Computer-aided breast cancer detection and classification in mammography: A comprehensive review

Breast cancer is an important topic in medical image analysis because it is a high-risk disease and the leading cause of death in women. Early detection of breast cancer improves treatment outcomes, which can be achieved by identifying it using mammography images. Computer-aided diagnostic systems detect and classify medical images of breast lesions, allowing radiologists to make accurate diagnoses. Deep learning algorithms improved the performance of these diagnoses systems. We utilized efficient deep learning approaches to propose a system that can detect breast cancer in mammograms. The proposed approach adopted relies on two main elements: improving image contrast to enhance marginal information and extracting discriminatory features sufficient to improve overall classification quality, these improvements achieved based on a new model from scratch to focus on enhancing the accuracy and reliability of breast cancer detection. The model trained on the digital database for screening mammography (DDSM) dataset and compared with different convolutional neural network (CNN) models, namely EfficientNetB1, EfficientNetB5, ResNet-50, and ResNet101. Moreover, to enhance the feature selection process, we have integrated adam optimizer in our methodology. In evaluation, the proposed method achieved 96.5% accuracy across the dataset. These results show the effectiveness of this method in identifying breast cancer through images.

This paper presents a comparison of feature selection methods for a unified detection of breast cancers in mammograms. A set of features, including curvilinear features, texture features, Gabor features, and multi-resolution features, were extracted from a region of 512x512 pixels containing normal tissue or breast cancer. Adaptive floating search and genetic algorithm were used for the feature selection, and a linear discriminant analysis (LDA) was used for the classification of cancer regions from normal regions. The performance is evaluated using Az the area under ROC curve. On a dataset consisting 296 normal regions and 164 cancer regions (53 masses, 56 spiculated lesions, and 55 calcifications), adaptive floating search achieved Az = 0.96 with comparison to Az = 0.93 of CHC genetic algorithm and Az = 0.90 of simple genetic algorithm.

The most commonly occurring cancer in the world is breast cancer with more than 500,000 cases across the world. The detection mechanism for breast cancer is endoscopist-dependent and necessitates a skilled pathologist. However, in recent years many computer-aided diagnoses (CADs) have been used to diagnose and classify breast cancer using traditional RGB images that analyze the images only in three-color channels. Nevertheless, hyperspectral imaging (HSI) is a pioneering non-destructive testing (NDT) image-processing technique that can overcome the disadvantages of traditional image processing which analyzes the images in a wide-spectrum band. Eight studies were selected for systematic diagnostic test accuracy (DTA) analysis based on the results of the Quadas-2 tool. Each of these studies’ techniques is categorized according to the ethnicity of the data, the methodology employed, the wavelength that was used, the type of cancer diagnosed, and the year of publication. A Deeks’ funnel chart, forest charts, and accuracy plots were created. The results were statistically insignificant, and there was no heterogeneity among these studies. The methods and wavelength bands that were used with HSI technology to detect breast cancer provided high sensitivity, specificity, and accuracy. The meta-analysis of eight studies on breast cancer diagnosis using HSI methods reported average sensitivity, specificity, and accuracy of 78%, 89%, and 87%, respectively. The highest sensitivity and accuracy were achieved with SVM (95%), while CNN methods were the most commonly used but had lower sensitivity (65.43%). Statistical analyses, including meta-regression and Deeks’ funnel plots, showed no heterogeneity among the studies and highlighted the evolving performance of HSI techniques, especially after 2019.

This research proposes a new framework for detection of breast cancer in mammograms. It extracts certain dynamic features to distinguish between benign and malignant mammograms. To this aim, this framework uses set of various techniques. First step we have achieved improvement on breast mammogram to improve the image accuracy based on this framework, after new method has been used for features extraction. New methods named Sparse Principal Component Analysis and Weighted Sparse Principal Component Analysis are used to select the distinctive features of the mammograms. The analyzed mammograms are then identified as benign or malignant through codebook technique is more efficient than other on the MIAS data set. The proposed framework tested on MIAS data set achieved an overall classification accuracy of 98% with codebook classifier for sequential selection of benign and malignant mammograms. Suggested method achieves good results when we have verified on various mammograms.

