Digital Mammograms Research Articles

Consistency of Artificial Intelligence (AI)-based Diagnostic Support Software in Short-term Digital Mammography Reimaging After Core Needle Biopsy.

To evaluate the consistency in the performance of Artificial Intelligence (AI)-based diagnostic support software in short-term digital mammography reimaging after core needle biopsy. Of 276 women who underwent short-term (<3 mo) serial digital mammograms followed by breast cancer surgery from Jan. to Dec. 2017, 550 breasts were included. All core needle biopsies for breast lesions were performed between serial exams. All mammography images were analyzed using a commercially available AI-based software providing an abnormality score (0-100). Demographic data for age, interval between serial exams, biopsy, and final diagnosis were compiled. Mammograms were reviewed for mammographic density and finding. Statistical analysis was performed to evaluate the distribution of variables according to biopsy and to test the interaction effects of variables with the difference in AI-based score according to biopsy. AI-based score of 550 exams (benign or normal in 263 and malignant in 287) showed significant difference between malignant and benign/normal exams (0.48 vs. 91.97 in first exam and 0.62 vs. 87.13 in second exam, P<0.0001). In comparison of serial exams, no significant difference was found in AI-based score. AI-based score difference between serial exams was significantly different according to biopsy performed or not (-0.25 vs. 0.07, P = 0.035). In linear regression analysis, there was no significant interaction effect of all clinical and mammographic characteristics with mammographic examinations performed after biopsy or not. The results from AI-based diagnostic support software for digital mammography was relatively consistent in short-term reimaging even after core needle biopsy.

Extended Mammogram Classification From Textural Features

"The efficient analysis of digital mammograms has an important role in the early detection of breast cancer and can lead to a higher percentage of recovery. This paper presents an extended computer-aided diagnosis system for the classification of mammograms into three classes (normal, benign and malignant). The performance of the system is evaluated for two different mammogram databases (MIAS and DDSM) in order to assess its robustness. We discuss the changes required in the system, particularly at the level of the image preprocessing and feature extraction. Computational experiments are performed based on different methods for feature extraction, selection and classification. The results indicate an accuracy of 66.95% for the MIAS dataset and 54.1% for DDSM obtained using genetic algorithm based feature selection and Random Forest classification. Keywords: Breast cancer detection, Mammogram classification, GLRLM, Feature selection, Random Forests, MIAS, DDSM. "

Evaluation of an AI Model to Assess Future Breast Cancer Risk.

Background Accurate breast cancer risk assessment after a negative screening result could enable better strategies for early detection. Purpose To evaluate a deep learning algorithm for risk assessment based on digital mammograms. Materials and Methods A retrospective observational matched case-control study was designed using the OPTIMAM Mammography Image Database from the National Health Service Breast Screening Programme in the United Kingdom from February 2010 to September 2019. Patients with breast cancer (cases) were diagnosed following a mammographic screening or between two triannual screening rounds. Controls were matched based on mammography device, screening site, and age. The artificial intelligence (AI) model only used mammograms at screening before diagnosis. The primary objective was to assess model performance, with a secondary objective to assess heterogeneity and calibration slope. The area under the receiver operating characteristic curve (AUC) was estimated for 3-year risk. Heterogeneity according to cancer subtype was assessed using a likelihood ratio interaction test. Statistical significance was set at P < .05. Results Analysis included patients with screen-detected (median age, 60 years [IQR, 55-65 years]; 2044 female, including 1528 with invasive cancer and 503 with ductal carcinoma in situ [DCIS]) or interval (median age, 59 years [IQR, 53-65 years]; 696 female, including 636 with invasive cancer and 54 with DCIS) breast cancer and 1:1 matched controls, each with a complete set of mammograms at the screening preceding diagnosis. The AI model had an overall AUC of 0.68 (95% CI: 0.66, 0.70), with no evidence of a significant difference between interval and screen-detected (AUC, 0.69 vs 0.67; P = .085) cancer. The calibration slope was 1.13 (95% CI: 1.01, 1.26). There was similar performance for the detection of invasive cancer versus DCIS (AUC, 0.68 vs 0.66; P = .057). The model had higher performance for advanced cancer risk (AUC, 0.72 ≥stage II vs 0.66 <stage II; P = .037). The AUC for detecting breast cancer in mammograms at diagnosis was 0.89 (95% CI: 0.88, 0.91). Conclusion The AI model was found to be a strong predictor of breast cancer risk for 3-6 years following a negative mammographic screening. © RSNA, 2023 Supplemental material is available for this article. See also the editorial by Mann and Sechopoulos in this issue.

