Breast Mammogram Images Research Articles

Selection of the Discriming Feature Using the BEMD’s BIMF for Classification of Breast Cancer Mammography Image

Mammogram exam images are useful in identifying diseases, such as breast cancer, which is one of the deadliest cancers, affecting adult women around the world. Computational image analysis and machine learning techniques can help experts identify abnormalities in these images. In this work we present a new system to help diagnose and analyze breast mammogram images. To do this, the system a method the Selection of the Most Discriminant Attributes of the images preprocessed by BEMD “SMDA-BEMD”, this entails picking the most pertinent traits from the collection of variables that characterize the state under study. A reduction of attribute based on a transformation of the data also called an extraction of characteristics by extracting the Haralick attributes from the Co-occurrence Matrices Methods “GLCM” this reduction which consists of replacing the initial set of data by a new reduced set, constructed at from the initial set of features extracted by images decomposed using Bidimensional Empirical Multimodal Decomposition “BEMD”, for discrimination of breast mammogram images (healthy and pathology) using BEMD. This decomposition makes it possible to decompose an image into several Bidimensional Intrinsic Mode Functions “BIMFs” modes and a residue. The results obtained show that mammographic images can be represented in a relatively short space by selecting the most discriminating features based on a supervised method where they can be differentiated with high reliability between healthy mammographic images and pathologies, However, certain aspects and findings demonstrate how successful the suggested strategy is to detect the tumor. A BEMD technique is used as preprocessing on mammographic images. This suggested methodology makes it possible to obtain consistent results and establishes the discrimination threshold for mammography images (healthy and pathological), the classification rate is improved (98.6%) compared to existing cutting-edge techniques in the field. This approach is tested and validated on mammographic medical images from the Kenitra-Morocco reproductive health reference center (CRSRKM) which contains breast mammographic images of normal and pathological cases.

Abstract A088: Utilizing Machine Learning Techniques to Investigate Mammograms for Breast Cancer Detection

Abstract Purpose: The prevalence of artificial intelligence (AI) in breast cancer screening and diagnosis has substantially increased over the past 5 years. AI can be used to assist in the interpretation of mammograms and other breast imaging modalities, as well as predict patient outcomes. This study aims to quantify AI's diagnostic accuracy and its ability to detect breast cancer from a large database of mammograms. The implementation of AI in breast cancer screening holds immense potential to not only enhance the accuracy of mammogram interpretation but also improve the overall efficiency of radiologists and healthcare providers. Furthermore, we aim to contribute to the advancement of the rapidly growing field of machine learning in medicine, particularly in breast cancer care. Our hope is that by applying this technology, we can improve patient outcomes and increase accessibility to breast cancer screening and early detection. Methods: A deep neural network (DNN) model was built on Tensorflow utilizing Radiological Society of North America Screening Mammography Breast Cancer Detection dataset, consisting of normal mammograms and abnormal mammograms with tumors. The model's efficacy was assessed using Area under the curve (AUC), precision, and recall, with images randomly split into training (80%), validation (10%), and test sets (10%). Four consecutive training sessions each lasting 2 hours and 13 minutes using 8,877 images consisting of 4,621 breast cancer and 4,456 normal breast mammogram images was done. Results: The model attained an AUC of 0.926, Specificity of 95%, Sensitivity of 73% and Accuracy of 84%. Conclusion: This DNN model was created for diagnosing breast cancer from mammograms, with higher AUC than the current standard. This study highlights the potential of AI to revolutionize breast cancer screening, prevention, and diagnosis, which will ultimately improve patient outcomes and increase accessibility for patients. The use of AI in detecting breast cancer on mammograms can not only provide support to radiologists but also improve their efficacy and accuracy, reducing the burden of high volume images. Additionally, the use of AI in detection and screening can address the barriers that come with physician shortages, especially in underserved areas. Extending AI’s reach to these areas of limited access can improve early detection and screening which tends to be lacking in under-resourced areas, thus addressing the gap in health equity worldwide. While this study highlights encouraging data at the intersection of AI and medicine, we acknowledge that AI’s role in medicine is not to replace but rather enhance the expertise of radiologists. Lastly, we hope that our developed tool can alleviate the workload of radiologists and increase efficiency in high-pressure settings such as emergency departments and rural areas, ultimately leading to improved patient care. Citation Format: Parsa Riazi Esfahani, Maya M Maalouf, Akshay J Reddy, Prashant Chawla. Utilizing Machine Learning Techniques to Investigate Mammograms for Breast Cancer Detection [abstract]. In: Proceedings of the AACR Special Conference in Cancer Research: Advances in Breast Cancer Research; 2023 Oct 19-22; San Diego, California. Philadelphia (PA): AACR; Cancer Res 2024;84(3 Suppl_1):Abstract nr A088.