Deep and machine learning techniques for medical imaging-based breast cancer: A comprehensive review

Discovery and development of novel therapies in advanced breast cancer: rapid development of ribociclib

disease control. Palbociclib plus fulvestrant allowed patients to maintain good quality of live (QoL) in the endocrine resistance setting while experiencing substantially delayed disease progression [5]. In the phase II trial PALOMA 1 evaluating palbociclib in combination with letrozole in treatment-naive patients, an improvement in progression-free survival could be seen (26.1 vs. 7.5 months) [6]. The results of the phase III trial PALOMA 2 evaluating letrozole with or without palbociclib in HR-positive, HER2negative advanced breast cancer patients presented at the ASCO Annual Meeting in June 2016 confirmed these positive findings [7]. All trials illustrate the high potential of CDK4/6 inhibition and the clinical impact of this new treatment approach. In this issue of Breast Care, Marcus Schmidt will highlight pre-clinical data and early clinical trials which led to an accelerated approval of palbociclib by the US Food and Drug Administration (FDA) as first-line treatment in combination with letrozole in advanced HR-positive and HER2-negative breast cancer [8]. Johannes Ettl adds more data about the clinical trials investigating palbociclib [9]. To date, 2 large clinical trials have been fully published and one was presented at a meeting. In his article, he discusses the results of these trials and their clinical relevance for the management of HR-positive advanced breast cancer. In addition, he gives information about QoL measurement in patients treated in the PALOMA 3 trial. Romualdo Barroso-Sousa and colleagues give an overview about new upcoming components, mainly abemaciclib and ribociclib [10]. The preclinical and clinical data are described as well as toxicity profiles and drug action. Ribociclib has already been investigated in the combination with antiestrogens in the MONALEESA trials and also with additional PI3K inhibitors. Abemaciclib is the only CDK4/6 inhibitor that passes the blood-brain barrier. But it also has a different toxicity profile. The combination with antiestrogens has been investigated in the MONARCH trials. Selective CDK4/6 inhibitors represent an important therapeutic advance in HR-positive breast cancer. The role in other breast canAlmost two thirds of breast cancers express the estrogen receptor (ER), which plays an important role in malignant growth stimulation and as therapeutic target. In postmenopausal patients, aromatase inhibitors (AI, e.g., letrozole and anastrozole) have become the treatment of choice in first-line therapy [1]. Unfortunately, some patients have a primary or de novo resistance to first-line endocrine therapy and even patients who initially respond will acquire resistance to treatment and relapse. On disease progression, second-line treatment options include other classes of AI (steroidal or nonsteroidal) and the ER antagonists fulvestrant and tamoxifen [2]. The study of resistance to endocrine therapies in hormone receptor (HR)-positive breast cancer has aimed at identifying new therapeutic strategies that enhance the efficacy of endocrine therapies. However, endocrine resistance is a frequent problem in breast cancer treatment. Yet, insights into estrogen mediated signaling allowed the development of therapeutic approaches interacting with the cell cycle which might overcome endocrine resistance in breast cancer patients. Dysregulation of the cell-cycle control is a frequent event in breast cancer and occurs via a number of different mechanisms. These dysregulations involving components of CDK4/6 and cyclin D lead to a survival advantage of the cancer cell. CDK4/6 inhibition can reduce cell growth and suppress DNA replication in tumors with functional tumor-suppressor retinoblastoma protein (RB). The cell-cycle machinery is important for efficacy of hormonal therapy in breast cancer, as ER-positive RB-negative xenograft models are resistant to tamoxifen [3]. In ER-positive metastatic breast cancer, often several lines of therapy are effective until patients require chemotherapy. Cellcycle control is a very promising additional option to prolong progression-free survival and time until chemotherapy is needed. Results from the phase III study PALOMA 3 showed that adding palbociclib to fulvestrant more than doubled the duration of disease control. Women with previously treated, HR-positive, HER2negative advanced breast cancer [4] gained almost 5 months of Published online: June 22, 2016

