The promise of artificial intelligence in diagnostic breast pathology

Accurate pathology diagnosis has remained the most essential factor in providing optimal breast cancer care across the globe. Core needle biopsies account for a significant portion of pathologists' workload, yet diagnostic variability remains especially for several difficult to diagnose entities such as borderline proliferative breast disease, atypical and low-grade breast lesions. Digital pathology and artificial intelligence (AI) are emerging tools that may help address these diagnostic challenges. To evaluate the diagnostic performance of the Pathology Artificial Intelligence Guidance Engine Breast (Paige PaBr), an AI tool, in analyzing digital histology images for breast cancer diagnosis, a retrospective study of 250 digitized breast biopsy images scanned at the University of Florida Jacksonville was conducted. AI-generated diagnoses were compared with reference diagnoses by experienced pathologists. Agreement, sensitivity, and specificity were calculated for suspicious for cancer and invasive lesions, respectively. For detection of suspicious lesions, AI showed 90.0% raw agreement with Cohen's kappa of 0.77 (95%CI: 0.69-0.86), sensitivity of 90.2%, and specificity of 89.5%. For invasive breast cancer specifically, Cohen's kappa was 0.82 (95%CI: 0.73-0.90). Of 76 invasive cases, 74 (97.4%) were correctly identified by AI. Among 98 cases of ductal carcinoma in situ (DCIS) and other proliferative lesions, 84 (85.7%) were classified as non-invasive, indicating high specificity. In summary, AI demonstrated substantial concordance with expert pathologists. These findings suggest that AI may serve as an adjunctive tool to support the evaluation of breast biopsies. Continued validation and prospective assessment are warranted to further define its potential role in routine pathology practice.