Filters








44 Hits in 4.7 sec

Learning contextual relationships in mammograms using a hierarchical pyramid neural network

P. Sajda, C. Spence, J. Pearson
2002 IEEE Transactions on Medical Imaging  
This paper describes a pattern recognition architecture, which we term hierarchical pyramid/neural network (HPNN), that learns to exploit image structure at multiple resolutions for detecting clinically  ...  The HPNN architecture consists of a hierarchy of neural networks, each network receiving feature inputs at a given scale as well as features constructed by networks lower in the hierarchy.  ...  Overview of Hierarchical Pyramid/Neural Network Architecture We have developed a pattern recognition architecture that learns contextual relationships between structure in images for detection and classification  ... 
doi:10.1109/42.996342 pmid:11989848 fatcat:6qx77c7pcjdkreausdpuv2y7ce

Integrating neural networks with image pyramids to learn target context

Paul Sajda, Clay D. Spence, Steve Hsu, John C. Pearson
1995 Neural Networks  
First, it is shown that a neural network constructed using relatively simple pyramid features is a more effective detector, in terms of its sensitivity, than a network which utilizes more complex object-taned  ...  Contextual relationships derived both from low-resolution imagery and supplemental data can be learned and used to improve the accuracy of detection.  ...  ) z We have used the neural network/pyramid system for detecting microcalcifications, cues to breast carcinomas, in mammograms.  ... 
doi:10.1016/0893-6080(95)00067-4 fatcat:3weeriqixncgrmmjmsozdxw774

Multi-Resolution and Wavelet Representations for Identifying Signatures of Disease

Paul Sajda, Andrew Laine, Yehoshua Zeevi
2002 Disease Markers  
These transforms construct a general representation of signals which can be used in detection, diagnosis and treatment monitoring.  ...  in a joint time-frequency and/or space-frequency domain.  ...  In all cases, integration is done using a single network. Sajda et al. [30] [31] [32] have developed a multiresolution neural network called the Hierarchical Pyramid Neural Network (HPNN).  ... 
doi:10.1155/2002/108741 pmid:14646044 pmcid:PMC3851637 fatcat:3igejnra3res3k7m3vhb3sklii

On Digital Mammogram Segmentation and Microcalcification Detection Using Multiresolution Wavelet Analysis

C.H. Chen, G.G. Lee
1997 Graphical Models and Image Processing  
The effectiveness of the mammograms were observed in 10 to 30% of the women approach has been tested with a number of mammographic who actually have breast cancer [2, 3] .  ...  The hierarchical multiresolution wavelet inforsometimes no larger than 0.1 mm in size and are responsimation in conjunction with the contextual information of the ble for the detection of approximately  ...  Parts a and c of Figs. 4 and 5 show the result of does not use the contextual model, however, achieved only mammogram digitization with varying sizes and shapes of a sensitivity of 80% with a specificity  ... 
doi:10.1006/gmip.1997.0443 fatcat:nwm45ft4hvg7foigtsl4v3wu2a

Two-stage multi-scale breast mass segmentation for full mammogram analysis without user intervention [article]

Yutong Yan, Pierre-Henri Conze, Gwenolé Quellec, Mathieu Lamard, Béatrice Cochener, Gouenou Coatrieux
2020 arXiv   pre-print
Second, a convolutional encoder-decoder network using nested and dense skip connections is employed to fine-delineate candidate masses.  ...  In this work, we present a two-stage multi-scale pipeline that provides accurate mass contours from high-resolution full mammograms.  ...  All these tasks are now routinely carried out in a purely data-driven fashion using convolutional neural networks (CNN).  ... 
arXiv:2002.12079v2 fatcat:4vrk7ap3fffftf72666mtvvloa

Dense Convolutional Network and Its Application in Medical Image Analysis

Tao Zhou, XinYu Ye, HuiLing Lu, Xiaomin Zheng, Shi Qiu, YunCan Liu, Chen Li
2022 BioMed Research International  
Dense convolutional network (DenseNet) is a hot topic in deep learning research in recent years, which has good applications in medical image analysis.  ...  The network structures of DenseNet are systematically summarized in this paper, which has certain positive significance for the research and development of DenseNet.  ...  Both methods learn mapping relationships in single-scale image space and cannot provide SR information across different scale of features, and although there is a Laplace pyramid structure to progressively  ... 
doi:10.1155/2022/2384830 pmid:35509707 pmcid:PMC9060995 fatcat:7jp3tmtph5hk5gthgcomeccnte

A Decision Support System (DSS) for Breast Cancer Detection Based on Invariant Feature Extraction, Classification, and Retrieval of Masses of Mammographic Images [chapter]

Mahmudur Rahman, Nuh Alpaslan
2018 Medical Imaging and Image-Guided Interventions [Working Title]  
and eigenvalues of the Hessian matrix in a histogram of oriented gradients (HOG), and finally classification and retrieval are performed based on using Support Vector Machines (SVM) and Extreme Learning  ...  This paper presents an integrated system for the breast cancer detection from mammograms based on automated mass detection, classification, and retrieval with a goal to support decision-making by retrieving  ...  On the other hand, ELM is a single-hidden layer feed-forward neural network (SLFNs) learning algorithm [48] .  ... 
doi:10.5772/intechopen.81119 fatcat:vgvg2xrqebht7b5caaij3fn5ny

