Detection and subtyping of basal cell carcinoma in whole-slide histopathology using weakly-supervised learning
Open accessAbstract
The frequency of basal cell carcinoma (BCC) cases is putting an increasing strain on dermatopathologists. BCC is the most common type of skin cancer, and its incidence is increasing rapidly worldwide. AI can play a significant role in reducing the time and effort required for BCC diagnostics and thus improve the overall efficiency of the process. To train such an AI system in a fully-supervised fashion however, would require a large amount of pixel-level annotation by already strained dermatopathologists. Therefore, in this study, our primary objective was to develop a weakly-supervised for the identification of basal cell carcinoma (BCC) and the stratification of BCC into low-risk and high-risk categories within histopathology whole-slide images (WSI). We compared Clustering-constrained Attention Multiple instance learning (CLAM) with StreamingCLAM and hypothesized that the latter would be the superior approach. A total of 5147 images were used to train and validate the models, which were subsequently tested on an internal set of 949 images and an external set of 183 images. The labels for training were automatically extracted from free-text pathology reports using a rule-based approach. All data has been made available through the COBRA dataset. The results showed that both the CLAM and StreamingCLAM models achieved high performance for the detection of BCC, with an area under the ROC curve (AUC) of 0.994 and 0.997, respectively, on the internal test set and 0.983 and 0.993 on the external dataset. Furthermore, the models performed well on risk stratification, with AUC values of 0.912 and 0.931, respectively, on the internal set, and 0.851 and 0.883 on the external set. In every single metric the StreamingCLAM model outperformed the CLAM model or is on par. The performance of both models was comparable to that of two pathologists who scored 240 BCC positive slides. Additionally, in the public test set, StreamingCLAM demonstrated a comparable AUC of 0.958, markedly superior to CLAM's 0.803. This difference was statistically significant and emphasized the strength and better adaptability of the StreamingCLAM approach.
The claims and statistics of this paper haven’t been checked yet.
Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.
Integrity signals
Registry
Cites
Statistics
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.
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 Radboud University Medical Center cohort includes 949 cases from the test split of the COBRA dataset of patients who underwent skin biopsy.
“The Radboud University Medical Center cohort includes 949 cases from the test split of the COBRA41 dataset of patients who underwent skin biopsy.”
From Generating dermatopathology reports from gigapixel whole slide images with HistoGPT (2025) · cites this paper as [41]
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
The self-check needs the paper’s full text.
Cites
Clinical-grade computational pathology using weakly supervised deep learning on whole slide images
Campanella, G., Hanna, M. G., Geneslaw, L., Miraflor, A., Werneck Krauss Silva, V., Busam, K. J., Brogi, E., Reuter, V. E., Klimstra, D. S., & Fuchs, T. J. (2019) · Nature Medicine · doi:10.1038/s41591-019-0508-1 · Cited by 2,799 · see citing works
Data-efficient and weakly supervised computational pathology on whole-slide images
Lu, M. Y., Williamson, D. F. K., Chen, T. Y., Chen, R. J., Barbieri, M., & Mahmood, F. (2021) · Nature Biomedical Engineering · doi:10.1038/s41551-020-00682-w · Cited by 2,282 · see citing works
A systematic review of worldwide incidence of nonmelanoma skin cancer
Lomas, A., Leonardi‐Bee, J., & Bath-Hextall, F. J. (2012) · British Journal of Dermatology · doi:10.1111/j.1365-2133.2012.10830.x · Cited by 1,943 · see citing works
Skin Cancer: Epidemiology, Disease Burden, Pathophysiology, Diagnosis, and Therapeutic Approaches
Apalla, Z., Nashan, D., Weller, R., & Castellsagué, X. (2017) · Dermatology and Therapy · doi:10.1007/s13555-016-0165-y · Cited by 466 · see citing works
Predictions of skin cancer incidence in the Netherlands up to 2015
de Vries, E., van de Poll-Franse, L. V., Louwman, M. W. J., de Gruijl, F. R., & Coebergh, J. W. W. (2005) · British Journal of Dermatology · doi:10.1111/j.1365-2133.2005.06386.x · Cited by 253 · see citing works
