Computer-aided Diagnosis Of Breast Cancer Research Articles

SwinHR: Hemodynamic-powered hierarchical vision transformer for breast tumor segmentation

Accurate and automated segmentation of breast tumors in dynamic contrast-enhanced magnetic resonance imaging (DCE-MRI) plays a critical role in computer-aided diagnosis and treatment of breast cancer. However, this task is challenging, due to random variation in tumor sizes, shapes, appearances, and blurred boundaries of tumors caused by inherent heterogeneity of breast cancer. Moreover, the presence of ill-posed artifacts in DCE-MRI further complicate the process of tumor region annotation. To address the challenges above, we propose a scheme (named SwinHR) integrating prior DCE-MRI knowledge and temporal–spatial information of breast tumors. The prior DCE-MRI knowledge refers to hemodynamic information extracted from multiple DCE-MRI phases, which can provide pharmacokinetics information to describe metabolic changes of the tumor cells over the scanning time. The Swin Transformer with hierarchical re-parameterization large kernel architecture (H-RLK) can capture long-range dependencies within DCE-MRI while maintaining computational efficiency by a shifted window-based self-attention mechanism. The use of H-RLK can extract high-level features with a wider receptive field, which can make the model capture contextual information at different levels of abstraction. Extensive experiments are conducted in large-scale datasets to validate the effectiveness of our proposed SwinHR scheme, demonstrating its superiority over recent state-of-the-art segmentation methods. Also, a subgroup analysis split by MRI scanners, field strength, and tumor size is conducted to verify its generalization. The source code is released on (https://github.com/GDPHMediaLab/SwinHR).

NeighborNet: Learning Intra- and Inter-Image Pixel Neighbor Representation for Breast Lesion Segmentation.

Breast lesion segmentation from ultrasound images is essential in computer-aided breast cancer diagnosis. To alleviate the problems of blurry lesion boundaries and irregular morphologies, common practices combine CNN and attention to integrate global and local information. However, previous methods use two independent modules to extract global and local features separately, such feature-wise inflexible integration ignores the semantic gap between them, resulting in representation redundancy/insufficiency and undesirable restrictions in clinic practices. Moreover, medical images are highly similar to each other due to the imaging methods and human tissues, but the captured global information by transformer-based methods in the medical domain is limited within images, the semantic relations and common knowledge across images are largely ignored. To alleviate the above problems, in the neighbor view, this paper develops a pixel neighbor representation learning method (NeighborNet) to flexibly integrate global and local context within and across images for lesion morphology and boundary modeling. Concretely, we design two neighbor layers to investigate two properties (i.e., number and distribution) of neighbors. The neighbor number for each pixel is not fixed but determined by itself. The neighbor distribution is extended from one image to all images in the datasets. With the two properties, for each pixel at each feature level, the proposed NeighborNet can evolve into the transformer or degenerate into the CNN for adaptive context representation learning to cope with the irregular lesion morphologies and blurry boundaries. The state-of-the-art performances on three ultrasound datasets prove the effectiveness of the proposed NeighborNet. The code is available at: https://github.com/fjcaoww/NeighborNet.

A dual-stage transformer and MLP-based network for breast ultrasound image segmentation

