Digital Database For Screening Mammography Research Articles

Parallel Hierarchical Multi-View Feature Fusion Based on Canonical Correlation Analysis for Mammogram Retrieval

Due to the diversity of image sources, content-based multi-source image fusion and retrieval have shown promising capabilities in computer vision tasks, and especially when applied in Computer-Aided Diagnosis (CAD) to automate and improve the accuracy of medical image analysis. The combination of computer vision and CAD systems has the potential to revolutionize healthcare by augmenting the expertise of clinicians, improving overall diagnostic accuracy and helping experts in the clinical decision-making process by classifying and retrieving similar annotated clinical images to a given query. In the context of multi-view mammography interpretation, the concept of multi-view feature fusion has recently been studied to improve retrieval performance while effectively guaranteeing the complementarity of both MLO and CC views. However, conventional multi-view feature fusion makes descriptors long and lacks to take into consideration the relationship between descriptors. To deal with this issue, we propose two hierarchical multi-view feature fusion methods, for multi-view mammogram retrieval, based on the Canonical Correlation Analysis (CCA), which is the most commonly used multivariate parametric test. In fact, we have adapted CCA to determine the relationship between two descriptors by processing latent correlation factors. Moreover, after extracting descriptors for each view, a comparative study of texture and shape fusion descriptors is proposed in order to identify the more discriminative features for multi-view mammogram retrieval. Then, a query-dependent distance metric preserving both visual resemblance and semantic similarity is carried out to dynamically determine the more appropriate distance measure for each query image. Extensive experiments on the challenging Curated Breast Imaging Subset of Digital Database for Screening Mammography (CBIS-DDSM) have demonstrated the effectiveness of the proposed hierarchical multi-view feature fusion for mammogram retrieval, which outperforms the performance achieved either by conventional fused information or by single view information. To improve the transparency of our paper, the source code of the proposed method and the related dataset (including readme files) are publicly accessible through the following GitHub link: https://github.com/ABDERRAHIMMAR/Multi-View-Feature-Fusion-for-Mammogram-Retrieval . This open-access resource empowers researchers and practitioners to delve deeper into our methodology, fostering collaboration and advancements in the field of computer-aided diagnosis and medical image analysis.

Offloading the computational complexity of transfer learning with generic features.

Deep learning approaches are generally complex, requiring extensive computational resources and having high time complexity. Transfer learning is a state-of-the-art approach to reducing the requirements of high computational resources by using pre-trained models without compromising accuracy and performance. In conventional studies, pre-trained models are trained on datasets from different but similar domains with many domain-specific features. The computational requirements of transfer learning are directly dependent on the number of features that include the domain-specific and the generic features. This article investigates the prospects of reducing the computational requirements of the transfer learning models by discarding domain-specific features from a pre-trained model. The approach is applied to breast cancer detection using the dataset curated breast imaging subset of the digital database for screening mammography and various performance metrics such as precision, accuracy, recall, F1-score, and computational requirements. It is seen that discarding the domain-specific features to a specific limit provides significant performance improvements as well as minimizes the computational requirements in terms of training time (reduced by approx. 12%), processor utilization (reduced approx. 25%), and memory usage (reduced approx. 22%). The proposed transfer learning strategy increases accuracy (approx. 7%) and offloads computational complexity expeditiously.

An automatic sparse-based deep cascade framework with multilayer representation for detecting breast cancer

This work proposes an effective sparse-based hybrid alternating deep-layer cascade model (HADLCM) for breast cancer detection. It is achieved by cascading sparse and collaborative representation alternatively, with a softmax vector representation at the interface of each cascade segment. Here, alternating deep-layer cascade model (ADLCM) followed by Laplacian of Gaussian-based modified high boosting filter (LoGMHBF) integrated with projection to discriminative subclasses (PDS)-based pre-processing is hybridized with ADLCM subsequent to PDS to improve feature discrimination ability. A class discriminant softmax vector representation is employed to cascade sparse and collaborative representations, leveraging the benefits of both. It improves hierarchical learning abilities by expanding shallow-sparse representation to an effective multi-layer learning approach for extracting deep-rooted discriminative information. The experimental results show the superiority of HADLCM to identify abnormality and malignancy with the accuracy of 98.17% and 97.75% in mini-DDSM (Digital Database for Screening Mammography); 94.87% and 95.00% in BUSI (Breast Ultrasound Image)BUSI, respectively.

