| |  Online-Ressource |
|---|
| Verfasst von: | Jin, Darui [VerfasserIn]  |
|---|
| | Liang, Shangying [VerfasserIn] |
|---|
| | Shmatko, Artem [VerfasserIn] |
|---|
| | Arnold, Alexander [VerfasserIn] |
|---|
| | Horst, David [VerfasserIn] |
|---|
| | Grünewald, Thomas G. P. [VerfasserIn] |
|---|
| | Gerstung, Moritz [VerfasserIn] |
|---|
| | Bai, Xiangzhi [VerfasserIn] |
|---|
| Titel: | Teacher-student collaborated multiple instance learning for pan-cancer PDL1 expression prediction from histopathology slides |
|---|
| Verf.angabe: | Darui Jin, Shangying Liang, Artem Shmatko, Alexander Arnold, David Horst, Thomas G. P. Grünewald, Moritz Gerstung & Xiangzhi Bai |
|---|
| E-Jahr: | 2024 |
|---|
| Jahr: | 09 April 2024 |
|---|
| Umfang: | 14 S. |
|---|
| Illustrationen: | Illustrationen |
|---|
| Fussnoten: | Gesehen am 28.10.2024 |
|---|
| Titel Quelle: | Enthalten in: Nature Communications |
|---|
| Ort Quelle: | [London] : Springer Nature, 2010 |
|---|
| Jahr Quelle: | 2024 |
|---|
| Band/Heft Quelle: | 15(2024), Artikel-ID 3063, Seite 1-14 |
|---|
| ISSN Quelle: | 2041-1723 |
|---|
| Abstract: | Programmed cell death ligand 1 (PDL1), as an important biomarker, is quantified by immunohistochemistry (IHC) with few established histopathological patterns. Deep learning aids in histopathological assessment, yet heterogeneity and lacking spatially resolved annotations challenge precise analysis. Here, we present a weakly supervised learning approach using bulk RNA sequencing for PDL1 expression prediction from hematoxylin and eosin (H&E) slides. Our method extends the multiple instance learning paradigm with the teacher-student framework, which assigns dynamic pseudo-labels for intra-slide heterogeneity and retrieves unlabeled instances using temporal ensemble model distillation. The approach, evaluated on 12,299 slides across 20 solid tumor types, achieves a weighted average area under the curve of 0.83 on fresh-frozen and 0.74 on formalin-fixed specimens for 9 tumors with PDL1 as an established biomarker. Our method predicts PDL1 expression patterns, validated by IHC on 20 slides, offering insights into histologies relevant to PDL1. This demonstrates the potential of deep learning in identifying diverse histological patterns for molecular changes from H&E images. |
|---|
| DOI: | doi:10.1038/s41467-024-46764-0 |
|---|
| URL: | Bitte beachten Sie: Dies ist ein Bibliographieeintrag. Ein Volltextzugriff für Mitglieder der Universität besteht hier nur, falls für die entsprechende Zeitschrift/den entsprechenden Sammelband ein Abonnement besteht oder es sich um einen OpenAccess-Titel handelt.
kostenfrei: Volltext: https://doi.org/10.1038/s41467-024-46764-0 |
|---|
| | kostenfrei: Volltext: https://www.nature.com/articles/s41467-024-46764-0 |
|---|
| | DOI: https://doi.org/10.1038/s41467-024-46764-0 |
|---|
| Datenträger: | Online-Ressource |
|---|
| Sprache: | eng |
|---|
| Sach-SW: | Bioinformatics |
|---|
| | Cancer imaging |
|---|
| | Image processing |
|---|
| | Machine learning |
|---|
| | Tumour biomarkers |
|---|
| K10plus-PPN: | 1906970432 |
|---|
| Verknüpfungen: | → Zeitschrift |
|---|
Teacher-student collaborated multiple instance learning for pan-cancer PDL1 expression prediction from histopathology slides / Jin, Darui [VerfasserIn]; 09 April 2024 (Online-Ressource)
