AB034. Weakly supervised artificial intelligence-based subtyping of thymic epithelial tumors using H&E whole slide images
Original Research

AB034. Weakly supervised artificial intelligence-based subtyping of thymic epithelial tumors using H&E whole slide images

Anna Salut Esteve Domínguez1, Farhan Akram1, Stephanie Peeters2, Lara Chalabreysse3, Nicolas Girard4, Dirk De Ruysscher2, Jan von der Thüsen1

1Department of Pathology and Clinical Bioinformatics, Erasmus Medical Center, Rotterdam, The Netherlands; 2Department of Radiation Oncology (Maastro), GROW Research Institute for Oncology and Reproduction, Maastricht University Medical Centre+, Maastricht, The Netherlands; 3Department of Pathology, Centre Hospitalier Universitaire de Lyon, Lyon, France; 4Department of Medical Oncology, Institut Curie, Paris, France

Correspondence to: Anna Salut Esteve Domínguez, MSc. Department of Pathology and Clinical Bioinformatics, Erasmus Medical Center, Dr. Molewaterplein 40, Rotterdam, 3015 GD, The Netherlands. Email: a.estevedominguez@erasmusmc.nl.

Background: Thymic epithelial tumors (TETs) are rare neoplasms classified by the World Health Organization (WHO) into thymomas (A, AB, B1, B2, B3) and thymic carcinomas (TCs). Due to overlapping histopathological features, accurate differentiation is challenging, leading to diagnostic variability among pathologists. This study aimed to develop a diagnostic tool to support precise subtyping, reduce ambiguity, improve treatment strategies, and ultimately enhance patient outcomes.

Methods: Our study utilized an in-house Erasmus Medical Center (EMC) dataset of 669 patients diagnosed by eight pathologists and an external Lyon dataset of 97 patients. After excluding cases with less than 70% agreement within the pathologist panel and irrelevant thymoma types (n=510), 159 EMC cases remained. Tumor areas were annotated, and 512×512-pixel tiles were taken at 10x magnification using QuPath. To reduce staining differences, Vahadane’s stain normalization method was used (see Figure 1). The dataset was divided at the patient level, resulting in 76 EMC cases and 12 Lyon cases for training, while 83 EMC cases and 85 Lyon cases were used for testing. After preprocessing, two separate AI models were developed: the first was designed to generate additional labels, while the second, built on the VGG16 architecture, was used to classify the subtypes A, AB, B1, B2, B3, and TC. To ensure the reliability of the results, stratified 3-fold cross-validation was employed.

Results: The model achieved an area under the curve (AUC) of 1 and a balanced accuracy (BAcc) of 0.97±0.02 on the validation set. On the 70–100% consensus test set, it recorded an AUC of 0.91±0.01 and BAcc of 0.78±0.03, while the 100% consensus test set yielded an AUC of 0.98±0.01 and BAcc of 0.89±0.01. On the external dataset, it reached an AUC of 0.93±0.01 and BAcc of 0.76±0.04. Grad-CAM visualizations showed subtype-specific patterns, although distinguishing group B remained challenging.

Conclusions: The model demonstrated robust accuracy in distinguishing between TET subtypes in both external and internal dataset, thereby providing substantial support to pathologists and facilitating informed treatment decisions. Nonetheless, similar to the difficulties faced by pathologists, the model’s efficacy was compromised in ambiguous cases characterized by mixed histological features. In future work, we will evaluate its performance on additional external.

Keywords: Thymic epithelial tumors (TETs); histopathology; subtyping; artificial intelligence classification (AI classification); deep learning

Figure 1 Workflow for histological image preprocessing, CNN training, and patient-level evaluation. CNN, convolutional neural network.

Acknowledgments

None.

Footnote

Funding: This work was supported by Hanarth Fonds grant 2022 (PI: S.P.).

Conflicts of Interest: All authors have completed the ICMJE uniform disclosure form (available at https://med.amegroups.com/article/view/10.21037/med-25-ab034/coif). N.G. serves as an unpaid editorial board member of Mediastinum from January 2024 to December 2025. J.v.d.T. serves as an unpaid editorial board member of Mediastinum from May 2024 to December 2025. S.P. reports support from Hanarth grant. D.D.R. reported grants or contracts from various entities, indicating institutional financial interests without personal financial gain from organizations such as AstraZeneca, BMS, Beigene, Philips, Olink, and Eli Lilly, where his involvement includes research grants, support, and advisory board participation. The other authors have no conflicts of interest to declare.

Ethical Statement: The authors are accountable for all aspects of the work in ensuring that questions related to the accuracy or integrity of any part of the work are appropriately investigated and resolved. The study was conducted in accordance with the Declaration of Helsinki and its subsequent amendments. The study was approved by the institutional ethics committee of Maastricht University Medical Center+ (METC-number: 2018-0491, amendment number: 2018-0491-A-9) and individual consent for this retrospective analysis was waived.

Open Access Statement: This is an Open Access article distributed in accordance with the Creative Commons Attribution-NonCommercial-NoDerivs 4.0 International License (CC BY-NC-ND 4.0), which permits the non-commercial replication and distribution of the article with the strict proviso that no changes or edits are made and the original work is properly cited (including links to both the formal publication through the relevant DOI and the license). See: https://creativecommons.org/licenses/by-nc-nd/4.0/.

doi: 10.21037/med-25-ab034
Cite this abstract as: Esteve Domínguez AS, Akram F, Peeters S, Chalabreysse L, Girard N, De Ruysscher D, von der Thüsen J. AB034. Weakly supervised artificial intelligence-based subtyping of thymic epithelial tumors using H&E whole slide images. Mediastinum 2025;9:AB034.

Article Options

Download Citation

Share