Automatic segmentation of breast lesions from ultrasound images plays an important role in computer-aided breast cancer diagnosis. Many deep learning methods based on convolutional neural networks (CNNs) have been proposed for breast ultrasound image segmentation. However, breast ultrasound image segmentation is still challenging due to ambiguous lesion boundaries. We propose a novel dual-stage framework based on Transformer and Multi-layer perceptron (MLP) for the segmentation of breast lesions. We combine the Swin Transformer block with an efficient pyramid squeezed attention block in a parallel design and introduce bi-directional interactions across branches, which can efficiently extract multi-scale long-range dependencies to improve the segmentation performance and robustness of the model. Furthermore, we introduce tokenized MLP block in the MLP stage to extract global contextual information while retaining fine-grained information to segment more complex breast lesions. We have conducted extensive experiments with state-of-the-art methods on three breast ultrasound datasets, including BUSI, BUL, and MT_BUS datasets. The dice coefficient reached 0.8127 ± 0.2178, and the intersection over union reached 0.7269 ± 0.2370 on benign lesions when the Hausdorff distance was maintained at 3.75 ± 1.83. The dice coefficient of malignant lesions is improved by 3.09% for BUSI dataset. The segmentation results on the BUL and MT_BUS datasets also show that our proposed model achieves better segmentation results than other methods. Moreover, the external experiments indicate that the proposed model provides better generalization capability for breast lesion segmentation. The dual-stage scheme and the proposed Transformer module achieve the fine-grained local information and long-range dependencies to relieve the burden of radiologists.

An efficient hybrid computer-aided breast cancer diagnosis system with wavelet packet transform and synthetically-generated contrast-enhanced spectral mammography images

Contrast-enhanced spectral mammography (CESM) is an emerging modality for breast cancer diagnosis. This work investigates the feasibility of a computationally-efficient computer-aided diagnosis (CAD) system for breast lesion classification. Moreover, to avoid the need for intravenous contrast agents, we investigated the synthesis of contrast-enhanced (SynCESM) images. A total of 504 pairs of low-energy (LE) and CESM images were collected from 160 female subjects. A semi-automatic active-contour method was used for lesion segmentation. Then, 20 morphological and textural features were extracted. To improve the computational efficiency of the proposed system, the wavelet packet transform (WPT) was applied. Then, the same features were extracted from the WPT-approximated segmented lesions. Using LE images, a sigmoid-kernel SVM classifier exhibited a 90.20% accuracy, an 88.39% sensitivity, an 88.26% specificity, and a 0.92 AUC. The per-frame classification time was significantly reduced from 1.1046 s to 0.0734 s with WPT. Using CESM images, we achieved a 93.26% accuracy, a 95.94% sensitivity, a 93.37% specificity, a 0.94 AUC, and a 0.0657 s classification time. Interestingly, with SynCESM images, reasonable performance was still obtained with a 92.14% accuracy, a 93.87% sensitivity, a 91.58% specificity, a 0.93 AUC and a 0.0657 s classification time. Finally, with hybrid pairs of LE and CESM images, we got the best performance with a 96.87% accuracy, a 97.23% sensitivity, a 95.47% specificity, a 0.98 AUC, and a 0.0696 s classification time. The results demonstrate several advantages of the proposed system including its clinical feasibility, lower complexity, and reduced need for contrast agents via synthetic data generation.

Mass segmentation and classification from film mammograms using cascaded deep transfer learning

Breast cancer is the most common type of cancer among women worldwide. Early breast cancers have a high chance of cure so early diagnosis is critical. Mammography screening allows early detection of breast cancer. There has been an increasing interest in the investigation of computer-aided breast cancer diagnosis recently due in part to the development of the novel high-performing deep learning models. In this study, cascaded deep transfer learning (DTL)-based segmentation methods were investigated to segment mass lesions using mammograms of Breast Cancer Digital Repository. In the first stage, the noise sources in the mammogram background were removed by deep learning-based breast segmentation. In the second stage, the mass segmentation performances of five-layer U-net and U-nets having pre-trained weights from VGG16, ResNet50, and Xception networks in the encoding path were investigated. The performances of attention U-net, residual U-net, MultiResUnet, DeepLabV3Plus, and Unet++ were also investigated. A Unet++ model that uses Xception network weights in the encoder region is proposed. The mass segmentation model predictions were used to estimate mass lesion characterization using DTL. On the test data, an AUC of 0.7829, Dice’s similarity coefficient of 0.6356 and intersection over union of 0.5408 were obtained for mass segmentation using the proposed U-net++Xception model. An AUC of 0.8188 and accuracy of 0.7619 were obtained for mass classification into benign versus malignant. The results show that the proposed DTL pipeline can be used for automatic mass segmentation and classification without using clinical data and may reduce the workload of radiologists.

