Evaluating Deep Learning-based Melanoma Classification using Immunohistochemistry and Routine Histology: A Three Center Study
This work addresses the need for improved diagnostic support systems for pathologists in melanoma detection, though it is incremental as it builds on existing deep learning methods for histology by extending them to IHC slides.
The study tackled the problem of automated melanoma classification by evaluating deep learning models on immunohistochemistry (MelanA) and routine histology (H&E) slides, finding that a combined classifier achieved AUROCs of 0.85 and 0.81 on out-of-distribution datasets, outperforming single-stain models.
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.