Pectoral Muscle Removal in Digital Mammograms Using Region Based Standard Otsu Technique

Pectoral Muscle Removal in Digital Mammograms Using Region Based Standard Otsu Technique

Developing a Supplementary Diagnostic Tool for Breast Cancer Risk Estimation Using Ensemble Transfer Learning.

Breast cancer is the most prevalent cancer worldwide. Thus, it is necessary to improve the efficiency of the medical workflow of the disease. Therefore, this study aims to develop a supplementary diagnostic tool for radiologists using ensemble transfer learning and digital mammograms. The digital mammograms and their associated information were collected from the department of radiology and pathology at Hospital Universiti Sains Malaysia. Thirteen pre-trained networks were selected and tested in this study. ResNet101V2 and ResNet152 had the highest mean PR-AUC, MobileNetV3Small and ResNet152 had the highest mean precision, ResNet101 had the highest mean F1 score, and ResNet152 and ResNet152V2 had the highest mean Youden J index. Subsequently, three ensemble models were developed using the top three pre-trained networks whose ranking was based on PR-AUC values, precision, and F1 scores. The final ensemble model, which consisted of Resnet101, Resnet152, and ResNet50V2, had a mean precision value, F1 score, and Youden J index of 0.82, 0.68, and 0.12, respectively. Additionally, the final model demonstrated balanced performance across mammographic density. In conclusion, this study demonstrates the good performance of ensemble transfer learning and digital mammograms in breast cancer risk estimation. This model can be utilised as a supplementary diagnostic tool for radiologists, thus reducing their workloads and further improving the medical workflow in the screening and diagnosis of breast cancer.

Using Deep Ensemble Learning In Digital Mammogram for Automated Classification Breast Mass

Using Deep Ensemble Learning In Digital Mammogram for Automated Classification Breast Mass

Mammography Datasets for Neural Networks-Survey.

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

Maternal Age at the Last Birth and the Risk for Breast Cancer: A Case Control-Retrospective Study and Mini-Review of the Literature

Objective: Maternal age at the last birth and the risk of developing breast cancer were subjects of epidemiologic research, with controversial results. In order to objectively assess the relationship between maternal age at the last birth and the risk of developing breast cancer, we carried out this case control-retrospective study. Material and Methods: In our case-control retrospective analysis, 342 women who visited two breast clinics in Greece and had given birth to live newborns were analyzed. Women with breast cancer were included in the case group, whereas women without the disease were included in the control group. All women underwent a clinical examination that included a breast ultrasound and, in those who were older than 40 years old, also a digital bilateral mammogram was performed. Results: Mann-Whitney test observed that p-value = 0.474 and concluded that there is no statistically significant difference in the distributions of maternal age at birth of the last child of the two groups of women and the risk of breast cancer development. Conclusion: Our study showed no statistically significant relationship between maternal age at the last birth and breast cancer. Further studies with a larger number of patients are mandatory in order to confirm this result.

Deep learning denoising of digital breast tomosynthesis: Observer performance study of the effect on detection of microcalcifications in breast phantom images.