BI-RADS-NET-V2: A Composite Multi-Task Neural Network for Computer-Aided Diagnosis of Breast Cancer in Ultrasound Images With Semantic and Quantitative Explanations.

Computer-aided Diagnosis (CADx) based on explainable artificial intelligence (XAI) can gain the trust of radiologists and effectively improve diagnosis accuracy and consultation efficiency. This paper proposes BI-RADS-Net-V2, a novel machine learning approach for fully automatic breast cancer diagnosis in ultrasound images. The BI-RADS-Net-V2 can accurately distinguish malignant tumors from benign ones and provides both semantic and quantitative explanations. The explanations are provided in terms of clinically proven morphological features used by clinicians for diagnosis and reporting mass findings, i.e., Breast Imaging Reporting and Data System (BI-RADS). The experiments on 1,192 Breast Ultrasound (BUS) images indicate that the proposed method improves the diagnosis accuracy by taking full advantage of the medical knowledge in BI-RADS while providing both semantic and quantitative explanations for the decision.

Spatially localized sparse approximations of deep features for breast mass characterization.

We propose a deep feature-based sparse approximation classification technique for classification of breast masses into benign and malignant categories in film screen mammographs. This is a significant application as breast cancer is a leading cause of death in the modern world and improvements in diagnosis may help to decrease rates of mortality for large populations. While deep learning techniques have produced remarkable results in the field of computer-aided diagnosis of breast cancer, there are several aspects of this field that remain under-studied. In this work, we investigate the applicability of deep-feature-generated dictionaries to sparse approximation-based classification. To this end we construct dictionaries from deep features and compute sparse approximations of Regions Of Interest (ROIs) of breast masses for classification. Furthermore, we propose block and patch decomposition methods to construct overcomplete dictionaries suitable for sparse coding. The effectiveness of our deep feature spatially localized ensemble sparse analysis (DF-SLESA) technique is evaluated on a merged dataset of mass ROIs from the CBIS-DDSM and MIAS datasets. Experimental results indicate that dictionaries of deep features yield more discriminative sparse approximations of mass characteristics than dictionaries of imaging patterns and dictionaries learned by unsupervised machine learning techniques such as K-SVD. Of note is that the proposed block and patch decomposition strategies may help to simplify the sparse coding problem and to find tractable solutions. The proposed technique achieves competitive performances with state-of-the-art techniques for benign/malignant breast mass classification, using 10-fold cross-validation in merged datasets of film screen mammograms.

Public health implications of computer-aided diagnosis and treatment technologies in breast cancer care.

Breast cancer remains a significant public health issue, being a leading cause of cancer-related mortality among women globally. Timely diagnosis and efficient treatment are crucial for enhancing patient outcomes, reducing healthcare burdens and advancing community health. This systematic review, following the PRISMA guidelines, aims to comprehensively synthesize the recent advancements in computer-aided diagnosis and treatment for breast cancer. The study covers the latest developments in image analysis and processing, machine learning and deep learning algorithms, multimodal fusion techniques and radiation therapy planning and simulation. The results of the review suggest that machine learning, augmented and virtual reality and data mining are the three major research hotspots in breast cancer management. Moreover, this paper discusses the challenges and opportunities for future research in this field. The conclusion highlights the importance of computer-aided techniques in the management of breast cancer and summarizes the key findings of the review.

Trustworthy Breast Ultrasound Image Semantic Segmentation Based on Fuzzy Uncertainty Reduction.

