scholarly journals Breast Cancer Detection Using Mammogram Images with Improved Multi-Fractal Dimension Approach and Feature Fusion

2021 ◽  
Vol 11 (24) ◽  
pp. 12122
Author(s):  
Dilovan Asaad Zebari ◽  
Dheyaa Ahmed Ibrahim ◽  
Diyar Qader Zeebaree ◽  
Mazin Abed Mohammed ◽  
Habibollah Haron ◽  
...  

Breast cancer detection using mammogram images at an early stage is an important step in disease diagnostics. We propose a new method for the classification of benign or malignant breast cancer from mammogram images. Hybrid thresholding and the machine learning method are used to derive the region of interest (ROI). The derived ROI is then separated into five different blocks. The wavelet transform is applied to suppress noise from each produced block based on BayesShrink soft thresholding by capturing high and low frequencies within different sub-bands. An improved fractal dimension (FD) approach, called multi-FD (M-FD), is proposed to extract multiple features from each denoised block. The number of features extracted is then reduced by a genetic algorithm. Five classifiers are trained and used with the artificial neural network (ANN) to classify the extracted features from each block. Lastly, the fusion process is performed on the results of five blocks to obtain the final decision. The proposed approach is tested and evaluated on four benchmark mammogram image datasets (MIAS, DDSM, INbreast, and BCDR). We present the results of single- and double-dataset evaluations. Only one dataset is used for training and testing in the single-dataset evaluation, whereas two datasets (one for training, and one for testing) are used in the double-dataset evaluation. The experiment results show that the proposed method yields better results on the INbreast dataset in the single-dataset evaluation, whilst better results are obtained on the remaining datasets in the double-dataset evaluation. The proposed approach outperforms other state-of-the-art models on the Mini-MIAS dataset.

Author(s):  
Md Abdullah Al Rakib ◽  
Shamim Ahmad ◽  
Md. Humayun Kabir Khan ◽  
Mainul Haque ◽  
Tareq Mohammad Faruqi ◽  
...  

Author(s):  
Aashika Rastogi

From the past few decades there is a solid increase in the frequency of cancer cases worldwide thus detection and identification at early stage is very crucial and is becoming more difficult with each passing day moreover there is scope of human error which makes it even more critical and tedious task. Thus, using Machine learning for cancer detection makes it task faster, accurate and effective. Through our project we wish to draw an analysis among various algorithm and libraries that have been used to detect cancer moreover we have implemented the same through Densenet201 which is a 201-layer deep neural network and have proved itself most accurate and precise method for cancer detection (breast cancer detection) also its implementation using chatbot would allow it to integrate with other apps, software, websites effortlessly.This could in turn increase user interaction with the chatbot thereby spreading more awareness and knowledge about the disease because not many people know about the disease and its early detection and could help bust myths and facts about disease. Our research also indicates that 96.4% people knew about the disease and 3.6% people were not aware about the disease moreover only 17.2% people were aware about males developing the disease and 37.9% people were aware about LGBTQ+ community developing disease. Also 62.1%-89.7% people were aware about the early signs. In addition to it 86.2% people knew about only one method of self examination and 72.4% people wanted to know more about the disease and get an accurate cure for it .


2014 ◽  
Vol 5 (4) ◽  
pp. 1-19
Author(s):  
Noah P. Svoboda ◽  
Abas Sabouni

This article describes the development of a method for a biocompatible sensor device for the intent of in-vivo breast tissue dielectric properties measurements. This article focuses on a specific type of sensor that utilizes an LC circuit with an inter-digital capacitor (IDC) with small size and high sensitivity for early stage breast cancer detection. To meet this objective an IDC was optimized in terms of contrast and miniaturized size via simulation techniques. For experimental testing, a scaled-up prototype inter-digital capacitor and spiral square inductor sensor was fabricated, and tested with known media, such as distilled water and glycerol. The results suggest that there is a need for further development, such as fabrication and testing for the biocompatible, miniaturized sensor for breast tissue application.


Sign in / Sign up

Export Citation Format

Share Document