The assessment of breast density is crucial in the context of breast cancer screening, especially in populations with a higher percentage of dense breast tissues. This study introduces a novel data augmentation technique termed Attention-Guided Erasing (AGE), devised to enhance the downstream classification of four distinct breast density categories in mammography following the BI-RADS recommendation in the Vietnamese cohort. The proposed method integrates supplementary information during transfer learning, utilizing visual attention maps derived from a vision transformer backbone trained using the self-supervised DINO method. These maps are utilized to erase background regions in the mammogram images, unveiling only the potential areas of dense breast tissues to the network. Through the incorporation of AGE during transfer learning with varying random probabilities, we consistently surpass classification performance compared to scenarios without AGE and the traditional random erasing transformation. We validate our methodology using the publicly available VinDr-Mammo dataset. Specifically, we attain a mean F1-score of 0.5910, outperforming values of 0.5594 and 0.5691 corresponding to scenarios without AGE and with random erasing (RE), respectively. This superiority is further substantiated by t-tests, revealing a p-value of p<0.0001, underscoring the statistical significance of our approach.

Abstract-Breast cancer (BC) significantly contributes to cancer-related mortality in women, underscoring the criticality of early detection for optimal patient outcomes. A mammography is a key tool for identifying and diagnosing breast abnormalities; however, accurately distinguishing malignant mass lesions remains challenging. To address this issue, we propose a novel deep learning approach for BC screening utilizing mammography images. Our proposed model comprises three distinct stages: data collection from established benchmark sources, image segmentation employing an Atrous Convolution-based Attentive and Adaptive Trans-Res-UNet (ACA-ATRUNet) architecture, and BC identification via an Atrous Convolution-based Attentive and Adaptive Multiscale DenseNet (ACA-AMDN) model. The hyperparameters within the ACA-ATRUNet and ACA-AMDN models are optimised using the Modified Mussel Length-based Eurasian Oystercatcher Optimization (MML-EOO) algorithm. Performance evaluation, leveraging multiple metrics, is conducted, and a comparative analysis against conventional methods is presented. Our experimental findings reveal that the proposed BC detection framework attains superior precision rates in early disease detection, demonstrating its potential to enhance mammography-based screening methodologies. Keywords: Breast Cancer; Mammograms; Atrous Convolution-based Attentive and Adaptive Trans-Res-UNet; Modified Mussel Length-based Eurasian Oystercatcher Optimization; Atrous Convolution based Attentive and Adaptive Multi-scale DenseNet 1. Introduction The most prevalent type of malignancy in women is BC. Next to cancer, it is the second leading reason of mortality in women [1]. One in every 36 female deaths is related to BC, or around 3% of all female deaths are caused by BC. In order to improve the survival rate of the patient, early BC identification is crucial [2]. Researchers are introducing increasingly accurate models for BC diagnosis into practice because of the tremendous fatality and high expense of cancer-related treatment [3, 4]. Radiotherapists use mammography as an efficient imaging method to detect and screen the presence of BC. Mammography is the primary clinical test for BC and is quite accurate in predicting BC. Breast lumps and calcifications are considered the early signs of BC, respectively.

Science and technology often facilitate one another; the latest discoveries in one will lead to new discoveries in the other. Along with innovations in engineering, medicine, and many other fields, this co-evolution can also be seen in physics. The continuing improvements in technology, in particular artificial intelligence (AI) and machine learning (ML), open doors for physics researchers to explore more precise and in-depth topics -- leading to new discoveries and a deeper understanding of our world. With roots in statistical mechanics, the mathematical foundation of AI development is shared with many branches of physics, making the two natural counterparts. Since "physics" is an extremely broad subject area and covers many different fields, each field may utilize AI differently.

Artificial intelligence (AI) models that evaluate medical images have potential to speed up and improve accuracy of cancer diagnoses, but they may also be vulnerable to cyberattacks. In a new study, University of Pittsburgh researchers simulated an attack that falsified mammogram images, fooling both an AI breast cancer diagnosis model and human breast imaging radiologist experts. The study, published today in Nature Communications, brings attention to a potential safety issue for medical AI known as "adversarial attacks," which seek to alter images or other inputs to make models arrive at incorrect conclusions. "What we want to show with this study is that this type of attack is possible, and it could lead AI models to make the wrong diagnosis -- which is a big patient safety issue," said senior author Shandong Wu, Ph.D., associate professor of radiology, biomedical informatics and bioengineering at Pitt. "By understanding how AI models behave under adversarial attacks in medical contexts, we can start thinking about ways to make these models safer and more robust." AI-based image recognition technology for cancer detection has advanced rapidly in recent years, and several breast cancer models have U.S. Food and Drug Administration (FDA) approval.

