Dual Consistency Enabled Weakly and Semi-Supervised Optic Disc and Cup Segmentation With Dual Adaptive Graph Convolutional Networks

Meng, Yanda; Zhang, Hongrun; Zhao, Yitian; Gao, Dongxu; Hamill, Barbra; Patri, Godhuli; Madhusudhan, Savita; Zheng, Yalin

doi:10.1109/tmi.2022.3203318

Cited by 19 publications

(6 citation statements)

References 44 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…To address these limitations, Li et al (2020) introduced an attention diagonal matrix to learn a better distance metric, which discarded the projection and re-projection processes. Inspired by (Li et al 2020), subsequent works (Meng et al 2021(Meng et al , 2023 developed the adjacency matrix based on energy aggregation in both image space and channel space. Moreover, a novel graph propagation model was constructed, which incorporated the boundary awareness.…”

Section: Graph Convolutional Network In Image Taskmentioning

confidence: 99%

See 1 more Smart Citation

Automatic breast ultrasound (ABUS) tumor segmentation based on global and local feature fusion

Li,

Ren,

Cheng

et al. 2024

Phys. Med. Biol.

View full text Add to dashboard Cite

Accurate segmentation of tumor regions in automated breast ultrasound (ABUS) images is of paramount importance in computer-aided diagnosis (CAD) system. However, the inherent diversity of tumors and the imaging interference pose great challenges to ABUS tumor segmentation. In this paper, we propose a global and local feature interaction model combined with graph fusion (GLGM), for 3D ABUS tumor segmentation. In GLGM, we construct a dual branch encoder-decoder, where both local and global features can be extracted. Besides, a global and local feature fusion (GLFF) module is designed, which employs the deepest semantic interaction to facilitate information exchange between local and global features. Additionally, to improve the segmentation performance for small tumors, a graph convolution-based shallow feature fusion module (SFFGC) is designed. It exploits the shallow feature to enhance the feature expression of small tumors in both local and global domains. The proposed method is evaluated on a private ABUS dataset and a public ABUS dataset. For the private ABUS dataset, the small tumors (volume smaller than 1 cm³) account for over 50% of the entire dataset. Experimental results show that the proposed GLGM model outperforms several state-of-the-art segmentation models in 3D ABUS tumor segmentation, particularly in segmenting small tumors.

show abstract

Section: Graph Convolutional Network In Image Taskmentioning

confidence: 99%

“…Finally, the forward process of the graph convolution is carried out, which is the same with (Meng et al 2023). The above process is for the global branch, and the difference for the local branch is just the input.…”

Section: Shallow Feature Fusion Module Based On Graph Convolutionmentioning

confidence: 99%

Automatic breast ultrasound (ABUS) tumor segmentation based on global and local feature fusion

Li,

Ren,

Cheng

et al. 2024

Phys. Med. Biol.

View full text Add to dashboard Cite

show abstract

“…GNNs [22] process graph data that is composed of nodes and edges as well as initial node features in medical image segmentation by representing anatomical structure associations [71], [90], [91]. The node comes from initial mask [71], intermediate convolutional features [90], [92] or VAE latent distribution [91]. The edge is related to spatial distance [93] or self-attention relationship [94].…”

Section: A Deep Learning Modelmentioning

confidence: 99%

Is denoising necessary for ultrasound image segmentation deep learning: review and benchmark

Liu,

Dong,

Qin

et al. 2023

Preprint

View full text Add to dashboard Cite

show abstract

“…Automatic segmentation of medical images is of great significance for clinical anatomy and pathological structure research including organ segmentation [ 1 ], optic disc segmentation [ 2 ], tumor segmentation [ 3 ], etc. With the remarkable performance of automatic medical segmentation, many practical applications have become available to achieve precise treatment and speedy disease diagnosis [ 4 , 5 ].…”

Section: Introductionmentioning

confidence: 99%

Attentional adversarial training for few-shot medical image segmentation without annotations

Awudong,

Li,

Liang

et al. 2024

PLoS ONE

View full text Add to dashboard Cite

Medical image segmentation is a critical application that plays a significant role in clinical research. Despite the fact that many deep neural networks have achieved quite high accuracy in the field of medical image segmentation, there is still a scarcity of annotated labels, making it difficult to train a robust and generalized model. Few-shot learning has the potential to predict new classes that are unseen in training with a few annotations. In this study, a novel few-shot semantic segmentation framework named prototype-based generative adversarial network (PG-Net) is proposed for medical image segmentation without annotations. The proposed PG-Net consists of two subnetworks: the prototype-based segmentation network (P-Net) and the guided evaluation network (G-Net). On one hand, the P-Net as a generator focuses on extracting multi-scale features and local spatial information in order to produce refined predictions with discriminative context between foreground and background. On the other hand, the G-Net as a discriminator, which employs an attention mechanism, further distills the relation knowledge between support and query, and contributes to P-Net producing segmentation masks of query with more similar distributions as support. Hence, the PG-Net can enhance segmentation quality by an adversarial training strategy. Compared to the state-of-the-art (SOTA) few-shot segmentation methods, comparative experiments demonstrate that the proposed PG-Net provides noticeably more robust and prominent generalization ability on different medical image modality datasets, including an abdominal Computed Tomography (CT) dataset and an abdominal Magnetic Resonance Imaging (MRI) dataset.

show abstract

Dual Consistency Enabled Weakly and Semi-Supervised Optic Disc and Cup Segmentation With Dual Adaptive Graph Convolutional Networks

Cited by 19 publications

References 44 publications

Automatic breast ultrasound (ABUS) tumor segmentation based on global and local feature fusion

Automatic breast ultrasound (ABUS) tumor segmentation based on global and local feature fusion

Is denoising necessary for ultrasound image segmentation deep learning: review and benchmark

Attentional adversarial training for few-shot medical image segmentation without annotations

Contact Info

Product

Resources

About