Breast cancer is a common and fatal disease among women worldwide. Therefore, the early and precise diagnosis of breast cancer plays a pivotal role to improve the prognosis of patients with this disease. Several studies have developed automated techniques using different medical imaging modalities to predict breast cancer development. However, few review studies are available to recapitulate the existing literature on breast cancer classification. These studies provide an overview of the classification, segmentation, or grading of many cancer types, including breast cancer, by using traditional machine learning approaches through hand-engineered features. This review focuses on breast cancer classification by using medical imaging multimodalities through state-of-the-art artificial deep neural network approaches. It is anticipated to maximize the procedural decision analysis in five aspects, such as types of imaging modalities, datasets and their categories, pre-processing techniques, types of deep neural network, and performance metrics used for breast cancer classification. Forty-nine journal and conference publications from eight academic repositories were methodically selected and carefully reviewed from the perspective of the five aforementioned aspects. In addition, this study provided quantitative, qualitative, and critical analyses of the five aspects. This review showed that mammograms and histopathologic images were mostly used to classify breast cancer. Moreover, about 55% of the selected studies used public datasets, and the remaining used exclusive datasets. Several studies employed augmentation, scaling, and image normalization pre-processing techniques to minimize inconsistencies in breast cancer images. Several types of shallow and deep neural network architecture were employed to classify breast cancer using images. The convolutional neural network was utilized frequently to construct an effective breast cancer classification model. Some of the selected studies employed a pre-trained network or developed new deep neural networks to classify breast cancer. Most of the selected studies used accuracy and area-under-the-curve metrics followed by sensitivity, precision, and F-measure metrics to evaluate the performance of the developed breast cancer classification models. Finally, this review presented 10 open research challenges for future scholars who are interested to develop breast cancer classification models through various imaging modalities. This review could serve as a valuable resource for beginners on medical image classification and for advanced scientists focusing on deep learning-based breast cancer classification through different medical imaging modalities.

Deep learning-based breast cancer classification through medical imaging modalities: state of the art and research challenges

Role of image thermography in early breast cancer detection- Past, present and future

Breast cancer diagnosis using thermography and convolutional neural networks.

A multi-level thresholding method for breast thermograms analysis using Dragonfly algorithm

Micro Abstract: A recent study from GLOBOCAN disclosed that during 2018 two million women worldwide had been diagnosed from breast cancer. This study presents a computer-aided diagnosis system based on convolutional neural networks as an alternative diagnosis methodology for breast cancer diagnosis with thermal images. Experimental results showed that lower false-positives and false-negatives classification rates are obtained when data pre-processing and data augmentation techniques are implemented in these thermal images. Background: There are many types of breast cancer screening techniques such as, mammography, magnetic resonance imaging, ultrasound and blood sample tests, which require either, expensive devices or personal qualified. Currently, some countries still lack access to these main screening techniques due to economic, social or cultural issues. The objective of this study is to demonstrate that computer-aided diagnosis(CAD) systems based on convolutional neural networks (CNN) are faster, reliable and robust than other techniques. Methods: We performed a study of the influence of data pre-processing, data augmentation and database size versus a proposed set of CNN models. Furthermore, we developed a CNN hyper-parameters fine-tuning optimization algorithm using a tree parzen estimator. Results: Among the 57 patients database, our CNN models obtained a higher accuracy (92\%) and F1-score (92\%) that outperforms several state-of-the-art architectures such as ResNet50, SeResNet50 and Inception. Also, we demonstrated that a CNN model that implements data-augmentation techniques reach identical performance metrics in comparison with a CNN that uses a database up to 50\% bigger. Conclusion: This study highlights the benefits of data augmentation and CNNs in thermal breast images. Also, it measures the influence of the database size in the performance of CNNs.

A CNN-based methodology for breast cancer diagnosis using thermal images

In this article, we present a new approach for breast thermogram image analysis by developing a fully automatic segmentation of right and left breast for asymmetry analysis, using shape features of the breast and Polynomial curve fitting. Segmentation results are validated with their respective Ground Truths. Histogram and grey level co-occurrence matrix-based texture features are extracted from the segmented images. Statistical test shows that features are highly significant in detection of breast cancer. We have obtained an accuracy of 90%, sensitivity of 87.5% and specificity of 92.5% for a set of eighty images with forty normal and forty abnormal using SVM RBF classifier.

