MI-SegNet: Mutual Information-Based US Segmentation for Unseen Domain Generalization

Bi, Yuan; Jiang, Zhongliang; Clarenbach, Ricarda; Ghotbi, Reza; Karlas, Angelos; Navab, Nassir

doi:10.1007/978-3-031-43901-8_13

Cited by 10 publications

(4 citation statements)

References 23 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The differences between the style and content are then fused independently, resulting in more effective and sophisticated image mixing. MI‐SegNet: Bi et al. designed a segmentation network based on mutual information, 23 which extracts style (image appearance) and anatomy (shape) features from ultrasound images. The network generates segmentation masks based on anatomical features, effectively excluding domain‐related features.…”

Section: Resultsmentioning

confidence: 99%

“…Instead of using the entire object regions, CutMix 33 cuts and pastes patches from one image onto the other image, along with the ground truth labels being mixed proportionally to the area of patches. To improve the generalization of ultrasound image segmentation networks, Bi et al 23 . designed a segmentation network based on mutual information, distinguishing image anatomical and domain features and employing a cross‐reconstruction method to train the network.…”

Section: Discussionmentioning

confidence: 99%

“…To improve the generalization of ultrasound image segmentation networks, Bi et al. 23 designed a segmentation network based on mutual information, distinguishing image anatomical and domain features and employing a cross‐reconstruction method to train the network. Zhou et al.…”

Section: Discussionmentioning

confidence: 99%

See 2 more Smart Citations

MFNet: Meta‐learning based on frequency‐space mix for MRI segmentation in nasopharyngeal carcinoma

Li,

Chen,

et al. 2024

J Cellular Molecular Medi

View full text Add to dashboard Cite

Deep learning techniques have been applied to medical image segmentation and demonstrated expert‐level performance. Due to the poor generalization abilities of the models in the deployment in different centres, common solutions, such as transfer learning and domain adaptation techniques, have been proposed to mitigate this issue. However, these solutions necessitate retraining the models with target domain data and annotations, which limits their deployment in clinical settings in unseen domains. We evaluated the performance of domain generalization methods on the task of MRI segmentation of nasopharyngeal carcinoma (NPC) by collecting a new dataset of 321 patients with manually annotated MRIs from two hospitals. We transformed the modalities of MRI, including T1WI, T2WI and CE‐T1WI, from the spatial domain to the frequency domain using Fourier transform. To address the bottleneck of domain generalization in MRI segmentation of NPC, we propose a meta‐learning approach based on frequency domain feature mixing. We evaluated the performance of MFNet against existing techniques for generalizing NPC segmentation in terms of Dice and MIoU. Our method evidently outperforms the baseline in handling the generalization of NPC segmentation. The MF‐Net clearly demonstrates its effectiveness for generalizing NPC MRI segmentation to unseen domains (Dice = 67.59%, MIoU = 75.74% T1W1). MFNet enhances the model's generalization capabilities by incorporating mixed‐feature meta‐learning. Our approach offers a novel perspective to tackle the domain generalization problem in the field of medical imaging by effectively exploiting the unique characteristics of medical images.

show abstract

Section: Resultsmentioning

confidence: 99%

Section: Discussionmentioning

confidence: 99%

See 1 more Smart Citation

MFNet: Meta‐learning based on frequency‐space mix for MRI segmentation in nasopharyngeal carcinoma

Li,

Chen,

et al. 2024

J Cellular Molecular Medi

View full text Add to dashboard Cite

show abstract

“…Similarly, Liu et al employed MI to extract discriminative representations to improve the generalization of recognition tasks against the disturbances of environment (Liu et al, 2021). Bi et al applied MI to explicitly disentangle the domain and anatomy features to enhance the generalization capability for US segmentation tasks (Bi et al, 2023).…”

Section: Related Workmentioning

confidence: 99%

Intelligent robotic sonographer: Mutual information-based disentangled reward learning from few demonstrations

Jiang,

Bi,

Zhou

et al. 2024

The International Journal of Robotics Research

Self Cite

View full text Add to dashboard Cite

Ultrasound (US) imaging is widely used for biometric measurement and diagnosis of internal organs due to the advantages of being real-time and radiation-free. However, due to inter-operator variations, resulting images highly depend on the experience of sonographers. This work proposes an intelligent robotic sonographer to autonomously “explore” target anatomies and navigate a US probe to standard planes by learning from the expert. The underlying high-level physiological knowledge from experts is inferred by a neural reward function, using a ranked pairwise image comparison approach in a self-supervised fashion. This process can be referred to as understanding the “language of sonography.” Considering the generalization capability to overcome inter-patient variations, mutual information is estimated by a network to explicitly disentangle the task-related and domain features in latent space. The robotic localization is carried out in coarse-to-fine mode based on the predicted reward associated with B-mode images. To validate the effectiveness of the proposed reward inference network, representative experiments were performed on vascular phantoms (“line” target), two types of ex vivo animal organ phantoms (chicken heart and lamb kidney representing “point” target), and in vivo human carotids. To further validate the performance of the autonomous acquisition framework, physical robotic acquisitions were performed on three phantoms (vascular, chicken heart, and lamb kidney). The results demonstrated that the proposed advanced framework can robustly work on a variety of seen and unseen phantoms as well as in vivo human carotid data. Code: https://github.com/yuan-12138/MI-GPSR . Video: https://youtu.be/u4ThAA9onE0 .

show abstract

Diffusion as Sound Propagation: Physics-Inspired Model for Ultrasound Image Generation

Domínguez,

Velikova,

Navab

et al. 2024

Lecture Notes in Computer Science

View full text Add to dashboard Cite

MI-SegNet: Mutual Information-Based US Segmentation for Unseen Domain Generalization

Cited by 10 publications

References 23 publications

MFNet: Meta‐learning based on frequency‐space mix for MRI segmentation in nasopharyngeal carcinoma

MFNet: Meta‐learning based on frequency‐space mix for MRI segmentation in nasopharyngeal carcinoma

Intelligent robotic sonographer: Mutual information-based disentangled reward learning from few demonstrations

Diffusion as Sound Propagation: Physics-Inspired Model for Ultrasound Image Generation

Contact Info

Product

Resources

About