Pathological Digital Biomarkers: Validation and Application
Source abstract
Abstract
Digital pathology offers powerful tools for biomarker discovery, analysis, and translation. Despite its advantages, the clinical adoption of digital pathology has been slow. A clinical and methodological validation is required for novel digital pathological biomarkers. Four steps are required to validate a novel pathological digital biomarker for clinical use: sample collection and processing, analytical validation, clinical validation, and clinical utility. The digital biomarkers and their diagnostic, monitoring, pharmacodynamic response, predictive, prognostic, safety, and risk assessment applications are discussed. Adopting pathological digital biomarkers can be used in conjunction with other diagnostic technologies to select the most appropriate patient treatment, thereby reducing patient suffering and healthcare costs.
Source: crossref · Quality: baseline
Research context
OpenAlex topics: AI in cancer detection · Radiomics and Machine Learning in Medical Imaging · Cell Image Analysis Techniques
SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.
Affiliations
College of Medicine, The Catholic University of Korea, 222 Banpo-daero, Seocho-gu, Seoul 06591, Korea
Department of Hospital Pathology, Yeouido St. Mary’s Hospital, College of Medicine, The Catholic University of Korea, Seoul 07345, Korea
Funding
National Research Foundation of Korea (NRF) · Institute of Clinical Medicine Research in the Yeouido St. Mary’s Hospital
References (87)
Show source-provided references
1. Pathology in drug discovery and development10.1002/path.4290 ↗
2. Light-sheet microscopy for slide-free non-destructive pathology of large clinical specimens10.1038/s41551-017-0084 ↗
3. Variability of practice in anatomic pathology and its effect on patient outcomes10.1053/j.semdp.2006.01.004 ↗
4. Digital image analysis in breast pathology—From image processing techniques to artificial intelligence10.1016/j.trsl.2017.10.010 ↗
5. Precision immunoprofiling by image analysis and artificial intelligence10.1007/s00428-018-2485-z ↗
6. Deep semi supervised generative learning for automated tumor proportion scoring on NSCLC tissue needle biopsies10.1038/s41598-018-35501-5 ↗
7. Deep learning for detecting tumour-infiltrating lymphocytes in testicular germ cell tumours10.1136/jclinpath-2018-205328 ↗
8. Diagnostic assessment of deep learning algorithms for detection of lymph node metastases in women with breast cancer10.1001/jama.2017.14585 ↗
9. Deep learning based tissue analysis predicts outcome in colorectal cancer10.1038/s41598-018-21758-3 ↗
10. Digital pathology and artificial intelligence in translational medicine and clinical practice10.1038/s41379-021-00919-2 ↗
11. Fraggetta, F., Caputo, A., Guglielmino, R., Pellegrino, M.G., Runza, G., and L’Imperio, V. (2021). A Survival Guide for the Rapid Transition to a Fully Digital Workflow: The “Caltagirone Example”. Diagnostics, 11.10.3390/diagnostics11101916 ↗
12. The Henry Ford Production System: Effective reduction of process defects and waste in surgical pathology10.1309/RGF6JD1NAP2DU88Q ↗
13. Role of informatics in patient safety and quality assurance10.1016/j.path.2015.02.011 ↗
14. Breaking a vicious cycle10.1126/scitranslmed.3005950 ↗
15. Image analysis and machine learning in digital pathology: Challenges and opportunities10.1016/j.media.2016.06.037 ↗
16. The evaluation of genomic applications in practice and prevention (EGAPP) initiative: Methods of the EGAPP working group10.1097/GIM.0b013e318184137c ↗
17. Artificial intelligence in digital pathology—New tools for diagnosis and precision oncology10.1038/s41571-019-0252-y ↗
18. Jahn, S.W., Plass, M., and Moinfar, F. (2020). Digital pathology: Advantages, limitations and emerging perspectives. J. Clin. Med., 9.10.3390/jcm9113697 ↗
19. Review of the current state of whole slide imaging in pathology10.4103/2153-3539.83746 ↗