Medical image semantic segmentation is essential in computer-aided diagnosis systems. It can separate tissues and lesions in the image and provide valuable information to radiologists and doctors. The breast ultrasound (BUS) images have advantages: no radiation, low cost, portable, etc. However, there are two unfavorable characteristics: (1) the dataset size is often small due to the difficulty in obtaining the ground truths, and (2) BUS images are usually in poor quality. Trustworthy BUS image segmentation is urgent in breast cancer computer-aided diagnosis systems, especially for fully understanding the BUS images and segmenting the breast anatomy, which supports breast cancer risk assessment. The main challenge for this task is uncertainty in both pixels and channels of the BUS images. In this paper, we propose a Spatial and Channel-wise Fuzzy Uncertainty Reduction Network (SCFURNet) for BUS image semantic segmentation. The proposed architecture can reduce the uncertainty in the original segmentation frameworks. We apply the proposed method to four datasets: (1) a five-category BUS image dataset with 325 images, and (2) three BUS image datasets with only tumor category (1830 images in total). The proposed approach compares state-of-the-art methods such as U-Net with VGG-16, ResNet-50/ResNet-101, Deeplab, FCN-8s, PSPNet, U-Net with information extension, attention U-Net, and U-Net with the self-attention mechanism. It achieves 2.03%, 1.84%, and 2.88% improvements in the Jaccard index on three public BUS datasets, and 6.72% improvement in the tumor category and 4.32% improvement in the overall performance on the five-category dataset compared with that of the original U-shape network with ResNet-101 since it can handle the uncertainty effectively and efficiently.

A Review of Computer-Aided Breast Cancer Diagnosis Using Sequential Mammograms.

Radiologists assess the results of mammography, the key screening tool for the detection of breast cancer, to determine the presence of malignancy. They, routinely, compare recent and prior mammographic views to identify changes between the screenings. In case a new lesion appears in a mammogram, or a region is changing rapidly, it is more likely to be suspicious, compared to a lesion that remains unchanged and it is usually benign. However, visual evaluation of mammograms is challenging even for expert radiologists. For this reason, various Computer-Aided Diagnosis (CAD) algorithms are being developed to assist in the diagnosis of abnormal breast findings using mammograms. Most of the current CAD systems do so using only the most recent mammogram. This paper provides a review of the development of methods to emulate the radiological approach and perform automatic segmentation and/or classification of breast abnormalities using sequential mammogram pairs. It begins with demonstrating the importance of utilizing prior views in mammography, through the review of studies where the performance of expert and less-trained radiologists was compared. Following, image registration techniques and their application to mammography are presented. Subsequently, studies that implemented temporal analysis or subtraction of temporally sequential mammograms are summarized. Finally, a description of the open access mammography datasets is provided. This comprehensive review can serve as a thorough introduction to the use of prior information in breast cancer CAD systems but also provides indicative directions to guide future applications.

Automated classification of breast cancer histologic grade using multiphoton microscopy and generative adversarial networks

Histological grade is one of the most powerful prognostic factors for breast cancer and impacts treatment decisions. However, a label-free and automated classification system for histological grading of breast tumors has not yet been developed. In this study, we employed label-free multiphoton microscopy (MPM) to acquire subcellular-resolution images of unstained breast cancer tissues. Subsequently, a deep-learning algorithm based on the generative adversarial network (GAN) was introduced to learn a representation using only MPM images without the histological grade information. Furthermore, to obtain abundant image information and determine the detailed differences between MPM images of different grades, a multiple-feature discriminator network based on the GAN was leveraged to learn the multi-scale spatial features of MPM images through unlabeled data. The experimental results showed that the classification accuracies for tumors of grades 1, 2, and 3 were 92.4%, 88.6%, and 89.0%, respectively. Our results suggest that the fusion of multiphoton microscopy and the GAN-based deep learning algorithm can be used as a fast and powerful clinical tool for the computer-aided intelligent pathological diagnosis of breast cancer.

A hybrid hemodynamic knowledge-powered and feature reconstruction-guided scheme for breast cancer segmentation based on DCE-MRI.

