An automated framework for localization, segmentation and super-resolution reconstruction of fetal brain MRI

Ebner, Michael; Wang, Guotai; Li, Wenqi; Aertsen, Michaël; Patel, Premal A.; Aughwane, Rosalind; Melbourne, Andrew; Doel, Tom; Dymarkowski, Steven; Coppi, Paolo De; David, Anna L.; Deprest, Jan; Ourselin, Sébastien; Vercauteren, Tom

doi:10.1016/j.neuroimage.2019.116324

Cited by 223 publications

(254 citation statements)

References 30 publications

Supporting

Mentioning

252

Contrasting

Order By: Relevance

“…For each subject's set of images, SR reconstruction was performed using three different methods: mialSRTK [4], Simple IRTK [1], and NiftyMIC [3] using the following steps: Preprocessing: The acquired images were bias corrected and de-noised prior to reconstruction using the tools included within each pipeline where applicable. Masking: Each reconstruction method had different masking requirements.…”

Section: Super-resolution Reconstructionmentioning

confidence: 99%

“…Artifacts resulting from fetal and maternal movement are present, leading to difficulty in differentiating tissue types. Recently, advances have been made in the processing and super-resolution (SR) reconstruction of motion-corrupted low resolution fetal brain scans into high resolution volumes [1][2][3][4][5][6][7]. The enhanced resolution and improved image quality of the SR data in comparison to the native low-resolution scans has in turn resulted in greatly improved volumetric fetal brain data, the segmentation of which has not been assessed in detail.…”

Section: Introductionmentioning

confidence: 99%

“…The enhanced resolution and improved image quality of the SR data in comparison to the native low-resolution scans has in turn resulted in greatly improved volumetric fetal brain data, the segmentation of which has not been assessed in detail. Segmentation of the fetal brain from maternal tissue in the original scans has been explored [3,[8][9][10][11]. Methods to segment the original low resolution MR scans into different brain tissues have also been evaluated [12], as well as for a single tissue type within a high resolution volume [13,14].…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Medical Ultrasound, and Preterm, Perinatal and Paediatric Image Analysis

2020

Lecture Notes in Computer Science

View full text Add to dashboard Cite

Segmentation of the developing fetal brain is an important step in quantitative analyses. However, manual segmentation is a very time-consuming task which is prone to error and must be completed by highly specialized individuals. Super-resolution reconstruction of fetal MRI has become standard for processing such data as it improves image quality and resolution. However, different pipelines result in slightly different outputs, further complicating the generalization of segmentation methods aiming to segment super-resolution data. Therefore, we propose using transfer learning with noisy multi-class labels to automatically segment high resolution fetal brain MRIs using a single set of segmentations created with one reconstruction method and tested for generalizability across other reconstruction methods. Our results show that the network can automatically segment fetal brain reconstructions into 7 different tissue types, regardless of reconstruction method used. Transfer learning offers some advantages when compared to training without pre-initialized weights, but the network trained on clean labels had more accurate segmentations overall. No additional manual segmentations were required. Therefore, the proposed network has the potential to eliminate the need for manual segmentations needed in quantitative analyses of the fetal brain independent of reconstruction method used, offering an unbiased way to quantify normal and pathological neurodevelopment.

show abstract

Section: Super-resolution Reconstructionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Medical Ultrasound, and Preterm, Perinatal and Paediatric Image Analysis

2020

Lecture Notes in Computer Science

View full text Add to dashboard Cite

show abstract

“…Compared to VVR-based techniques, motion correction using retrospective SVR followed by image reconstruction has shown significantly improved results in a range of MRI applications including diffusion-weighted imaging (DWI) of non-cooperative patients, e.g. ( Bastiani et al, 2019 ; Hutter et al, 2018 ; Marami et al, 2016 ; 2019 ), fetal brain MRI ( Alansary et al, 2017 ; Ebner et al, 2019b ; Gholipour et al, 2010 ; Kainz et al, 2015 ; Marami et al, 2017 ), fetal cardiac MRI ( van Amerom et al, 2019 ; Lloyd et al, 2019 ), and body MRI ( Ebner et al, 2019a ; Kurugol et al, 2017 ).…”