20. Potential quality pitfalls of digitalized whole slide image of breast pathology in routine practice10.1038/s41379-021-01000-8 ↗
21. Integrating digital pathology into clinical practice10.1038/s41379-021-00929-0 ↗
22. Routine digital pathology workflow: The Catania experience10.4103/jpi.jpi_58_17 ↗
23. Validating whole slide imaging systems for diagnostic purposes in pathology: Guideline update from the College of American Pathologists in collaboration with the American Society for Clinical Pathology and the Association for Pathology Informatics10.5858/arpa.2020-0723-CP ↗
24. Validation of biomarkers to predict response to immunotherapy in cancer: Volume I—Pre-analytical and analytical validation10.1186/s40425-016-0178-1 ↗
25. Computerized tumor multinucleation index (MuNI) is prognostic in p16+ oropharyngeal carcinoma10.1172/JCI145488 ↗
26. Digital pathology and computational image analysis in nephropathology10.1038/s41581-020-0321-6 ↗
27. Digital pathology and artificial intelligence10.1016/S1470-2045(19)30154-8 ↗
28. Color standardization and optimization in whole slide imaging10.1186/1746-1596-6-S1-S15 ↗
29. Validation of new cancer biomarkers: A position statement from the European group on tumor markers10.1373/clinchem.2015.239863 ↗
30. Taking a new biomarker into routine use–a perspective from the routine clinical biochemistry laboratory10.1002/prca.201000073 ↗
31. Establishing standardized immune phenotyping of metastatic melanoma by digital pathology10.1038/s41374-021-00653-y ↗
32. Prediction of early recurrence of hepatocellular carcinoma after resection using digital pathology images assessed by machine learning10.1038/s41379-020-00671-z ↗
33. Central pathology review for phase III clinical trials: The enabling effect of virtual microscopy10.5858/arpa.2012-0093-RA ↗
34. Effector memory T cells, early metastasis, and survival in colorectal cancer10.1056/NEJMoa051424 ↗
35. In situ cytotoxic and memory T cells predict outcome in patients with early-stage colorectal cancer10.1200/JCO.2008.19.6147 ↗
36. Systematic analysis of breast cancer morphology uncovers stromal features associated with survival10.1126/scitranslmed.3002564 ↗
37. Locality sensitive deep learning for detection and classification of nuclei in routine colon cancer histology images10.1109/TMI.2016.2525803 ↗
38. The use of digital pathology and image analysis in clinical trials10.1002/cjp2.127 ↗
39. Dissecting the business case for adoption and implementation of digital pathology: A white paper from the digital pathology association10.4103/jpi.jpi_67_20 ↗
40. Clinical evidence supporting pharmacogenomic biomarker testing provided in US Food and Drug Administration drug labels10.1001/jamainternmed.2014.5266 ↗
41. Copeptin: Clinical use of a new biomarker10.1016/j.tem.2007.11.001 ↗
42. Pembrolizumab versus chemotherapy for PD-L1–positive non–small-cell lung cancer10.1056/NEJMoa1606774 ↗
43. Pembrolizumab versus chemotherapy for previously untreated, PD-L1-expressing, locally advanced or metastatic non-small-cell lung cancer (KEYNOTE-042): A randomised, open-label, controlled, phase 3 trial10.1016/S0140-6736(18)32409-7 ↗
44. Artificial Intelligence–Powered Spatial Analysis of Tumor-Infiltrating Lymphocytes as Complementary Biomarker for Immune Checkpoint Inhibition in Non–Small-Cell Lung Cancer10.1200/JCO.21.02010 ↗
45. Amann, J., Blasimme, A., Vayena, E., Frey, D., and Madai, V.I. (2020). Explainability for artificial intelligence in healthcare: A multidisciplinary perspective. BMC Med. Inform. Decis. Mak., 20.10.1186/s12911-020-01332-6 ↗
46. Altman, D.G., McShane, L.M., Sauerbrei, W., Taube, S.E., and Cavenagh, M.M. (2014). REMARK (REporting recommendations for tumor MARKer prognostic studies). Guidelines for Reporting Health Research: A User’s Manual, Wiley.10.1002/9781118715598.ch23 ↗
47. Next generation diagnostic pathology: Use of digital pathology and artificial intelligence tools to augment a pathological diagnosis10.1186/s13000-019-0921-2 ↗
