DS3-Net: Difficulty-perceived Common-to-T1ce Semi-Supervised Multimodal MRI Synthesis Network
Not on the map. Why?
Abstract (arXiv)
Contrast-enhanced T1 (T1ce) is one of the most essential magnetic resonance imaging (MRI) modalities for diagnosing and analyzing brain tumors, especially gliomas. In clinical practice, common MRI modalities such as T1, T2, and fluid attenuation inversion recovery are relatively easy to access while T1ce is more challenging considering the additional cost and potential risk of allergies to the contrast agent. Therefore, it is of great clinical necessity to develop a method to synthesize T1ce from other common modalities. Current paired image translation methods typically have the issue of requiring a large amount of paired data and do not focus on specific regions of interest, e.g., the tumor region, in the synthesization process. To address these issues, we propose a Difficulty-perceived common-to-T1ce Semi-Supervised multimodal MRI Synthesis network (DS3-Net), involving both paired and unpaired data together with dual-level knowledge distillation. DS3-Net predicts a difficulty map to progressively promote the synthesis task. Specifically, a pixelwise constraint and a patchwise contrastive constraint are guided by the predicted difficulty map. Through extensive experiments on the publiclyavailable BraTS2020 dataset, DS3-Net outperforms its supervised counterpart in each respect. Furthermore, with only 5% paired data, the proposed DS3-Net achieves competitive performance with state-of-theart image translation methods utilizing 100% paired data, delivering an average SSIM of 0.8947 and an average PSNR of 23.60.
Key facts. Cited by 1 paper in the map (data through 7 Oct 2026). Builds on 23 of its 30 references that are in the map. First posted on arXiv 14 Mar 2022.
Builds on
23 of 30 references.
References · 23
- 2015U-Net: Convolutional Networks for Biomedical Image Segmentationcited by 19,604
- 2015Distilling the Knowledge in a Neural Networkcited by 10,076
- 2018Representation Learning with Contrastive Predictive Codingcited by 7,662
- 2017Squeeze-and-Excitation Networkscited by 4,763
- 2016Image-to-Image Translation with Conditional Adversarial Networkscited by 4,510
- 2017Decoupled Weight Decay Regularizationcited by 1,722
- 2016Least Squares Generative Adversarial Networkscited by 1,000
- 2020Contrastive Learning for Unpaired Image-to-Image Translationcited by 637
- 2021Semi-Supervised Semantic Segmentation with Cross Pseudo Supervisioncited by 462
- 2016Precomputed Real-Time Texture Synthesis with Markovian Generative Adversarial Networkscited by 192
- 2018MedGAN: Medical Image Translation using GANscited by 152
- 2018Image Synthesis in Multi-Contrast MRI with Conditional Generative Adversarial Networkscited by 131
11 more
- 2019Missing MRI Pulse Sequence Synthesis using Multi-Modal Generative Adversarial Networkcited by 98
- 2019Brain Tumor Segmentation on MRI with Missing Modalitiescited by 42
- 2021Latent Correlation Representation Learning for Brain Tumor Segmentation with Missing MRI Modalitiescited by 42
- 2018Semi-Supervised Semantic Image Segmentation with Self-correcting Networkscited by 36
- 2019DiamondGAN: Unified Multi-Modal Generative Adversarial Networks for MRI Sequences Synthesiscited by 36
- 2019mustGAN: Multi-Stream Generative Adversarial Networks for MR Image Synthesiscited by 34
- 2020Deep Semi-supervised Knowledge Distillation for Overlapping Cervical Cell Instance Segmentationcited by 30
- 2020Brain tumor segmentation with missing modalities via latent multi-source correlation representationcited by 19
- 2019Brain segmentation based on multi-atlas guided 3D fully convolutional network ensemblescited by 3
- 2021Fast T2w/FLAIR MRI Acquisition by Optimal Sampling of Information Complementary to Pre-acquired T1w MRIcited by 2
- 2022Multi-modal Brain Tumor Segmentation via Missing Modality Synthesis and Modality-level Attention Fusioncited by 2
Built on by
Citing papers per year: 2024: 1.
1 paper.