Deep Learning Framework for Real-Time Fetal Brain Segmentation in MRI

Faghihpirayesh, Razieh; Karimi, Davood; Erdoğmuş, Deni̇z; Gholipour, Ali

doi:10.1007/978-3-031-17117-8_6

Cited by 4 publications

(4 citation statements)

References 25 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…A 3D rotation is commonly represented with a 3 × 3 matrix R with 9 elements that are subject to six norm and orthogonality constraints (i.e., R should be orthogonal and detR = 1). The set of 3D rotations form the Special Orthogonal Group SO (3). With rotation matrices we have nine parameters to represent a 3D rotation, which is excessive compared to other parametrizations.…”

Section: Rotation Representations Analysismentioning

confidence: 99%

“…[13][14][15] All reconstructed volumes had isotropic voxels of size 0.8 mm 3 . Brain masks were generated on the reconstructed volumes using an existing deep learning segmentation method 3,4 and manually corrected in ITK-SNAP as needed. Brain-extracted reconstructed images were then registered to a spatiotemporal fetal brain MRI atlas.…”

Section: Dataset and Implementationmentioning

confidence: 99%

“…Recent efforts have employed deep learning techniques on fetal brain studies such as segmentation, [2][3][4] localization, 2 and reconstruction. 1,5 In an original work on regression for pose estimation, Kendal et al proposed a regression convolutional neural network (CNN), called PoseNet, to regress the camera pose (i.e., position and orientation) relative to a canonical space.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Automatic brain pose estimation in fetal MRI

Faghihpirayesh

Karimi

Erdoğmuş³

et al. 2023

Medical Imaging 2023: Image Processing

View full text Add to dashboard Cite

In this paper, we present a 3D pose regression model using Convolutional Neural Networks (CNNs) for unconstrained end-to-end fetal brain pose estimation in fetal MRI. We focus on investigating across different pose representation schemes and address the problem of ambiguous rotation labels by introducing the rotation matrix formalism for our ground truth data. We propose a continuous 6D rotation matrix representation for efficient and robust direct pose regression. Our model learns to predict different rotation representations of the 3D pose directly based on the MRI volume. We used a geodesic loss to evaluate our model and compare its performance with alternative methods. We trained and tested our model on arbitrarily oriented MRI volumes of fetal brains scanned in-utero at a wide gestational age range. Experimental results on synthetically transformed data, show that our method with a continuous 6D rotation matrix representation, achieved an average geodesic error of 6.33 • without any post-processing, which was smaller than the error for all competing methods. Our proposed method can be a useful base for fetal brain motion tracking, motion detection, and 3D reconstruction. Code, data, and the trained models are available at https://github.com/bchimagine/fetal-brain-pose-estimation.

show abstract

Section: Rotation Representations Analysismentioning

confidence: 99%

Section: Dataset and Implementationmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Automatic brain pose estimation in fetal MRI

Faghihpirayesh

Karimi

Erdoğmuş³

et al. 2023

Medical Imaging 2023: Image Processing

View full text Add to dashboard Cite

show abstract

“…Recent work highlighted the use of AI methods during the acquisition in motion detection, correction, and automatic planning. Specifically in fetal MRI, work showed the ability to perform quality control, 14 automatic segmentation, 15,16 and automatic tracking. 17,18 Automatic field-of-view prescription was shown in the abdomen using deep learning segmentations 19 and in the heart using tracking based on landmarks 20 with successful detection ratings of 99.7%-100% for cine images and Euclidean distances between manual and automatically detected labels from 2 to 3.5 mm.…”

Section: Introductionmentioning

confidence: 99%

Fully automated planning for anatomical fetal brain MRI on 0.55T

Neves Silva,

McElroy,

Aviles Verdera

et al. 2024

Magnetic Resonance in Med

View full text Add to dashboard Cite

PurposeWidening the availability of fetal MRI with fully automatic real‐time planning of radiological brain planes on 0.55T MRI.MethodsDeep learning‐based detection of key brain landmarks on a whole‐uterus echo planar imaging scan enables the subsequent fully automatic planning of the radiological single‐shot Turbo Spin Echo acquisitions. The landmark detection pipeline was trained on over 120 datasets from varying field strength, echo times, and resolutions and quantitatively evaluated. The entire automatic planning solution was tested prospectively in nine fetal subjects between 20 and 37 weeks. A comprehensive evaluation of all steps, the distance between manual and automatic landmarks, the planning quality, and the resulting image quality was conducted.ResultsProspective automatic planning was performed in real‐time without latency in all subjects. The landmark detection accuracy was 4.2 2.6 mm for the fetal eyes and 6.5 3.2 for the cerebellum, planning quality was 2.4/3 (compared to 2.6/3 for manual planning) and diagnostic image quality was 2.2 compared to 2.1 for manual planning.ConclusionsReal‐time automatic planning of all three key fetal brain planes was successfully achieved and will pave the way toward simplifying the acquisition of fetal MRI thereby widening the availability of this modality in nonspecialist centers.

show abstract