The noise in digital breast tomosynthesis (DBT) includes x-ray quantum noise and detector readout noise. The total radiation dose of a DBT scan is kept at about the level of a digital mammogram but the detector noise is increased due to acquisition of multiple projections. The high noise can degrade the detectability of subtle lesions, specifically microcalcifications (MCs). We previously developed a deep-learning-based denoiser to improve the image quality of DBT. In the current study, we conducted an observer performance study with breast radiologists to investigate the feasibility of using deep-learning-based denoising to improve the detection of MCs in DBT. We have a modular breast phantom set containing seven 1-cm-thick heterogeneous 50% adipose/50% fibroglandular slabs custom-made by CIRS, Inc. (Norfolk, VA). We made six 5-cm-thick breast phantoms embedded with 144 simulated MC clusters of four nominal speck sizes (0.125-0.150, 0.150-0.180, 0.180-0.212, 0.212-0.250mm) at random locations. The phantoms were imaged with a GE Pristina DBT system using the automatic standard (STD) mode. The phantoms were also imaged with the STD+ mode that increased the average glandular dose by 54% to be used as a reference condition for comparison of radiologists' reading. Our previously trained and validated denoiser was deployed to the STD images to obtain a denoised DBT set (dnSTD). Seven breast radiologists participated as readers to detect the MCs in the DBT volumes of the six phantoms under the three conditions (STD, STD+, dnSTD), totaling 18 DBT volumes. Each radiologist read all the 18 DBT volumes sequentially, which were arranged in a different order for each reader in a counter-balanced manner to minimize any potential reading order effects. They marked the location of each detected MC cluster and provided a conspicuity rating and their confidence level for the perceived cluster. The visual grading characteristics (VGC) analysis was used to compare the conspicuity ratings and the confidence levels of the radiologists for the detection of MCs. The average sensitivities over all MC speck sizes were 65.3%, 73.2%, and 72.3%, respectively, for the radiologists reading the STD, dnSTD, and STD+ volumes. The sensitivity for dnSTD was significantly higher than that for STD (p<0.005, two-tailed Wilcoxon signed rank test) and comparable to that for STD+. The average false positive rates were 3.9±4.6, 2.8±3.7, and 2.7±3.9 marks per DBT volume, respectively, for reading the STD, dnSTD, and STD+ images but the difference between dnSTD and STD or STD+ did not reach statistical significance. The overall conspicuity ratings and confidence levels by VGC analysis for dnSTD were significantly higher than those for both STD and STD+ (p≤0.001). The critical alpha value for significance was adjusted to be 0.025 with Bonferroni correction. This observer study using breast phantom images showed that deep-learning-based denoising has the potential to improve the detection of MCs in noisy DBT images and increase radiologists' confidence in differentiating noise from MCs without increasing radiation dose. Further studies are needed to evaluate the generalizability of these results to the wide range of DBTs from human subjects and patient populations in clinical settings.

Processing of digital mammogram images using optimized ELM with deep transfer learning for breast cancer diagnosis

Processing of digital mammogram images using optimized ELM with deep transfer learning for breast cancer diagnosis

International Interobserver Variability of Breast Density Assessment

PurposeThe aim of this study was to determine variability in visually assessed mammographic breast density categorization among radiologists practicing in Indonesia, the Netherlands, South Africa, and the United States. MethodsTwo hundred consecutive 2-D full-field digital screening mammograms obtained from September to December 2017 were selected and retrospectively reviewed from four global locations, for a total of 800 mammograms. Three breast radiologists in each location (team) provided consensus density assessments of all 800 mammograms using BI-RADS® density categorization. Interreader agreement was compared using Gwet’s AC2 with quadratic weighting across all four density categories and Gwet’s AC1 for binary comparison of combined not dense versus dense categories. Variability of distribution among teams was calculated using the Stuart-Maxwell test of marginal homogeneity across all four categories and using the McNemar test for not dense versus dense categories. To compare readers from a particular country on their own 200 mammograms versus the other three teams, density distribution was calculated using conditional logistic regression. ResultsFor all 800 mammograms, interreader weighted agreement for distribution among four density categories was 0.86 (Gwet’s AC2 with quadratic weighting; 95% confidence interval, 0.85-0.88), and for not dense versus dense categories, it was 0.66 (Gwet’s AC1; 95% confidence interval, 0.63-0.70). Density distribution across four density categories was significantly different when teams were compared with one another and one team versus the other three teams combined (P < .001). Overall, all readers placed the largest number of mammograms in the scattered and heterogeneous categories. ConclusionsAlthough reader teams from four different global locations had almost perfect interreader agreement in BI-RADS density categorization, variability in density distribution across four categories remained statistically significant.

Impact of Artificial Intelligence System and Volumetric Density on Risk Prediction of Interval, Screen-Detected, and Advanced Breast Cancer.

