Impact of image based artificial intelligence on workflow efficiency and diagnostic accuracy in clinical practice: a pathology-focused literature review

Authors

  • Sophia Petschnak Klinik Favoriten, Wiener Gesundheitsverbund, Institut für klinische Pathologie, Molekularpathologie und Mikrobiologie https://orcid.org/0009-0008-4232-3891

DOI:

https://doi.org/10.60733/PMGR.2026.06

Keywords:

artificial intelligence, digital pathology, workflow efficiency, diagnostic accuracy

Abstract

Histological diagnostics enable patient-specific therapy options. Given rising cancer incidence and a growing shortage of qualified personnel, implementing digital pathology workflows with AI integration appears to be a promising solution. This review assesses the literature on AI implementation in pathology regarding diagnostic accuracy, workflow efficiency, and documented challenges. Publications from January 2025 to February 2026 focusing on AI in histology and cytology were evaluated. From 318 identified studies, 16 articles were included after applying inclusion and quality criteria, comprising narrative reviews, pilot studies, validation and implementation studies. Included studies demonstrated high diagnostic accuracy and potential for improved workflow efficiency. Reduction of interobserver variability and standardization of biomarker testing were identified as key benefits. Open questions regarding validation, regulation, and ethics remain. AI-assisted pathology diagnostics shows promising potential regarding diagnostic quality, efficiency, and addressing current staffing challenges. Cost-effectiveness and regulatory aspects require further evaluation.

Author Biography

Sophia Petschnak, Klinik Favoriten, Wiener Gesundheitsverbund, Institut für klinische Pathologie, Molekularpathologie und Mikrobiologie

Sophia Petschnak serves as head of the department of pathology at Klinik Favoriten, part of the Wiener Gesundheitsverbund, where her clinical expertise lies in molecular pathology. Since 2023, she has additionally focused on the implementation of digital pathology in routine histological practice.

References

[1] E. Y. T. Wong et al., “ESMO guidance on the use of Large Language Models in Clinical Practice (ELCAP),” Annals of Oncology, vol. 36, no. 12, pp. 1447–1457, Dec. 2025, doi: 10.1016/j.annonc.2025.09.001.

[2] C.-W. Park et al., “Artificial Intelligence in Health Care: Current Applications and Issues,” J Korean Med Sci, vol. 35, no. 42, p. e379, 2020, doi: 10.3346/jkms.2020.35.e379.

[3] A. B. Farris, C. Cohen, T. E. Rogers, and G. H. Smith, “Whole Slide Imaging for Analytical Anatomic Pathology and Telepathology: Practical Applications Today, Promises, and Perils,” Archives of Pathology & Laboratory Medicine, vol. 141, no. 4, pp. 542–550, Apr. 2017, doi: 10.5858/arpa.2016-0265-SA.

[4] H. Sung et al., “Global Cancer Statistics 2020: GLOBOCAN Estimates of Incidence and Mortality Worldwide for 36 Cancers in 185 Countries,” CA: A Cancer Journal for Clinicians, vol. 71, no. 3, pp. 209–249, 2021, doi: 10.3322/caac.21660.

[5] B. Märkl, L. Füzesi, R. Huss, S. Bauer, and T. Schaller, “Number of pathologists in Germany: comparison with European countries, USA, and Canada,” Virchows Arch, vol. 478, no. 2, pp. 335–341, Feb. 2021, doi: 10.1007/s00428-020-02894-6.

[6] A. Borbat, T. Novikova, M. Yaroslavtsev, and A. Bychkov, “Not choosing pathology: An essay-based survey of first-year clinical residents,” American Journal of Clinical Pathology, vol. 160, no. 6, pp. 593–598, Dec. 2023, doi: 10.1093/ajcp/aqad091.

[7] V. Gassenmaier et al., “Understanding the pathology workforce: motivations, job satisfaction, and training perspectives in Germany,” Virchows Arch, Oct. 2025, doi: 10.1007/s00428-025-04277-1.

