Cover Image

Evaluating deep learning-based melanoma classification using immunohistochemistry and routine histology: a three center study

Pathologists routinely use immunohistochemical (IHC)-stained tissue slides against MelanA in addition to hematoxylin and eosin (H&E)-stained slides to improve their accuracy in diagnosing melanomas. The use of diagnostic Deep Learning (DL)-based support systems for automated examination of tissu...

Full description

Saved in:
Bibliographic Details
Main Authors: Wies, Christoph (Author) , Schneider, Lucas (Author) , Haggenmüller, Sarah (Author) , Bucher, Tabea-Clara (Author) , Hobelsberger, Sarah (Author) , Heppt, Markus V. (Author) , Ferrara, Gerardo (Author) , Krieghoff-Henning, Eva I. (Author) , Brinker, Titus Josef (Author)
Format: Article (Journal)
Language:English
Published: January 19, 2024
In: PLOS ONE
Year: 2024, Volume: 19, Issue: 1, Pages: 1-13
ISSN:1932-6203
DOI:10.1371/journal.pone.0297146
Online Access:Verlag, lizenzpflichtig, Volltext: https://doi.org/10.1371/journal.pone.0297146
Verlag, lizenzpflichtig, Volltext: https://journals.plos.org/plosone/article?id=10.1371/journal.pone.0297146
Get full text
Author Notes:Christoph Wies, Lucas Schneider, Sarah Haggenmüller, Tabea-Clara Bucher, Sarah Hobelsberger, Markus V. Heppt, Gerardo Ferrara, Eva I. Krieghoff-Henning, Titus J. Brinker
Description
Summary:Pathologists routinely use immunohistochemical (IHC)-stained tissue slides against MelanA in addition to hematoxylin and eosin (H&E)-stained slides to improve their accuracy in diagnosing melanomas. The use of diagnostic Deep Learning (DL)-based support systems for automated examination of tissue morphology and cellular composition has been well studied in standard H&E-stained tissue slides. In contrast, there are few studies that analyze IHC slides using DL. Therefore, we investigated the separate and joint performance of ResNets trained on MelanA and corresponding H&E-stained slides. The MelanA classifier achieved an area under receiver operating characteristics curve (AUROC) of 0.82 and 0.74 on out of distribution (OOD)-datasets, similar to the H&E-based benchmark classification of 0.81 and 0.75, respectively. A combined classifier using MelanA and H&E achieved AUROCs of 0.85 and 0.81 on the OOD datasets. DL MelanA-based assistance systems show the same performance as the benchmark H&E classification and may be improved by multi stain classification to assist pathologists in their clinical routine.
Item Description:Gesehen am 23.09.2024
Physical Description:Online Resource
ISSN:1932-6203
DOI:10.1371/journal.pone.0297146

Similar Items