Amongst all types of cancer, breast cancer has become one of the most common cancers in the UK threatening millions of people\'s health. Early detection of breast cancer plays a key role in timely treatment for morbidity reduction. Compared to biopsy, which takes tissues from the lesion for further analysis, image-based methods are less time-consuming and pain-free though they are hampered by lower accuracy due to high false positivity rates. Nevertheless, mammography has become a standard screening method due to its high efficiency and low cost with promising performance. Breast mass, as the most palpable symptom of breast cancer, has received wide attention from the community. As a result, the past decades have witnessed the speeding development of computer-aided systems that are aimed at providing radiologists with useful tools for breast mass analysis based on mammograms. However, the main issues of these systems include low accuracy and require enough computational power on a large scale of datasets. To solve these issues, we developed a novel breast mass classification system called DF-dRVFL. On the public dataset DDSM with more than 3500 images, our best model based on deep random vector functional link network showed promising results through five-cross validation with an averaged AUC of 0.93 and an average accuracy of 81.71%. Compared to sole deep learning based methods, average accuracy has increased by 0.38. Compared with the state-of-the-art methods, our method showed better performance considering the number of images for evaluation and the overall accuracy.

In this paper, we propose a novel deep learning method for joint classification and segmentation of breast masses based on radio-frequency (RF) ultrasound (US) data. In comparison to commonly used classification and segmentation techniques, utilizing B-mode US images, we train the network with RF data (data before envelope detection and dynamic compression), which are considered to include more information on tissue\'s physical properties than standard B-mode US images. Our multi-task network, based on the Y-Net architecture, can effectively process large matrices of RF data by mixing 1D and 2D convolutional filters. We use data collected from 273 breast masses to compare the performance of networks trained with RF data and US images. The multi-task model developed based on the RF data achieved good classification performance, with area under the receiver operating characteristic curve (AUC) of 0.90. The network based on the US images achieved AUC of 0.87. In the case of the segmentation, we obtained mean Dice scores of 0.64 and 0.60 for the approaches utilizing US images and RF data, respectively. Moreover, the interpretability of the networks was studied using class activation mapping technique and by filter weights visualizations.

Masses are one of the early signs of breast cancer, and the survival rate of women suffering from breast cancer can be improved if masses can be correctly identified as benign or malignant. However, their classification is challenging due to the similarity in texture patterns of both types of mass. The existing methods for this problem have low sensitivity and specificity. Based on the hypothesis that diverse contextual information of a mass region forms a strong indicator for discriminating benign and malignant masses and the idea of the ensemble classifier, we introduce a computer-aided system for this problem. The system uses multiple regions of interest (ROIs) encompassing a mass region for modeling diverse contextual information, a single ResNet-50 model (or its density-specific modification) as a backbone for local decisions, and stacking with SVM as a base model to predict the final decision. A data augmentation technique is introduced for fine-tuning the backbone model. The system was thoroughly evaluated on the benchmark CBIS-DDSM dataset using its provided data split protocol, and it achieved a sensitivity of 98.48% and a specificity of 92.31%. Furthermore, it was found that the system gives higher performance if it is trained and tested using the data from a specific breast density BI-RADS class. The system does not need to fine-tune/train multiple CNN models; it introduces diverse contextual information by multiple ROIs. The comparison shows that the method outperforms the state-of-the-art methods for classifying mass regions into benign and malignant. It will help radiologists reduce their burden and enhance their sensitivity in the prediction of malignant masses.

The convolutional neural network (CNN) is a promising technique to detect breast cancer based on mammograms. Training the CNN from scratch, however, requires a large amount of labeled data. Such a requirement usually is infeasible for some kinds of medical image data such as mammographic tumor images. Because improvement of the performance of a CNN classifier requires more training data, the creation of new training images, image augmentation, is one solution to this problem. We applied the generative adversarial network (GAN) to generate synthetic mammographic images from the digital database for screening mammography (DDSM). From the DDSM, we cropped two sets of regions of interest (ROIs) from the images: normal and abnormal (cancer/tumor). Those ROIs were used to train the GAN, and the GAN then generated synthetic images. For comparison with the affine transformation augmentation methods, such as rotation, shifting, scaling, etc., we used six groups of ROIs [three simple groups: affine augmented, GAN synthetic, real (original), and three mixture groups of any two of the three simple groups] for each to train a CNN classifier from scratch. And, we used real ROIs that were not used in training to validate classification outcomes. Our results show that, to classify the normal ROIs and abnormal ROIs from DDSM, adding GAN-generated ROIs in the training data can help the classifier prevent overfitting, and on validation accuracy, the GAN performs about 3.6% better than affine transformations for image augmentation. Therefore, GAN could be an ideal augmentation approach. The images augmented by GAN or affine transformation cannot substitute for real images to train CNN classifiers because the absence of real images in the training set will cause over-fitting.