[8] P. Glasziou et al., “Evidence for underuse of effective medical services around the world,” The Lancet, vol. 390, no. 10090, pp. 169–177, Jul. 2017, doi: 10.1016/S0140-6736(16)30946-1.

[9] F. Deman et al., “Practical implementation of AI in a non‐academic, non‐commercial Pathology laboratory: Real world experience and lessons learned,” Histopathology, vol. 87, no. 5, pp. 635–646, Nov. 2025, doi: 10.1111/his.15481.

[10] K. Nakagawa et al., “AI in Pathology: What could possibly go wrong?,” Semin Diagn Pathol, vol. 40, no. 2, pp. 100–108, Mar. 2023, doi: 10.1053/j.semdp.2023.02.006.

[11] S. Vos et al., “Making Pathologists Ready for the New Artificial Intelligence Era: Changes in Required Competencies,” Mod Pathol, vol. 38, no. 2, p. 100657, Feb. 2025, doi: 10.1016/j.modpat.2024.100657.

[12] M. Petticrew and H. Roberts, Systematic reviews in the social sciences: A practical guide. in Systematic reviews in the social sciences: A practical guide. Malden: Blackwell Publishing, 2006, pp. xv, 336. doi: 10.1002/9780470754887.

[13] V. Ivanov et al., “Use of AI Histopathology in Breast Cancer Diagnosis,” Medicina, vol. 61, no. 10, p. 1878, Oct. 2025, doi: 10.3390/medicina61101878.

[14] A. Marra et al., “Artificial intelligence entering the pathology arena in oncology: current applications and future perspectives,” Annals of Oncology, vol. 36, no. 7, pp. 712–725, Jul. 2025, doi: 10.1016/j.annonc.2025.03.006.

[15] J. Wang, T. Wang, R. Han, D. Shi, and B. Chen, “Artificial intelligence in cancer pathology: Applications, challenges, and future directions,” Cytojournal, vol. 22, p. 45, Apr. 2025, doi: 10.25259/Cytojournal_272_2024.

[16] C.-H. Wu, M.-H. Chang, H.-J. Chen, H.-H. Tsai, C.-J. Chien, and J.-C. Wang, “Artificial Intelligence-Based Automatic Mitosis Scoring in Breast Cancer Improves Inter-Observer Concordance and Efficiency,” Clinical Breast Cancer, vol. 25, no. 7, pp. e912–e919, Oct. 2025, doi: 10.1016/j.clbc.2025.04.021.

[17] F. D. Allard et al., “Intraobserver and Interobserver Variability in the Assessment of Dysplasia in Ampullary Mucosal Biopsies,” Am J Surg Pathol, vol. 42, no. 8, pp. 1095–1100, Aug. 2018, doi: 10.1097/PAS.0000000000001079.

[18] E. A. Rakha, C. M. Quinn, E. Provenzano, S. E. Pinder, and I. O. Ellis, “Diagnostic Discordance and Error in Breast Pathology: Causes, Classifications, and Medicolegal Implications,” Mod Pathol, vol. 39, no. 1, p. 100942, Jan. 2026, doi: 10.1016/j.modpat.2025.100942.

[19] L. J. H. Smits et al., “Diagnostic variability in the histopathological assessment of advanced colorectal adenomas and early colorectal cancer in a screening population,” Histopathology, vol. 80, no. 5, pp. 790–798, Apr. 2022, doi: 10.1111/his.14601.

[20] C. McGenity et al., “Artificial intelligence in digital pathology: a systematic review and meta-analysis of diagnostic test accuracy,” npj Digit. Med., vol. 7, no. 1, p. 114, May 2024, doi: 10.1038/s41746-024-01106-8.

[21] I. Rienda, J. Vale, J. Pinto, A. Polónia, and C. Eloy, “Using artificial intelligence to prioritize pathology samples: report of a test drive,” Virchows Arch, vol. 487, no. 1, pp. 203–208, Jul. 2025, doi: 10.1007/s00428-024-03988-1.