Prediction and analysis of breast cancer based on transfer learning from DDSM mammography images

Breast cancer is a cancer mostly found in women, causing a high morality rate. It appears as a lump in the breast initially, and as cancer cells spread, the other organs are endangered. Research shows that the earlier the breast cancer is detected, the higher rate of recovering will be. The main methods of breast cancer detection are mainly using various physical methods to probe the internal condition of the patients breast. Breast X-ray imaging, also known as mammography, is the most widely used. It uses low-dose X-ray technology to observe the breast tissue and help doctors figure out the exact condition of the patient. With the advancements in deep learning and image recognition, the analysis of mammograms can be previously done by the computer, easing the pressure on doctors. Digital Database for Screening Mammography (DDSM) dataset is a mammography dataset specifically designed for the development of mammography detection models. It contains huge amounts of mammograms and provides the labels corresponding to them. In this study, the performances of normal deep learning model and transfer learning model on the DDSM dataset are compared. Pretrained neural network models are employed and fine-tuned on the DDSM dataset to adapt to the features of mammographic images. Experimental results demonstrate significant improvements through transfer learning, outperforming traditional methods with Convolutional Neural Network (CNN). Finally, the models are evaluated in multiple aspects, conclusions and prospects are analysed based on the results.

Breast cancer detection using ensemble of convolutional neural networks

Early detection leading to timely treatment in the initial stages of cancer may decrease the breast cancer death rate. We propose deep learning techniques along with image processing for the detection of tumors. The availability of online datasets and advances in graphical processing units (GPU) have promoted the application of deep learning models for the detection of breast cancer. In this paper, deep learning models using convolutional neural network (CNN) have been built to automatically classify mammograms into benign and malignant. Issues like overfitting and dataset imbalance are overcome. Experimentation has been done on two publicly available datasets, namely mammographic image analysis society (MIAS) database and digital database for screening mammography (DDSM). Robustness of the models is accomplished by merging the datasets. In our experimentation, MatConvNet has achieved an accuracy of 94.2% on the merged dataset, performing the best amongst all the CNN models used individually. Hungarian optimization algorithm is employed for selection of individual CNN models to form an ensemble. Ensemble of CNN models led to an improved performance, resulting in an accuracy of 95.7%.

MSA-GCN: A Multi-information Selection Aggregation Graph Convolutional Network for Breast Tumor Grading.

Physicians typically combine multi-modal data to make a graded diagnosis of breast tumors. However, most existing breast tumor grading methods rely solely on image information, resulting in limited accuracy in grading. This paper proposes a Multi-information Selection Aggregation Graph Convolutional Networks (MSA-GCN) for breast tumor grading. Firstly, to fully utilize phenotypic data reflecting the clinical and pathological characteristics of tumors, an automatic combination screening and weight encoder is proposed for phenotypic data, which can construct a population graph with improved structural information. Then, a graph structure is designed through similarity learning to reflect the correlation between patient image features. Finally, a multi-information selection aggregation mechanism is employed in the graph convolution model to extract the effective features of multi-modal data and enhance the classification performance of the model. The proposed method is evaluated on different clinical datasets from the Digital Database for Screening Mammography (DDSM) and INbreast. The average classification accuracies are 90.74% and 85.35%, respectively, surpassing the performance of existing methods. In conclusion, our method effectively fuses image and non-image information, leading to a significant improvement in the accuracy of breast tumor grading.

