Digital quantification of PRAME for distinguishing melanoma from nevi compared to manual assessment

Johan Enevoldsen; Mette Bak Brogård; Johanne Lade-Keller; Kristina Bang Christensen; Jeanette Bæhr Georgsen; Patricia Switten Nielsen; Torben Steiniche

doi:10.1016/j.prp.2024.155543

Digital quantification of PRAME for distinguishing melanoma from nevi compared to manual assessment

Johan Enevoldsen, Mette Bak Brogård^*, Johanne Lade-Keller, Kristina Bang Christensen, Jeanette Bæhr Georgsen, Patricia Switten Nielsen, Torben Steiniche

^*Corresponding author for this work

Research output: Contribution to journal/Conference contribution in journal/Contribution to newspaper › Journal article › Research › peer-review

Abstract

Aims: In this proof-of-concept study, we propose a new method for automated digital quantification of PRAME (PReferentially expressed Antigen of MElanoma) as a diagnostic aid to distinguish between benign and malignant melanocytic lesions. The proposed method utilizes immunohistochemical virtual double nuclear staining for PRAME and SOX10 to precisely identify the melanocytic cells of interest, which is combined with digital image analyse to quantify a PRAME-index. Methods: Our study included 10 compound nevi, 3 halo nevi, and 10 melanomas. Tissue slides were stained with PRAME, scanned, the cover glass removed, stained with SOX10, scanned again, and finally analysed digitally. The digitally quantified PRAME-index was compared with a manual qualitative assessment by a dermatopathologist using the standard PRAME-scoring system. Results: The digitally quantified PRAME-index showed a sensitivity of 70 % and a specificity of 100 % for separating melanomas from benign lesions. The manual qualitative PRAME-score showed a sensitivity of 60 % and a specificity of 100 %. Comparing the two methods using ROC-analyses, our digital quantitative method (AUC: 0.931, 95 % CI: 0.834;1.00, SD: 0.050) remains on par with the manual qualitative method (AUC: 0.877, 95 % CI: 0.725;1.00, SD: 0.078). Conclusion: We found our novel digital quantitative method was at least as precise at classifying lesions as benign or malignant as the current manual qualitative assessment. Our method has the advantages of being operator-independent, objective, and replicable. Furthermore, our method can easily be implemented in an already digitalized pathology department. Given the small cohort size, more studies are to be done to validate our findings.

Original language	English
Article number	155543
Journal	Pathology Research and Practice
Volume	262
Number of pages	8
ISSN	0344-0338
DOIs	https://doi.org/10.1016/j.prp.2024.155543
Publication status	Published - Aug 2024

Keywords

digital image analysis
digital pathology
melanocytic lesions
Melanoma
multiplex immunohistochemistry
PRAME

Access to Document

10.1016/j.prp.2024.155543Licence: CC BY

Cite this

@article{273dddbf49f5492c9e19fa90b799c5f5,

title = "Digital quantification of PRAME for distinguishing melanoma from nevi compared to manual assessment",

abstract = "Aims: In this proof-of-concept study, we propose a new method for automated digital quantification of PRAME (PReferentially expressed Antigen of MElanoma) as a diagnostic aid to distinguish between benign and malignant melanocytic lesions. The proposed method utilizes immunohistochemical virtual double nuclear staining for PRAME and SOX10 to precisely identify the melanocytic cells of interest, which is combined with digital image analyse to quantify a PRAME-index. Methods: Our study included 10 compound nevi, 3 halo nevi, and 10 melanomas. Tissue slides were stained with PRAME, scanned, the cover glass removed, stained with SOX10, scanned again, and finally analysed digitally. The digitally quantified PRAME-index was compared with a manual qualitative assessment by a dermatopathologist using the standard PRAME-scoring system. Results: The digitally quantified PRAME-index showed a sensitivity of 70 % and a specificity of 100 % for separating melanomas from benign lesions. The manual qualitative PRAME-score showed a sensitivity of 60 % and a specificity of 100 %. Comparing the two methods using ROC-analyses, our digital quantitative method (AUC: 0.931, 95 % CI: 0.834;1.00, SD: 0.050) remains on par with the manual qualitative method (AUC: 0.877, 95 % CI: 0.725;1.00, SD: 0.078). Conclusion: We found our novel digital quantitative method was at least as precise at classifying lesions as benign or malignant as the current manual qualitative assessment. Our method has the advantages of being operator-independent, objective, and replicable. Furthermore, our method can easily be implemented in an already digitalized pathology department. Given the small cohort size, more studies are to be done to validate our findings.",

keywords = "digital image analysis, digital pathology, melanocytic lesions, Melanoma, multiplex immunohistochemistry, PRAME",

author = "Johan Enevoldsen and Brog{\aa}rd, {Mette Bak} and Johanne Lade-Keller and Christensen, {Kristina Bang} and Georgsen, {Jeanette B{\ae}hr} and Nielsen, {Patricia Switten} and Torben Steiniche",

year = "2024",

month = aug,

doi = "10.1016/j.prp.2024.155543",

language = "English",

volume = "262",

journal = "Pathology Research and Practice",

issn = "0344-0338",

publisher = "Elsevier GmbH - Urban und Fischer",

}

Digital quantification of PRAME for distinguishing melanoma from nevi compared to manual assessment. / Enevoldsen, Johan ; Brogård, Mette Bak; Lade-Keller, Johanne et al.
In: Pathology Research and Practice, Vol. 262, 155543, 08.2024.

