ARTIFICIAL INTELLIGENCE Variability in early colorectal cancer assessments (a) (b)


invasive breast cancer: A nationwide study of 33,043 patients in the Netherlands. Int J Cancer. 2020;146(3):769-780. doi:10.1002/ ijc.32330


5 Allsbrook WC Jr, Mangold KA, Johnson MH, Lane RB, Lane CG, Epstein JI. Interobserver reproducibility of Gleason grading of prostatic carcinoma: general pathologist. Hum Pathol. 2001;32(1):81-88. doi:10.1053/hupa.2001.21135


1 in 2 discrepant cases


3 in 10 potential clinical consequences


Fig 3. Illustrative representation of the diagnostic variability in the histopathological assessment of early colorectal cancer in a screening population. (a) Discrepancies in evaluations of early colorectal carcinomas. (b) The potential impact of these diagnostic discrepancies on treatment approaches and clinical outcomes. Source: Smits et al.7


and eosin (H&E)-stained whole-slide images (Fig 4), assisting pathologists in their quantification.


What sets Aiosyn Mitosis Breast closer to pathology practice: n Regulatory compliance: IVDR certification ensures the device has undergone rigorous validation and meets the highest clinical and safety standards.


n Validated performance across different settings: multi-centre clinical study with 28 pathologists from nine countries demonstrated reduced variability and time spent in mitosis counting.11


n Integration-ready: the modular and vendor-neutral approach makes it compatible with existing digital pathology platforms.


n Flexible pilot programmes: laboratories can try the solution first hand before committing to full integration, evaluating their productivity and consistency gains before implementation.


Surveyed clinical study pathologists reported improved confidence and efficiency in mitotic count assessments when using the tool.11


adoption of AI, preventing its benefits from being realised. Although integration costs may seem considerable, the highest expense of delaying AI adoption transcends financial metrics. It is measured in variability, uncertainty, and lost opportunities for better patient outcomes. AI-powered pathology image analysis is not merely a technological upgrade. Institutions integrating deep-learning tools position themselves at the forefront of precision diagnostics, delivering care that is not only faster and more efficient but also more consistent and equitable. Implementing AI-assisted assessments will enable organisations to build trust in pathology as a precise medical discipline and, more critically, to enhance the quality of patient care. Furthermore, these solutions can democratise access to expert pathology care, improving decision-making in areas lacking specialised expertise and bringing a high standard of quality globally.


References 1 Verghese G, Lennerz JK, Ruta D, et al.


With over 90% of


participants interested in incorporating the algorithm into their daily workflow11 and several integrations already planned, Aiosyn Mitosis Breast is ready to bring these benefits to pathology practice.


Improving diagnostic consistency and patient outcomes


Despite notable progress toward digitising pathology laboratories across Europe and the United Kingdom, fully digital operations remain the exception rather than the norm. This limited infrastructure, coupled with high implementation costs and limited trust, continues to delay the widespread


42


Computational pathology in cancer diagnosis, prognosis, and prediction - present day and prospects. J Pathol. 2023;260(5):551-563. doi:10.1002/ path.6163


2 Bessen JL, Alexander M, Foroughi O, et al. Perspectives on Reducing Barriers to the Adoption of Digital and Computational Pathology Technology by Clinical Labs. Diagnostics (Basel). 2025;15(7):794. doi:10.3390/diagnostics15070794


3 Elmore JG, Longton GM, Carney PA, et al. Diagnostic concordance among pathologists interpreting breast biopsy specimens. JAMA. 2015;313(11):1122- 1132. doi:10.1001/jama.2015.1405


4 van Dooijeweert C, van Diest PJ, Willems SM, et al. Significant inter- and intra-laboratory variation in grading of


6 Postma EL, Verkooijen HM, van Diest PJ, Willems SM, van den Bosch MA, van Hillegersberg R. Discrepancy between routine and expert pathologists’ assessment of non-palpable breast cancer and its impact on locoregional and systemic treatment. Eur J Pharmacol. 2013;717(1-3):31-35. doi:10.1016/j. ejphar.2012.12.033


7 Smits LJH, Vink-Börger E, van Lijnschoten G, et al. Diagnostic variability in the histopathological assessment of advanced colorectal adenomas and early colorectal cancer in a screening population. Histopathology. 2022;80(5):790-798. doi:10.1111/his.14601


8 Kleiner DE, Brunt EM, Van Natta M, et al. Design and validation of a histological scoring system for nonalcoholic fatty liver disease. Hepatology. 2005;41(6):1313- 1321. doi:10.1002/hep.20701


9 Stoler MH, Schiffman M. Atypical Squamous Cells of Undetermined Significance-Low-grade Squamous Intraepithelial Lesion Triage Study (ALTS) Group. Interobserver reproducibility of cervical cytologic and histologic interpretations: realistic estimates from the ASCUS-LSIL Triage Study. JAMA. 2001;285(11):1500-1505. doi:10.1001/ jama.285.11.1500


10 Serón D, Moreso F. Protocol biopsies in renal transplantation: prognostic value of structural monitoring. Kidney Int. 2007;72(6):690-697. doi:10.1038/ sj.ki.5002396


11 Tessier L, Gonzalez-Gonzalo C, Tellez D, Bulten W, Balkenhol M, van der Laak J. AI-Assisted Mitosis Counting in Breast Cancer, a Large-Scale Validation Study (Poster). Aiosyn Radboud UMC. https://www.aiosyn.com/wp-content/ uploads/2025/02/Poster_Aiosyn_Mitosis_ Breast_clinical_performance_study.pdf


12 Bulten W, Balkenhol M, Belinga JA, et al. Artificial intelligence assistance significantly improves Gleason grading of prostate biopsies by pathologists. Mod Pathol. 2021;34(3):660-671. doi:10.1038/s41379- 020-0640-y


13 Marrón-Esquivel JM, Duran-Lopez L, Linares-Barranco A, Dominguez- Morales JP. A comparative study of the inter-observer variability on Gleason grading against Deep Learning-based approaches for prostate cancer. Comput Biol Med. 2023;159:106856. doi:10.1016/j.


OCTOBER 2025 WWW.PATHOLOGYINPRACTICE.COM


Page 1  |  Page 2  |  Page 3  |  Page 4  |  Page 5  |  Page 6  |  Page 7  |  Page 8  |  Page 9  |  Page 10  |  Page 11  |  Page 12  |  Page 13  |  Page 14  |  Page 15  |  Page 16  |  Page 17  |  Page 18  |  Page 19  |  Page 20  |  Page 21  |  Page 22  |  Page 23  |  Page 24  |  Page 25  |  Page 26  |  Page 27  |  Page 28  |  Page 29  |  Page 30  |  Page 31  |  Page 32  |  Page 33  |  Page 34  |  Page 35  |  Page 36  |  Page 37  |  Page 38  |  Page 39  |  Page 40  |  Page 41  |  Page 42  |  Page 43  |  Page 44  |  Page 45  |  Page 46  |  Page 47  |  Page 48  |  Page 49  |  Page 50  |  Page 51  |  Page 52  |  Page 53  |  Page 54  |  Page 55  |  Page 56