Automatically and accurately annotating tumor in dynamic contrast-enhanced magnetic resonance imaging (DCE-MRI), which provides a noninvasive in vivo method to evaluate tumor vasculature architectures based on contrast accumulation and washout, is a crucial step in computer-aided breast cancer diagnosis and treatment. However, it remains challenging due to the varying sizes, shapes, appearances and densities of tumors caused by the high heterogeneity of breast cancer, and the high dimensionality and ill-posed artifacts of DCE-MRI. In this paper, we propose a hybrid hemodynamic knowledge-powered and feature reconstruction-guided scheme that integrates pharmacokinetics prior and feature refinement to generate sufficiently adequate features in DCE-MRI for breast cancer segmentation. The pharmacokinetics prior expressed by time intensity curve (TIC) is incorporated into the scheme through objective function called dynamic contrast-enhanced prior (DCP) loss. It contains contrast agent kinetic heterogeneity prior knowledge, which is important to optimize our model parameters. Besides, we design a spatial fusion module (SFM) embedded in the scheme to exploit intra-slices spatial structural correlations, and deploy a spatial-kinetic fusion module (SKFM) to effectively leverage the complementary information extracted from spatial-kinetic space. Furthermore, considering that low spatial resolution often leads to poor image quality in DCE-MRI, we integrate a reconstruction autoencoder into the scheme to refine feature maps in an unsupervised manner. We conduct extensive experiments to validate the proposed method and show that our approach can outperform recent state-of-the-art segmentation methods on breast cancer DCE-MRI dataset. Moreover, to explore the generalization for other segmentation tasks on dynamic imaging, we also extend the proposed method to brain segmentation in DSC-MRI sequence. Our source code will be released on https://github.com/AI-medical-diagnosis-team-of-JNU/DCEDuDoFNet.

Mammogram classification based on a novel convolutional neural network with efficient channel attention

Early accurate mammography screening and diagnosis can reduce the mortality of breast cancer. Although CNN-based breast cancer computer-aided diagnosis (CAD) systems have achieved significant results in recent years, precise diagnosis of lesions in mammogram remains a challenge due to low signal-to-noise ratio (SNR) and physiological characteristics. Many researchers achieved excellent performance in detecting mammographic images by inputting region of interest (ROI) annotations while ROI annotations require a great quantity of manual labor, time and resources. We propose a two-stage method that combines images preprocessing and model optimization to address the aforementioned challenges. Firstly, we propose the breast database preprocess (BDP) method to preprocess INbreast then we get INbreast†. The only label we need is benign or malignant label of one mammogram, not manual labeling such as ROI annotations. Secondly, we apply focal loss to ECA-Net50 which is an improved model based on ResNet50 with efficient channel attention (ECA) module. Our method can adaptively extract the key features of mammograms, meanwhile solving the problem of hard-to-classify samples and unbalanced categories. The AUC value of our method on INbreast† is 0.960, accuracy is 0.929, Recall is 0.928. The precision of our method on INbreast† is 0.883 which improved by 0.254 compared to ResNet50. In addition, we use Grad-CAM to visualize the effect of our model. The visualized heatmaps extracted by our method can focus more on lesion regions. Both numerical and visualized experiments demonstrate that our method achieves satisfactory performance.

Joint Localization and Classification of Breast Cancer in B-Mode Ultrasound Imaging via Collaborative Learning With Elastography

Convolutional neural networks (CNNs) have been successfully applied in the computer-aided ultrasound diagnosis for breast cancer. Up to now, several CNN-based methods have been proposed. However, most of them consider tumor localization and classification as two separate steps, rather than performing them simultaneously. Besides, they suffer from the limited diagnosis information in the B-mode ultrasound (BUS) images. In this study, we develop a novel network ResNet-GAP that incorporates both localization and classification into a unified procedure. To enhance the performance of ResNet-GAP, we leverage stiffness information in the elastography ultrasound (EUS) modality by collaborative learning in the training stage. Specifically, a dual-channel ResNet-GAP network is developed, one channel for BUS and the other for EUS. In each channel, multiple class activity maps (CAMs) are generated using a series of convolutional kernels of different sizes. The multi-scale consistency of the CAMs in both channels are further considered in network optimization. Experiments on 264 patients in this study show that the newly developed ResNet-GAP achieves an accuracy of 88.6%, a sensitivity of 95.3%, a specificity of 84.6%, and an AUC of 93.6% on the classification task, and a 1.0NLF of 87.9% on the localization task, which is better than some state-of-the-art approaches.