One of the signs of early breast cancer is the presence of microcalcification clusters in mammograms. Automated diagnostic aids for detection of breast cancer in mammograms must determine the presence of microcalcification clusters with high enough accuracy to serve as a clinical tool. To do so, the automated system has to process the digitized mammogram with at least three different types of algorithms. The first is segmentation of individual small candidate structures that are separated from the background tissue. The second is extraction of quantitative features from each candidate structure, to represent size, shape, texture, contrast, etc. The third is classification of candidate structures as microcalcification or other tissue, using the feature values, based on automated training against ground truth provided by clinical experts. An optional fourth type of algorithm, enhancement, may also be used as a preprocessing step, depending on the image quality, to reduce the noise level of the image or to increase the contrast of candidate objects before segmentation is applied. In this multistage process, the role of segmentation is essential because the delineation of each candidate object dictates the extracted features, and subsequently their classification. This chapter focuses on segmentation algorithms that are especially suited for segmenting small, low-contrast, arbitrarily shaped objects such as microcalcifications in mammograms. Segmentation algorithms used to separate objects of interest from the image background are primarily based on three different approaches. Some algorithms determine the pixels of the object by comparing their brightness values to either a global or local threshold. The second type of algorithm first determines the edge pixels of the object using a gradient operator, then an edge-linking technique forms a closed contour and labels all pixels within the edge contour. The third approach is to grow a region of contiguous pixels starting from a seed pixel selected inside the object. The segmentation of microcalcifications in mammograms is especially demanding because each microcalcification is a very small, low-contrast object embedded in a nonuniform background that may have significant spatial high-frequency components. An edge detector applied to a mammogram finds edges throughout the image and may also overlook the edges of some microcalcifications due to their low contrast. Segmentation of small, low-contrast objects such as microcalcifications cannot effectively be based on conventional edge detection, especially because linking edge pixels obtained on a mammogram is not practical. Most algorithms reported for segmentation of microcalcifications are based either on thresholding or region growing, with or without enhancement. The segmentation algorithm suggested in Refs. 1 and 2 compares each pixel to a local threshold computed within a square neighborhood around the pixel. The size of the neighborhood is selected by the user, and the threshold is set as the mean value of pixels in the neighborhood plus their rms value multiplied by a selected coefficient. This threshold represents the highest value that the background pixels in that neighborhood are expected to have. Pixels that have values greater than the threshold are connected to form the segmented region.

Breast cancer accounts for an extremely high annual death rate. Many tools have been created to facilitate earlier diagnosis of breast cancer, which is the most common cancer among females. According to the research, cancer of the breast is also regarded as the second most deadly form of the disease. It is the most prominent kind of the disease and the top reason for death among females worldwide. Any progress made in the early detection and identification of cancer is crucial to maintaining good health. Therefore, it is essential to improve both the therapeutic aspect and the survival standard of patients by utilizing high precision in cancer prognosis. A reliable, effective, and speedy reaction from medical professionals is provided by an automatic disease identification system, which also reduces the danger of death. Recently, breast cancer screening methods that utilise deep learning have shown promising results, allowing for earlier identification and thereby enhancing patients’ chances of survival thanks to the introduction of artificial intelligence (AI). Deep learning reduces the need for manual intervention while extracting features, in comparison to traditional machine learning methods. We provide a brief overview of deep learning techniques, data availability, and the many breast cancer screening options, such as mammography, thermography, ultrasound, and MRI. Using demographic, laboratory, & mammographic data, this investigation sought to forecast breast cancer using various Deep learning algorithms. Ultimately, we apply artificial intelligence to breast cancer clinical trials and compare the proposed approach to current algorithms.

