Book ChapterDOI
An Intelligent Internet of Medical Things with Deep Learning Based Automated Breast Cancer Detection and Classification Model
Mahantesh Mathapati,S. Chidambaranathan,Abdul Wahid Nasir,G. Vimalarani,S. Sheeba Rani,T. Gopalakrishnan +5 more
- pp 181-193
TLDR
An intelligent IoMT based breast cancer detection and diagnosis using deep learning model that has the capability of effectively detecting and classifying breast cancer from mammogram images is presented.Abstract:
In recent decades, breast cancer (BC) is a significant cause of high mortality rate among women. The earlier identification of breast cancer helps to increase the survival rate by the use of appropriate medications. At the same time, internet of medical things (IoMT) and digital mammography finds helpful to diagnose breast cancer effectively in the beginning level itself. This paper presents an intelligent IoMT based breast cancer detection and diagnosis using deep learning model. IoMT based image acquisition process takes place to gather the digital mammogram images. The proposed model performs a set of processes namely preprocessing, K-means clustering based segmentation, local binary pattern (LBP) based feature extraction and deep neural network (DNN) based classification. The presented LBP-DNN model has the capability of effectively detecting and classifying breast cancer from mammogram images. The LBP-DNN model has been validated using MIAS database and an extensive comparative analysis is carried out to evaluate its performance. The experimental results ensured the superior performance of the LBP-DNN model with the maximum sensitivity of 71.64%, specificity of 75.87% and accuracy of 70.53%.read more
Citations
More filters
Journal ArticleDOI
Cognitive Computing-Based Mammographic Image Classification on an Internet of Medical
TL;DR: In this article , a deep learning-enabled multi-objective mayfly optimization algorithm (DL-MOMFO) was proposed for breast cancer diagnosis and classification in the IoMT environment.
Journal ArticleDOI
Extended Mammogram Classification From Textural Features
TL;DR: In this paper , an extended computer-aided diagnosis system for the classification of mammograms into three classes (normal, benign and malignant) was presented, and the performance of the system was evaluated for two different mammogram databases (MIAS and DDSM) in order to assess its robustness.
Journal ArticleDOI
Deep learning enabled smart charging technology for electric vehicles
TL;DR: In this paper , a deep learning algorithm-based smart charging strategy is proposed to minimize the total energy cost of the vehicle by making charging decisions considering demand time series, pricing, environment, driving, and other auxiliary data.
Journal ArticleDOI
IoT based smart devices framework for grid demand response management
TL;DR: In this paper , a distributed framework that operates efficiently on the Internet of Things-based smart grid environment is presented, where a universal collaboration software approach is used for validation of demand response policies while enabling real-time simulation and management.
Journal ArticleDOI
A novel approach for image restoration using convolution network-based image denoising technique
TL;DR: In this paper , a blind deblurring of atmospheric turbulence based on the convolutional network is proposed to correct the temporally varying blur, reduction spatially, and geometric distortion.
References
More filters
Journal ArticleDOI
Artificial neural networks in mammography: application to decision making in the diagnosis of breast cancer.
TL;DR: It is concluded that three-layer, feed-forward neural networks with a back-propagation algorithm trained for the interpretation of mammograms on the basis of features extracted from mammograms by experienced radiologists may provide a potentially useful tool in the mammographic decision-making task of distinguishing between benign and malignant lesions.
Journal ArticleDOI
The Causes of Medical Malpractice Suits against Radiologists in the United States
TL;DR: Errors in diagnosis are the most common generic cause of malpractice suits against radiologists, followed by nonvertebral fractures and spinal fractures.
Journal ArticleDOI
Optimal Feature Selection-Based Medical Image Classification Using Deep Learning Model in Internet of Medical Things
R. Joshua Samuel Raj,S. Jeya Shobana,Irina V. Pustokhina,Denis A. Pustokhin,Deepak Gupta,K. Shankar +5 more
TL;DR: The researchers proposed the Optimal Feature Selection based Medical Image Classification using DL model by incorporating preprocessing, feature selection and classification and found the optimal features improved the classification result and increased the accuracy, specificity and sensitivity in the diagnosis of medical images.
Journal ArticleDOI
Automatic microcalcification and cluster detection for digital and digitised mammograms
Arnau Oliver,Albert Torrent,Xavier Lladó,Meritxell Tortajada,Lidia Tortajada,Melcior Sentís,Jordi Freixenet,Reyer Zwiggelaar +7 more
TL;DR: A knowledge-based approach based on using local features extracted from a bank of filters to obtain a local description of the microcalcifications morphology that performs an initial training step in order to automatically learn and select the most salient features, which are subsequently used in a boosted classifier to perform the detection of individual microCalcifications.
Proceedings ArticleDOI
Forest Species Recognition Using Deep Convolutional Neural Networks
TL;DR: This paper investigates the usage of deep learning techniques, in particular Convolutional Neural Networks (CNN), for texture classification in two forest species datasets - one with macroscopic images and another with microscopic images and presents a method able to cope with the high-resolution texture images to achieve high accuracy and avoid the burden of training and defining an architecture with a large number of free parameters.