A Hierarchical Transformer Encoder to Improve Entire Neoplasm Segmentation on Whole Slide Image of Hepatocellular Carcinoma
Abstract: In digital histopathology, entire neoplasm segmentation on Whole Slide Image (WSI) of Hepatocellular Carcinoma (HCC) plays an important role, especially as a preprocessing filter to automatically exclude healthy tissue, in histological molecular correlations mining and other downstream histopathological tasks. The segmentation task remains challenging due to HCC's inherent high-heterogeneity and the lack of dependency learning in large field of view. In this article, we propose a novel deep learning architecture with a hierarchical Transformer encoder, HiTrans, to learn the global dependencies within expanded 4096$\times$4096 WSI patches. HiTrans is designed to encode and decode the patches with larger reception fields and the learned global dependencies, compared to the state-of-the-art Fully Convolutional Neural networks (FCNN). Empirical evaluations verified that HiTrans leads to better segmentation performance by taking into account regional and global dependency information.
- Jacques Ferlay et al., “Cancer incidence and mortality worldwide: sources, methods and major patterns in GLOBOCAN 2012,” International Journal of Cancer, vol. 136, no. 5, pp. E359–386, 2015.
- Julien Calderaro et al., “Molecular and histological correlations in liver cancer,” Journal of Hepatology, vol. 71, no. 3, pp. 616–630, 2019.
- Ming Y. Lu et al., “Data-efficient and weakly supervised computational pathology on whole-slide images,” Nature Biomedical Engineering, vol. 5, no. 6, pp. 555–570, 2021.
- Qinghe Zeng et al., “Artificial intelligence predicts immune and inflammatory gene signatures directly from hepatocellular carcinoma histology,” Journal of Hepatology, vol. 77, no. 1, pp. 116–127, 2022.
- Blanca Maria Priego Torres et al., “Automatic segmentation of whole-slide h&e stained breast histopathology images using a deep convolutional neural network architecture,” Expert Syst. Appl., vol. 151, pp. 113387, 2020.
- Mousumi Roy et al., “Convolutional autoencoder based model HistoCAE for segmentation of viable tumor regions in liver whole-slide images,” Scientific Reports, vol. 11, no. 1, pp. 139, 2021.
- Rüdiger Schmitz et al., “Multi-scale fully convolutional neural networks for histopathology image segmentation: From nuclear aberrations to the global tissue architecture,” Medical Image Anal., vol. 70, pp. 101996, 2021.
- Ashish Vaswani et al., “Attention is all you need,” in NeurIPS, 2017, pp. 5998–6008.
- Alexey Dosovitskiy et al., “An image is worth 16x16 words: Transformers for image recognition at scale,” in ICLR, 2021.
- Richard J. Chen et al., “Scaling vision transformers to gigapixel images via hierarchical self-supervised learning,” in CVPR, 2022, pp. 16123–16134.
- Yoo Jung Kim et al., “PAIP 2019: Liver cancer segmentation challenge,” Medical Image Anal., vol. 67, pp. 101854, 2021.
- Kaiming He et al., “Deep residual learning for image recognition,” in CVPR, 2016, pp. 770–778.
- Ozan Ciga et al., “Self supervised contrastive learning for digital histopathology,” Machine Learning with Applications, vol. 7, pp. 100198, 2022.
- Ting Chen et al., “A simple framework for contrastive learning of visual representations,” in ICML, 2020, pp. 1597–1607.
- Ilya Loshchilov et al., “Fixing weight decay regularization in adam,” CoRR, vol. abs/1711.05101, 2017.
- Olaf Ronneberger et al., “U-net: Convolutional networks for biomedical image segmentation,” in MICCAI, 2015, pp. 234–241.
- Liang-Chieh Chen et al., “Rethinking atrous convolution for semantic image segmentation,” CoRR, vol. abs/1706.05587, 2017.
- Hengshuang Zhao et al., “Pyramid scene parsing network,” in CVPR, 2017, pp. 6230–6239.
- Enze Xie et al., “Segformer: Simple and efficient design for semantic segmentation with transformers,” in NeurIPS, 2021, pp. 12077–12090.
Paper Prompts
Sign up for free to create and run prompts on this paper using GPT-5.
Top Community Prompts
Collections
Sign up for free to add this paper to one or more collections.