A learning-based approach to breast cancer screening using mammography images

<p>The current big challenge facing radiologists in healthcare is the automatic detection and classification of masses in breast mammogram images. In the last few years, many researchers have proposed various solutions to this problem. These solutions are effectively dependent and work on annotated breast image data. But these solutions fail when applied to unlabeled and non-annotated breast image data. Therefore, this paper provides the solution to this problem with the help of a neural network that considers any kind of unlabeled data for its procedure. In this solution, the algorithm automatically extracts tumors in images using a segmentation approach, and after that, the features of the tumor are extracted for further processing. This approach used a double thresholding-based segmentation technique to obtain a perfect location of the tumor region, which was not possible in existing techniques in the literature. The experimental results also show that the proposed algorithm provides better accuracy compared to the accuracy of existing algorithms in the literature.</p>

Abstract B014: Improving prediction of second events after DCIS using whole breast mammogram images

Abstract Purpose: We aim to improve prediction of subsequent events after DCIS. Current models show relatively poor performance predicting subsequent events and often are limited to ipsilateral events. National population-based SEER data including over160,000 cases of DCIS and followed an average of 90 months indicate that second events (including risk of invasive breast cancer – IBC) are equality likely in the ipsilateral and contralateral breast. Thus, additional information on risk may be obtained by more complete modeling of risk estimating recurrence. Mammographic images have been largely ignored despite evidence that even breast density improves prediction of breast cancer in the general population. Furthermore, we have shown whole breast mammogram images (WBI) included in Cox models significantly improves prediction of breast cancer risk over using mammographic breast density alone and breast cancer risk factors. Population: We retrieved digital mammograms for women diagnosed with DCIS at Washington University School of Medicine from 2008 onwards and followed for subsequent diagnosis of pathology confirmed breast lesions. Using more than 100 cases and controls matched on year of mammogram and age we fit Cox models to evaluate risk of ipsilateral invasive breast cancer. To compare and accommodate laterality of subsequent breast lesions, we fit competing risk models using baseline covariates that are available on the women-level as well as WBI that are side-specific. Results: Preliminary analysis shows WBI predicts subsequent invasive breast cancer. Further, we will demonstrate appropriate models adjusting for competing risk gives unbiased estimates of invasive breast cancer. Conclusion: WBI and competing risk analysis improves our understanding of associations for side of occurrence of subsequent breast lesions after an initial diagnosis of DCIS. Citation Format: Shu (Joy) Jiang, Graham A. Colditz. Improving prediction of second events after DCIS using whole breast mammogram images [abstract]. In: Proceedings of the AACR Special Conference on Rethinking DCIS: An Opportunity for Prevention?; 2022 Sep 8-11; Philadelphia, PA. Philadelphia (PA): AACR; Can Prev Res 2022;15(12 Suppl_1): Abstract nr B014.

Microcalcification Discrimination in Mammography Using Deep Convolutional Neural Network: Towards Rapid and Early Breast Cancer Diagnosis.

