Artificial intelligence strategy integrating morphologic and architectural biomarkers provides robust diagnostic accuracy for disease progression in chronic lymphocytic leukemia.
CLL/SLL
Richter transformation
accelerated CLL
architecture
artificial intelligence
cellular biomarker
deep learning
disease progression
large B-cell lymphoma
small lymphocytic lymphoma
Journal
The Journal of pathology
ISSN: 1096-9896
Titre abrégé: J Pathol
Pays: England
ID NLM: 0204634
Informations de publication
Date de publication:
01 2022
01 2022
Historique:
revised:
04
08
2021
received:
11
06
2021
accepted:
03
09
2021
pubmed:
11
9
2021
medline:
4
1
2022
entrez:
10
9
2021
Statut:
ppublish
Résumé
Artificial intelligence-based tools designed to assist in the diagnosis of lymphoid neoplasms remain limited. The development of such tools can add value as a diagnostic aid in the evaluation of tissue samples involved by lymphoma. A common diagnostic question is the determination of chronic lymphocytic leukemia (CLL) progression to accelerated CLL (aCLL) or transformation to diffuse large B-cell lymphoma (Richter transformation; RT) in patients who develop progressive disease. The morphologic assessment of CLL, aCLL, and RT can be diagnostically challenging. Using established diagnostic criteria of CLL progression/transformation, we designed four artificial intelligence-constructed biomarkers based on cytologic (nuclear size and nuclear intensity) and architectural (cellular density and cell to nearest-neighbor distance) features. We analyzed the predictive value of implementing these biomarkers individually and then in an iterative sequential manner to distinguish tissue samples with CLL, aCLL, and RT. Our model, based on these four morphologic biomarker attributes, achieved a robust analytic accuracy. This study suggests that biomarkers identified using artificial intelligence-based tools can be used to assist in the diagnostic evaluation of tissue samples from patients with CLL who develop aggressive disease features. © 2021 The Pathological Society of Great Britain and Ireland. Published by John Wiley & Sons, Ltd.
Identifiants
pubmed: 34505705
doi: 10.1002/path.5795
pmc: PMC9526447
mid: NIHMS1837401
doi:
Substances chimiques
Biomarkers, Tumor
0
Types de publication
Journal Article
Langues
eng
Sous-ensembles de citation
IM
Pagination
4-14Subventions
Organisme : NCI NIH HHS
ID : R00 CA218667
Pays : United States
Informations de copyright
© 2021 The Pathological Society of Great Britain and Ireland. Published by John Wiley & Sons, Ltd.
Références
Nat Med. 2019 Oct;25(10):1519-1525
pubmed: 31591589
Haematologica. 2010 Sep;95(9):1526-33
pubmed: 20421272
Cancers (Basel). 2020 Mar 26;12(4):
pubmed: 32224980
Nat Med. 2019 Jul;25(7):1054-1056
pubmed: 31160815
Arch Pathol Lab Med. 2022 Jan 2;146(2):182-193
pubmed: 34086849
Nat Med. 2019 Aug;25(8):1301-1309
pubmed: 31308507
Med Image Anal. 2019 Dec;58:101563
pubmed: 31561183
Int J Lab Hematol. 2018 May;40 Suppl 1:54-61
pubmed: 29741256
Am J Clin Pathol. 2020 May 5;153(6):743-759
pubmed: 32067039
NPJ Digit Med. 2020 May 1;3:63
pubmed: 32377574
IEEE Trans Med Imaging. 2017 Jul;36(7):1550-1560
pubmed: 28287963
Front Bioeng Biotechnol. 2019 Apr 02;7:53
pubmed: 31001524
Lab Invest. 2020 Oct;100(10):1300-1310
pubmed: 32472096
Nat Med. 2018 Oct;24(10):1559-1567
pubmed: 30224757
Am J Hematol. 2016 Oct;91(10):1036-43
pubmed: 27414262
Ann Clin Lab Sci. 2019 Mar;49(2):153-160
pubmed: 31028058
Nat Commun. 2020 Nov 26;11(1):6004
pubmed: 33244018
Comput Med Imaging Graph. 2019 Jul;75:84-92
pubmed: 31238184