OBJECTIVE: We propose a deep learning-based approach to breast mass classification in sonography and compare it with the assessment of four experienced radiologists employing breast imaging reporting and data system 4th edition lexicon and assessment protocol.
METHODS: Several transfer learning techniques are employed to develop classifiers based on a set of 882 ultrasound images of breast masses. Additionally, we introduce the concept of a matching layer. The aim of this layer is to rescale pixel intensities of the grayscale ultrasound images and convert those images to red, green, blue (RGB) to more efficiently utilize the discriminative power of the convolutional neural network pretrained on the ImageNet dataset. We present how this conversion can be determined during fine-tuning using back-propagation. Next, we compare the performance of the transfer learning techniques with and without the color conversion. To show the usefulness of our approach, we additionally evaluate it using two publicly available datasets.
RESULTS: Color conversion increased the areas under the receiver operating curve for each transfer learning method. For the better-performing approach utilizing the fine-tuning and the matching layer, the area under the curve was equal to 0.936 on a test set of 150 cases. The areas under the curves for the radiologists reading the same set of cases ranged from 0.806 to 0.882. In the case of the two separate datasets, utilizing the proposed approach we achieved areas under the curve of around 0.890.
CONCLUSIONS: The concept of the matching layer is generalizable and can be used to improve the overall performance of the transfer learning techniques using deep convolutional neural networks. When fully developed as a clinical tool, the methods proposed in this paper have the potential to help radiologists with breast mass classification in ultrasound.

To develop and test a deep learning based computer-aided diagnosis (CAD) scheme of mammograms for classifying between malignant and benign masses.
An image dataset involving 560 regions of interest (ROIs) extracted from digital mammograms was used. After down-sampling each ROI from 512×512 to 64×64 pixel size, we applied an 8 layer deep learning network that involves 3 pairs of convolution-max-pooling layers for automatic feature extraction and a multiple layer perceptron (MLP) classifier for feature categorization to process ROIs. The 3 pairs of convolution layers contain 20, 10, and 5 feature maps, respectively. Each convolution layer is connected with a max-pooling layer to improve the feature robustness. The output of the sixth layer is fully connected with a MLP classifier, which is composed of one hidden layer and one logistic regression layer. The network then generates a classification score to predict the likelihood of ROI depicting a malignant mass. A four-fold cross validation method was applied to train and test this deep learning network.
The results revealed that this CAD scheme yields an area under the receiver operation characteristic curve (AUC) of 0.696±0.044, 0.802±0.037, 0.836±0.036, and 0.822±0.035 for fold 1 to 4 testing datasets, respectively. The overall AUC of the entire dataset is 0.790±0.019.
This study demonstrates the feasibility of applying a deep learning based CAD scheme to classify between malignant and benign breast masses without a lesion segmentation, image feature computation and selection process.

Evaluation of segmentation algorithms usually involves comparisons of segmentations to gold-standard delineations without regard to the ultimate medical decision-making task. We compare two segmentation evaluations methods-a Dice similarity coefficient (DSC) evaluation and a diagnostic classification task-based evaluation method using lesions from breast computed tomography. In our investigation, we use results from two previously developed lesion-segmentation algorithms [a global active contour model (GAC) and a global with local aspects active contour model]. Although similar DSC values were obtained (0.80 versus 0.77), we show that the global + local active contour (GLAC) model, as compared with the GAC model, is able to yield significantly improved classification performance in terms of area under the receivers operating characteristic (ROC) curve in the task of distinguishing malignant from benign lesions. [Area under the [Formula: see text] compared to 0.63, [Formula: see text]]. This is mainly because the GLAC model yields better detailed information required in the calculation of morphological features. Based on our findings, we conclude that the DSC metric alone is not sufficient for evaluating segmentation lesions in computer-aided diagnosis tasks.

Nakagami imaging is an attractive tissue characterization method, as the parameter estimated at each location is related to properties of the tissues. The application to clinical ultrasound images is problematic, as the estimation of the parameters is disturbed by the presence of complex structures. We propose to consider separately the different aspects potentially affecting the value of the Nakagami parameters and quantify their effects on the estimation. This framework is applied to the classification of breast masses. Quantitative parameters are computed on two groups of ultrasound images of benign and malignant tumors. A statistical analysis of the result indicated that the previously observed difference between average values of the Nakagami parameters is explained mostly by estimation errors. In the future, new methods for reliable computation of Nakagami parameters need to be developed, and factors of error should be considered in studies using Nakagami parameters.