Breast cancer is among the most common types of cancer in women and under the cases of misdiagnosed, or delayed in treatment, the mortality risk is high. The existence of breast microcalcifications is common in breast cancer patients and they are an effective indicator for early sign of breast cancer. However, microcalcifications are often missed and wrongly classified during screening due to their small sizes and indirect scattering in mammogram images. Motivated by this issue, this project proposes an adaptive transfer learning deep convolutional neural network in segmenting breast mammogram images with calcifications cases for early breast cancer diagnosis and intervention. Mammogram images of breast microcalcifications are utilized to train several deep neural network models and their performance is compared. Image filtering of the region of interest images was conducted to remove possible artifacts and noises to enhance the quality of the images before the training. Different hyperparameters such as epoch, batch size, etc were tuned to obtain the best possible result. In addition, the performance of the proposed fine-tuned hyperparameter of ResNet50 is compared with another state-of-the-art machine learning network such as ResNet34, VGG16, and AlexNet. Confusion matrices were utilized for comparison. The result from this study shows that the proposed ResNet50 achieves the highest accuracy with a value of 97.58%, followed by ResNet34 of 97.35%, VGG16 96.97%, and finally AlexNet of 83.06%.

Detection and Weak Segmentation of Masses in Gray-Scale Breast Mammogram Images Using Deep Learning.

PurposeIn this paper, we propose deep-learning methodology with which to enhance the mass differentiation performance of convolutional neural network (CNN)-based architecture.Materials and MethodsWe differentiated breast mass lesions from gray-scale X-ray mammography images based on regions of interest (ROIs). Our dataset comprised breast mammogram images for 150 cases of malignant masses from which we extracted the mass ROI, and we composed a CNN-based deep learning model trained on this dataset to identify ROI mass lesions. The test dataset was created by shifting some of the training data images. Thus, although both datasets were different, they retained a deep structural similarity. We then applied our trained deep-learning model to detect masses on 8-bit mammogram images containing malignant masses. The input images were preprocessed by applying a scaling parameter of intensity before being used to train the CNN model for mass differentiation.ResultsThe highest area under the receiver operating characteristic curve was 0.897 (Î 20).ConclusionOur results indicated that the proposed patch-wise detection method can be utilized as a mass detection and segmentation tool.

Breast tumor segmentation on medical images using combination of fuzzy clustering and threshold

Breast tumor segmentation and boundary detection are crucial stages in breast cancer therapy and follow-up. Radiologists can minimize the high workload associated with screening for breast cancer by automating this complex process. This article proposes a system for segmenting breast and unaffected areas (breast) tumors on medical images using a combination of fuzzy clustering and thresholding (FCMT) tools. This computer diagnostic method works with each section of the mammary gland without learning segmentation and definition of boundaries. As part of the approbation, two databases of breast mammogram images were used. To increase the image quality, we used pre-processing techniques such as contrast augmentation before applying the FCMT for segmentation. To assess the effectiveness of the devised approach, the Mean Square Error, dice coefficient, Structured Similarity Index, Peak Signal-to-Noise Ratio, accuracy, and sensitivity were computed. Using the proposed FCMT segmentation technique, a mean intersection over union (IoU) of 93.85 was attained. The presented approach is more resilient and accurate in segmenting tumor progression on medical images, according to the findings of the experiments.

Evaluation Of Machine Learning Classifiers In Breast Cancer Diagnosis

Breast Cancer is one among the most deadly diseases that threaten women. It affects women in general but men are also not exceptions to it. Most breast cancers end up fatal except for a few cases. Early diagnosis of the disease helps in successful treatment and cure. Computer Aided Detection (CADe) or Computer Aided Diagnosis (CADx) System helps physicians to take prompt decisions in the field of medical imaging. CAD systems are aimed at identifying the abnormalities at the earliest in the human body which a human professional may fail to detect. Machine learning techniques in the field of medical imaging are increasingly being used in the accurate diagnosis of breast cancer. Machine learning classifiers such as Support Vector Machine and Neural Network are examined in this paper. Breast mammogram images, both normal and pathological images were used in this experiment. The machine learning classifiers were employed to identify the given image as either Benign ore Malignant. Performance of both the classifiers was recorded and it was observed that the Neural Network classifier excelled in the diagnosis with 98% accuracy than the Support Vector Machine classifier.

