AI in Breast Cancer Pathology: Accuracy and Efficiency

Research Highlight PN Demonstrating the accuracy and efficiency of artificial intelligence integrated workflows for primary breast cancer diagnosis A comparative paired reader analysis

Full Article

The following abstract is drawn from a recently published paper in Journal of Pathology Informatics | ScienceDirect.com by Elsevier. We invite you to read the full paper and join the conversation, become a member of the Pathology News community to share your thoughts, ask questions, and engage with others around this work.

Authors: J. Parry^a, S. Jindal^a, T. Blackmur^b, P. Channathodiyil^c, E.-A. Raiber-Moreau^c, J. Lee^d, D. Mevorach^e, G. Mallel^e, R. Broderick^f, S. Ambrogio^e, M. Vecsler^e

Abstract

Evidence on the real-world impact of artificial intelligence (AI) decision support on diagnostic efficiency and workflow outcomes in primary breast cancer pathology remains limited. This retrospective, single-site, paired reader, two-arm study evaluated the impact of AI-assisted digital pathology (DP + AI) versus standard DP on workflow efficiency and diagnostic performance in digitized consecutive breast biopsy cases. Primary endpoints were pathologist review time, lab turnaround time (TAT), and usability (survey-based). Secondary endpoints included diagnostic performance of pathologists across both arms and standalone AI against adjudicated reference standard. Analyses included descriptive statistics, paired t-test, and diagnostic performance metrics with 95% confidence intervals (CIs). The study included 194 digitized breast biopsies. The mean pathologist overall review time was reduced by 43.5% in DP + AI (40.18 [95% CI: 36.20–44.16] s) versus DP (71.12 [95% CI: 64.39–77.84] s) (p < 0.0001). Diagnostic agreement was 97.42% with DP and 99.48% with DP + AI, with 100% sensitivity observed in the DP + AI workflow. The standalone AI showed high diagnostic accuracy, with area under the curve values ≥0.99 across cancer subtypes. Usability survey showed high satisfaction, ease of use, and perceived clinical utility. Baseline TAT analysis of 3298 cases, independent of study cohort, showed longer TAT for cases requiring immunohistochemistry (IHC; 3.73 days) than for those not requiring (1.17 days). Retrospective workflow modelling suggested that AI-guided IHC pre-ordering could potentially reduce TAT by approximately 2.5 days for patients. DP + AI showed improvements in workflow efficiency while maintaining diagnostic performance. These findings suggest that integration of AI into routine breast pathology workflows may support faster diagnosis, optimized laboratory operations, and improved scalability.

Read the full article: Demonstrating the accuracy and efficiency of artificial intelligence integrated workflows for primary breast cancer diagnosis: A comparative paired reader analysis – ScienceDirect

^aHealius Limited, Western Diagnostic Pathology, Perth, Australia

^bHealius Limited, Brisbane, Australia

^cAstraZeneca, Cambridge, United Kingdom

^dAstraZeneca, Dubai, United Arab Emirates

^eIbex Medical Analytics, Tel Aviv, Israel

^fIbex Medical Analytics, Boston, MA, USA

Summary

This study evaluates the real-world impact of artificial intelligence (AI) decision support on diagnostic efficiency and workflow outcomes in primary breast cancer pathology. Conducted as a retrospective, single-site, paired-reader, two-arm study, it compared AI-assisted digital pathology (DP + AI) against standard DP in digitized consecutive breast biopsy cases. Key endpoints included pathologist review time, lab turnaround time (TAT), usability, and diagnostic performance. The analysis involved 194 breast biopsies, revealing a 43.5% reduction in mean pathologist review time with DP + AI (40.18 s) compared to DP alone (71.12 s), with statistical significance (p < 0.0001). Diagnostic agreement improved from 97.42% (DP) to 99.48% (DP + AI), with 100% sensitivity in the AI-assisted workflow. Standalone AI demonstrated high diagnostic accuracy, with AUC values ≥0.99 across cancer subtypes. Usability surveys indicated high satisfaction, ease of use, and perceived clinical utility. An independent baseline TAT analysis of 3298 cases showed longer TAT for cases requiring immunohistochemistry (IHC; 3.73 days) versus those without (1.17 days). Retrospective modeling suggested AI-guided IHC pre-ordering could reduce TAT by approximately 2.5 days. These findings demonstrate that DP + AI enhances workflow efficiency while maintaining diagnostic accuracy, supporting faster diagnoses, optimized lab operations, and improved scalability in breast pathology. The integration of AI into routine workflows presents a promising avenue for improving diagnostic efficiency without compromising performance.