Transfer learning for deep neural networks-based classification of breast cancer X-ray images

ABSTRACT Nowadays, deep neural networks (DNNs) are helpful tools for mammogram classification in breast cancer screening. But, in Vietnam, there is a relatively small number of mammograms for training DNNs. Therefore, this study aims to apply transfer learning techniques to improve the performance of DNN models. In the first step, 10,418 breast cancer images from the Digital Database for Screening Mammography were used for training the CNN model ResNet 34. In the second step, we fine-tune this model on the Hanoi Medical University (HMU) database with 6,248 Vietnamese mammograms. The optimal model of ResNet 34 among these models achieves a macAUC of 0.766 in classifying breast cancer X-ray images into three Breast Imaging-Reporting and Data System (BI-RADS) categories, BI-RADS 045 (‘incomplete and malignance’), BI-RADS 1 (‘normal’), and BI-RADS 23 (‘benign’), when tested on the test dataset. This result is higher than the result of the ResNet 50 model trained only on the X-ray dataset of 7,912 breast cancer images of the HMU dataset, which achieves a macAUC of 0.754. A comparison of the performance of the proposed model of ResNet 34 applying transfer learning with other works shows that our model’s evaluation results are higher than those of the compared models.

Breast Cancer Detection with an Ensemble of Deep Learning Networks Using a Consensus-Adaptive Weighting Method.

Breast cancer's high mortality rate is often linked to late diagnosis, with mammograms as key but sometimes limited tools in early detection. To enhance diagnostic accuracy and speed, this study introduces a novel computer-aided detection (CAD) ensemble system. This system incorporates advanced deep learning networks-EfficientNet, Xception, MobileNetV2, InceptionV3, and Resnet50-integrated via our innovative consensus-adaptive weighting (CAW) method. This method permits the dynamic adjustment of multiple deep networks, bolstering the system's detection capabilities. Our approach also addresses a major challenge in pixel-level data annotation of faster R-CNNs, highlighted in a prominent previous study. Evaluations on various datasets, including the cropped DDSM (Digital Database for Screening Mammography), DDSM, and INbreast, demonstrated the system's superior performance. In particular, our CAD system showed marked improvement on the cropped DDSM dataset, enhancing detection rates by approximately 1.59% and achieving an accuracy of 95.48%. This innovative system represents a significant advancement in early breast cancer detection, offering the potential for more precise and timely diagnosis, ultimately fostering improved patient outcomes.

Automated classification of fat-infiltrated axillary lymph nodes on screening mammograms.

Fat-infiltrated axillary lymph nodes (LNs) are unique sites for ectopic fat deposition. Early studies showed a strong correlation between fatty LNs and obesity-related diseases. Confirming this correlation requires large-scale studies, hindered by scarce labeled data. With the long-term goal of developing a rapid and generalizable tool to aid data labeling, we developed an automated deep learning (DL)-based pipeline to classify the status of fatty LNs on screening mammograms. Our internal data set included 886 mammograms from a tertiary academic medical institution, with a binary status of the fat-infiltrated LNs based on the size and morphology of the largest visible axillary LN. A two-stage DL model training and fine-tuning pipeline was developed to classify the fat-infiltrated LN status using the internal training and development data set. The model was evaluated on a held-out internal test set and a subset of the Digital Database for Screening Mammography. Our model achieved 0.97 (95% CI: 0.94-0.99) accuracy and 1.00 (95% CI: 1.00-1.00) area under the receiver operator characteristic curve on 264 internal testing mammograms, and 0.82 (95% CI: 0.77-0.86) accuracy and 0.87 (95% CI: 0.82-0.91) area under the receiver operator characteristic curve on 70 external testing mammograms. This study confirmed the feasibility of using a DL model for fat-infiltrated LN classification. The model provides a practical tool to identify fatty LNs on mammograms and to allow for future large-scale studies to evaluate the role of fatty LNs as an imaging biomarker of obesity-associated pathologies. Our study is the first to classify fatty LNs using an automated DL approach.

