffuse optical spectroscopy is a relatively new, noninvasive and nonionizing technique for breast cancer diagnosis. In the present study, we have introduced a novel handheld diffuse optical breast scan (DOB-Scan) probe to measure optical properties of the breast in vivo and create functional and compositional images of the tissue. In addition, the probe gives more information about breast tissue’s constituents, which helps distinguish a healthy and cancerous tissue. Two symmetrical light sources, each including four different wavelengths, are used to illuminate the breast tissue. A high-resolution linear array detector measures the intensity of the back-scattered photons at different radial destinations from the illumination sources on the surface of the breast tissue, and a unique image reconstruction algorithm is used to create four cross-sectional images for four different wavelengths. Different from fiber optic-based illumination techniques, the proposed method in this paper integrates multi-wavelength light-emitting diodes to act as pencil beam sources into a scattering medium like breast tissue. This unique design and its compact structure reduce the complexity, size and cost of a potential probe. Although the introduced technique miniaturizes the probe, this study points to the reliability of this technique in the phantom study and clinical breast imaging. We have received ethical approval to test the DOB-Scan probe on patients and we are currently testing the DOB-Scan probe on subjects who are diagnosed with breast cancer.

Advanced Imaging Techniques for the Detection of Breast Cancer

2012 ◽  
pp. 65-69 ◽  
Author(s):  
Maxine Jochelson
Keyword(s):  
Breast Cancer ◽  
High Risk ◽  
Breast Imaging ◽  
Early Stage ◽  
Imaging Techniques ◽  
Breast Cancer Mortality ◽  
Digital Breast Tomosynthesis ◽  
Ct Scanning ◽  
High Risk Women ◽  
Contrast Enhanced

Overview: Mammography is the only breast imaging examination that has been shown to reduce breast cancer mortality. Population-based sensitivity is 75% to 80%, but sensitivity in high-risk women with dense breasts is only in the range of 50%. Breast ultrasound and contrast-enhanced breast magnetic resonance imaging (MRI) have become additional standard modalities used in the diagnosis of breast cancer. In high-risk women, ultrasound is known to detect approximately four additional cancers per 1,000 women. MRI is exquisitely sensitive for the detection of breast cancer. In high-risk women, it finds an additional four to five cancers per 100 women. However, both ultrasound and MRI are also known to lead to a large number of additional benign biopsies and short-term follow-up examinations. Many new breast imaging tools have improved and are being developed to improve on our current ability to diagnose early-stage breast cancer. These can be divided into two groups. The first group is those that are advances in current techniques, which include digital breast tomosynthesis and contrast-enhanced mammography and ultrasound with elastography or microbubbles. The other group includes new breast imaging platforms such as breast computed tomography (CT) scanning and radionuclide breast imaging. These are exciting advances. However, in this era of cost and radiation containment, it is imperative to look at all of them objectively to see which will provide clinically relevant additional information.

Sign in / Sign up

Export Citation Format

Share Document