Multiple instance learning using pathology foundation models effectively predicts kidney disease diagnosis and clinical classification

Recently developed pathology foundation models, pretrained on large-scale pathology datasets, have demonstrated excellent performance in various downstream tasks. This study evaluated the utility of pathology foundation models combined with multiple instance learning (MIL) for kidney pathology analy...

Celý popis

Uložené v:

Podrobná bibliografia
Vydané v:	Scientific reports Ročník 15; číslo 1; s. 35298 - 12
Hlavní autori:	Kurata, Yu, Mimura, Imari, Kodera, Satoshi, Abe, Hiroyuki, Yamada, Daisuke, Kume, Haruki, Ushiku, Tetsuo, Tanaka, Tetsuhiro, Takeda, Norihiko, Nangaku, Masaomi
Médium:	Journal Article
Jazyk:	English
Vydavateľské údaje:	London Nature Publishing Group UK 09.10.2025 Nature Publishing Group Nature Portfolio
Predmet:	631/114 692/4022 692/699 Artificial intelligence Classification Clinical outcomes Datasets Diabetes Diabetes mellitus Diabetic Nephropathies - diagnosis Diabetic Nephropathies - pathology Female Foundation model Humanities and Social Sciences Humans Kidney - pathology Kidney diseases Kidney Diseases - classification Kidney Diseases - diagnosis Kidney Diseases - pathology Kidneys Machine Learning Male multidisciplinary Multiple instance learning Multiple-Instance Learning Algorithms Nephritis Neural networks Pathology Precision medicine Proteinuria Renal pathology ROC Curve Science Science (multidisciplinary) Japan Artificial intelligence Multiple instance learning Renal pathology Foundation model
ISSN:	2045-2322, 2045-2322
On-line prístup:	Získať plný text
Tagy:	Pridať tag Žiadne tagy, Buďte prvý, kto otaguje tento záznam!

Popis
Shrnutí:	Recently developed pathology foundation models, pretrained on large-scale pathology datasets, have demonstrated excellent performance in various downstream tasks. This study evaluated the utility of pathology foundation models combined with multiple instance learning (MIL) for kidney pathology analysis. We used 242 hematoxylin and eosin-stained whole slide images (WSIs) from the Kidney Precision Medicine Project (KPMP) and Japan-Pathology Artificial Intelligence Diagnostics Project databases as the development cohort, comprising 47 healthy controls, 35 acute interstitial nephritis, and 160 diabetic kidney disease (DKD) slides. External validation was performed using 83 WSIs from the University of Tokyo Hospital. Pretrained pathology foundation models were utilized as patch encoders and compared with ImageNet-pretrained ResNet50. Using the extracted patch features, we trained MIL models to classify diagnoses. In internal validation, all foundation models outperformed ResNet50, achieving area under the receiver operating characteristic curve (AUROC) over 0.980. In external validation, the performance of ResNet50 markedly dropped, which was in contrast to all foundation models. Visualization of attention heatmaps confirmed that foundation models accurately recognized diagnostically relevant structures. In overt proteinuria (albuminuria ≥ 300 mg/gCre or proteinuria ≥ 1000 mg/gCre) prediction task, foundation models also outperformed ResNet50. We successfully integrated pathology foundation models with MIL to achieve robust diagnostic performance.
Bibliografia:	ObjectType-Article-1 SourceType-Scholarly Journals-1 ObjectType-Feature-2 content type line 14 content type line 23
ISSN:	2045-2322 2045-2322
DOI:	10.1038/s41598-025-19297-9