Purpose: The Breast Imaging Reporting and Data System (BI-RADS) lexicon was developed to standardize mammographic reporting to assess cancer risk and facilitate the decision to biopsy. Because of substantial interobserver variability in the application of the BI-RADS lexicon, the decision to biopsy varies greatly and results in overdiagnosis and excessive biopsies. The false-positive rate from mammograms is estimated to be 7% to approximately 10% overall, but within the BI-RADS 4 category, it is greater than 70%. Therefore, we developed the Breast Cancer Risk Calculator (BRISK) to target a well-characterized and specific patient subgroup (BI-RADS 4) rather than a broad heterogeneous group in assessing breast cancer risk.
Methods: BRISK provides a novel precise risk assessment model to reduce overdiagnosis and unnecessary biopsies. It was developed by applying natural language processing and deep learning methods on 5,147 patient records archived in the Houston Methodist systemwide data warehouse from 2006 to May 2015, including imaging and pathology reports, mammographic images, and patient demographics. Key characteristics for BI-RADS 4 patients were collected and computed to output an index measure for biopsy recommendation that is clinically relevant and informative and improves upon the traditional BI-RADS 4 scores.
Results: For the validation set, we assessed data from 1,247 BI-RADS 4 patients, including mammographic images and medical reports. The BRISK model sensitivity to predict malignancy was 100%, whereas the specificity was 74%. The total accuracy of our implemented model in BRISK was 81%. Overall area under the curve was 0.93.
Conclusion: BRISK for abnormal mammogram uses integrative artificial intelligence technology and has demonstrated high sensitivity in the prediction of malignancy. Prospective evaluation is under way and can lead to improvement in patient-physician engagement in making informed decisions with regard to biopsy.
Download full-text PDF |
Source |
|---|---|
| http://www.ncbi.nlm.nih.gov/pmc/articles/PMC10445790 | PMC |
| http://dx.doi.org/10.1200/CCI.18.00121 | DOI Listing |
Publication Analysis
Top Keywords
Similar Publications
Post-therapeutic support and rehabilitation for breast cancer women in complete remission in a thermal resort: study protocol for the PACThe Real-Life conditions observational trial.
BMC Cancer
January 2025
Division de la Recherche Clinique, Centre Jean PERRIN, 58 rue Montalembert, Clermont-Ferrand, 63011, France.
Background: Over the past twenty years, the post-cancer rehabilitation has been developed, usually in a hospital setting. Although this allows better care organization and improved security, it is perceived as stressful and restrictive by the "cancer survivor". Therefore, the transfer of benefits to everyday life is more difficult, or even uncertain.
View Article and Find Full Text PDFTriaging mammography with artificial intelligence: an implementation study.
Breast Cancer Res Treat
January 2025
Google Health, 1600 Amphitheatre Pkwy, Mountain View, CA, 94043, USA.
Purpose: Many breast centers are unable to provide immediate results at the time of screening mammography which results in delayed patient care. Implementing artificial intelligence (AI) could identify patients who may have breast cancer and accelerate the time to diagnostic imaging and biopsy diagnosis.
Methods: In this prospective randomized, unblinded, controlled implementation study we enrolled 1000 screening participants between March 2021 and May 2022.
Evaluation of the role of circular RNA (circ-FAF1) as a diagnostic biomarker for breast cancer in a cohort of Egyptian breast cancer patients.
Mol Biol Rep
January 2025
Department of Clinical Pathology, Faculty of Medicine, Alexandria University, Alexandria, Egypt.
Background: The identification of circulating potential biomarkers may help earlier diagnosis of breast cancer, which is critical for effective treatment and better disease outcomes. We aimed to study the role of circ-FAF1 as a diagnostic biomarker in female breast cancer using peripheral blood samples of these patients, and to investigate the relation between circ-FAF1 and different clinicopathological features of the included patients.
Methods And Results: This case-control study enrolled 60 female breast cancer patients and 60 age-matched healthy control subjects.
Liraglutide and denatonium benzoate attenuate T2DM-induced metabolic, neurological, and testicular changes in rats: Targeting oxidative stress, inflammation, and BCRP transporter.
J Mol Histol
January 2025
Clinical Pharmacology Department, Faculty of Medicine, Alexandria University, Alexandria, Egypt.
Type 2 diabetes mellitus (T2DM) adversely affects various organs, including the brain and its blood barrier. In addition to the brain, hyperglycemia damages the testes. The testes possess blood-tissue barriers that share common characteristics and proteins with the blood-brain barrier (BBB), including breast cancer-resistant protein (BCRP).
View Article and Find Full Text PDFOngoing Symptoms and Concerns Experienced by Low-Risk Breast Cancer Survivors Following Active Treatment.
Ann Surg Oncol
January 2025
Department of Surgery, School of Medicine and Public Health, Wisconsin Surgical Outcomes Research Program, University of Wisconsin, Madison, WI, USA.
Introduction: Little is known about the symptom burden of breast cancer survivors with early-stage disease. Many studies have focused on symptoms of patients who are undergoing or recently completed systemic therapy. However, with the increased use of Oncotype DX, the proportion of early-stage hormone receptor-positive patients who undergo chemotherapy has declined, making existing studies of the symptom experience less useful for these patients.
View Article and Find Full Text PDFWant AI Summaries of new PubMed Abstracts delivered to your In-box?
Enter search terms and have AI summaries delivered each week - change queries or unsubscribe any time!