YOLO-LOGO: A transformer-based YOLO segmentation model for breast mass detection and segmentation in digital mammograms

Background and objectiveBoth mass detection and segmentation in digital mammograms play a crucial role in early breast cancer detection and treatment. Furthermore, clinical experience has shown that they are the upstream tasks of pathological classification of breast lesions. Recent advancements in deep learning have made the analyses faster and more accurate. This study aims to develop a deep learning model architecture for breast cancer mass detection and segmentation using the mammography. MethodsIn this work we proposed a double shot model for mass detection and segmentation simultaneously using a combination of YOLO (You Only Look Once) and LOGO (Local-Global) architectures. Firstly, we adopted YoloV5L6, the state-of-the-art object detection model, to position and crop the breast mass in mammograms with a high resolution; Secondly, to balance training efficiency and segmentation performance, we modified the LOGO training strategy to train the whole images and cropped images on the global and local transformer branches separately. The two branches were then merged to form the final segmentation decision. ResultsThe proposed YOLO-LOGO model was tested on two independent mammography datasets (CBIS-DDSM and INBreast). The proposed model performs significantly better than previous works. It achieves true positive rate 95.7% and mean average precision 65.0% for mass detection on CBIS-DDSM dataset. Its performance for mass segmentation on CBIS-DDSM dataset is F1-score=74.5% and IoU=64.0%. The similar performance trend is observed in another independent dataset INBreast as well. ConclusionsThe proposed model has a higher efficiency and better performance, reduces computational requirements, and improves the versatility and accuracy of computer-aided breast cancer diagnosis. Hence it has the potential to enable more assistance for doctors in early breast cancer detection and treatment, thereby reducing mortality.

Computer-Aided Breast Cancer Diagnosis: Comparative Analysis of Breast Imaging Modalities and Mammogram Repositories.

The accurate assessment or diagnosis of breast cancer depends on image acquisition and image analysis and interpretation. The expert radiologist makes image interpretation, and this process has been greatly benefited by computer technology. For image acquisition, various imaging modalities have been developed and used over the years. This research examines several imaging modalities and their associated benefits and drawbacks. Commonly used parameters such as sensitivity and specificity are also offered to evaluate the usefulness of different imaging modalities. The main focus of the research is on mammograms. Despite the availability of breast cancer datasets of imaging modalities such as MRI, ultrasounds, and thermograms, mammogram datasets are used mainly by the domain researcher. They are considered an international gold standard for the early detection of breast cancer. We discussed and analyzed widely used and publicly available mammogram repositories. We further discussed some common key constraints related to mammogram datasets to develop the deep learningbased computer-aided diagnosis (CADx) systems for breast cancer. The ideas for their improvements have also been presented.

Feature Generalization for Breast Cancer Detection in Histopathological Images.

