PD-L1 expression assessment in Angiosarcoma improves with artificial intelligence support

F H Reith ^1,2,3,4, A Jarosch ⁵, J P Albrecht ^1,2,4

¹Max Delbrück Center for Molecular Medicine in the Helmholtz Association.
²Helmholtz Imaging, Berlin, Germany.
³Charité - Universitätsmedizin Berlin, Berlin, Germany.
⁴Humboldt-Universität Berlin, Faculty of Mathematics and Natural Sciences, Berlin, Germany.
⁵Charité - Universitätsmedizin Berlin, corporate member of Freie Universität Berlin, Humboldt-Universität zu Berlin, Department of Pathology, Berlin, Germany.
⁶Charité - Universitätsmedizin Berlin, corporate member of Freie Universität Berlin and Humboldt Universität zu Berlin, Department of Dermatology, Berlin, Germany.
⁷Charité - Universitätsmedizin Berlin, corporate member of Freie Universität Berlin, Humboldt-Universität zu Berlin and Berlin Institute of Health, Department of Hematology, Oncology, and Tumor Immunology, Berlin, Germany.
⁸German Cancer Consortium (DKTK), partner site Berlin, and German Cancer Research Center (DKFZ), Heidelberg, Germany.
⁹Charité - Universitätsmedizin Berlin, corporate member of Freie Universität Berlin and Humboldt-Universität zu Berlin, Berlin, Germany.
¹⁰Berlin Institute of Health at Charité, Universitätsmedizin Berlin, BIH Biomedical Innovation Academy, BIH Charité (Junior) Clinician Scientist Program, Berlin, Germany.
¹¹Charité - Universitätsmedizin Berlin, corporate member of Freie Universität Berlin and Humboldt Universität zu Berlin, Institute for Radiology, Berlin, Germany.
¹²Charité - Universitätsmedizin Berlin, corporate member of Freie Universität Berlin and Humboldt Universität zu Berlin, Department of Surgery, Experimental Surgery, Berlin, Germany.
¹³Charité - Universitätsmedizin Berlin, corporate member of Freie Universität Berlin and Humboldt Universität zu Berlin and Berlin Institute of Health, Center for Musculoskeletal Surgery, Berlin, Germany.
¹⁴Inselspital, Bern University Hospital, University of Bern, Department of Medical Oncology, Bern, Switzerland.
¹⁵University of Potsdam, Digital Engineering Faculty, Potsdam, Germany.

⁰Max Delbrück Center for Molecular Medicine in the Helmholtz Association.

Journal of Pathology Informatics +

|

June 16, 2025

View abstract on PubMed

Summary

AI tools can assist pathologists in accurately assessing tumor proportion score (TPS) for immunotherapy decisions, especially for rare cancers like angiosarcoma. This approach improves diagnostic accuracy and aids treatment selection.

Area Of Science

Oncology
Computational Pathology
Artificial Intelligence

Background

Tumoral PD-L1 expression is crucial for immunotherapy selection in cancer treatment.
Accurate assessment of tumor proportion score (TPS) is challenging for pathologists due to time constraints, leading to low inter-observer concordance.
Rare cancer types pose a data bottleneck for developing AI-based predictive tools.

Purpose Of The Study

To develop and validate an AI-powered pipeline for predicting tumor proportion score (TPS) in cancer.
To address the challenge of limited training data for rare cancers using pre-trained, generalist models.
To evaluate the practical utility of AI-assisted TPS scoring in improving pathological assessments.

Main Methods

Developed and open-sourced a computational pipeline leveraging pre-trained models for TPS prediction.
Applied the pipeline to predict TPS, particularly for rare cancer types like angiosarcoma.
Facilitated a feedback loop where pathologists reassessed cases with significant AI-pathologist disagreement.

Main Results

The AI pipeline demonstrated strong TPS prediction performance even with limited training data.
Pathologists frequently updated their TPS scores after reviewing AI predictions that differed significantly from their initial assessment.
The AI tool served as a valuable 'second opinion,' enhancing diagnostic accuracy.

Conclusions

AI-based TPS prediction tools are technically feasible and practically valuable for assisting pathologists, especially in rare cancers.
Leveraging generalist, pre-trained models overcomes data limitations for developing AI diagnostic aids in underrepresented cancer types.
AI assistance has the potential to improve decision-making quality in cancer immunotherapy selection.

Keywords:

AI-assisted diagnosis Angiosarcoma Artificial intelligence Digital pathology Immunotherapy PD-L1 expression