Improved skin cancer detection using CNN

Juveriya Shaikh, Rubeena Khan, Yashwant Ingle, Nuzhat Shaikh
2022 International Journal of Health Sciences  
The goal of this article is to utilize a convolutional neural network to segment skin lesion images.  ...  A variety of machine learning techniques have been developed in the past to detect such malignancies before they worsen.  ...  Back propagation or feed-forward architecture is used by a neural network to learn the weights present at each network connection/link.  ... 
doi:10.53730/ijhs.v6ns2.8762 fatcat:bs4pgy3ju5c4vc2aclkchlcq64

U-net and its variants for medical image segmentation: A review of theory and applications

Nahian Siddique, Sidike Paheding, Colin P. Elkin, Vijay Devabhaktuni
2021 IEEE Access  
Furthermore, while U-net is largely a segmentation tool, there have been instances of the use of U-net in other applications.  ...  We also discuss the many innovations that have advanced in deep learning and discuss how these tools facilitate U-net.  ...  This results in a network resembling a u-shape and, more importantly, propagates contextual information along the network, which allows it to segment objects in an area using context from a larger overlapping  ... 
doi:10.1109/access.2021.3086020 fatcat:b6cd45zsojfwhoer3sw5euei5e

Deep Semantic Segmentation of Natural and Medical Images: A Review [article]

Saeid Asgari Taghanaki, Kumar Abhishek, Joseph Paul Cohen, Julien Cohen-Adad, Ghassan Hamarneh
2020 arXiv   pre-print
In the medical image analysis domain, image segmentation can be used for image-guided interventions, radiotherapy, or improved radiological diagnostics.  ...  In this review, we categorize the leading deep learning-based medical and non-medical image segmentation solutions into six main groups of deep architectural, data synthesis-based, loss function-based,  ...  (2015) using a spatial pyramid pooling module or encode-decoder structure ( Figure 10 ) are used in deep neural networks for semantic segmentation tasks.  ... 
arXiv:1910.07655v3 fatcat:uxrrmb3jofcsvnkfkuhfwi62yq

Image Similarity to Improve the Classification of Breast Cancer Images

Dave Tahmoush
2009 Algorithms  
In this work, image feature clustering is done to reduce the noise and the feature space, and the results are used in a distance function that uses a learned threshold in order to produce a classification  ...  Only the cancerous part of the image is relevant, so the techniques must learn to recognize cancer in noisy mammograms and extract features from that cancer to appropriately classify images.  ...  Learning techniques have included support vector machines [48] and neural networks [46] .  ... 
doi:10.3390/a2041503 fatcat:zlpiydtzovdptgfaxgt5duqo5a

Medical Image Segmentation Using Deep Learning: A Survey [article]

Risheng Wang, Tao Lei, Ruixia Cui, Bingtao Zhang, Hongying Meng, Asoke K. Nandi
2021 arXiv   pre-print
Deep learning has been widely used for medical image segmentation and a large number of papers has been presented recording the success of deep learning in the field.  ...  In this paper, we present a comprehensive thematic survey on medical image segmentation using deep learning techniques. This paper makes two original contributions.  ...  However, most of medical images are 3D volume data, but a 2D convolutional neural network cannot learn temporal information in the third dimension, and a 3D convolutional neural network often requires  ... 
arXiv:2009.13120v3 fatcat:ntgbqwkz55axrjum72elbm6rry

Medical image segmentation using deep learning: A survey

Risheng Wang, Tao Lei, Ruixia Cui, Bingtao Zhang, Hongying Meng, Asoke K. Nandi
2022 IET Image Processing  
Deep learning has been widely used for medical image segmentation and a large number of papers has been presented recording the success of deep learning in the field.  ...  For supervised learning approaches, we analyse literatures in three aspects: the selection of backbone networks, the design of network blocks, and the improvement of loss functions.  ...  However, most of medical images are 3D volume data, but a 2D convolutional neural network cannot learn temporal information in the third dimension, and a 3D convolutional neural network often requires  ... 
doi:10.1049/ipr2.12419 fatcat:zvgj3vdzqbfbzjoglgmtnn6ukq

Review on skin cancer detection using AI

Yashwant S. Ingle, N. F. Shaikh
2022 International Journal of Health Sciences  
In this paper there is a review on ways can detect disease and alert us before something becomes serious.  ...  Machine learning will be utilized to determine the ailment and assist us in detecting the outcome. Support vector machine is the most prevalently used classification techniques.  ...  it..Back propagation or feed-forward architecture is used by a neural network to learn the weights present at each network connection/link.For the underlying dataset, both architectures use a distinct  ... 
doi:10.53730/ijhs.v6ns2.5008 fatcat:2f6m6yyvybatzlenccml4tjlqe

PeMNet for Pectoral Muscle Segmentation

Xiang Yu, Shui-Hua Wang, Juan Manuel Górriz, Xian-Wei Jiang, David S. Guttery, Yu-Dong Zhang
2022 Biology  
Here, we proposed a novel deep learning framework, which we code-named PeMNet, for breast pectoral muscle segmentation in mammography images.  ...  By doing so, CAMs in early stages of a deep convolution network can be effectively passed on to later stages of the network and therefore leads to better information usage.  ...  In this study, we used transfer learning technique for view classification as we used GoogLeNet trained on a natural image classification tasks as the source network instead of training it from scratch  ... 
doi:10.3390/biology11010134 pmid:35053131 pmcid:PMC8772963 fatcat:2lrhawvxkrc65m56whja4ext3q
« Previous Showing results 1 — 15 out of 44 results