CoChat
Sign Up
Cited by 8AI in cancer detectionCancer and Skin LesionsCutaneous Melanoma Detection and Management

The DOI matches its Crossref record; 24 of the 24 references it cites were found in a registry or an index.

Deep learning based histological classification of adnex tumors

Jansen, Philipp, Arrastia, Jean Le’Clerc, Baguer, Daniel Otero, Schmidt, Maximilian, Landsberg, Jennifer, Wenzel, Jörg, Emberger, Michael, Schadendorf, Dirk, Hadaschik, Eva, Maass, Peter, Griewank, Klaus Georg·2024·European Journal of Cancer
DOI 10.1016/j.ejca.2023.113431
Open this paper in CoChat — free account

Abstract

Background Cutaneous adnexal tumors are a diverse group of tumors arising from structures of the hair appendages. Although often benign, malignant entities occur which can metastasize and lead to patients´ death. Correct diagnosis is critical to ensure optimal treatment and best possible patient outcome. Artificial intelligence (AI) in the form of deep neural networks has recently shown enormous potential in the field of medicine including pathology, where we and others have found common cutaneous tumors can be detected with high sensitivity and specificity. To become a widely applied tool, AI approaches will also need to reliably detect and distinguish less common tumor entities including the diverse group of cutaneous adnexal tumors.Methods To assess the potential of AI to recognize cutaneous adnexal tumors, we selected a diverse set of these entities from five German centers. The algorithm was trained with samples from four centers and then tested on slides from the fifth center.Results The neural network was able to differentiate 14 different cutaneous adnexal tumors and distinguish them from more common cutaneous tumors (i.e. basal cell carcinoma and seborrheic keratosis). The total accuracy on the test set for classifying 248 samples into these 16 diagnoses was 89.92 %. Our findings support AI can distinguish rare tumors, for morphologically distinct entities even with very limited case numbers (< 50) for training.Conclusion This study further underlines the enormous potential of AI in pathology which could become a standard tool to aid pathologists in routine diagnostics in the foreseeable future. The final diagnostic responsibility will remain with the pathologist.

Overview

Integrity signals

Registry

Crossref · 10.1016/j.ejca.2023.113431

Cites

24 of 24 references verified0 citation errors · 0 not checkable

Statistics

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

Verification

Claims the paper makes

This paper’s full text isn’t openly available, 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?

  • AI has shown considerable promise in the histological classification of adnexal tumors, a group of skin neoplasms with overlapping features where ancillary studies like immunohistochemistry are of limited utility.

    “AI has shown also considerable promise in the histological classification of adnexal tumors, a group of skin neoplasms with overlapping features where other ancillary studies, like immunohistochemistry, are of limited utility.”

    From Artificial Intelligence in Dermatopathology: An Update and Review of the Current Literature (2026) · cites this paper as [31]

  • AI has potential to assist dermatopathologists in diagnosing less common skin tumors, enhancing diagnostic efficiency and accuracy.

    “The study underscores the potential of AI to assist dermatopathologists in diagnosing less common skin tumors, enhancing diagnostic efficiency and accuracy.”

    From Artificial Intelligence in Dermatopathology: An Update and Review of the Current Literature (2026) · cites this paper as [31]

  • The CNN successfully distinguished some rare adnexal tumors from more common skin lesions like BCC and seborrheic keratosis, even with limited training data (fewer than 50 cases per class).

    “Notably, it successfully distinguished some rare tumors within this category from more common skin lesions like BCC and seborrheic keratosis, even with limited training data (fewer than 50 cases per class).”

    From Artificial Intelligence in Dermatopathology: An Update and Review of the Current Literature (2026) · cites this paper as [31]

  • A CNN classified 14 different cutaneous adnexal tumors using histopathological images with an overall classification accuracy of 89.92% across 248 samples.

    “A recent study developed a CNN to classify 14 different cutaneous adnexal tumors using histopathological images [31]. The model achieved an overall classification accuracy of 89.92% across 248 samples.”

    From Artificial Intelligence in Dermatopathology: An Update and Review of the Current Literature (2026) · cites this paper as [31]

  • Rare entities such as adnexal tumors are underrepresented, which limits generalizability.

    “In addition, rare entities such as adnexal tumors are underrepresented, which limits generalizability [31].”

    From Artificial Intelligence in Dermatopathology: An Update and Review of the Current Literature (2026) · cites this paper as [31]

Citations

Cites

Flagged first, then by citations

Research works printed but not linked: 1

  1. Jansen, 2022, Evaluation of a deep learning approach to differentiate bowen’s disease and seborrheic keratosis, Cancers, 14, 10.3390/cancers14143518 · DOI

Cited by

Sorted by citations

Related

Metadata

Authors
Jansen, P., Arrastia, J. L., Baguer, D. O., Schmidt, M., Landsberg, J., Wenzel, J., Emberger, M., Schadendorf, D., Hadaschik, E., Maass, P., & Griewank, K. G.
Affiliations
  • University Hospital Bonn (DE)
  • University of Bremen (DE)
  • Essen University Hospital (DE)
Corresponding author
Griewank, Klaus Georg
ORCID
Venue
European Journal of Cancer
Publisher
Elsevier BV
Published
2024-01
Volume
196
Pages
113431
ISSN
0959-8049 (ISSN-L)
DOI
10.1016/j.ejca.2023.113431
OpenAlex
W4388706671
Cited by
8
References
24
Citations by year
2026: 3 · 2025: 4 · 2024: 1
FWCI
0.75
Type
journal article
Language
en
Open access
closed
Licence
Locations
  • European Journal of Cancer (publishedVersion)
  • PubMed (publishedVersion)
  • Universitätsbibliographie, Universität Duisburg-Essen (submittedVersion)
Funders
  • European Social Fund Plus
  • Bundesministerium für Wirtschaft und Klimaschutz
Topics
  • Physical Sciences › Computer Science › Artificial Intelligence › AI in cancer detection
  • Health Sciences › Medicine › Dermatology › Cancer and Skin Lesions
  • Health Sciences › Medicine › Oncology › Cutaneous Melanoma Detection and Management
Keywords
skin adnexal tumors, histological classification, deep learning, artificial intelligence in pathology, deep neural network, basal cell carcinoma, seborrheic keratosis, cross-center validation
MeSH terms
Deep Learning, Algorithms, Artificial Intelligence, Humans, Skin Neoplasms, Neural Networks, Computer

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