The diagnosis of solid tumors of epithelial origin (carcinomas) represents a major part of the workload in clinical histopathology. Carcinomas consist of malignant epithelial cells arranged in more or less cohesive clusters of variable size and shape, together with stromal cells, extracellular matrix, and blood vessels. Distinguishing stroma from epithelium is a critical component of artificial intelligence (AI) methods developed to detect and analyze carcinomas. In this paper, we propose a novel automated workflow that enables large-scale guidance of AI methods to identify the epithelial component. The workflow is based on re-staining existing hematoxylin and eosin (H&E) formalin-fixed paraffin-embedded sections by immunohistochemistry for cytokeratins, cytoskeletal components specific to epithelial cells. Compared to existing methods, clinically available H&E sections are reused and no additional material, such as consecutive slides, is needed. We developed a simple and reliable method for automatic alignment to generate masks denoting cytokeratin-rich regions, using cell nuclei positions that are visible in both the original and the re-stained slide. The registration method has been compared to state-of-the-art methods for alignment of consecutive slides and shows that, despite being simpler, it provides similar accuracy and is more robust. We also demonstrate how the automatically generated masks can be used to train modern AI image segmentation based on U-Net, resulting in reliable detection of epithelial regions in previously unseen H&E slides. Through training on real-world material available in clinical laboratories, this approach therefore has widespread applications toward achieving AI-assisted tumor assessment directly from scanned H&E sections. In addition, the re-staining method will facilitate additional automated quantitative studies of tumor cell and stromal cell phenotypes.

Department of Pathology Masaryk Memorial Cancer Institute Brno Czech Republic

Faculty of Informatics Masaryk University Brno Czech Republic

Institute of Computer Science Masaryk University Brno Czech Republic

000      

00000naa a2200000 a 4500

001      

bmc22010885

003      

CZ-PrNML

005      

20220506131517.0

007      

ta

008      

220425s2022 xxk f 000 0|eng||

009      

AR

024    7_

$a 10.1002/cjp2.249 $2 doi

035    __

$a (PubMed)34716754

040    __

$a ABA008 $b cze $d ABA008 $e AACR2

041    0_

$a eng

044    __

$a xxk

100    1_

$a Brázdil, Tomáš $u Faculty of Informatics, Masaryk University, Brno, Czech Republic $1 https://orcid.org/0000000245473261

245    10

$a Automated annotations of epithelial cells and stroma in hematoxylin-eosin-stained whole-slide images using cytokeratin re-staining / $c T. Brázdil, M. Gallo, R. Nenutil, A. Kubanda, M. Toufar, P. Holub

520    9_

$a The diagnosis of solid tumors of epithelial origin (carcinomas) represents a major part of the workload in clinical histopathology. Carcinomas consist of malignant epithelial cells arranged in more or less cohesive clusters of variable size and shape, together with stromal cells, extracellular matrix, and blood vessels. Distinguishing stroma from epithelium is a critical component of artificial intelligence (AI) methods developed to detect and analyze carcinomas. In this paper, we propose a novel automated workflow that enables large-scale guidance of AI methods to identify the epithelial component. The workflow is based on re-staining existing hematoxylin and eosin (H&E) formalin-fixed paraffin-embedded sections by immunohistochemistry for cytokeratins, cytoskeletal components specific to epithelial cells. Compared to existing methods, clinically available H&E sections are reused and no additional material, such as consecutive slides, is needed. We developed a simple and reliable method for automatic alignment to generate masks denoting cytokeratin-rich regions, using cell nuclei positions that are visible in both the original and the re-stained slide. The registration method has been compared to state-of-the-art methods for alignment of consecutive slides and shows that, despite being simpler, it provides similar accuracy and is more robust. We also demonstrate how the automatically generated masks can be used to train modern AI image segmentation based on U-Net, resulting in reliable detection of epithelial regions in previously unseen H&E slides. Through training on real-world material available in clinical laboratories, this approach therefore has widespread applications toward achieving AI-assisted tumor assessment directly from scanned H&E sections. In addition, the re-staining method will facilitate additional automated quantitative studies of tumor cell and stromal cell phenotypes.

650    _2

$a umělá inteligence $7 D001185

650    12

$a deep learning $7 D000077321

650    _2

$a eosin $7 D004801

650    _2

$a epitelové buňky $7 D004847

650    _2

$a hematoxylin $7 D006416

650    _2

$a lidé $7 D006801

650    12

$a keratiny $7 D007633

650    _2

$a barvení a značení $7 D013194

655    _2

$a časopisecké články $7 D016428

655    _2

$a práce podpořená grantem $7 D013485

700    1_

$a Gallo, Matej $u Faculty of Informatics, Masaryk University, Brno, Czech Republic $1 https://orcid.org/0000000211191792

700    1_

$a Nenutil, Rudolf $u Department of Pathology, Masaryk Memorial Cancer Institute, Brno, Czech Republic

700    1_

$a Kubanda, Andrej $u Faculty of Informatics, Masaryk University, Brno, Czech Republic

700    1_

$a Toufar, Martin $u Faculty of Informatics, Masaryk University, Brno, Czech Republic

700    1_

$a Holub, Petr $u Institute of Computer Science, Masaryk University, Brno, Czech Republic $1 https://orcid.org/000000025358616X

773    0_

$w MED00205747 $t The journal of pathology. Clinical research $x 2056-4538 $g Roč. 8, č. 2 (2022), s. 129-142

856    41

$u https://pubmed.ncbi.nlm.nih.gov/34716754 $y Pubmed

910    __

$a ABA008 $b sig $c sign $y p $z 0

990    __

$a 20220425 $b ABA008

991    __

$a 20220506131509 $b ABA008

999    __

$a ok $b bmc $g 1788819 $s 1162083

BAS    __

$a 3

BAS    __

$a PreBMC

BMC    __

$a 2022 $b 8 $c 2 $d 129-142 $e 20211030 $i 2056-4538 $m The journal of pathology. Clinical research $n J Pathol Clin Res $x MED00205747

LZP    __

$a Pubmed-20220425