Kim, D. P., Kus, K. J. B., & Ruiz, E. S. (2018) · Hematology/Oncology Clinics of North America · doi:10.1016/j.hoc.2018.09.004 · Cited by 251 · see citing works
Incidence, Mortality, and Trends of Nonmelanoma Skin Cancer in Germany
Leiter, U., Keim, U., Eigentler, T., Katalinic, A., Holleczek, B., Martus, P., & Garbe, C. (2017) · Journal of Investigative Dermatology · doi:10.1016/j.jid.2017.04.020 · Cited by 229 · see citing works
Ianni, J. D., Soans, R. E., Sankarapandian, S., Chamarthi, R. V., Ayyagari, D., Olsen, T. G., Bonham, M. J., Stavish, C. C., Motaparthi, K., Cockerell, C. J., et al. (2020) · Scientific Reports · doi:10.1038/s41598-020-59985-2 · Cited by 113 · see citing works
Streaming Convolutional Neural Networks for End-to-End Learning With Multi-Megapixel Images
Pinckaers, H., van Ginneken, B., & Litjens, G. J. S. (2020) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2020.3019563 · Cited by 112 · see citing works
Self-citationAn unsupervised feature learning framework for basal cell carcinoma image analysis
Arévalo, J., Cruz-Roa, Á., Arias, V., Romero, E., & Gonzalez, F. A. (2015) · Artificial Intelligence in Medicine · doi:10.1016/j.artmed.2015.04.004 · Cited by 99 · see citing works
Residual cyclegan for robust domain transformation of histopathological tissue slides
de Bel, T., Bokhorst, J., van der Laak, J. A. W. M., & Litjens, G. J. S. (2021) · Medical Image Analysis · doi:10.1016/j.media.2021.102004 · Cited by 95 · see citing works
Self-citationJiang, Y., Xiong, J., Li, H. Y., Yang, X., Yu, W. T., Gao, M., Zhao, X., Ma, Y., Zhang, W., Guan, Y. F., et al. (2019) · British Journal of Dermatology · doi:10.1111/bjd.18026 · Cited by 72 · see citing works
Fernández‐Figueras, M. T., Malvehi, J., Tschandl, P., et al. (2021) · Journal of the European Academy of Dermatology and Venereology · doi:10.1111/jdv.17849 · Cited by 34 · see citing works
Nedved, D., Tonkovic‐Capin, V., Hunt, E. L., et al. (2013) · Journal of Cutaneous Pathology · doi:10.1111/cup.12256 · Cited by 33 · see citing works
Yacob, F., Siarov, J., Villiamsson, K., Suvilehto, J. T., Sjöblom, L., Kjellberg, M., & Neittaanmäki, N. (2023) · Scientific Reports · doi:10.1038/s41598-023-33863-z · Cited by 33 · see citing works
Sankarapandian, S., Kohn, S., Spurrier, V., Grullon, S., Soans, R. E., Ayyagari, K. D., Chamarthi, R. V., Motaparthi, K., Lee, J. B., Shon, W., et al. (2021) · IEEE International Conference on Computer Vision Workshops · doi:10.1109/iccvw54120.2021.00076 · Cited by 29 · see citing works
Flagged first, then by citations
Cited by
Sorted by citations
Generating dermatopathology reports from gigapixel whole slide images with HistoGPT
Tran, M., Schmidle, P., Guo, R. R., Wagner, S. J., Koch, V., Lupperger, V., Novotny, B., Murphree, D. H., Hardway, H. D., D’Amato, M., et al. (2025) · Nature Communications · doi:10.1038/s41467-025-60014-x · Cited by 36 · see citing works
Self-citation
- Authors
- Geijs, D. J., Dooper, S., Aswolinskiy, W., Hillen, L. M., Amir, A. L., & Litjens, G.
- Affiliations
- Radboud University Medical Center (NL)
- Maastricht University Medical Centre (NL)
- Corresponding author
- Geijs, Daan J.
- Venue
- Medical Image Analysis
- Publisher
- Elsevier BV
- Published
- 2024-04
- Volume
- 93
- Pages
- 103063
- ISSN
- 1361-8415 (ISSN-L)
- OpenAlex
- W4389839624
- Cited by
- 27
- References
- 16
- Citations by year
- 2026: 10 · 2025: 14 · 2024: 3
- FWCI
- 2.54
- Type
- journal article
- Language
- en
- Open access
- hybrid
- doi.org
- Licence
- Locations
- Medical Image Analysis (publishedVersion, cc-by-sa)
- PubMed (publishedVersion)
- Research Publications (Maastricht University) (publishedVersion, cc-by)
- Radboud Repository (Radboud University) (submittedVersion, cc-by-sa)
- Radboud Repository (Radboud University) (submittedVersion)
- Funders
- Nederlandse Organisatie voor Wetenschappelijk Onderzoek
- HORIZON EUROPE European Research Council (101041730)
- Topics
- Physical Sciences › Computer Science › Artificial Intelligence › AI in cancer detection
- Health Sciences › Medicine › Oncology › Cutaneous Melanoma Detection and Management
- Health Sciences › Medicine › Epidemiology › Nonmelanoma Skin Cancer Studies
- Keywords
- basal cell carcinoma, whole slide images, weakly supervised learning, clams, multiple instance learning, attention mechanism, risk stratification, skin cancer detection, dermatopathology
- MeSH terms
- Supervised Machine Learning, Basal Cell Carcinoma, Humans, Skin Neoplasms, Area Under Curve
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