Artificial intelligence (AI) algorithms improve breast cancer detection on mammography, but their contribution to long-term risk prediction for advanced and interval cancers is unknown. We identified 2,412 women with invasive breast cancer and 4,995 controls matched on age, race, and date of mammogram, from two US mammography cohorts, who had two-dimensional full-field digital mammograms performed 2-5.5 years before cancer diagnosis. We assessed Breast Imaging Reporting and Data System density, an AI malignancy score (1-10), and volumetric density measures. We used conditional logistic regression to estimate odds ratios (ORs), 95% CIs, adjusted for age and BMI, and C-statistics (AUC) to describe the association of AI score with invasive cancer and its contribution to models with breast density measures. Likelihood ratio tests (LRTs) and bootstrapping methods were used to compare model performance. On mammograms between 2-5.5 years prior to cancer, a one unit increase in AI score was associated with 20% greater odds of invasive breast cancer (OR, 1.20; 95% CI, 1.17 to 1.22; AUC, 0.63; 95% CI, 0.62 to 0.64) and was similarly predictive of interval (OR, 1.20; 95% CI, 1.13 to 1.27; AUC, 0.63) and advanced cancers (OR, 1.23; 95% CI, 1.16 to 1.31; AUC, 0.64) and in dense (OR, 1.18; 95% CI, 1.15 to 1.22; AUC, 0.66) breasts. AI score improved prediction of all cancer types in models with density measures (PLRT values < .001); discrimination improved for advanced cancer (ie, AUC for dense volume increased from 0.624 to 0.679, Δ AUC 0.065, P = .01) but did not reach statistical significance for interval cancer. AI imaging algorithms coupled with breast density independently contribute to long-term risk prediction of invasive breast cancers, in particular, advanced cancer.

An in silico study on the detectability of field cancerization through parenchymal analysis of digital mammograms.

Parenchymal analysis has shown promising performance for the assessment of breast cancer risk through the characterization of the texture features of mammography images. However, the working principles behind this practice are yet not well understood. Field cancerization is a phenomenon associated with genetic and epigenetic alterations in large volumes of cells, putting them on a path of malignancy before the appearance of recognizable cancer signs. Evidence suggests that it can induce changes in the biochemical and optical properties of thetissue. The aim of this work was to study whether the extended genetic mutations and epigenetic changes due to field cancerization, and the impact they have on the biochemistry of breast tissues are detecTable in the radiological patterns of mammography images. An in silico experiment was designed, which implied the development of a field cancerization model to modify the optical tissue properties of a cohort of 60 voxelized virtual breast phantoms. Mammography images from these phantoms were generated and compared with images obtained from their non-modified counterparts, i.e. without field cancerization. We extracted 33 texture features from the breast area to quantitatively assess the impact of the field cancerization model. We analyzed the similarity and statistical equivalence of texture features with and without field cancerization using the t-test, Wilcoxon sign rank test and Kolmogorov-Smirnov test, and performed a discrimination test using multinomial logistic regression analysis with lasso regularization. With modifications of the optical tissue properties on 3.9% of the breast volume, some texture features started to fail to show equivalence (p\le0.05). At 7.9% volume modification, a high percent of texture features showed statistically significant differences (p\le0.05) and non-equivalence. At this level, multinomial logistic regression analysis of texture features showed a statistically significant performance in the discrimination of mammograms from breasts with and without field cancerization (AUC= 0.89, 95% CI: 0.75 - 1.00). These results support the idea that field cancerization is a feasible underlying working principle behind the distinctive performance of parenchymal analysis in breast cancer riskassessment. This article is protected by copyright. All rights reserved.

Web-Based System for Remote Mammogram Processing

This paper presents a web-based system for remote processing of mammographic images (mammograms) using Matlab Web Service. The Matlab Web Service is a toolbox for accessing Matlab applications from the internet. We created an image processing system that combines the computational and graphical abilities of Matlab with remote access through the internet. Our system for mammogram processing is a Matlab application stored on a local workstation. By using a web browser users can upload their data (mammogram and parameters necessary for image processing) and view the results obtained after processing (notification about the breast cancer existence). The presented computer system for mammogram processing includes three modules: image preprocessing, feature extraction, and classification. The preprocessing phase consists of the image de-noising, region of interest extraction and image contrast enhancement. The second phase is based on feature extraction techniques for detecting abnormalities in digital mammograms. A total of 20 texture features based on gray-level co-occurrence matrices are used to evaluate the effectiveness of textural information possessed by mass regions. To investigate the ability of the feature set in differentiating abnormal from normal tissue, we employed three different classifiers: Support vector machine classifier, Naive Bayes classifier and K-Nearest Neighbor classifier. The efficiency of classification is provided using a cross-validation technique. The main characteristics of the proposed web-based diagnostic system are that users can use application written in Matlab without installing Matlab software, and they do not need to have any knowledge about programming in Matlab to run application.

