Experimental assessment of color deconvolution and color normalization for automated classification of histology images stained with hematoxylin and eosin

Histological evaluation plays a major role in cancer diagnosis and treatment. The appearance of H&E-stained images can vary significantly as a consequence of differences in several factors, such as reagents, staining conditions, preparation procedure and image acquisition system. Such potential...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Bianconi, Francesco (VerfasserIn) , Kather, Jakob Nikolas (VerfasserIn) , Reyes-Aldasoro, Constantino Carlos (VerfasserIn)
Dokumenttyp: Article (Journal)
Sprache:Englisch
Veröffentlicht: 11 November 2020
In: Cancers
Year: 2020, Jahrgang: 12, Heft: 11
ISSN:2072-6694
DOI:10.3390/cancers12113337
Online-Zugang:Verlag, lizenzpflichtig, Volltext: https://doi.org/10.3390/cancers12113337
Verlag, lizenzpflichtig, Volltext: https://www.mdpi.com/2072-6694/12/11/3337
Volltext
Verfasserangaben:Francesco Bianconi, Jakob N. Kather and Constantino Carlos Reyes-Aldasoro

MARC

LEADER 00000caa a2200000 c 4500
001 1746899336
003 DE-627
005 20220819093350.0
007 cr uuu---uuuuu
008 210202s2020 xx |||||o 00| ||eng c
024 7 |a 10.3390/cancers12113337  |2 doi 
035 |a (DE-627)1746899336 
035 |a (DE-599)KXP1746899336 
035 |a (OCoLC)1341390042 
040 |a DE-627  |b ger  |c DE-627  |e rda 
041 |a eng 
084 |a 33  |2 sdnb 
100 1 |a Bianconi, Francesco  |e VerfasserIn  |0 (DE-588)122620970X  |0 (DE-627)1746899352  |4 aut 
245 1 0 |a Experimental assessment of color deconvolution and color normalization for automated classification of histology images stained with hematoxylin and eosin  |c Francesco Bianconi, Jakob N. Kather and Constantino Carlos Reyes-Aldasoro 
264 1 |c 11 November 2020 
336 |a Text  |b txt  |2 rdacontent 
337 |a Computermedien  |b c  |2 rdamedia 
338 |a Online-Ressource  |b cr  |2 rdacarrier 
500 |a Gesehen am 02.02.2021 
520 |a Histological evaluation plays a major role in cancer diagnosis and treatment. The appearance of H&E-stained images can vary significantly as a consequence of differences in several factors, such as reagents, staining conditions, preparation procedure and image acquisition system. Such potential sources of noise can all have negative effects on computer-assisted classification. To minimize such artefacts and their potentially negative effects several color pre-processing methods have been proposed in the literature—for instance, color augmentation, color constancy, color deconvolution and color transfer. Still, little work has been done to investigate the efficacy of these methods on a quantitative basis. In this paper, we evaluated the effects of color constancy, deconvolution and transfer on automated classification of H&E-stained images representing different types of cancers—specifically breast, prostate, colorectal cancer and malignant lymphoma. Our results indicate that in most cases color pre-processing does not improve the classification accuracy, especially when coupled with color-based image descriptors. Some pre-processing methods, however, can be beneficial when used with some texture-based methods like Gabor filters and Local Binary Patterns. 
650 4 |a color 
650 4 |a E staining 
650 4 |a H&amp 
650 4 |a histology images 
650 4 |a texture 
700 1 |a Kather, Jakob Nikolas  |d 1989-  |e VerfasserIn  |0 (DE-588)1064064914  |0 (DE-627)812897587  |0 (DE-576)423589091  |4 aut 
700 1 |a Reyes-Aldasoro, Constantino Carlos  |e VerfasserIn  |0 (DE-588)1185512683  |0 (DE-627)1664859411  |4 aut 
773 0 8 |i Enthalten in  |t Cancers  |d Basel : MDPI, 2009  |g 12(2020,11) Artikel-Nummer 3337, 18 Seiten  |h Online-Ressource  |w (DE-627)614095670  |w (DE-600)2527080-1  |w (DE-576)313958548  |x 2072-6694  |7 nnas  |a Experimental assessment of color deconvolution and color normalization for automated classification of histology images stained with hematoxylin and eosin 
773 1 8 |g volume:12  |g year:2020  |g number:11  |a Experimental assessment of color deconvolution and color normalization for automated classification of histology images stained with hematoxylin and eosin 
856 4 0 |u https://doi.org/10.3390/cancers12113337  |x Verlag  |x Resolving-System  |z lizenzpflichtig  |3 Volltext 
856 4 0 |u https://www.mdpi.com/2072-6694/12/11/3337  |x Verlag  |z lizenzpflichtig  |3 Volltext 
951 |a AR 
992 |a 20210202 
993 |a Article 
994 |a 2020 
998 |g 1064064914  |a Kather, Jakob Nikolas  |m 1064064914:Kather, Jakob Nikolas  |d 910000  |d 910100  |e 910000PK1064064914  |e 910100PK1064064914  |k 0/910000/  |k 1/910000/910100/  |p 2 
999 |a KXP-PPN1746899336  |e 3847923307 
BIB |a Y 
SER |a journal 
JSO |a {"relHost":[{"physDesc":[{"extent":"Online-Ressource"}],"recId":"614095670","disp":"Experimental assessment of color deconvolution and color normalization for automated classification of histology images stained with hematoxylin and eosinCancers","origin":[{"publisher":"MDPI","dateIssuedKey":"2009","publisherPlace":"Basel","dateIssuedDisp":"2009-"}],"note":["Gesehen am 27.05.2020"],"type":{"media":"Online-Ressource","bibl":"periodical"},"language":["eng"],"title":[{"title_sort":"Cancers","title":"Cancers"}],"pubHistory":["1.2009 -"],"name":{"displayForm":["Molecular Diversity Preservation International (MDPI)"]},"part":{"year":"2020","issue":"11","text":"12(2020,11) Artikel-Nummer 3337, 18 Seiten","volume":"12"},"id":{"zdb":["2527080-1"],"eki":["614095670"],"issn":["2072-6694"]}}],"person":[{"family":"Bianconi","role":"aut","given":"Francesco","display":"Bianconi, Francesco"},{"display":"Kather, Jakob Nikolas","family":"Kather","given":"Jakob Nikolas","role":"aut"},{"role":"aut","given":"Constantino Carlos","family":"Reyes-Aldasoro","display":"Reyes-Aldasoro, Constantino Carlos"}],"origin":[{"dateIssuedKey":"2020","dateIssuedDisp":"11 November 2020"}],"name":{"displayForm":["Francesco Bianconi, Jakob N. Kather and Constantino Carlos Reyes-Aldasoro"]},"title":[{"title_sort":"Experimental assessment of color deconvolution and color normalization for automated classification of histology images stained with hematoxylin and eosin","title":"Experimental assessment of color deconvolution and color normalization for automated classification of histology images stained with hematoxylin and eosin"}],"id":{"eki":["1746899336"],"doi":["10.3390/cancers12113337"]},"note":["Gesehen am 02.02.2021"],"language":["eng"],"type":{"media":"Online-Ressource","bibl":"article-journal"},"recId":"1746899336"} 
SRT |a BIANCONIFREXPERIMENT1120