ASAP: Automated Style-Aware Similarity Measurement for Selection of Annotated Pre-Training Datasets in 2D Biomedical Imaging
Open Access
- 26 March 2025
- journal article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 13, 54794-54807
Abstract
Medical imaging scenarios are characterized by varying image modalities, several organs/cell shapes, and little annotated data because of the expertise required for labeling. The successful use of state-of-the-art deep-learning approaches requires a large amount of annotated data or a pre-trained model. Despite the constant publication of new annotated datasets and pre-trained models, a vast subset of them remains untapped, owing to the challenges in effectively applying transfer learning or domain adaptation across varying scenarios. In this paper, we propose an automated style-aware framework for predicting the similarity value of a new biomedical dataset with respect to the state-of-the-art annotated datasets, selecting the most suitable annotated dataset for transfer learning or domain adaptation. Our pipeline, consisting of an autoencoder trained with self-supervised learning through a comprehensive loss function that considers the image reconstruction, style features, and dataset membership, does not need any kind of labels in training and test stages. The resulting 2D latent space represents a similarity measurement, which is demonstrated to correlate with the pre-training results in a task of binary semantic segmentation, and can provide the dataset that offers the optimal results for pre-labeling or pre-training a new biomedical task. Our results demonstrate the superior performance of this measurement with respect to manual selection and the state-of-the-art approaches. Therefore, ASAP can speed up the deployment processes of new biomedical applications. Our code is publicly available at https://github.com/miguel55/ASAP.Keywords
Funding Information
- Ministerium für Wissenschaft, Forschung und Kunst Baden-Württemberg (HoreKa Supercomputer)
- Helmholtz Association (HAICORE@KIT Initiative)
- Helmholtz Association (MSE Program)
- Helmholtz Association (NACIP program)
- Ministerio de Ciencia e Innovación (PID2020-118504GB-I00)
- Comunidad de Madrid (Y2020/NMT-6660)
- Ministerio de Educación, Cultura y Deporte (FPU18/02825)
- KIT Publication Fund
This publication has 62 references indexed in Scilit:
- A Brief Review of Domain Adaptation2021
- Evaluating Similarity Measures for Dataset Search2020
- PanNuke: An Open Pan-Cancer Histology Dataset for Nuclei Instance Segmentation and Classification2019
- Large-Scale Annotation of Biomedical Data and Expert Label Synthesis and Hardware Aware Learning for Medical Imaging and Computer Assisted Intervention2019
- Exploring the Similarity of Medical Imaging Classification Problems2017
- U-Net: Convolutional Networks for Biomedical Image Segmentation2015
- Microsoft COCO: Common Objects in Context2014
- Image Similarity Measures2010
- Nonlinear principal component analysis using autoassociative neural networksAIChE Journal, 1991
- Principal Component Analysis1986