Detection and Classification of Breast Cancer in Mammography Images Using Pattern Recognition Methods

Introduction: In this paper, a method is presented to classify the breast cancer masses according to new geometric features. Methods: After obtaining digital breast mammogram images from the digital database for screening mammography (DDSM), image preprocessing was performed. Then, by using image processing methods, an algorithm was developed for automatic extracting of masses from other normal parts of the breast image. In this study, 19 final different features of each image were extracted to generate the feature vector for classifier input. The proposed method not only determined the boundary of masses but also classified the type of masses such as benign and malignant ones. The neural network classification methods such as the radial basis function (RBF), probabilistic neural network (PNN), and multi-layer perceptron (MLP) as well as the Takagi-Sugeno-Kang (TSK) fuzzy classification, the binary statistic classifier, and the k-nearest neighbors (KNN) clustering algorithm were used for the final decision of mass class. Results: The best results of the proposed method for accuracy, sensitivity, and specificity metrics were obtained 97%±4.36, 100%±0 and 96%±5.81, respectively for support vector machine (SVM) classifier. Conclusions: By comparing the results of the proposed method with the results of the other previous methods, the efficiency of the proposed algorithm was reported.

Quantum Noise Removal from Breast Mammograms Using Genetic Programming based Hybrid Ensemble Filter

Quantum noise are more likely to occur in mammographic images and it effects the accuracy of classification. In this paper, Genetic Programming (GP) based novel hybrid ensemble method designed for noise amputation from breast mammogram images has been proposed. Three different filters Frost filter, Weiner filter and Non Local Means has been fused by using Genetic Programming for noise removal. The fused GP based filter calculate the value by combining three filters and replacing them with the noisy pixels. Peak signal to noise ratio (PSNR) and Structure Similarity Index measure (SSIM) as a quantitative measures has been employed for evaluation of proposed method with different existing methods. Experimental results show that proposed method bring forward better results as compared to existing methods. Keywords: Frost, genetic programming, non local mean, quantum noise, weiner.

Applying a modified version of Lyapunov exponent for cancer diagnosis in biomedical images: the case of breast mammograms

Recently, there has been a great interest in the application of Lyapunov exponents for calculation of chaos levels in dynamical systems. Accordingly, this study aims at presenting two new methods for utilizing Lyapunov exponents to evaluate the spatiotemporal chaos in various images. Further, early detection of cancerous tumors could be obtained by measuring the chaotic indices in biomedical images. Unlike the available systems described by partial differential equations, the proposed method employs a number of interactive dynamic variables for image modeling. Since the Lyapunov exponents cannot be applied to such systems, the image model should be modified. The mean Lyapunov exponent is defined as a chaotic index for measuring the contour borders irregularities in images to detect benign or malignant tumors. Moreover, a two-dimensional mean Lyapunov exponent is incorporated to identify irregularities existing in each axis of the targeted images. Experiments on a set of region of interest in breast mammogram images yielded a sensitivity of 95 % and a specificity of 97.3 % and verified the remarkable precision of the proposed methods in classifying of breast lesions obtained from breast mammogram images.

Multi class Abnormal Breast Tis sue segmentation using Texture Features and Analyzing the Growth Factor Using Power Law

