Segmentation of Masses on Mammograms Using Data Augmentation and Deep Learning

AbstractThe diagnosis of breast cancer in early stage is essential for successful treatment. Detection can be performed in several ways, the most common being through mammograms. The projections acquired by this type of examination are directly affected by the composition of the breast, which density can be similar to the suspicious masses, being a challenge the identification of malignant lesions. In this article, we propose a computer-aided detection (CAD) system to aid in the diagnosis of masses in digitized mammograms using a model based in the U-Net, allowing specialists to monitor the lesion over time. Unlike most of the studies, we propose the use of an entire base of digitized mammograms using normal, benign, and malignant cases. Our research is divided into four stages: (1) pre-processing, with the removal of irrelevant information, enhancement of the contrast of 7989 images of the Digital Database for Screening Mammography (DDSM), and obtaining regions of interest. (2) Data augmentation, with horizontal mirroring, zooming, and resizing of images; (3) training, with tests of six-based U-Net models, with different characteristics; (4) testing, evaluating four metrics, accuracy, sensitivity, specificity, and Dice Index. The tested models obtained different results regarding the assessed parameters. The best model achieved a sensitivity of 92.32%, specificity of 80.47%, accuracy of 85.95% Dice Index of 79.39%, and AUC of 86.40%. Even using a full base without case selec...
Source: Journal of Digital Imaging - Category: Radiology Source Type: research

Related Links:

This study included 3,675 cancer-free women within the Nurses ’ Health Study (NHS) and Nurses’ Health Study II (NHSII) cohorts. Percent breast density (PD), absolute dense area (DA), and non-dense area (NDA) were measured from digitized film mammograms using a computer-assisted thresholding technique; all measures were square root-transformed. Information on medication use was collected in 1980 (NHS) and 1989 (NHSII) and updated biennially. Medication use was defined as none, past or current; average cumulative dose and frequency were calculated for all past or current users from all bi-annual questionnaires pr...
Source: Cancer Causes and Control - Category: Cancer & Oncology Source Type: research
Abstract Mammography remains the most prevalent imaging tool for early breast cancer screening. The language used to describe abnormalities in mammographic reports is based on the Breast Imaging Reporting and Data System (BI-RADS). Assigning a correct BI-RADS category to each examined mammogram is a strenuous and challenging task for even experts. This paper proposes a new and effective computer-aided diagnosis (CAD) system to classify mammographic masses into four assessment categories in BI-RADS. The mass regions are first enhanced by means of histogram equalization and then semiautomatically segmented based on ...
Source: Biomed Res - Category: Research Authors: Tags: Biomed Res Int Source Type: research
Massage therapy's ability to mitigate breast imaging associated anxiety has not been previously studied. Anxiety is, however, often cited as a harm of screening mammography with few options offered to diminish anxiety other than not screening. Reducing anxiety may improve compliance, and reduce breast cancer mortality and morbidity. A complimentary massage therapy program evaluated patient acceptance, anxiety perception and perceived value of massage.
Source: Clinical Imaging - Category: Radiology Authors: Tags: Breast Imaging Source Type: research
Breast MRI can produce more false positives on initial screening in women at...Read more on AuntMinnie.comRelated Reading: Bilateral breast MRI needed even after mastectomy Who gets breast cancer treatment during a pandemic? MRI features help predict breast cancer prognosis Shorter MRI works for patients with breast cancer history Breast MRI works as presurgical toolComments: 5/28/2020 3:40:02 AMDaniel Corcos Many high-risk women carry mutations in genes involved in the repair of DNA breaks caused by X-rays. As mammography screening leads to a high cancer incidence in the general population (Corcos &Bleyer,...
Source: Headlines - Category: Radiology Source Type: news
Siemens Healthineers subsidiary PETNet Solutions and Zionexa have announced...Read more on AuntMinnie.comRelated Reading: ASTRO: Radiation therapy slashes breast cancer recurrence MRI + mammography detects recurrent breast cancer Blue Earth, PETNet expand Axumin distribution SNMMI: FDG-PET predicts breast cancer outcomes Blue Earth, PETNet roll out Axumin
Source: Headlines - Category: Radiology Source Type: news
Breast cancer is the most common nonskin cancer in women and the second leading cause of breast cancer death for women in the United States. Mammography screening is proven to significantly decrease breast cancer mortality, with a 40% or more reduction expected with annual use starting at age 40 for women of average risk. However, less than half of all eligible women have a mammogram annually. The elimination of cost sharing for screening made possible by the Affordable Care Act (2010) encouraged screening but mainly for those already insured.
Source: Journal of the American College of Radiology : JACR - Category: Radiology Authors: Tags: Original article Source Type: research
As the death tolls rise to the coronavirus pandemic, those of us who specialize in oncology are bracing for another wave of victims: People not yet diagnosed with cancer.
Source: NYT Health - Category: Consumer Health News Authors: Tags: Tests (Medical) Coronavirus (2019-nCoV) Breast Cancer Doctors Leukemia Emergency Medical Treatment Hospitals Mammography Colonoscopy Source Type: news
Conclusion: We improved the prediction performance of DCIS upstaging by embedding two related pathology classes in different training phases. Significance: The three new strategies of embedding related class data all outperformed the baseline model, thus demonstrating not only feature similarities among these different classes, but also the potential for improving classification by using other related classes.
Source: IEEE Transactions on Biomedical Engineering - Category: Biomedical Engineering Source Type: research
Among the many remarkable things that have happened since the COVID-19 pandemic began is that a lot of our usual medical care has simply stopped. According to a recent study, routine testing for cervical cancer, cholesterol, and blood sugar is down nearly 70% across the country. Elective surgeries, routine physical examinations, and other screening tests have been canceled or rescheduled so that people can stay at home, avoid being around others who might be sick, and avoid unknowingly spreading the virus. Many clinics, hospitals, and doctors’ offices have been closed for weeks except for emergencies. Even if these f...
Source: Harvard Health Blog - Category: Consumer Health News Authors: Tags: Health Health care Healthy Aging Men's Health Women's Health Source Type: blogs
Existing protocol to re-assess women after six months is appropriate; imaging can identify cancers that have spread to lymph nodes.
Source: Diagnostic Imaging - Category: Radiology Authors: Tags: Breast Cancer Mammography Screening Source Type: news
More News: Breast Cancer | Cancer | Cancer & Oncology | Computers | Databases & Libraries | Learning | Mammography | Radiology | Study | Training | Universities & Medical Training