Data augmentation guided breast tumor segmentation based on generative adversarial neural networks

Breast tumor segmentation built on Dynamic Contrast-Enhanced Magnetic Resonance Imaging is a noteworthy phase for the quantifiable radiomics study of breast cancer. Manual tumor explanation is an inefficient method and encompasses medical associates, influenced, persuaded to error, and inter-user divergence. The quantities of contemporary preparations have exposed the competence of deep learning depictions in image segmentation. At this point, we designate a 3D Connected-AUNets for tumor segmentation from 3D MRIs built on encoder–decoder design. Owing to a constrained training dataset size, a generative adversarial networks channel is complementary to modernizing the input image itself to recognize the shared decoder and implement added controls on its layers. Based on the preliminary segmentation of Connected-AUNets, a fully connected 3D condition random field is used to improve segmentation results by determining 2D neighbor areas and 3D volume statistics. Furthermore, 3D connected components assessment is used to sustain around large components and reduce segmentation noise. The proposed system has been estimated on two regularly available datasets, apparently INbreast and the Curated Breast Imaging Subset of Digital Database for Screening Mammography. The proposed system has also been evaluated using a private dataset. The experimental significances show that the proposed model outperforms the state-of-the-art processes for breast tumor segmentation.

Serial dependence in perception across naturalistic generative adversarial network-generated mammogram.

Human perception and decisions are biased toward previously seen stimuli. This phenomenon is known as serial dependence and has been extensively studied for the last decade. Recent evidence suggests that clinicians' judgments of mammograms might also be impacted by serial dependence. However, the stimuli used in previous psychophysical experiments on this question, consisting of artificial geometric shapes and healthy tissue backgrounds, were unrealistic. We utilized realistic and controlled generative adversarial network (GAN)-generated radiographs to mimic images that clinicians typically encounter. Mammograms from the digital database for screening mammography (DDSM) were utilized to train a GAN. This pretrained GAN was then adopted to generate a large set of authentic-looking simulated mammograms: 20 circular morph continuums, each with 147 images, for a total of 2940 images. Using these stimuli in a standard serial dependence experiment, participants viewed a random GAN-generated mammogram on each trial and subsequently matched the GAN-generated mammogram encountered using a continuous report. The characteristics of serial dependence from each continuum were analyzed. We found that serial dependence affected the perception of all naturalistic GAN-generated mammogram morph continuums. In all cases, the perceptual judgments of GAN-generated mammograms were biased toward previously encountered GAN-generated mammograms. On average, perceptual decisions had 7% categorization errors that were pulled in the direction of serial dependence. Serial dependence was found even in the perception of naturalistic GAN-generated mammograms created by a GAN. This supports the idea that serial dependence could, in principle, contribute to decision errors in medical image perception tasks.

Benign and Malignant Breast Tumor Classification in Ultrasound and Mammography Images via Fusion of Deep Learning and Handcraft Features.

Breast cancer is a disease that affects women in different countries around the world. The real cause of breast cancer is particularly challenging to determine, and early detection of the disease is necessary for reducing the death rate, due to the high risks associated with breast cancer. Treatment in the early period can increase the life expectancy and quality of life for women. CAD (Computer Aided Diagnostic) systems can perform the diagnosis of the benign and malignant lesions of breast cancer using technologies and tools based on image processing, helping specialist doctors to obtain a more precise point of view with fewer processes when making their diagnosis by giving a second opinion. This study presents a novel CAD system for automated breast cancer diagnosis. The proposed method consists of different stages. In the preprocessing stage, an image is segmented, and a mask of a lesion is obtained; during the next stage, the extraction of the deep learning features is performed by a CNN-specifically, DenseNet 201. Additionally, handcrafted features (Histogram of Oriented Gradients (HOG)-based, ULBP-based, perimeter area, area, eccentricity, and circularity) are obtained from an image. The designed hybrid system uses CNN architecture for extracting deep learning features, along with traditional methods which perform several handcraft features, following the medical properties of the disease with the purpose of later fusion via proposed statistical criteria. During the fusion stage, where deep learning and handcrafted features are analyzed, the genetic algorithms as well as mutual information selection algorithm, followed by several classifiers (XGBoost, AdaBoost, Multilayer perceptron (MLP)) based on stochastic measures, are applied to choose the most sensible information group among the features. In the experimental validation of two modalities of the CAD design, which performed two types of medical studies-mammography (MG) and ultrasound (US)-the databases mini-DDSM (Digital Database for Screening Mammography) and BUSI (Breast Ultrasound Images Dataset) were used. Novel CAD systems were evaluated and compared with recent state-of-the-art systems, demonstrating better performance in commonly used criteria, obtaining ACC of 97.6%, PRE of 98%, Recall of 98%, F1-Score of 98%, and IBA of 95% for the abovementioned datasets.