Classifications of benign and malignant mammogram images using Gabor‐modified CNN architecture

AbstractBreast cancer is one of the leading life killing cancers in women patients around the world. Digital mammogram is used to detect and segment the abnormal mass portions in breast region. In this article, the breast cancer regions are detected and segmented using the Gabor transform based Convolutional Neural Networks (CNN) classification approach. This proposed breast cancer detection method consist of the following modules Kirsch's edge detector, Gabor transform, CNN classification and Segmentation. The cancer pixels and healthy pixels are differentiated in edge pixels. Hence, the Kirsch's edge detector is used to detect the fine edge boundary pixelsthe in source mammogram image. Then, the spatial edge detected mammogram image is converted into multi resolution mammogram image using Gabor transform. This transformed multi resolution mammogram image is classified into Normal, Benign or Malignant in this article using the proposed CNN architecture. The developed CNN structure extracts more complex feature maps from their internal layers to improve the classification rate. The conventional and proposed CNN structure is differed with respect to the internal layers. The proposed CNN structure is optimized by reducing the usage of the internals and increases Convolutional Filters (CF) in each Convolutional Layer during utilization design process. After classification process over, the cancer regions in the abnormal mammogram images are segmented using morphological functions. The proposed breast cancer detection is evaluated on Mammographic Image Analysis Society (MIAS) dataset and their cancer region segmentation results are 98.4% of sensitivity, 98.9% of specificity and 99.2% of cancer region segmentation accuracy. The average Detection Rate (DR) of the proposed breast cancer detection method is about 98.3% on the set of mammogramthe images from MIAS dataset. These simulation results are compared with other state‐of‐the art methods and cross verified by the k‐fold verification algorithm.

Implications for downstream workload based on calibrating an artificial intelligence detection algorithm by standalone-reader or combined-reader sensitivity matching.

In double-reading of screening mammograms, artificial intelligence (AI) algorithms hold promise as a potential replacement for one of the two readers. The choice of operating point, or abnormality threshold, for the AI algorithm will affect cancer detection and workload. In our retrospective study, the baseline approach was based on matching stand-alone reader sensitivity, while the alternative approach was based on matching the combined-reader sensitivity of two humans and of AI plus human. Full-field digital screening mammograms within the Stockholm County area between February 1, 2012, and December 30, 2015, acquired on Philips equipment, were collected. All exams of women with breast cancer within 23 months of screening and a random selection of healthy controls were included. An exam-level continuous AI abnormality score was generated (Insight MMG from Lunit Inc). Sensitivity and abnormal interpretation rates were estimated for operating points defined by the standalone-reader approach and the combined-reader approach. The study population included 1684 exams of women with breast cancer and 5024 exams of healthy women. Observations of healthy women were up-sampled to attain a realistic proportion of cancer. The observed sensitivity for reader 1, 2 and 1+2 was 69.7%, 75.6%, and 78.6%, respectively, at an abnormal interpretation rate of 4.4%, 4.6%, and 6.1%, respectively. For the combination of reader 1 + AI we estimated a sensitivity of 82.4% for standalone-reader matching and 78.6% for combined-reader matching, at an abnormal interpretation rate of 12.6% and 7.0%, respectively. Setting the operating point by matching stand-alone AI stand-alone with a radiologist will nearly double the downstream workload compared to a modest increase of 15% for the alternative method of matching sensitivity between the combination of AI and a radiologist with two radiologists.

Lifetime changes in body fatness and breast density in postmenopausal women: the FEDRA study

BackgroundHigh mammographic breast density (MBD) is an established risk factor for breast cancer (BC). Body fatness conveys an increased BC risk in postmenopause but is associated with less dense breasts. Here, we studied the relationship between body fatness and breast composition within the FEDRA (Florence-EPIC Digital mammographic density and breast cancer Risk Assessment) longitudinal study.MethodsRepeated anthropometric data and MBD parameters (obtained through an automated software on BC screening digital mammograms) were available for all participants, as well as information on other BC risk factors. Multivariate linear regression and functional data analysis were used to longitudinally evaluate the association of body fatness, and changes thereof over time, with dense (DV) and non-dense (NDV) breast volumes and volumetric percent density (VPD).ResultsA total of 5,262 women were included, with anthropometric data available at 20 and 40 years of age, at EPIC baseline (mean 49.0 years), and an average of 9.4 years thereafter. The mean number of mammograms per woman was 3.3 (SD 1.6). Body fatness (and increases thereof) at any age was positively associated with DV and NDV (the association being consistently stronger for the latter), and inversely associated with VPD. For instance, an increase by 1 kg/year between the age of 40 years and EPIC baseline was significantly associated with 1.97% higher DV, 8.85% higher NDV, and 5.82% lower VPD.ConclusionBody fatness and its increase from young adulthood until midlife are inversely associated with volumetric percent density, but positively associated with dense and non-dense breast volumes in postmenopausal women.