Recent period has witnessed benchmarked performance of transfer learning using deep architectures in computer-aided diagnosis (CAD) of breast cancer. In this perspective, the pre-trained neural network needs to be fine-tuned with relevant data to extract useful features from the dataset. However, in addition to the computational overhead, it suffers the curse of overfitting in case of feature extraction from smaller datasets. Handcrafted feature extraction techniques as well as feature extraction using pre-trained deep networks come into rescue in aforementioned situation and have proved to be much more efficient and lightweight compared to deep architecture-based transfer learning techniques. This research has identified the competence of classifying breast cancer images using feature engineering and representation learning over the established and contemporary notion of using transfer learning techniques. Moreover, it has revealed superior feature learning capacity with feature fusion in contrast to the conventional belief of understanding unknown feature patterns better with representation learning alone. Experiments have been conducted on two different and popular breast cancer image datasets, namely, KIMIA Path960 and BreakHis datasets. A comparison of image-level accuracy is performed on these datasets using the above-mentioned feature extraction techniques. Image level accuracy of 97.81% is achieved for KIMIA Path960 dataset using individual features extracted with handcrafted (color histogram) technique. Fusion of uniform Local Binary Pattern (uLBP) and color histogram features has resulted in 99.17% of highest accuracy for the same dataset. Experimentation with BreakHis dataset has resulted in highest classification accuracy of 88.41% with color histogram features for images with 200X magnification factor. Finally, the results are contrasted to that of state-of-the-art and superior performances are observed on many occasions with the proposed fusion-based techniques. In case of BreakHis dataset, the highest accuracies 87.60% (with least standard deviation) and 85.77% are recorded for 200X and 400X magnification factors, respectively, and the results for the aforesaid magnification factors of images have exceeded the state-of-the-art.

BREAST CANCER CAD SYSTEM BY USING TRANSFER LEARNING AND ENHANCED ROI

Computer systems are being employed in specialized professions such as medical diagnosis to alleviate some of the costs and to improve dependability and scalability. This paper implements a computer aided breast cancer diagnosis system. It utilizes the publicly available mini MIAS mammography image dataset. Images are preprocessed to clean isolate breast tissue region. Extracted regions are used to adjust and verify a pretrained convolutional deep neural network, the GoogLeNet. The implemented model shows good performance results compared to other published works with accuracy of 86.6%, sensitivity of 75% and specificity of 88.9%.

BREAST CANCER CAD SYSTEM BY USING TRANSFER LEARNING AND ENHANCED ROI

Computer systems are being employed in specialized professions such as medical diagnosis to alleviate some of the costs and to improve dependability and scalability. This paper implements a computer aided breast cancer diagnosis system. It utilizes the publicly available mini MIAS mammography image dataset. Images are preprocessed to clean isolate breast tissue region. Extracted regions are used to adjust and verify a pretrained convolutional deep neural network, the GoogLeNet. The implemented model shows good performance results compared to other published works with accuracy of 86.6%, sensitivity of 75% and specificity of 88.9%.

Automatic Breast Mass Segmentation and Classification Using Subtraction of Temporally Sequential Digital Mammograms

Cancer remains a major cause of morbidity and mortality globally, with 1 in 5 of all new cancers arising in the breast. The introduction of mammography for the radiological diagnosis of breast abnormalities, significantly decreased their mortality rates. Accurate detection and classification of breast masses in mammograms is especially challenging for various reasons, including low contrast and the normal variations of breast tissue density. Various Computer-Aided Diagnosis (CAD) systems are being developed to assist radiologists with the accurate classification of breast abnormalities. In this study, subtraction of temporally sequential digital mammograms and machine learning are proposed for the automatic segmentation and classification of masses. The performance of the algorithm was evaluated on a dataset created especially for the purposes of this study, with 320 images from 80 patients (two time points and two views of each breast) with precisely annotated mass locations by two radiologists. Ninety-six features were extracted and ten classifiers were tested in a leave-one-patient-out and k-fold cross-validation process. Using Neural Networks, the detection of masses was 99.9% accurate. The classification accuracy of the masses as benign or suspicious increased from 92.6%, using the state-of-the-art temporal analysis, to 98%, using the proposed methodology. The improvement was statistically significant (p-value < 0.05). These results demonstrate the effectiveness of the subtraction of temporally consecutive mammograms for the diagnosis of breast masses. Clinical and Translational Impact Statement: The proposed algorithm has the potential to substantially contribute to the development of automated breast cancer Computer-Aided Diagnosis systems with significant impact on patient prognosis.