This paper motivated to design and develop an automatic model for multi-class breast tissue segmentation and find the growth of the cancer in breast mammogram images. Various breast tissues are categorized by a novel texture features such as PTPSA[Piecewise Triangular Prism Surface Area], intensity difference and regular-intensity in mammogram images. Using CRF-[Classical Random Forest] method segmentation and classification of the features can be obtained in mammogram images. The input image feature values are compared to the ground-truth values for confirming the true positive rate of the proposed approach. Efficacy of abnormal breast tissue segmentation is evaluated using publicly available MIAS training dataset.In this paper, we investigate the consequences of an option, yet just as conceivable, suspicion of tumor growth, to be specific power growth law, acknowledged in direct expand in tumor breadth. We exhibit a simple model for tumor growth, whose global flow demonstrates power law growth of the tumor, much under boundless supplement supply. For corroboration, it is carried out and examined one-, two- and three-dimensional tumor growth tests both in vitro, in MCF-7 cells (breast malignancy cell line) and in vivo, in mouse xenografts.After successful tissue segmentation, the growth of the tissue is analyzed using Power Law. Performance evaluation of the proposed approach can be obtained by comparing the simulation output with the ground truth data. The accuracy of the proposed approach reaches up to 97% for MIAS database in term of tumor detection. Also, simulating radiotherapy under power law, Gompertz and exponential tumor growth, it is indicated that the power law model predicts profoundly diverse conclusions for the usually used treatment. This shows the significance of utilizing the proper tumor growth model when computing ideal measurement fractionation plan for radiotherapy.

Fourier irregularity index: A new approach to measure tumor mass irregularity in breast mammogram images

Shape descriptors have been identified as important features in distinguishing malignant masses from benign masses. Thus, an effective morphological irregularity measure could provide a helpful reference to indicate the likelihood of malignancy of breast masses. In this paper, a new Fourier-Transform-based measure of irregularity—Fourier Irregularity Index (F 2), is proposed to provide reliable malignant/benign tumor/mass classification. The proposed measure has been evaluated on 418 breast masses, including 190 malignant masses and 218 benign lesions identified by radiologists on film mammograms. The results show the proposed measure has better performance than other approaches, such as Compactness Index (CI), Fractal Dimension (FD) and the Fourier-descriptor-based shape Factor (FF). Furthermore, these mentioned measures are paired to investigate the possibility of performance improvement. The results showed the combination of F 2 and CI further enhances the performance in indicating the likelihood of malignancy of breast masses.

MRT letter: Quantum noise removal and classification of breast mammogram images

Because of the limitations of the X-ray hardware systems in mammogram machines, the quality of the breast mammogram images may undergo from poor resolution or low contrast. Quantum noise occurs in the mammogram images during acquisition due to low-count X-ray photons. In this work, an adaptive frost filter has been used to remove quantum noise. Local binary patterns have been extracted to classify breast mammograms into benign and malignant using different classifiers. Results show the superiority of the proposed algorithm in terms of sensitivity, specificity, and accuracy. Mammographic Institute Society Analysis database of mammography has been used for experimentation. Peak signal-to-noise ratio and structural similarity index measure are used to test the validity of adaptive frost filter. Experiment results show that proposed technique produces better results.

Quantum and impulse noise filtering from breast mammogram images

Recent advances in the field of image processing have shown that level of noise highly affect the quality and accuracy of classification when working with mammographic images. In this paper, we have proposed a method that consists of two major modules: noise detection and noise filtering. For detection purpose, neural network is used which effectively detect the noise from highly corrupted images. Pixel values of the window and some other features are used as feature for the training of neural network. For noise removal, three filters are used. The weighted average value of these three filters is filled on noisy pixels. The proposed technique has been tested on salt & pepper and quantum noise present in mammogram images. Peak signal to noise ratio (PSNR) and structural similarity index measure (SSIM) are used for comparison of proposed technique with different existing techniques. Experiments shows that proposed technique produce better results as compare to existing methods.

MRT letter: Segmentation and texture‐based classification of breast mammogram images

Breast cancer is the most common cancer diagnosed among women. In this article, support vector machine is used to classify digital mammogram images into malignant and benign. Wiener filter is used to handle the possible quantum noise, which is more likely to occur in mammograms. Stack-based connected component method is proposed for background removal, and the image is enhanced using retinax method. Seeded region growing algorithm is used to remove the pectoral muscle part of the mammogram. We have extracted 13 different multidomains' features for classification. Results show the superiority of the proposed algorithm in terms of sensitivity, specificity, and accuracy. We have used MIAS database of mammography for experimentation.