Artificial intelligence and machine learning systems continue to be adopted into an ever wider array of healthcare applications, such as assisting doctors with medical image diagnostics. Capable of understanding X-rays and rapidly generating MRIs -- sometimes even able to spot cases of COVID -- these systems have also proven effective at noticing early signs of breast cancer which might otherwise be missed by radiologists. Google and IBM, as well as medical centers and university research teams around the world, have all sought to develop such cancer-catching algorithms. They can spot worrisome lumps as well as radiologists can and predict future onsets of the disease "significantly" better than the humans that trained them. However many medical AI imaging systems produce markedly less accurate results for black and brown people -- despite WOC being 43 percent more likely to die from breast cancer compared to their white counterparts.

More than a year since they announced a partnership to advance machine learning advancement in areas such as oncology, precision medicine and imaging, the researchers of the Pittsburgh Health Data Alliance and AWS, are unveiling new AI-based techniques to assess breast cancer risk, understand tumor growth and better spot markers of depression. In one project, a team in the radiology department at University of Pittsburgh are using deep-learning systems to analyze mammograms in order to predict the short‐term risk of developing breast cancer and develop a more personalized approach for patients undergoing screening. Researchers gathered more than 450 de-identified normal screening mammogram images from 226 patients, half of whom later developed breast cancer and half of whom did not. With help from AWS tools, they developed two different machine learning models to analyze the images for characteristics that could help predict breast cancer risk. Both outperformed the simple measure of breast density, which today is the primary imaging marker for breast cancer risk.

In the existing research of mammogram image classification, either clinical data or image features of a specific type is considered along with the supervised classifiers such as Neural Network (NN) and Support Vector Machine (SVM). This paper considers automated classification of breast tissue type as benign or malignant using Weighted Feature Support Vector Machine (WFSVM) through constructing the precomputed kernel function by assigning more weight to relevant features using the principle of maximizing deviations. Initially, MIAS dataset of mammogram images is divided into training and test set, then the preprocessing techniques such as noise removal and background removal are applied to the input images and the Region of Interest (ROI) is identified. The statistical features and texture features are extracted from the ROI and the clinical features are obtained directly from the dataset. The extracted features of the training dataset are used to construct the weighted features and precomputed linear kernel for training the WFSVM, from which the training model file is created. Using this model file the kernel matrix of test samples is classified as benign or malignant. This analysis shows that the texture features have resulted in better accuracy than the other features with WFSVM and SVM. However, the number of support vectors created in WFSVM is less than the SVM classifier.

A recent study by IBM Research, together with Sage Bionetworks, Kaiser Permanente Washington Health Research Institute, and the University of Washington School of Medicine, has uncovered how combining machine learning algorithms and assessments by radiologists could improve the overall accuracy of breast cancer screenings. Mammogram screenings, commonly used by radiologists for the early detection of breast cancer, according to IBM researcher Stefan Harrer, frequently rely on a radiologist's expertise to visually identify signs of cancer, which is not always accurate. "Through the current state of human interpretation of mammography images, two things happen: Misdiagnosis in terms of missing the cancer and also diagnosing cancer when it's not there," Harrer told ZDNet. "Both cases are highly undesirable -- you never want to miss a cancer when it's there, but also if you're diagnosing a cancer and it's not there, it creates enormous pressure on patients, on the healthcare system, that could be avoided. "That is exactly where we aim to improve things through the incorporation of AI (artificial intelligence) to decrease the rate of false positives, which is the diagnosis of cancer, and also to decrease missing the cancer when there is one." The research used more than 310,800 de-identified mammograms and clinical data from Kaiser Permanente Washington (KPWA) and the Karolinska Institute (KI) in Sweden. Of the combined datasets, KI contributed around 166,500 examinations from 6,800 women, of which 780 were cancer positive; while the remaining 144,200 examinations were provided by KPWA from 85,500 women, of which 941 were cancer positive. "We had hundreds of thousands of mammograms that were annotated.

While there has been controversy over when and how often women should be screened for breast cancer using mammograms, studies consistently show that screening can lead to earlier detection of the disease, when it's more treatable. So improving how effectively mammograms can detect abnormal growths that could be cancerous is a priority in the field. AI could play a role in accomplishing that--computer-based machine learning might help doctors to read mammograms more accurately. In a study published Jan. 1 in Nature, researchers from Google Health, and from universities in the U.S. and U.K., report on an AI model that reads mammograms with fewer false positives and false negatives than human experts. The algorithm, based on mammograms taken from more than 76,000 women in the U.K. and more than 15,000 in the U.S., reduced false positive rates by nearly 6% in the U.S., where women are screened every one to two years, and by 1.2% in the U.K., where women are screened every three years.

Pharmaceutical companies spend a lot of time testing potential drugs, and they end up wasting much of that effort on candidates that don't pan out. Kyle Swanson wants to change that. A master's student in computer science and engineering, Swanson is working on a project that involves feeding a computer information about chemical compounds that have or have not worked as drugs in the past. From this input, the machine "learns" to predict which kinds of new compounds have the most promise as drug candidates, potentially saving money and time otherwise spent on testing. Several prominent companies have already adopted the software as their new model.