SmartHisto: Bayesian active learning for histology images
- 1Department of Computer Science, Iowa State University, Ames, Iowa, United States of America
- 2National Animal Disease Center, Agricultural Research Service, United States Department of Agriculture, Ames, Iowa, United States of America
Abstract
Accurate and efficient characterization of biological images is crucial for advancing systems biology and medical research. Recent advancements in deep learning and image processing have enabled neural network models to rapidly accelerate image analysis by utilizing large expert-annotated datasets. However, in histopathology, the size of whole-slide images makes expert annotation expensive, limiting the acquisition of sufficiently large annotated datasets and posing a major challenge for developing automated, AI-driven image analysis pipelines. To address this limitation, we propose a novel active learning-based framework to train image segmentation models interactively. Our approach employs a Bayesian neural network to identify informative regions in unlabeled images rather than entire images, making expert labeling more cost-effective. We validate our framework on multiple benchmark datasets with variable staining at fixed magnifications, demonstrating substantial reductions in annotation requirements. Notably, our method achieves a mean IoU of 0.75, significantly outperforming competing approaches, which averaged 0.60. Author summary: Histopathology is fundamental to investigating tissue and immune responses, host-pathogen interactions, and disease mechanisms. However, histopathology is highly resource-intensive and requires specialized training, dramatically increasing the costs of annotating whole-slide images and, consequently, the expenses of large-scale studies involving numerous labs and specialists. We developed a computational tool to overcome these challenges, implementing a robust uncertainty-based sampling algorithm in conjunction with a next-generation Bayesian Convolutional Neural Network. This algorithm can be used for hypothesis testing and discovery by reducing the reliance on large, precisely annotated training datasets required in automated image analysis pipelines. The base model, when trained to identify lung tissue types using a small set of annotated images, outperforms state-of-the-art models and can efficiently annotate thousands of images much more quickly than a human. Models trained by the proposed algorithm will serve as a standardized approach for pathologists and disease researchers to train automated image segmentation pipelines for large-scale histopathology.
Related
- Spatially guided translation from histology images to transcriptomic profiles using foundation model-driven contrastive learning
- RNA-guided contrastive learning enhances patient-level prediction from histology
- Deep Learning-Based Inference of Mutational Signature Exposures from Histology Across Tumour Types
- A unified deep learning framework for multi-lesion detection in diabetic retinopathy using fundus images
- Leveraging deep learning for prognostic stratification of hepatocellular carcinoma using histopathological images
BibTeX
@article{vijendran2026smarthisto,
title = {{SmartHisto: Bayesian active learning for histology images}},
author = {Sriram Vijendran and Bailey Arruda and Tavis K. Anderson and Oliver Eulenstein},
journal = {PLOS Computational Biology},
year = {2026},
month = sep,
doi = {10.1371/journal.pcbi.1013611},
url = {https://journals.plos.org/ploscompbiol/article?id=10.1371/journal.pcbi.1013611},
note = {CC BY 4.0},
}
RIS
TY - JOUR
TI - SmartHisto: Bayesian active learning for histology images
AU - Sriram Vijendran
AU - Bailey Arruda
AU - Tavis K. Anderson
AU - Oliver Eulenstein
PY - 2026
DA - 2026/09/17
JO - PLOS Computational Biology
DO - 10.1371/journal.pcbi.1013611
UR - https://journals.plos.org/ploscompbiol/article?id=10.1371/journal.pcbi.1013611
AB - Accurate and efficient characterization of biological images is crucial for advancing systems biology and medical research. Recent advancements in deep learning and image processing have enabled neural network models to rapidly accelerate image analysis by utilizing large expert-annotated datasets. However, in histopathology, the size of whole-slide images makes expert annotation expensive, limiting the acquisition of sufficiently large annotated datasets and posing a major challenge for developing automated, AI-driven image analysis pipelines. To address this limitation, we propose a novel active learning-based framework to train image segmentation models interactively. Our approach employs a Bayesian neural network to identify informative regions in unlabeled images rather than entire images, making expert labeling more cost-effective. We validate our framework on multiple benchmark datasets with variable staining at fixed magnifications, demonstrating substantial reductions in annotation requirements. Notably, our method achieves a mean IoU of 0.75, significantly outperforming competing approaches, which averaged 0.60. Author summary: Histopathology is fundamental to investigating tissue and immune responses, host-pathogen interactions, and disease mechanisms. However, histopathology is highly resource-intensive and requires specialized training, dramatically increasing the costs of annotating whole-slide images and, consequently, the expenses of large-scale studies involving numerous labs and specialists. We developed a computational tool to overcome these challenges, implementing a robust uncertainty-based sampling algorithm in conjunction with a next-generation Bayesian Convolutional Neural Network. This algorithm can be used for hypothesis testing and discovery by reducing the reliance on large, precisely annotated training datasets required in automated image analysis pipelines. The base model, when trained to identify lung tissue types using a small set of annotated images, outperforms state-of-the-art models and can efficiently annotate thousands of images much more quickly than a human. Models trained by the proposed algorithm will serve as a standardized approach for pathologists and disease researchers to train automated image segmentation pipelines for large-scale histopathology.
SN - 1553-7358
ER -