The following abstract is drawn from a recently published paper in Academic Radiology. We invite you to read the full paper and join the conversation, become a member of the Radiology News community to share your thoughts, ask questions, and engage with others around this work.
Authors: Wu Lin Low Ong, FRCR, Consultant Radiologista,1, Wei Ming Ian Tay, FRCR, Consultant Radiologistb,2, Ma. Theresa Buenaflor, FPCR, Consultant Radiologistc,3, Merit Elmaadawy, MD, Consultantd,4, Janaki P. Dharmarajan, DNB, Senior Consultante,5, Noree Jane A. Lastrilla, FPCR, Training Officer for Breast Imagingf, Suchana Kushvaha, MD, Consultant Radiologistg,6, Rowena Lyn Alabado, FPCR, Consultant Radiologisth,7, Christopher Lai, PhD, Professori,8, Rajesh Kumar Sharma, PhD, Chief Scientific Oficerj,9, Niketa Chotai, Dr., FRCR, Consultant Radiologistk
Abstract
Rationale and Objectives
Breast cancer is the most common malignancy among females globally and across most Asian countries. In 2022, Asia’s age-standardized incidence rate (ASIR) was 34.3/100,000, with age-standardized mortality rate (ASMR) of 10.5.1000,000. Many Asian countries experience high incidence-to-mortality ratio due to limited organized screening programs, resource constraints and manpower limitations. The application of artificial intelligence (AI) in mammography interpretation may help address these challenges.
Materials and Methods
This multinational retrospective study evaluated the performance of AI-based computer-aided diagnosis (AI-CAD) in mammographic interpretation. A total of 302 digital mammograms, including 89 biopsy-proven breast cancers, were interpreted by nine experienced breast radiologists from multiple Asian institutions. Each radiologist participated in two reading sessions—one unaided and one with AI-CAD assistance. Diagnostic performance and reading time were compared between sessions.
Results
AI-CAD assistance significantly improved diagnostic performance, with the average area under the receiver operating characteristic curve (area under the curve [AUC]) increasing from 0.799 to 0.851 (p = 0.0151). Specificity improved from 77.0–88.4% (p = 0.03), while sensitivity showed no statistically significant difference. AI assistance also led to a significant reduction in average interpretation time, from 121.5 to 83.2 s per case (p < 0.001).
Conclusion
AI-CAD significantly enhances specificity and reduces reading time in mammographic interpretation without compromising sensitivity. These findings support the integration of AI in breast cancer screening workflows, to improve diagnostic efficiency and optimize clinical outcomes. Importantly, they also underscore the importance of maintaining human oversight and critical judgment when using AI in clinical practice.
Read the full article: Bolstering the Performance of Breast Radiologists with AI-CAD in Mammography: A Multireader Study – Academic Radiology
aDepartment of Oncologic Imaging, National Cancer Center, Singapore (W.L.L.O.)
bDepartment of Breast Imaging and Intervention, Singapore General Hospital, Singapore (W.M.I.T.)
cHealthway Cancer Care Hospital, Philippines (M.T.B.)
dDepartment of Radiology, Mansoura University, Egypt (M.E.)
eDepartment of Breast Imaging, Lisie Hospital, India (J.P.D.)
fCardinal Santos Medical Center, Philippines (N.J.A.L.)
gDepartment of Breast Imaging, Prajnam Complete Breast Care, India (S.K.)
hDepartment of Breast Imaging, Davao Doctors Hospital, Philippines (R.L.A.)
iDepartment of Medical Imaging, Tung Wah College, Hong Kong, China (C.L.)
jBIEDX Pte Ltd., Singapore (R.K.S.)
kDepartment of Women’s Imaging, RadLink Diagnostic and Imaging Center, Singapore (N.C.)
1ORCID: 0000‑0003‑2579‑3476
2ORCID: 0000-0003-0401-1420
3ORCID: 0000-0001-7257-1265
4ORCID: 0000-0003-2487-6616
5ORCID: 0000-0001-9778-0311
6ORCID: 0000-0002-5732-0190
7ORCID: 0009-0001-9601-6730
8ORCID: 0000-0002-8010-7232
9ORCID: 0000-0002-1857-960X
