Keep it accurate and robust: An enhanced nuclei analysis framework
Open Access
- 22 November 2024
- journal article
- research article
- Published by American Association for the Advancement of Science (AAAS) in Computational and Structural Biotechnology Journal
- Vol. 24, 699-710
Abstract
Accurate segmentation and classification of nuclei in histology images is critical but challenging due to nuclei heterogeneity, staining variations, and tissue complexity. Existing methods often struggle with limited dataset variability, with patches extracted from similar whole slide images (WSI), making models prone to falling into local optima. Here we propose a new framework to address this limitation and enable robust nuclear analysis. Our method leverages dual-level ensemble modeling to overcome issues stemming from limited dataset variation. Intra-ensembling applies diverse transformations to individual samples, while inter-ensembling combines networks of different scales. We also introduce enhancements to the HoVer-Net architecture, including updated encoders, nested dense decoding and model regularization strategy. We achieve state-of-the-art results on public benchmarks, including 1st place for nuclear composition prediction and 3rd place for segmentation/classification in the 2022 Colon Nuclei Identification and Counting (CoNIC) Challenge. This success validates our approach for accurate histological nuclei analysis. Extensive experiments and ablation studies provide insights into optimal network design choices and training techniques. In conclusion, this work proposes an improved framework advancing the state-of-the-art in nuclei analysis. We will release our code and models to serve as a toolkit for the community.Keywords
This publication has 43 references indexed in Scilit:
- An improved Hover-net for nuclear segmentation and classification in histopathology imagesNeural Computing and Applications, 2023
- Attention augmented distance regression and classification network for nuclei instance segmentation and type classification in histology imagesBiomedical Signal Processing and Control, 2022
- Evolving support vector machines using fruit fly optimization for medical data classificationKnowledge-Based Systems, 2016
- Diagnostic Concordance Among Pathologists Interpreting Breast Biopsy SpecimensJAMA, 2015
- Data Mining Process2015
- Mitosis Detection in Breast Cancer Histology Images with Deep Neural Networks2013
- A support vector machine classifier with rough set-based feature selection for breast cancer diagnosisExpert Systems with Applications, 2011
- Image-guided decision support system for pathologyMachine Vision and Applications, 1999
- Nuclear image analysis of immunohistochemically stained cells in breast carcinomasHistochemistry and Cell Biology, 1996
- An expert system for the detection of cervical cancer cells using knowledge-based image analyzerArtificial Intelligence in Medicine, 1996