Breast cancer remains one of the major global health challenges, the Human Epidermal Receptor-2 (HER-2) subtype is characterized by aggressive tumor growth due to overexpression of the HER2-positive. Early detection of HER2-positive breast cancer is crucial for improving patient’s outcomes and reducing the risk of metastatic disease. Circulating Tumor DNA is DNA fragments which are released by cancer cells into the bloodstream, and has emerged as a promising non-invasive biomarker for early cancer detection. This review will explore the role of ctDNA in the early detection of HER2-positive breast cancer and its role in prognosis. Studies have shown the high relevance of ctDNA as a diagnostic biomarker, particularly in early-stage disease. Multiple studies have evaluated the role of ctDNA in breast cancer patients, which results consistently showed a strong relation between ctDNA detection and early-stage disease. Additionally, research has indicated that high ctDNA levels are related with a higher risk of recurrence and poorer survival outcomes. The non-invasive nature of ctDNA testing offers several advantages compared to traditional methods, including the ability of monitoring disease progression and treatment response without any need for invasive procedures. Early detection of HER2-positive breast cancer through ctDNA analysis can potentially improve patient outcomes by enabling timely intervention and targeted therapies. By identifying patients with high risk and monitoring disease status, ctDNA testing may contribute to more effective management of HER2-positive breast cancer. While ctDNA analysis shows great promise, it is also important to acknowledge the current limitations and challenges associated with its clinical application. Issues such as standardization of detection methods, sensitivity, and specificity need to be addressed to ensure the widespread adoption of ctDNA testing in routine clinical practice. In conclusion, ctDNA represents a promising biomarker for the early detection and management of HER2-positive breast cancer. Further research and advancements in ctDNA analysis are essential to completely realize its potential and improve patient outcomes.

The object of this work is the application of steerable filters for the diagnosis of breast cancer. Because of the very specific geometry of malignant densities, we intend to apply a multiscale and orientation shiftable method for the detection of breast cancer in mammograms. Stellate masses have an irregular appearance and are frequently surrounded by a radiating pattern of linear spicules. Multiscale approaches using oriented filters have proved to be efficient to detect such stellate patterns. We first use the fact that tumors are always brighter than the surrounding tissues to locate suspicious regions. The detection is then based on steerable filters, which can be steered to any orientation fixed by the user, and are synthesized using a limited number of basis filters. These filters are used in a recursive multi-scale transform: the steerable pyramid. Using the steerable pyramid, oriented contrast enhancement is performed. The resulting enhanced image is then analyzed to estimate whether a stellate mass is present or not.

To deal with computer aided detection of breast cancer in mammograms, an efficient automated preprocessing stage is the most vital step which assists radiologist’s decision. The approach proposes a model for the segmentation and enhancement of the breast region. The proposed method includes gradient weight map followed by region property-based extraction and morphological operations for background suppression and artifacts removal. Intensity adjustment and Otsu’s thresholding methods were adopted for breast region extraction. Finally, enhancement of the breast region is accomplished by Contrast-Limited Adaptive Histogram Equalization (CLAHE) and Decorrelation stretch. Experimentation conducted on mini Mammographic Image Analysis Society (miniMIAS) dataset shows segmentation accuracy of about 97.64%. Enhancement contributes with better feature discrimination with high Peak Signal Noise Ratio (PSNR) and low Root Mean Square Error (RMSE).KeywordsMammogramsSegmentationGradient weightOtsu’s thresholdContrast-Limited Adaptive Histogram Equalization (CLAHE)Decorrelation stretch