[22] M. D. M. Rivera Rolon et al., “Implementing 100% quality control in a cervical cytology workflow using whole slide images and artificial intelligence provided by the Techcyte SureViewTM System,” Cancer Cytopathology, vol. 133, no. 6, p. e70019, Jun. 2025, doi: 10.1002/cncy.70019.

[23] R. Grobholz, F. Burn, and L. Prause, “Modern integrative prostate cancer diagnostics,” Current Opinion in Urology, vol. 36, no. 2, pp. 171–179, Mar. 2026, doi: 10.1097/MOU.0000000000001361.

[24] P. Raciti et al., “Clinical Validation of Artificial Intelligence-Augmented Pathology Diagnosis Demonstrates Significant Gains in Diagnostic Accuracy in Prostate Cancer Detection,” Arch Pathol Lab Med, vol. 147, no. 10, pp. 1178–1185, Oct. 2023, doi: 10.5858/arpa.2022-0066-OA.

[25] S. Zhang, T. Yang, X. Liu, J. Yang, and X. Zheng, “Antibody repertoire sequencing analysis,” ABBS, vol. 54, no. 6, pp. 864–873, May 2022, doi: 10.3724/abbs.2022062.

[26] V. Brodsky et al., “Generative Artificial Intelligence in Anatomic Pathology,” Archives of Pathology & Laboratory Medicine, vol. 149, no. 4, pp. 298–318, Apr. 2025, doi: 10.5858/arpa.2024-0215-RA.

[27] M. A. VandeHaar et al., “Challenges and Opportunities in Cytopathology Artificial Intelligence,” Bioengineering, vol. 12, no. 2, p. 176, Feb. 2025, doi: 10.3390/bioengineering12020176.

[28] F. G. Mayall, M. D. Goodhead, L. de Mendonça, S. E. Brownlie, A. Anees, and S. Perring, “Artificial intelligence-based triage of large bowel biopsies can improve workflow,” J Pathol Inform, vol. 14, p. 100181, 2023, doi: 10.1016/j.jpi.2022.100181.

[29] C. Mayall, H. Mayall, F. G. Mayall, L. Perring, D. Truman, and I. Bodger, “AI is quicker and more accurate than pathologists at SNOMED coding pathology reports,” J Clin Pathol, vol. 79, no. 3, pp. 179–185, Mar. 2026, doi: 10.1136/jcp-2025-210320.

[30] Y. Chong and A. Bychkov, “Commercially Available Artificial Intelligence Solutions for Gynaecologic Cytology Screening and Their Integration Into Clinical Workflow,” Cytopathology, vol. 37, no. 1, pp. 24–44, Jan. 2026, doi: 10.1111/cyt.70023.

[31] A. Blilie et al., “Artificial intelligence-assisted prostate cancer diagnosis for reduced use of immunohistochemistry,” Commun Med, vol. 5, no. 1, p. 425, Oct. 2025, doi: 10.1038/s43856-025-01185-y.

[32] C. Eloy et al., “Clinical advantages in providing artificial intelligence-assisted prostate cancer diagnosis: A pilot study,” Pathology - Research and Practice, vol. 271, p. 156007, Jul. 2025, doi: 10.1016/j.prp.2025.156007.

[33] R. N. Flach et al., “Head-to-Head Comparison of 2 Artificial Intelligence Tools for Detecting Lymph Node Metastases in Whole-Slide Pathology Images Within and Beyond Their Intended Use,” Modern Pathology, vol. 38, no. 12, p. 100905, Dec. 2025, doi: 10.1016/j.modpat.2025.100905.

[34] D. Y. Zhang, R. Sali, M. Zhu, and V. Zhang, “Introduction of an Integrated Pathology Image Management, Artificial Intelligence, and Reporting System,” JoVE, no. 221, p. 68270, Jul. 2025, doi: 10.3791/68270.

Downloads

Published

2026-06-11

Issue

Vol. 3 No. 1 (2026)

Section

From the Classroom

Categories