SONNET: A Self-Guided Ordinal Regression Neural Network for Segmentation and Classification of Nuclei in Large-Scale Multi-Tissue Histology Images

Doan, Tan Nhu Nhat; Song, Bong Keun; Vuong, Trinh Thi Le; Kim, Kyungeun; Kwak, Jin Tae

doi:10.1109/jbhi.2022.3149936

Cited by 42 publications

(9 citation statements)

References 35 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Graham [7] proposes a CNN of three branches, two for segmentation, and one for classification. Doan [6] predicts a weight map to highlight hard pixel samples for classification. However, these approaches are limited by the receptive field of CNNs, and fail to harvest long-range contexts and spatial distributions of nuclei instances.…”

Section: A Nuclei Classification For Histopathology Imagesmentioning

confidence: 99%

Which Pixel to Annotate: A Label-Efficient Nuclei Segmentation Framework

Lou

et al. 2023

IEEE Trans. Med. Imaging

View full text Add to dashboard Cite

Section: A Nuclei Classification For Histopathology Imagesmentioning

confidence: 99%

Which Pixel to Annotate: A Label-Efficient Nuclei Segmentation Framework

Lou

et al. 2023

IEEE Trans. Med. Imaging

View full text Add to dashboard Cite

“…Figure 2 shows some examples from the MoNuSAC dataset with the groundtruth and prediction by our proposed method. The GlySAC (gastric lymphocyte segmentation and classification) [21] dataset contains 59 images with various types of nuclei such as lymphocytes, cancerous epithelial and normal epithelial nuclei, stromal nuclei and endothelial nuclei. Sets of 34 and 25 images are used as the training and test sets, respectively.…”

Section: Datasetsmentioning

confidence: 99%

Mulvernet: Nucleus Segmentation and Classification of Pathology Images Using the HoVer-Net and Multiple Filter Units

Kim

2023

Electronics

View full text Add to dashboard Cite

Nucleus segmentation and classification are crucial in pathology image analysis. Automated nuclear classification and segmentation methods support analysis and understanding of cell characteristics and functions, and allow the analysis of large-scale nuclear forms in the diagnosis and treatment of diseases. Common problems in these tasks arise from the inconsistent sizes and shapes of the cells in each pathology image. This study aims to develop a new method to address these problems based primarily on the horizontal and vertical distance network (HoVer-Net), multiple filter units, and attention gate mechanisms. The results of the study will significantly impact cell segmentation and classification by showing that a multiple filter unit improves the performance of the original HoVer-Net model. In addition, our experimental results show that the Mulvernet achieves outperforming results in both nuclei segmentation and classification compared to several methods. The ability to segment and classify different types of nuclei automatically has a direct influence on further pathological analysis, offering great potential not only to accelerate the diagnostic process in clinics but also for enhancing our understanding of tissue and cell properties to improve patient care and management.

show abstract

“…To separate complex and diverse nuclear boundaries, a hybrid attention block in Han-Net [ 21 ] was used to explore attention information and build correlations between different pixels to further expand the U-Net. SONNET [ 22 ] was a self-guided ordinal regression neural network for nuclear segmentation, which exploits the intrinsic characteristics of nuclei and focuses on highly uncertain areas during training. Liu et al [ 23 ] proposed an Att-MoE (Attention-based Mixture of Experts) model for nuclear and cytoplasmic segmentation in fluorescent histology images, which integrates multiple expert networks using a single gating network.…”

Section: Related Workmentioning

confidence: 99%

TSHVNet: Simultaneous Nuclear Instance Segmentation and Classification in Histopathological Images Based on Multiattention Mechanisms

Chen

Jia

Zhang

et al. 2022

BioMed Research International

View full text Add to dashboard Cite

Accurate nuclear instance segmentation and classification in histopathologic images are the foundation of cancer diagnosis and prognosis. Several challenges are restricting the development of accurate simultaneous nuclear instance segmentation and classification. Firstly, the visual appearances of different category nuclei could be similar, making it difficult to distinguish different types of nuclei. Secondly, it is thorny to separate highly clustering nuclear instances. Thirdly, rare current studies have considered the global dependencies among diverse nuclear instances. In this article, we propose a novel deep learning framework named TSHVNet which integrates multiattention modules (i.e., Transformer and SimAM) into the state-of-the-art HoVer-Net for the sake of a more accurate nuclear instance segmentation and classification. Specifically, the Transformer attention module is employed on the trunk of the HoVer-Net to model the long-distance relationships of diverse nuclear instances. The SimAM attention modules are deployed on both the trunk and branches to apply the 3D channel and spatial attention to assign neurons with appropriate weights. Finally, we validate the proposed method on two public datasets: PanNuke and CoNSeP. The comparison results have shown the outstanding performance of the proposed TSHVNet network among the state-of-art methods. Particularly, as compared to the original HoVer-Net, the performance of nuclear instance segmentation evaluated by the PQ index has shown 1.4% and 2.8% increases on the CoNSeP and PanNuke datasets, respectively, and the performance of nuclear classification measured by F 1 _score has increased by 2.4% and 2.5% on the CoNSeP and PanNuke datasets, respectively. Therefore, the proposed multiattention-based TSHVNet is of great potential in simultaneous nuclear instance segmentation and classification.

show abstract

SONNET: A Self-Guided Ordinal Regression Neural Network for Segmentation and Classification of Nuclei in Large-Scale Multi-Tissue Histology Images

Cited by 42 publications

References 35 publications

Which Pixel to Annotate: A Label-Efficient Nuclei Segmentation Framework

Which Pixel to Annotate: A Label-Efficient Nuclei Segmentation Framework

Mulvernet: Nucleus Segmentation and Classification of Pathology Images Using the HoVer-Net and Multiple Filter Units

TSHVNet: Simultaneous Nuclear Instance Segmentation and Classification in Histopathological Images Based on Multiattention Mechanisms

Contact Info

Product

Resources

About