Background Earlier detection of breast cancer through mammography screening has reduced disease-specific mortality; however, confounding issues such as technical challenges, breast density, and tumor size can result in false negatives and ultimately later stage diagnosis. Next generation liquid biopsy has the potential to complement mammography and enable earlier detection for more women. We have previously demonstrated high sensitivity and specificity for early detection of invasive breast cancer (IBC) by utilizing a novel category of cancer-associated small RNAs, termed orphan noncoding RNAs (oncRNAs), through a liquid biopsy platform. Here, we further improve the ability to detect breast cancer in a larger, multi-source cohort through an AI-driven approach and demonstrate potential for detection of ductal carcinoma in-situ (DCIS). Methods We utilized The Cancer Genome Atlas (TCGA) small RNA-seq database to discover a library of 20,538 oncRNAs, through a female-specific analysis, that were significantly enriched among 1,103 breast tumors compared to 349 normal tissue samples spanning multiple tissue sites. The diagnostic performance of these oncRNAs were assessed in an independent cohort of archived serum samples from 663 female individuals, sourced from Indivumed (Hamburg, Germany), Proteogenex (Inglewood, CA), and MT Group (Los Angeles, CA), including 279 breast cancer patients of various stages (221 IBC and 58 DCIS; mean age: 57.0 ± 13.8 years; ever-smoker: 25.8%) and 304 age-matched controls (mean age: 58.5 ± 13.9 years; ever-smoker: 23.4%) without breast cancer. All samples were collected between 2010–2022 at time of diagnosis for breast cancer patients. We sequenced the small RNA content of these samples at an average depth of 25.28 ± 9.37 million 50-bp single-end reads. We detected 18,025 (87.8%) unique breast cancer-specific oncRNA species within at least one sample from the study cohort. We then trained a generative AI model using 5-fold cross-validation to predict cancer status for all samples. Results Our oncRNA-based model achieved an overall AUC of 0.95 (95% CI, 0.93–0.97) for prediction of IBC versus cancer-free controls with a sensitivity of 0.87 (0.82–0.91) at 90% specificity. We observed high sensitivities, also at 90% specificity, across all tumor stages and tumor sizes (Table 1). Sensitivities for the earliest stage and smallest tumor size were 0.87 (0.78–0.93) and 0.81 (0.61–0.93) for Stage I (n=83) and T1a–b ( >1mm to ≤10mm; n=26), respectively. Additionally, in a small single-source cohort, we also saw high model accuracy and sensitivity for DCIS, which we aim to confirm in additional cohorts. While our overall cancer cohort primarily consisted of individuals with luminal breast cancer, our model had high sensitivities across all breast cancer subtypes at 0.90 (0.84–0.94), 0.73 (0.59–0.85), and 0.86 (0.42–1.0) for luminal (n=181), HER2 positive (n=49), and triple negative (n=7), respectively. Conclusions We further demonstrate the potential utility of oncRNAs as a blood-based biomarker using an AI algorithm for sensitive and accurate early detection of breast cancer in a large cohort. Additionally, we have shown that this oncRNA-based assay performs well in detecting small, early-stage invasive breast tumors, with potential to detect precursors of breast cancer. Table 1: Model sensitivity in breast cancer by tumor stage and size For each tumor stage and size, as defined by the AJCC 7th Edition breast cancer staging system, sensitivity and 95% Pearson-Clopper confidence intervals (CI) are reported at 90% specificity for the number of samples (N). Citation Format: Noura Tbeileh, Taylor Cavazos, Mehran Karimzadeh, Jeffrey Wang, Alice Huang, Dung Ngoc Lam, Seda Kilinc, Jieyang Wang, Xuan Zhao, Andy Pohl, Helen Li, Lisa Fish, Kimberly Chau, Marra Francis, Lee Schwartzberg, Patrick Arensdorf, Hani Goodarzi, Fereydoun Hormozdiari, Babak Alipanahi. Cell-free orphan noncoding RNAs and AI enable early detection of invasive breast cancer and ductal carcinoma in-situ [abstract]. In: Proceedings of the 2023 San Antonio Breast Cancer Symposium; 2023 Dec 5-9; San Antonio, TX. Philadelphia (PA): AACR; Cancer Res 2024;84(9 Suppl):Abstract nr PO2-13-08.

In the modern era, cancer is a major public health concern. Breast cancer is one of the leading causes of death among women. Breast cancer is becoming the top cause of death in women worldwide. Early identification of breast cancer allows patients to receive proper treatment, improving their chances of survival. The proposed Generative Adversarial Networks (GAN) approach is designed to aid in the detection and diagnosis of breast cancer. GANs are deep learning algorithms that generate new data instances that mimic the training data. GAN is made up of two parts: a generator that learns to generate false data and a discriminator that learns from this false data. Furthermore, the histogram of oriented gradients (HOG) is utilized as a feature descriptor in image processing and other computer vision techniques. Gradient orientation in the detection window and region of interest is determined by the histogram of oriented gradients descriptor approach. Using an image dataset and deep learning techniques, the proposed research (GAN-HOG) aims to improve the efficiency and performance of breast cancer diagnosis. The deep learning method is used here to analyze image data by segmenting and classifying the input photographs from the dataset. Unlike many existing nonlinear classification models, the proposed method employs a conditional distribution for the outputs. The proposed model GAN-HOG had an accuracy of 98.435%, a ResNet50 accuracy of 87.826%, a DCNN accuracy of 92.547%, a VGG16 accuracy of 89.453%, and an SVM accuracy of 95.546%.

Early Detection of Breast Cancer in Mammograms Using a Combined Segmentation and ResNet Framework