FR-Net: Joint Reconstruction and Segmentation in Compressed Sensing Cardiac MRI

Huang, Qi‐Fang; Yang, Dong; Yi, Jingru; Axel, Leon; Metaxas, Dimitris N.

doi:10.1007/978-3-030-21949-9_38

Cited by 27 publications

(22 citation statements)

References 12 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…3. (a) is the cascade of a segmentation UNET to the IDSLR network, similar to [21], which is trained end-to-end with the loss function specified by (14). For fair comparison, we match the number of learnable parameters of this approach with that of the proposed scheme.…”

Section: State-of-the-art Methods For Comparison 1) Calibrationless P...mentioning

confidence: 99%

“…Recently, some researchers have looked into minimizing these errors by coupling image denoising or reconstruction tasks with segmentation, thus improving both tasks [25]. [21] considers the cascade of reconstruction and segmentation networks, which are trained end-to-end, while [22] introduces an architecture as shown in Fig. 3.…”

Section: End-to-end Multi-task Training Approachesmentioning

confidence: 99%

“…The proposed work has conceptual similarities to the cascade of reconstruction and segmentation networks [21] and the recent JRS [22]. The use of the same latent spaces in our approach facilitates the improved exploitation of the synergies, which offers improved performance and enables the semisupervised approach rather than the cascade approach [21]. In addition to being restricted to the single-channel MRI setting, the JRS framework has some important distinctions from the proposed approach.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Joint Calibrationless Reconstruction and Segmentation of Parallel MRI

Pramanik¹,

Wu²,

Jacob³

2021

Preprint

View full text Add to dashboard Cite

The volume estimation of brain regions from MRI data is a key problem in many clinical applications, where the acquisition of data at high spatial resolution is desirable. While parallel MRI and constrained image reconstruction algorithms can accelerate the scans, image reconstruction artifacts are inevitable, especially at high acceleration factors. We introduce a novel image domain deep-learning framework for calibrationless parallel MRI reconstruction, coupled with a segmentation network to improve image quality and to reduce the vulnerability of current segmentation algorithms to image artifacts resulting from acceleration. The combination of the proposed image domain deep calibrationless approach with the segmentation algorithm offers improved image quality, while increasing the accuracy of the segmentations. The novel architecture with an encoder shared between the reconstruction and segmentation tasks is seen to reduce the need for segmented training datasets. In particular, the proposed few-shot training strategy requires only 10% of segmented datasets to offer good performance.

show abstract

Section: State-of-the-art Methods For Comparison 1) Calibrationless P...mentioning

confidence: 99%

Section: End-to-end Multi-task Training Approachesmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Joint Calibrationless Reconstruction and Segmentation of Parallel MRI

Pramanik¹,

Wu²,

Jacob³

2021

Preprint

View full text Add to dashboard Cite

show abstract

“…But its efficiency can still be improved. Recently, many deep learning methods based on convolutional neural networks have been introduced for MR segmentation from kspace data [20][21][22][23][24]. Schlemper et al [20] proposed using two neural networks, namely end-to-end synthesis network (SynNet) and latent feature interpolation network (LI-Net) to directly predict segmentation results from under-sampled k-space data.…”

Section: Introductionmentioning

confidence: 99%

“…The LI-Net constructs a latent feature interpolation network with improved results. Huang et al [22] proposed a Joint-FR-Net that consists of a reconstruction module derived from the fast iterative shrinkagethresholding algorithm (FISTA) and a segmentation module based on U-Net [21]. Huang et al [23] proposed a unique task-driven attention module that utilizes intermediate segmentation estimation to facilitate image-domain feature extraction from the raw data to bridge the gap between reconstruction and segmentation.…”

Section: Introductionmentioning

confidence: 99%

Multi-task MR Imaging with Iterative Teacher Forcing and Re-weighted Deep Learning

Qi¹,

Gong²,

Liu³

et al. 2020

Preprint

View full text Add to dashboard Cite

Noises, artifacts, and loss of information caused by the magnetic resonance (MR) reconstruction may compromise the final performance of the downstream applications. In this paper, we develop a re-weighted multi-task deep learning method to learn prior knowledge from the existing big dataset and then utilize them to assist simultaneous MR reconstruction and segmentation from the under-sampled k-space data. The multi-task deep learning framework is equipped with two network sub-modules, which are integrated and trained by our designed iterative teacher forcing scheme (ITFS) under the dynamic re-weighted loss constraint (DRLC). The ITFS is designed to avoid er-

show abstract

Complementation‐reinforced network for integrated reconstruction and segmentation of pulmonary gas MRI with high acceleration

Xiao

Wang

et al. 2023

Medical Physics

View full text Add to dashboard Cite

BackgroundHyperpolarized (HP) gas MRI enables the clear visualization of lung structure and function. Clinically relevant biomarkers, such as ventilated defect percentage (VDP) derived from this modality can quantify lung ventilation function. However, long imaging time leads to image quality degradation and causes discomfort to the patients. Although accelerating MRI by undersampling k‐space data is available, accurate reconstruction and segmentation of lung images are quite challenging at high acceleration factors.PurposeTo simultaneously improve the performance of reconstruction and segmentation of pulmonary gas MRI at high acceleration factors by effectively utilizing the complementary information in different tasks.MethodsA complementation‐reinforced network is proposed, which takes the undersampled images as input and outputs both the reconstructed images and the segmentation results of lung ventilation defects. The proposed network comprises a reconstruction branch and a segmentation branch. To effectively exploit the complementary information, several strategies are designed in the proposed network. Firstly, both branches adopt the encoder‐decoder architecture, and their encoders are designed to share convolutional weights for facilitating knowledge transfer. Secondly, a designed feature‐selecting block discriminately feeds shared features into decoders of both branches, which can adaptively pick suitable features for each task. Thirdly, the segmentation branch incorporates the lung mask obtained from the reconstructed images to enhance the accuracy of the segmentation results. Lastly, the proposed network is optimized by a tailored loss function that efficiently combines and balances these two tasks, in order to achieve mutual benefits.ResultsExperimental results on the pulmonary HP 129Xe MRI dataset (including 43 healthy subjects and 42 patients) show that the proposed network outperforms state‐of‐the‐art methods at high acceleration factors (4, 5, and 6). The peak signal‐to‐noise ratio (PSNR), structural similarity (SSIM), and Dice score of the proposed network are enhanced to 30.89, 0.875, and 0.892, respectively. Additionally, the VDP obtained from the proposed network has good correlations with that obtained from fully sampled images (r = 0.984). At the highest acceleration factor of 6, the proposed network promotes PSNR, SSIM, and Dice score by 7.79%, 5.39%, and 9.52%, respectively, in comparison to the single‐task models.ConclusionThe proposed method effectively enhances the reconstruction and segmentation performance at high acceleration factors up to 6. It facilitates fast and high‐quality lung imaging and segmentation, and provides valuable support in the clinical diagnosis of lung diseases.

show abstract

FR-Net: Joint Reconstruction and Segmentation in Compressed Sensing Cardiac MRI

Cited by 27 publications

References 12 publications

Joint Calibrationless Reconstruction and Segmentation of Parallel MRI

Joint Calibrationless Reconstruction and Segmentation of Parallel MRI

Multi-task MR Imaging with Iterative Teacher Forcing and Re-weighted Deep Learning

Complementation‐reinforced network for integrated reconstruction and segmentation of pulmonary gas MRI with high acceleration

Contact Info

Product

Resources

About