CoChat
Sign Up
Cited by 231AI in cancer detectionCutaneous Melanoma Detection and ManagementRadiomics and Machine Learning in Medical Imaging

Pathologist-level classification of histopathological melanoma images with deep neural networks

Open access
Hekler, Achim, Utikal, Jochen Sven, Enk, Alexander H., Berking, Carola, Klode, Joachim, Schadendorf, Dirk, Jansen, Philipp, Franklin, Cindy +5 more·2019·European Journal of Cancer
DOI 10.1016/j.ejca.2019.04.021
Open this paper in CoChat — free account

Abstract

BACKGROUND: The diagnosis of most cancers is made by a board-certified pathologist based on a tissue biopsy under the microscope. Recent research reveals a high discordance between individual pathologists. For melanoma, the literature reports 25-26% of discordance for classifying a benign nevus versus malignant melanoma. Deep learning was successfully implemented to enhance the precision of lung and breast cancer diagnoses. The aim of this study is to illustrate the potential of deep learning to assist human assessment for a histopathologic melanoma diagnosis. METHODS: Six hundred ninety-five lesions were classified by an expert histopathologist in accordance with current guidelines (350 nevi and 345 melanomas). Only the haematoxylin and eosin stained (H&E) slides of these lesions were digitalised using a slide scanner and then randomly cropped. Five hundred ninety-five of the resulting images were used for the training of a convolutional neural network (CNN). The additional 100 H&E image sections were used to test the results of the CNN in comparison with the original class labels. FINDINGS: The total discordance with the histopathologist was 18% for melanoma (95% confidence interval [CI]: 7.4-28.6%), 20% for nevi (95% CI: 8.9-31.1%) and 19% for the full set of images (95% CI: 11.3-26.7%). INTERPRETATION: Even in the worst case, the discordance of the CNN was about the same compared with the discordance between human pathologists as reported in the literature. Despite the vastly reduced amount of data, time necessary for diagnosis and cost compared with the pathologist, our CNN archived on-par performance. Conclusively, CNNs indicate to be a valuable tool to assist human melanoma diagnoses.

Integrity signals

Registry

Crossref · 10.1016/j.ejca.2019.04.021

Cites

17 of 17 references verified0 citation errors · 0 not checkable

Statistics

Recomputing p-values needs the paper’s full text.

Claims the paper makes

We couldn’t retrieve this paper’s full text, so its claims and self-check weren’t run. The registry and citation checks still apply.

Claims other papers make about this one

Each is checked against this paper’s own text: does it say what the citing paper says it does?

  • The Hekler et al. algorithm can only assess whether a lesion is more likely to be a nevus or melanoma, unlike pathologists who consider a wide range of differential diagnoses.

    “the algorithm’s binary classification approach; unlike pathologists, who must consider a wide range of differential diagnoses, the model can only assess whether a lesion is more likely to be a nevus or melanoma.”

    From Artificial Intelligence in Dermatopathology: An Update and Review of the Current Literature (2026) · cites this paper as [14]

  • Deep learning models can match or exceed human-level performance under certain conditions in distinguishing benign nevi from malignant melanoma.

    “While the results suggest that deep learning models can match or exceed human-level performance under certain conditions”

    From Artificial Intelligence in Dermatopathology: An Update and Review of the Current Literature (2026) · cites this paper as [14]

  • ResNet50 is a commonly used CNN model in classification of cutaneous lesions, including melanoma, achieving high diagnostic accuracy.

    “One of the most commonly used is ResNet50, a CNN model well known for its success in image classification and used in classification of many cutaneous lesions, including melanoma classification, achieving a high diagnostic accuracy [14,18].”

    From Artificial Intelligence in Dermatopathology: An Update and Review of the Current Literature (2026) · cites this paper as [14]

  • Hekler et al.'s ResNet50 CNN model had an overall disagreement with pathologists of 18% for melanoma cases and 20% for nevi.

    “The overall disagreement with the pathologist was 18% for melanoma cases and 20% for nevi.”

    From Artificial Intelligence in Dermatopathology: An Update and Review of the Current Literature (2026) · cites this paper as [14]

  • Hekler et al. found DNNs gave 100% sensitivity and 98.9% specificity for nodular basal cell carcinoma, 98.8% sensitivity and 100% specificity in dermal nevi, and 100% sensitivity and specificity in seborrheic keratosis.

    “The DNN gave excellent results with 100% sensitivity and 98.9% specificity for nodular basal cell carcinoma. It also yielded a high sensitivity of 98.8% and a specificity of 100% in dermal nevi and sensitivity and specificity of 100% in seborrheic keratosis.”

    From Revolutionizing dermatopathology using AI in skin diagnostics: scoping review (2026) · cites this paper as [29]

Cites

Flagged first, then by citations

Cited by

Sorted by citations

Related

Authors
Hekler, A., Utikal, J. S., Enk, A. H., Berking, C., Klode, J., Schadendorf, D., Jansen, P., Franklin, C., Holland-Letz, T., Krahl, D., von Kalle, C., Fröhling, S., & Brinker, T. J.
Affiliations
  • German Cancer Research Center (DE)
  • University Hospital Heidelberg (DE)
  • LMU Klinikum (DE)
  • Essen University Hospital (DE)
  • University Hospital Cologne (DE)
Corresponding author
Brinker, Titus Josef
ORCID
Venue
European Journal of Cancer
Publisher
Elsevier BV
Published
2019-07
Volume
115
Pages
79-83
ISSN
0959-8049 (ISSN-L)
DOI
10.1016/j.ejca.2019.04.021
OpenAlex
W2945626616
Cited by
231
References
17
Citations by year
2026: 12 · 2025: 19 · 2024: 30 · 2023: 36 · 2022: 54 · 2021: 41 · 2020: 24 · 2019: 14
FWCI
15.40
Type
journal article
Language
en
Open access
Licence
Locations
  • European Journal of Cancer (publishedVersion, cc-by-nc-nd)
  • PubMed (publishedVersion)
  • Kölner Universitäts PublikationsServer (Universität zu Köln) (publishedVersion)
Topics
  • Physical Sciences › Computer Science › Artificial Intelligence › AI in cancer detection
  • Health Sciences › Medicine › Oncology › Cutaneous Melanoma Detection and Management
  • Health Sciences › Medicine › Radiology, Nuclear Medicine and Imaging › Radiomics and Machine Learning in Medical Imaging
Keywords
melanoma, histopathology, convolutional neural networks, computer-aided diagnosis, benign nevi, H&E staining, slide scanning, melanoma classification
MeSH terms
Pathologists, Deep Learning, Biopsy, Diagnosis, Computer-Assisted, Humans, Image Interpretation, Computer-Assisted, Melanoma, Microscopy, Nevus, Predictive Value of Tests, Skin Neoplasms, Reproducibility of Results, Observer Variation

About these checks

Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.

Statistics and arithmetic are recomputed, not judged.

Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.

What counts as a claim ›How we measure confidence ›How we check this ›

Are you an author, or do you see a problem with this page? Request a review