Salvato in:
Dettagli Bibliografici
Autori principali: Zhao, Shuo, Zhou, Yu, Chen, Jianxu
Natura: Preprint
Pubblicazione: 2025
Soggetti:
Accesso online:https://arxiv.org/abs/2511.04811
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866917067287953408
author Zhao, Shuo
Zhou, Yu
Chen, Jianxu
author_facet Zhao, Shuo
Zhou, Yu
Chen, Jianxu
contents Biomedical image segmentation is critical for precise structure delineation and downstream analysis. Traditional methods often struggle with noisy data, while deep learning models such as U-Net have set new benchmarks in segmentation performance. nnU-Net further automates model configuration, making it adaptable across datasets without extensive tuning. However, it requires a substantial amount of annotated data for cross-validation, posing a challenge when only raw images but no labels are available. Large foundation models offer zero-shot generalizability, but may underperform on specific datasets with unique characteristics, limiting their direct use for analysis. This work addresses these bottlenecks by proposing a data-centric AI workflow that leverages active learning and pseudo-labeling to combine the strengths of traditional neural networks and large foundation models while minimizing human intervention. The pipeline starts by generating pseudo-labels from a foundation model, which are then used for nnU-Net's self-configuration. Subsequently, a representative core-set is selected for minimal manual annotation, enabling effective fine-tuning of the nnU-Net model. This approach significantly reduces the need for manual annotations while maintaining competitive performance, providing an accessible solution for biomedical researchers to apply state-of-the-art AI techniques in their segmentation tasks. The code is available at https://github.com/MMV-Lab/AL_BioMed_img_seg.
format Preprint
id arxiv_https___arxiv_org_abs_2511_04811
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle An Active Learning Pipeline for Biomedical Image Instance Segmentation with Minimal Human Intervention
Zhao, Shuo
Zhou, Yu
Chen, Jianxu
Computer Vision and Pattern Recognition
Artificial Intelligence
Machine Learning
68T07, 68U10
I.2.10; I.4.6; J.3
Biomedical image segmentation is critical for precise structure delineation and downstream analysis. Traditional methods often struggle with noisy data, while deep learning models such as U-Net have set new benchmarks in segmentation performance. nnU-Net further automates model configuration, making it adaptable across datasets without extensive tuning. However, it requires a substantial amount of annotated data for cross-validation, posing a challenge when only raw images but no labels are available. Large foundation models offer zero-shot generalizability, but may underperform on specific datasets with unique characteristics, limiting their direct use for analysis. This work addresses these bottlenecks by proposing a data-centric AI workflow that leverages active learning and pseudo-labeling to combine the strengths of traditional neural networks and large foundation models while minimizing human intervention. The pipeline starts by generating pseudo-labels from a foundation model, which are then used for nnU-Net's self-configuration. Subsequently, a representative core-set is selected for minimal manual annotation, enabling effective fine-tuning of the nnU-Net model. This approach significantly reduces the need for manual annotations while maintaining competitive performance, providing an accessible solution for biomedical researchers to apply state-of-the-art AI techniques in their segmentation tasks. The code is available at https://github.com/MMV-Lab/AL_BioMed_img_seg.
title An Active Learning Pipeline for Biomedical Image Instance Segmentation with Minimal Human Intervention
topic Computer Vision and Pattern Recognition
Artificial Intelligence
Machine Learning
68T07, 68U10
I.2.10; I.4.6; J.3
url https://arxiv.org/abs/2511.04811