Computational model for breast cancer diagnosis using HFSE framework

Mammography is one of the imaging modalities used in diagnosing breast cancer at an earlier stage. Misdiagnosis leads to risks for the patients. Better feature extraction and selection techniques can reduce misdiagnoses as they are essential in better-performing classifiers. The proposed approach in this paper introduces a novel Hybrid Feature Extraction and Hybrid Feature Selection (HFSE) framework. It uses mammograms from Digital Database for Screening Mammography (DDSM) datasets to classify mammograms into benign and malignant images. This paper presents a novel hybrid feature extraction approach from the Gray level co-occurrence matrix (GLCM), Linear local binary pattern (LBP), Gabor, and Tamura. Combinedly, it extracts 104 features to train the advanced classifiers such as Logistic Regression, Linear Perceptron, Support Vector Machine, Decision Tree, and Artificial Neural Network. The proposed Hybrid feature extraction method vigorously compares combinations of existing single feature extraction methods. The paper also presents a novel hybrid feature selection approach to choose a subset of the most relevant feature. It compares the Intrinsic feature with the proposed hybrid feature selection method. Hyperparameter tuning and Pipeline optimization techniques applied to the classifiers improve their performance metrics. The experimental results show that the proposed framework performs better using Hybrid feature extraction and feature selection on Artificial Neural Networks. This paper makes a comparative analysis of the related works. It outperforms by achieving a classifier accuracy of 94.57%, specificity of 91.80%, the sensitivity of 95.59 %, and an F1-score of 94.89% on Artificial Neural Networks.

Impact of multi-source data augmentation on performance of convolutional neural networks for abnormality classification in mammography.

To date, most mammography-related AI models have been trained using either film or digital mammogram datasets with little overlap. We investigated whether or not combining film and digital mammography during training will help or hinder modern models designed for use on digital mammograms. To this end, a total of six binary classifiers were trained for comparison. The first three classifiers were trained using images only from Emory Breast Imaging Dataset (EMBED) using ResNet50, ResNet101, and ResNet152 architectures. The next three classifiers were trained using images from EMBED, Curated Breast Imaging Subset of Digital Database for Screening Mammography (CBIS-DDSM), and Digital Database for Screening Mammography (DDSM) datasets. All six models were tested only on digital mammograms from EMBED. The results showed that performance degradation to the customized ResNet models was statistically significant overall when EMBED dataset was augmented with CBIS-DDSM/DDSM. While the performance degradation was observed in all racial subgroups, some races are subject to more severe performance drop as compared to other races. The degradation may potentially be due to ( 1) a mismatch in features between film-based and digital mammograms ( 2) a mismatch in pathologic and radiological information. In conclusion, use of both film and digital mammography during training may hinder modern models designed for breast cancer screening. Caution is required when combining film-based and digital mammograms or when utilizing pathologic and radiological information simultaneously.

Federated learning aided breast cancer detection with intelligent Heuristic-based deep learning framework