Research output: Contribution to journal/Conference contribution in journal/Contribution to newspaper › Journal article › Research › peer-review

TY - JOUR

T1 - Digital quantification of PRAME for distinguishing melanoma from nevi compared to manual assessment

AU - Enevoldsen, Johan

AU - Brogård, Mette Bak

AU - Lade-Keller, Johanne

AU - Christensen, Kristina Bang

AU - Georgsen, Jeanette Bæhr

AU - Nielsen, Patricia Switten

AU - Steiniche, Torben

PY - 2024/8

Y1 - 2024/8

N2 - Aims: In this proof-of-concept study, we propose a new method for automated digital quantification of PRAME (PReferentially expressed Antigen of MElanoma) as a diagnostic aid to distinguish between benign and malignant melanocytic lesions. The proposed method utilizes immunohistochemical virtual double nuclear staining for PRAME and SOX10 to precisely identify the melanocytic cells of interest, which is combined with digital image analyse to quantify a PRAME-index. Methods: Our study included 10 compound nevi, 3 halo nevi, and 10 melanomas. Tissue slides were stained with PRAME, scanned, the cover glass removed, stained with SOX10, scanned again, and finally analysed digitally. The digitally quantified PRAME-index was compared with a manual qualitative assessment by a dermatopathologist using the standard PRAME-scoring system. Results: The digitally quantified PRAME-index showed a sensitivity of 70 % and a specificity of 100 % for separating melanomas from benign lesions. The manual qualitative PRAME-score showed a sensitivity of 60 % and a specificity of 100 %. Comparing the two methods using ROC-analyses, our digital quantitative method (AUC: 0.931, 95 % CI: 0.834;1.00, SD: 0.050) remains on par with the manual qualitative method (AUC: 0.877, 95 % CI: 0.725;1.00, SD: 0.078). Conclusion: We found our novel digital quantitative method was at least as precise at classifying lesions as benign or malignant as the current manual qualitative assessment. Our method has the advantages of being operator-independent, objective, and replicable. Furthermore, our method can easily be implemented in an already digitalized pathology department. Given the small cohort size, more studies are to be done to validate our findings.

AB - Aims: In this proof-of-concept study, we propose a new method for automated digital quantification of PRAME (PReferentially expressed Antigen of MElanoma) as a diagnostic aid to distinguish between benign and malignant melanocytic lesions. The proposed method utilizes immunohistochemical virtual double nuclear staining for PRAME and SOX10 to precisely identify the melanocytic cells of interest, which is combined with digital image analyse to quantify a PRAME-index. Methods: Our study included 10 compound nevi, 3 halo nevi, and 10 melanomas. Tissue slides were stained with PRAME, scanned, the cover glass removed, stained with SOX10, scanned again, and finally analysed digitally. The digitally quantified PRAME-index was compared with a manual qualitative assessment by a dermatopathologist using the standard PRAME-scoring system. Results: The digitally quantified PRAME-index showed a sensitivity of 70 % and a specificity of 100 % for separating melanomas from benign lesions. The manual qualitative PRAME-score showed a sensitivity of 60 % and a specificity of 100 %. Comparing the two methods using ROC-analyses, our digital quantitative method (AUC: 0.931, 95 % CI: 0.834;1.00, SD: 0.050) remains on par with the manual qualitative method (AUC: 0.877, 95 % CI: 0.725;1.00, SD: 0.078). Conclusion: We found our novel digital quantitative method was at least as precise at classifying lesions as benign or malignant as the current manual qualitative assessment. Our method has the advantages of being operator-independent, objective, and replicable. Furthermore, our method can easily be implemented in an already digitalized pathology department. Given the small cohort size, more studies are to be done to validate our findings.

KW - digital image analysis

KW - digital pathology

KW - melanocytic lesions

KW - Melanoma

KW - multiplex immunohistochemistry

KW - PRAME

UR - http://www.scopus.com/inward/record.url?scp=85201422358&partnerID=8YFLogxK

U2 - 10.1016/j.prp.2024.155543

DO - 10.1016/j.prp.2024.155543

M3 - Journal article

C2 - 39154604

AN - SCOPUS:85201422358

SN - 0344-0338

VL - 262

JO - Pathology Research and Practice

JF - Pathology Research and Practice

M1 - 155543

ER -

Digital quantification of PRAME for distinguishing melanoma from nevi compared to manual assessment

Abstract

Keywords

Access to Document

Other files and links

Fingerprint

Cite this