Despite category 4 subdivision providing better positive predictive value for biopsies, they are not done often enough.
Use of category 4 subdivisions in diagnostic mammography allowed for positive predictive value for biopsies performed (PPV3) to specify malignancy ranges, according to a study published in the journal Radiology.
Researchers from the University of Wisconsin School of Medicine and Public Health, in Madison; the American College of Radiology in Reston, Va.; and Stanford University School of Medicine in Calif., performed a retrospective review to determine the utilization and PPV of the American College of Radiology (ACR) Breast Imaging Data and Reporting System (BI-RADS) category 4 subdivisions in diagnostic mammography in the National Mammography Database (NMD).
The researchers reviewed data from 1,309,950 diagnostic mammograms submitted to the NMD from Jan. 1, 2008 to Dec. 30, 2014, and utilization rates of BI-RADS category 4 subdivisions were compared by year, facility (type, location, census region), and examination (indication, finding type) characteristics. PPV3 was calculated overall and according to category 4 subdivision. The Ï2 test was used to test for significant associations.
The results showed that of 1,309,950 diagnostic mammograms, 125,447 (9.6 percent) were category 4. Of these, 41,841 (33.3 percent) were subdivided. Subdivision utilization rates were higher in:
• Practices that were community, suburban, or in the West
• For examination indication of prior history of breast cancer
• For the imaging finding of architectural distortion
Breaking down the 41,841 category 4 subdivided examinations:
• 4A constituted 55.6 percent (23,258) of the examinations
• 4B constituted 31.8 percent (13,302) of the examinations
• 4C constituted 12.6 percent (5,281) of the examinations.
Pathologic outcomes were available in 91,563 examinations, and overall category 4 PPV3 was 21.1 percent (19,285). There was a statistically significant difference in PPV3 according to category 4 subdivision. PPV:
• 4A was 7.6 percent (1,274 of 16,784)
• 4B was 22 percent (2,317 of 10,408)
• 4C was 69.3 percent (2,839 of 4,099)
The researchers concluded that although BI-RADS suggests the use of subdivisions, they were utilized in the minority (33.3%) of category 4 diagnostic mammograms, with variability based on facility and examination characteristics. When subdivisions were used, PPV3s were in BI-RADS–specified malignancy ranges. This analysis supports the use of subdivisions in broad practice and, given benefits for patient care, should motivate increased utilization, they wrote.
Could a Deep Learning Model for Mammography Improve Prediction of DCIS and Invasive Breast Cancer?
April 15th 2024Artificial intelligence (AI) assessment of mammography images may significantly enhance the prediction of invasive breast cancer and ductal carcinoma in situ (DCIS) in women with breast cancer, according to new research presented at the Society for Breast Imaging (SBI) conference.
Mammography-Based AI Abnormality Scoring May Improve Prediction of Invasive Upgrade of DCIS
April 9th 2024Emerging research suggests that an artificial intelligence (AI) score of 75 or greater for mammography abnormalities more than doubles the likelihood of invasive upgrade of ductal carcinoma in situ (DCIS) diagnosed with percutaneous biopsy.
Mammography Study: AI Improves Breast Cancer Detection and Reduces Reading Time with DBT
April 3rd 2024An emerging artificial intelligence (AI) model demonstrated more than 12 percent higher specificity and reduced image reading time by nearly six seconds in comparison to unassisted radiologist interpretation of digital breast tomosynthesis (DBT) images.