Section: Introductionmentioning

confidence: 99%

SLIMM: Slice localization integrated MRI monitoring

et al. 2020

View full text Add to dashboard Cite

Functional MRI (fMRI) is extremely challenging to perform in subjects who move because subject motion disrupts blood oxygenation level dependent (BOLD) signal measurement. It has become common to use retrospective framewise motion detection and censoring in fMRI studies to eliminate artifacts arising from motion. Data censoring results in significant loss of data and statistical power unless the data acquisition is extended to acquire more data not corrupted by motion. Acquiring more data than is necessary leads to longer than necessary scan duration, which is more expensive and may lead to additional subject non-compliance. Therefore, it is well established that real-time prospective motion monitoring is crucial to ensure data quality and reduce imaging costs. In addition, real-time monitoring of motion allows for feedback to the operator and the subject during the acquisition, to enable intervention to reduce the subject motion. The most widely used form of motion monitoring for fMRI is based on volume-to-volume registration (VVR), which quantifies motion as the misalignment between subsequent volumes. However, motion is not constrained to occur only at the boundaries of volume acquisition, but instead may occur at any time. Consequently, each slice of an fMRI acquisition may be displaced by motion, and assessment of whole volume to volume motion may be insensitive to both intra-volume and inter-volume motion that is revealed by displacement of the slices. We developed the first slice-by-slice self-navigated motion monitoring system for fMRI by developing a real-time slice-to-volume registration (SVR) algorithm. Our real-time SVR algorithm, which is the core of the system, uses a local image patch-based matching criterion along with a Levenberg-Marquardt optimizer, all accelerated via symmetric multi-processing, with interleaved and simultaneous multi-slice acquisition schemes. Extensive experimental results on real motion data demonstrated that our fast motion monitoring system, named S lice L ocalization I ntegrated M RI M onitoring (SLIMM), provides more accurate motion measurements than a VVR based approach. Therefore, SLIMM offers improved online motion monitoring which is particularly important in fMRI for challenging patient populations. Real-time motion monitoring is crucial for online data quality control and assurance, for enabling feedback to the subject and the operator to act to mitigate motion, and in adaptive acquisition strategies that aim to ensure enough data of sufficient quality is acquired without acquiring excess data.

show abstract

“…Spatial resolution is a key factor of evaluating the quality of magnetic resonance imagery (MRI). Images having high spatial resolution produce rich structural details, enabling accurate image analysis 1 and detailed anatomical information for accurate quantitative analysis 2 . MRI is widely used to assess brain disease and development 3,4 .…”

Section: Introductionmentioning

confidence: 99%

Deep Robust Residual Network for Brain MRI Super-Resolution

Song¹,

Wang²,

Liu³

et al. 2020

Preprint

View full text Add to dashboard Cite

Spatial resolution is a key factor of quantitatively evaluating the quality of magnetic resonance imagery (MRI). Super-resolution (SR) approaches can improve its spatial resolution by reconstructing high-resolution (HR) images from low-resolution (LR) ones to meet clinical and scientific requirements. To increase the quality of brain MRI, we study a robust residual-learning SR network (RRLSRN) to generate a sharp HR brain image from an LR input. Given that the Charbonnier loss can handle outliers well, and Gradient Difference Loss (GDL) can sharpen an image, we combine the Charbonnier loss and GDL to improve the robustness of the model and enhance the texture information of SR results. Two MRI datasets of adult brain, Kirby 21 and NAMIC, were used to train and verify the effectiveness of our model. To further verify the generalizability and robustness of the proposed model, we collected eight clinical fetal brain MRI data for evaluation. The experimental results show that the proposed deep residual-learning network achieved superior performance and high efficiency over other compared methods.

show abstract

An automated framework for localization, segmentation and super-resolution reconstruction of fetal brain MRI

Cited by 223 publications

References 30 publications

Medical Ultrasound, and Preterm, Perinatal and Paediatric Image Analysis

Medical Ultrasound, and Preterm, Perinatal and Paediatric Image Analysis

SLIMM: Slice localization integrated MRI monitoring

Deep Robust Residual Network for Brain MRI Super-Resolution

Contact Info

Product

Resources

About