Variations of image interpretations of radiologists from different populations in mammography and tomosynthesis with different levels of breast density.

This study aims to investigate the diagnostic performances of Australian and Shanghai-based Chinese radiologists in reading full-field digital mammogram (FFDM) and digital breast tomosynthesis (DBT) with different levels of breast density. Eighty-two Australian radiologists interpreted a 60-case FFDM set, and 29 radiologists also reported a 35-case DBT set. Sixty Shanghai radiologists read the same FFDM set, and 32 radiologists read the DBT set. The diagnostic performances of Australian and Shanghai radiologists were assessed using truth data (cancer cases were biopsy proven) and compared overall in specificity, case sensitivity, lesion sensitivity, receiver operating characteristics (ROC) area under the curve, and jack-knife free-response receiver operating characteristics (JAFROC) figure of merit, and they were stratified by case characteristics using the Mann-Whitney U test. The Spearman rank test was used to explore the association between radiologists' performances and their work experience in mammogram interpretation. There were significantly higher performances of Australian radiologists compared with Shanghai radiologists in low breast density for case sensitivity, lesion sensitivity, ROC, and JAFROC in the FFDM set ( ); in high breast density, Shanghai radiologists' performances in lesion sensitivity and JAFROC were also lower than Australian radiologists ( ). In the DBT test set, Australian radiologists performed better than Shanghai radiologists in cancer detection in both low and high breast density. The work experience of Australian radiologists was positively linked to their diagnostic performances, whereas this association was not statistically significant in Shanghai radiologists. There were significant variations in reading performances between Australian and Shanghai radiologists in FFDM and DBT across different levels of breast density, lesion types, and lesion sizes. An effective training initiative tailored to suit local readers is essential to enhancing the diagnostic accuracy of Shanghai radiologists.

The FEDRA Longitudinal Study: Repeated Volumetric Breast Density Measures and Breast Cancer Risk

Mammographic breast density (MBD) is a strong independent risk factor for breast cancer (BC). We investigated the association between volumetric MBD measures, their changes over time, and BC risk in a cohort of women participating in the FEDRA (Florence-EPIC Digital mammographic density and breast cancer Risk Assessment) study. The study was carried out among 6148 women with repeated MBD measures from full-field digital mammograms and repeated information on lifestyle habits, reproductive history, and anthropometry. The association between MBD measures (modeled as time-dependent covariates), their relative annual changes, and BC risk were evaluated by adjusted Cox models. During an average of 7.8 years of follow-up, 262 BC cases were identified. BC risk was directly associated with standard deviation increments of volumetric percent density (VPD, HR 1.37, 95%CI 1.22-1.54) and dense volume (DV, HR 1.29, 95%CI 1.18-1.41). An inverse association emerged with non-dense volume (NDV, HR 0.82, 95%CI 0.69-0.98). No significant associations emerged between annual changes in VPD, DV, NDV, and BC risk. Higher values of MBD measures, modeled as time-dependent covariates, were positively associated with increased BC risk, while an inverse association was evident for increasing NDV. No effect of annual changes in MBD emerged.

On the Pulling Linear Regression and Its Applications in Digital Mammograms

Regression analysis is a statistical approach used to investigate the correlations between variables, especially linear regression, that is a simple but effective approach for analyzing the relationship between a dependent variable and one independent variable. Since it has limitations based on the assumption that the mean of the noise should be zero, there are still some areas where it may be improved. In this article, we introduce a novel data fitting algorithm called the pulling linear regression, which is separated into two types: the line-pulling linear regression and the band-pulling linear regression. The method is developed from linear regression, which can create the regression line from the function that uses noise with various distributions. The result demonstrates that the sequence of sum square errors of the pulling linear regression is convergent. Moreover, we have a numerical example to show that the performance of the proposed algorithm is better than that of linear regression when the mean of the noise is not zero. And the last, we have an application to smooth the boundary of the pectoral muscle in digital mammograms. We found that the regression line of the proposed algorithm can do better than the linear regression when we would like to remove only the muscle part.