48. Explainable AI (xAI) for anatomic pathology10.1097/PAP.0000000000000264 ↗
49. Reproducibility of biomedical research–the importance of editorial vigilance10.1016/j.bdq.2017.01.002 ↗
50. Biomarkers and surrogate endpoints: Preferred definitions and conceptual framework10.1067/mcp.2001.113989 ↗
51. FDA-NIH Biomarker Working Group (2016). BEST (Biomarkers, Endpoints, and Other Tools) Resource [Internet].
52. Osareh, A., and Shadgar, B. (2010, January 20–22). Machine learning techniques to diagnose breast cancer. Proceedings of the 2010 5th International Symposium on Health Informatics and Bioinformatics, Ankara, Turkey.10.1109/HIBIT.2010.5478895 ↗
53. Prognostic value of automatically extracted nuclear morphometric features in whole slide images of male breast cancer10.1038/modpathol.2012.126 ↗
54. Lee, G., Sparks, R., Ali, S., Shih, N.N., Feldman, M.D., Spangler, E., Rebbeck, T., Tomaszewski, J.E., and Madabhushi, A. (2014). Co-occurring gland angularity in localized subgraphs: Predicting biochemical recurrence in intermediate-risk prostate cancer patients. PLoS ONE, 9.10.1371/journal.pone.0097954 ↗
55. Using machine learning algorithms to predict immunotherapy response in patients with advanced melanoma10.1158/1078-0432.CCR-20-2415 ↗
56. Quantitative assessment of inflammatory infiltrates in kidney transplant biopsies using multiplex tyramide signal amplification and deep learning10.1038/s41374-021-00601-w ↗
57. Biomarker definitions and their applications10.1177/1535370217750088 ↗
58. Evaluation of a Novel Quantitative Digital Pathology Technique as a Tool for Predicting Prostate Cancer Recurrence10.1016/j.ijrobp.2015.07.1110 ↗
59. Caie, P.D. (2022, September 25). Discovery of Novel Prognostic Tools to Stratify High Risk Stage II Colorectal Cancer Patients Utilising Digital Pathology. Available online: http://hdl.handle.net/1842/19527.
60. Naoumov, N.V., Brees, D., Loeffler, J., Chng, E., Ren, Y., Lopez, P., Tai, D., Lamle, S., and Sanyal, A.J. (J. Hepatol., 2022). Digital pathology with artificial intelligence analyses provides greater insights into treatment-induced fibrosis regression in NASH, J. Hepatol., in press.10.1016/j.jhep.2022.06.018 ↗
61. Applications of machine learning in drug discovery and development10.1038/s41573-019-0024-5 ↗
62. Quantitative image analysis for tissue biomarker use: A white paper from the digital pathology association10.1097/PAI.0000000000000930 ↗
63. Biomarker: Predictive or prognostic?10.1200/JCO.2015.63.3651 ↗
64. Validation of grading of non-invasive urothelial carcinoma by digital pathology for routine diagnosis10.1186/s12885-021-08698-4 ↗
65. Deep learning-enabled breast cancer hormonal receptor status determination from base-level H&E stains10.1038/s41467-020-19334-3 ↗
66. Predicting treatment response to neoadjuvant chemoradiotherapy in local advanced rectal cancer by biopsy digital pathology image features10.1002/ctm2.110 ↗
67. Modelling the spatial heterogeneity and molecular correlates of lymphocytic infiltration in triple-negative breast cancer10.1098/rsif.2014.1153 ↗
68. Future-proofing pathology: The case for clinical adoption of digital pathology10.1136/jclinpath-2017-204644 ↗