Asymmetry analysis of breast thermograms using automated segmentation and texture features

Breast thermography is a non-invasive imaging technique used for early detection of breast cancer based on temperatures. Temperature matrix of breast provides minute variations in temperatures, which is significant in early detection of breast cancer. The minimum, maximum temperatures and the their range may be different for each breast thermogram. Normalization of temperature matrices of breast thermograms is essential to bring the different range of temperatures to the common scale. In this article, we demonstrate the importance of temperature matrix normalization of breast thermograms. This paper also proposes a novel method for automatically classifying breast thermogram images using local energy features of wavelet sub-bands. A significant subset of features is selected by a random subset feature selection (RSFS) and genetic algorithm. Features selected by RSFS method are found to be relevant in detection of asymmetry between right and left breast. We have obtained an accuracy of 91%, sensitivity 87.23% and specificity 94.34% using SVM Gaussian classifier for normalized breast thermograms. Accuracy of classification between a set of hundred normalized and corresponding set of non-normalized breast thermograms are compared. An increase in accuracy of 16% is obtained for normalized breast thermograms in comparison with non-normalized breast thermograms.

Role of normalization of breast thermogram images and automatic classification of breast cancer

In this article, a study of various medical imaging modalities and survey of computer aided detection (CAD) approaches used for the detection of breast cancer are presented. Early breast cancer detection, is important as it can increase the rate of diagnosis, cure and survival of the affected women. Medical imaging techniques can detect early signs of breast cancer. They are also used to diagnose, stage breast cancer and guide treatments. This article explains the imaging procedure, analysis of images, benefits and limitations of standard medical imaging techniques such as mammography, ultrasound, magnetic resonance imaging, and thermography. Also some of modern imaging techniques are discussed here. Comparative study of mammography, ultrasound, thermography and magnetic resonance imaging describes the benefits of thermography in early detection of breast cancer. CAD provides a fast, reliable, and cost-effective second opinion to support doctors with the diagnostic management of breast cancer. This article reviews various CAD algorithms developed and studied for mammography, ultrasound and thermography. From the literature review, it is observed that accuracy of detection of breast abnormalities using CAD are decided by many factors, such as size of database, image quality, segmentation of region of interest, extracted features and classifiers used, etc.

Medical imaging techniques and computer aided diagnostic approaches for the detection of breast cancer with an emphasis on thermography - a review

Mortality rate of breast cancer can be reduced by detecting breast cancer in its early stage. Breast thermography plays an important role in early detection of breast cancer, as it can detect tumors when the physiological changes start in the breast prior to structural changes. Computer Aided Detection (CAD) systems improve the diagnostic accuracy by providing a detailed analysis of images, which are not visible to the naked eye. The performance of CAD systems depends on many factors. One of the important factors is the classifier used for classification of breast thermograms. In this paper, we made a comparison of classifier performances using two ensemble classifiers namely Ensemble Bagged Trees and AdaBoost. Spatial and spectral features are used for classification. Ensemble Bagged Trees classifier performed better than AdaBoost in terms of accuracy of classification, but training time required is higher than AdaBoost classifier. An accuracy of 87%, sensitivity of 83% and specificity of 90.6% is obtained using Ensemble Bagged Trees classifier.

Detection of breast thermograms using ensemble classifiers

Classification and detection of the brain tumour at early stages have always been a concern to reduce the mortality rate. Though the brain tumour detection is possible in Magnetic Resonance Imaging (MRI), the detailed detection of the tumour type has been a concern. This article proposed a comparatively efficient method to detect the dangerous malignant tumour and hence begin the treatment at an early stage. At first, MRI images are filtered by cascading mean, median and Weiner filter. Due to the high density and texture, skull tends to appear as a detected region, which is often mistaken as part of a tumour. The stripping of the skull is done to isolate the Region of Interest (ROI) of the brain from the background. Once an abnormality in the image is confirmed for a tumour, its' classification into Low-Grade Glioma (LGG) and High-Grade Glioma (HGG) are done using Open by Reconstruction followed by thresholding segmentation method & Convolution Neural Networks (CNNs). An accuracy of 92.3% is obtained by first CNN in classifying abnormal brain MRI with normal brain MRI. An accuracy of 98.4% is obtained by second CNN in distinguishing HGG with LGG.

Dayakshini Sathish

Papers

Asymmetry analysis of breast thermograms using automated segmentation and texture features

Role of normalization of breast thermogram images and automatic classification of breast cancer

Medical imaging techniques and computer aided diagnostic approaches for the detection of breast cancer with an emphasis on thermography - a review

Detection of breast thermograms using ensemble classifiers

Early Detection of Brain Tumour in MRI Images using Open by Reconstruction and Convolution Neural Networks