Breast cancer is the second largest cause of female cancer death and one of the most hazardous diseases that leads to a higher mortality rate. One of the eminent medical approaches is breast cancer recognition, which offers scientists and researchers huge complications. Breast cancer detection at an early stage permits the patients to receive suitable treatment, which increases the chances of survival. Thus, this paper utilizes a new form of artificial intelligence training called Federated Learning (FL), especially for breast cancer detection. FL permits individual hospitals to benefit from the rich datasets of multiple non-affiliated hospitals without centralizing the data in one place. Consequently, the mammogram images are collected from the Digital Database for Screening Mammography (DDSM) dataset. Hence, FL utilizes numerous collaborators to build a strong deep-learning model using a large dataset. In this paper, a hybridization of this type of training with meta-heuristic and deep learning is aimed to be proposed for breast cancer diagnosis. This model encloses diverse steps that include (a) image collection, (b) feature extraction, and (c) classification phase. Initially, the mammogram images related to breast cancer are collected with the concept of FL from the affected individuals. Federated learning helps in reducing the processing time and ensures better performance of the proposed model. The obtained images are considered for the feature extraction phase, where the DenseNet architecture is used for extracting the features, which are used into the classification phase with the help of Enhanced Recurrent Neural Networks (E-RNN) for detecting breast cancer. Here, the performance is enhanced by tuning certain parameters in the RNN network using a hybrid optimization algorithm called Hybrid Dragon-Rider Optimization (HDRO) with Dragonfly Algorithm (DA) and Red deer algorithm (RDA) to achieve accurate classification results. Thus, the simulation outcome of the designed method shows 95% and 91% regarding accuracy and MCC. The experimental results demonstrate the effectiveness of the suggested breast cancer diagnosis model through the comparison with conventional approaches using diverse quantitative measures.

English

Breast cancer is among the top causes of fatalities related to cancer in females. Radiologists commonly use mammogram images to detect breast tumors in their early stages. However, mammography can produce low-contrast images, making it difficult and time-consuming to segment abnormal regions. Deep convolutional neural networks (CNNs) are commonly used for image evaluations. This study used deep CNN models to develop a computer-aided diagnostic (CAD) system for feature extraction and classification. The proposed approach consists of three phases. In the first phase, a shallow, deep CNN model comprising five convolutional layers, five max-pooling layers, one batch normalization layer, and one dropout layer was developed and used to extract recombined images and novel features. In the second phase, the Inception-v3 model was used for label smoothing and classification due to its multiple filters with different sizes. In the third phase, features were extracted using shallow, deep CNN and Inception-v3 models. The Infallible Euclidean distance-based nonlinear dimensionality reduction approach was used to minimize dimensionality. Finally, the Gini-index-based C4.5 decision tree was used for the binary classification of mammogram images from the Digital Database for Screening Mammography (DDSM) + Curated Breast Imaging Subset of DDSM (CBIS-DDSM) and Mammographic Image Analysis Society (MIAS) datasets. The proposed hybrid shallow, deep CNN and Inception-v3 model achieved 99.52% accuracy, a 96% AUC on the DDSM + CBISDDSM dataset, and an accuracy of 97.53% and an AUC value of 97% on the MIAS dataset. Compared with other cutting-edge CAD systems, the proposed hybrid approach achieved higher accuracy by combining in-depth features across both datasets.

A YOLO-based AI system for classifying calcifications on spot magnification mammograms

ObjectivesUse of an AI system based on deep learning to investigate whether the system can aid in distinguishing malignant from benign calcifications on spot magnification mammograms, thus potentially reducing unnecessary biopsies.MethodsIn this retrospective study, we included public and in-house datasets with annotations for the calcifications on both craniocaudal and mediolateral oblique vies, or both craniocaudal and mediolateral views of each case of mammograms. All the lesions had pathological results for correlation. Our system comprised an algorithm based on You Only Look Once (YOLO) named adaptive multiscale decision fusion module. The algorithm was pre-trained on a public dataset, Curated Breast Imaging Subset of Digital Database for Screening Mammography (CBIS-DDSM), then re-trained and tested on the in-house dataset of spot magnification mammograms. The performance of the system was investigated by receiver operating characteristic (ROC) analysis.ResultsWe included 1872 images from 753 calcification cases (414 benign and 339 malignant) from CBIS-DDSM. From the in-house dataset, 636 cases (432 benign and 204 malignant) with 1269 spot magnification mammograms were included, with all lesions being recommended for biopsy by radiologists. The area under the ROC curve for our system on the in-house testing dataset was 0.888 (95% CI 0.868–0.908), with a sensitivity of 88.4% (95% CI 86.9–8.99%), specificity of 80.8% (95% CI 77.6–84%), and an accuracy of 84.6% (95% CI 81.8–87.4%) at the optimal cutoff value. Using the system with two views of spot magnification mammograms, 80.8% benign biopsies could be avoided.ConclusionThe AI system showed good accuracy for classification of calcifications on spot magnification mammograms which were all categorized as suspicious by radiologists, thereby potentially reducing unnecessary biopsies.