69. International validation of the consensus Immunoscore for the classification of colon cancer: A prognostic and accuracy study10.1016/S0140-6736(18)30789-X ↗
70. Complete digital pathology for routine histopathology diagnosis in a multicenter hospital network10.5858/arpa.2018-0541-OA ↗
71. qFibrosis: A fully-quantitative innovative method incorporating histological features to facilitate accurate fibrosis scoring in animal model and chronic hepatitis B patients10.1016/j.jhep.2014.02.015 ↗
72. Development of a computational high-throughput tool for the quantitative examination of dose-dependent histological features10.1177/0192623314544379 ↗
73. Sethunath, D., Morusu, S., Tuceryan, M., Cummings, O.W., Zhang, H., Yin, X.M., Vanderbeck, S., Chalasani, N., and Gawrieh, S. (2018). Automated assessment of steatosis in murine fatty liver. PLoS ONE, 13.10.1371/journal.pone.0197242 ↗
74. Nascimento, D.S., Valente, M., Esteves, T., De Pina, M.D.F., Guedes, J.G., Freire, A., Quelhas, P., and Pinto-Do-Ó, P. (2011). MIQuant–semi-automation of infarct size assessment in models of cardiac ischemic injury. PLoS ONE, 6.10.1371/journal.pone.0025045 ↗
75. Seger, S., Stritt, M., Vezzali, E., Nayler, O., Hess, P., Groenen, P.M., and Stalder, A.K. (2018). A fully automated image analysis method to quantify lung fibrosis in the bleomycin-induced rat model. PLoS ONE, 13.10.1371/journal.pone.0193057 ↗
76. Gilhodes, J.C., Julé, Y., Kreuz, S., Stierstorfer, B., Stiller, D., and Wollin, L. (2017). Quantification of pulmonary fibrosis in a bleomycin mouse model using automated histological image analysis. PLoS ONE, 12.10.1371/journal.pone.0170561 ↗
77. Pathophysiologic implications of reduced podocyte number in a rat model of progressive glomerular injury10.2353/ajpath.2006.050398 ↗
78. Mechanistic investigations of test article–induced pancreatic toxicity at the endocrine–exocrine interface in the rat10.1177/0192623313508851 ↗
79. Challenges in the development, deployment, and regulation of artificial intelligence in anatomic pathology10.1016/j.ajpath.2020.10.018 ↗
80. Harnessing non-destructive 3D pathology10.1038/s41551-020-00681-x ↗
81. Computer extracted features from initial H&E tissue biopsies predict disease progression for prostate cancer patients on active surveillance10.3390/cancers12092708 ↗
82. Automated segmentation and tracking of mitochondria in live-cell time-lapse images10.1038/s41592-021-01234-z ↗
83. Computationally Derived Image Signature of Stromal Morphology Is Prognostic of Prostate Cancer Recurrence Following Prostatectomy in African American PatientsStroma Predicts Prostate Cancer Outcome in African Americans10.1158/1078-0432.CCR-19-2659 ↗
84. Prostate cancer risk stratification via non-destructive 3D pathology with deep learning-assisted gland analysis10.1158/0008-5472.CAN-21-2843 ↗
85. Artificial intelligence and digital pathology: Challenges and opportunities10.4103/jpi.jpi_53_18 ↗
86. Food and Drug Administration (2017). CFR—Code of Federal Regulations Title 21—Food and Drugs Chapter I—Food and Drug Administration Department of Health and Human Services Subchapter B—Food for Human Consumption [Internet].
87. Food and Drug Administration (2021). Artificial Intelligence and Machine Learning (AI/ML) Software as a Medical Device Action Plan.