Breast Cancer:Tumor Detection in Mammogram Images Using Modified AlexNet Deep Convolution Neural Network

Omonigho, Emmanuel Lawrence; David, Michaël; Adejo, Achonu; Aliyu, Saliyu

doi:10.1109/icmcecs47690.2020.240870

Cited by 36 publications

(19 citation statements)

References 9 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The yielded results in this research using the AlexNet have surpassed the recent results achieved in the literature. The overall accuracy of the AlexNet, GoogLeNet on the MIAS Dataset achieved in [42], and [9] was 95.70%, 91.58% respectively. And as depicted in Table I, the conventional machine learning approached has yielded an extraordinary result that is greater than the results achieved the pretrained CNN networks.…”

Section: Resultsmentioning

confidence: 97%

“…Their CAD system achieved 99.7% for mass detection and 97% for classification. Several studies show that the pretrained CNN models such as Resnet [19], Alexnet [20], [21] and GoogleNet [30] demonstrate higher results using unaugmented patches and more enhanced results with augmented ones. Different CNN models [22] [23] show different detection and classification accuracies and performance depending on the application, techniques and datasets used.…”

Section: Related Workmentioning

confidence: 99%

See 1 more Smart Citation

Evaluating Deep and Statistical Machine Learning Models in the Classification of Breast Cancer from Digital Mammograms

Alhussan¹,

Samee²,

Ghoneim³

et al. 2021

IJACSA

View full text Add to dashboard Cite

Section: Resultsmentioning

confidence: 97%

Section: Related Workmentioning

confidence: 99%

Evaluating Deep and Statistical Machine Learning Models in the Classification of Breast Cancer from Digital Mammograms

Alhussan¹,

Samee²,

Ghoneim³

et al. 2021

IJACSA

View full text Add to dashboard Cite

“…Horizontal and vertical flipping methods were used by Omonigho et al [ 26 ] to augment the training set. By augmenting the training set with scaling, horizontal flip, and rotation, the authors could achieve 95.70% overall accuracy on the modified AlexNet model.…”

Section: Basic Image Augmentation Techniquesmentioning

confidence: 99%

Image Augmentation Techniques for Mammogram Analysis

et al. 2022

View full text Add to dashboard Cite

Research in the medical imaging field using deep learning approaches has become progressively contingent. Scientific findings reveal that supervised deep learning methods’ performance heavily depends on training set size, which expert radiologists must manually annotate. The latter is quite a tiring and time-consuming task. Therefore, most of the freely accessible biomedical image datasets are small-sized. Furthermore, it is challenging to have big-sized medical image datasets due to privacy and legal issues. Consequently, not a small number of supervised deep learning models are prone to overfitting and cannot produce generalized output. One of the most popular methods to mitigate the issue above goes under the name of data augmentation. This technique helps increase training set size by utilizing various transformations and has been publicized to improve the model performance when tested on new data. This article surveyed different data augmentation techniques employed on mammogram images. The article aims to provide insights into basic and deep learning-based augmentation techniques.

show abstract

“…To increase the effectiveness of training and testing of proposed work, a large dataset is required. Hence image augmentation technique discussed in (Omonigho et al, 2020;Khan et al, 2019;Zhang et al, 2018) is used. Image augmentation is the process of using transformation techniques (like scaling, rotation, flip etc.)…”

Section: Proposed Workmentioning

confidence: 99%

“…In this work, deep features refer to those features that are extracted from the DCNN model. In (Omonigho et al, 2020), authors proposed a modified version of the Alexnet model, which has been taken as a reference model in this work. This DCNN architecture has been modified and deep features extracted from FC2 layer (shown at Serial no.…”

Section: Proposed Workmentioning

confidence: 99%

Ensemble Boosted Tree based Mammogram image classification using Texture features and extracted smart features of Deep Neural Network

Sharma

Purwar

2022

ADCAIJ

View full text Add to dashboard Cite

This work proposes a technique of breast cancer detection from mammogram images. It is a multistage process which classifies the mammogram images into benign or malignant category. During preprocessing, images of Mammographic Image Analysis Society (MIAS) database are passed through a couple of filters for noise removal, thresholding and cropping techniques to extract the region of interest, followed by augmentation process on database to enhance its size. Features from Deep Convolution Neural Network (DCNN) are merged with texture features to form final feature vector. Using transfer learning, deep features are extracted from a modified DCNN, whose training is performed on 69% of randomly selected images of database from both categories. Features of Grey Level Co-Occurrence Matrix (GLCM) and Local Binary Pattern (LBP) are merged to form texture features. Mean and variance of four parameters (contrast, correlation, homogeneity and entropy) of GLCM are computed in four angular directions, at ten distances. Ensemble Boosted Tree classifier using five-fold cross-validation mode, achieved an accuracy, sensitivity, specificity of 98.8%, 100% and 92.55% respectively on this feature vector.

show abstract

Breast Cancer:Tumor Detection in Mammogram Images Using Modified AlexNet Deep Convolution Neural Network

Cited by 36 publications

References 9 publications

Evaluating Deep and Statistical Machine Learning Models in the Classification of Breast Cancer from Digital Mammograms

Evaluating Deep and Statistical Machine Learning Models in the Classification of Breast Cancer from Digital Mammograms

Image Augmentation Techniques for Mammogram Analysis

Ensemble Boosted Tree based Mammogram image classification using Texture features and extracted smart features of Deep Neural Network

Contact Info

Product

Resources

About