Mammography Datasets for Neural Networks-Survey.

Deep neural networks have gained popularity in the field of mammography. Data play an integral role in training these models, as training algorithms requires a large amount of data to capture the general relationship between the model's input and output. Open-access databases are the most accessible source of mammography data for training neural networks. Our work focuses on conducting a comprehensive survey of mammography databases that contain images with defined abnormal areas of interest. The survey includes databases such as INbreast, the Curated Breast Imaging Subset of Digital Database for Screening Mammography (CBIS-DDSM), the OPTIMAM Medical Image Database (OMI-DB), and The Mammographic Image Analysis Society Digital Mammogram Database (MIAS). Additionally, we surveyed recent studies that have utilized these databases in conjunction with neural networks and the results they have achieved. From these databases, it is possible to obtain at least 3801 unique images with 4125 described findings from approximately 1842 patients. The number of patients with important findings can be increased to approximately 14,474, depending on the type of agreement with the OPTIMAM team. Furthermore, we provide a description of the annotation process for mammography images to enhance the understanding of the information gained from these datasets.

Deep Transfer Learning to Classify Mass and Calcification Pathologies from Screen Film Mammograms

The number of breast cancer diagnosis is the biggest among all cancers, but it can be treated if diagnosed early. Mammography is commonly used for detecting abnormalities and diagnosing the breast cancer. Breast cancer screening and diagnosis are still being performed by radiologists. In the last decade, deep learning was successfully applied on big image classification databases such as ImageNet. Deep learning methods for the automated breast cancer diagnosis is under investigation. In this study, breast cancer mass and calcification pathologies are classified by using deep transfer learning methods. A total of 3,360 patches were used from the Digital Database for Screening Mammography (DDSM) and CBIS-DDSM mammogram databases for convolutional neural network training and testing. Transfer learning was applied using Resnet50, Xception, NASNet, and EfficientNet-B7 network backbones. The best classification performance was achieved by the Xception network. On the original CBIS-DDSM test data, an AUC of 0.9317 was obtained for the five-way classification problem. The results are promising for the implementation of automated diagnosis of breast cancer.

Breast cancer: toward an accurate breast tumor detection model in mammography using transfer learning techniques

Female breast cancer has now surpassed lung cancer as the most common form of cancer globally. Although several methods exist for breast cancer detection and diagnosis, mammography is the most effective and widely used technique. In this study, our purpose is to propose an accurate breast tumor detection model as the first step into cancer detection. To guarantee diversity and a larger amount of data, we collected samples from three different databases: the Mammographic Image Analysis Society MiniMammographic (MiniMIAS), the Digital Database for Screening Mammography (DDSM), and the Chinese Mammography Database (CMMD). Several filters were used in the pre-processing phase to extract the Region Of Interest (ROI), remove noise, and enhance images. Next, transfer learning, data augmentation, and Global Pooling (GAP/GMP) techniques were used to avoid imagery overfitting and to increase accuracy. To do so, seven pre-trained Convolutional Neural Networks (CNNs) were modified in several trials with different hyper-parameters to determine which ones are the most suitable for our situation and the criteria that influenced our results. The selected pre-trained CNNs were Xception, InceptionV3, ResNet101V2, ResNet50V2, ALexNet, VGG16, and VGG19. The obtained results were satisfying, especially for ResNet50V2 followed by InceptionV3 reaching the highest accuracy of 99.9%, and 99.54% respectively. Meanwhile, the remaining models achieved great results as well, proving that our approach starting from the chosen filters, databases, and pre-trained models with the fine-tuning phase and the used global pooling technique is effective for breast tumor detection. Furthermore, we also managed to determine the most suitable hyper-parameters for each model using our collected dataset.