Automated Localization of Fetal Organs in MRI Using Random Forests with Steerable Features

Keraudren, Kevin; Kainz, Bernhard; Oktay, Ozan; Kyriakopoulou, Vanessa; Rutherford, Mary A.; Hajnal, Joseph V.; Rueckert, Daniel

doi:10.1007/978-3-319-24574-4_74

Cited by 17 publications

(20 citation statements)

References 10 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The arbitrary orientation of the fetus inside the womb and the large possible range of developmental age makes establishing a semantic understanding of the scene very challenging. [Keraudren et al (2015)] show for example how steerable image features and a Random Forest classification can be used to establish a mapping to a standardised fetal body coordinate system, which defines a semantic neighbourhood relationship for the localisation and segmentation of randomly oriented fetal organs. Figure 2 illustrates this process.…”

Section: Semantic Imagingmentioning

confidence: 99%

“…Figure 2 illustrates this process. Starting from a segmentation of the fetal brain (purple) we can localize other fetal organs by transforming them into a standard body coordinate system, thus establishing a spatial relationship [Keraudren et al (2015)], which can be learned together with image features. The panel on the left shows the initial predictions of organ class likelihoods and the panel on right shows the final segmentation.…”

Section: Semantic Imagingmentioning

confidence: 99%

See 1 more Smart Citation

Learning clinically useful information from images: Past, present and future

Rueckert

Glocker

Kainz

2016

Medical Image Analysis

Self Cite

View full text Add to dashboard Cite

Over the last decade, research in medical imaging has made significant progress in addressing challenging tasks such as image registration and image segmentation. In particular, the use of model-based approaches has been key in numerous, successful advances in methodology. The advantage of modelbased approaches is that they allow the incorporation of prior knowledge acting as a regularisation that favours plausible solutions over implausible ones. More recently, medical imaging has moved away from hand-crafted, and often explicitly designed models towards data-driven, implicit models that are constructed using machine learning techniques. This has led to major improvements in all stages of the medical imaging pipeline, from acquisition and reconstruction to analysis and interpretation. As more and more imaging data is becoming available, e.g., from large population studies, this trend is likely to continue and accelerate. At the same time new developments in machine learning, e.g., deep learning, as well as significant improvements in computing power, e.g., parallelisation on graphics hardware, offer new potential for data-driven, semantic and intelligent medical imaging. This article outlines the work of the BioMedIA group in this area and highlights some of the challenges and opportunities for future work.

show abstract

Section: Semantic Imagingmentioning

confidence: 99%

Section: Semantic Imagingmentioning

confidence: 99%

Learning clinically useful information from images: Past, present and future

Rueckert

Glocker

Kainz

2016

Medical Image Analysis

Self Cite

View full text Add to dashboard Cite

show abstract

“…Therefore, a fully automatic motion correction method for the whole uterus, as it is presented in this paper, is very desirable and will enable the application of standard 3D image analysis techniques, e.g. , [28], [29].…”

Section: Introductionmentioning

confidence: 99%

PVR: Patch-to-Volume Reconstruction for Large Area Motion Correction of Fetal MRI

Alansary

Rajchl

McDonagh

et al. 2017

IEEE Trans. Med. Imaging

Self Cite

View full text Add to dashboard Cite

In this paper, we present a novel method for the correction of motion artifacts that are present in fetal magnetic resonance imaging (MRI) scans of the whole uterus. Contrary to current slice-to-volume registration (SVR) methods, requiring an inflexible anatomical enclosure of a single investigated organ, the proposed patch-to-volume reconstruction (PVR) approach is able to reconstruct a large field of view of non-rigidly deforming structures. It relaxes rigid motion assumptions by introducing a specific amount of redundant information that is exploited with parallelized patchwise optimization, super-resolution, and automatic outlier rejection. We further describe and provide an efficient parallel implementation of PVR allowing its execution within reasonable time on commercially available graphics processing units, enabling its use in the clinical practice. We evaluate PVR’s computational overhead compared with standard methods and observe improved reconstruction accuracy in the presence of affine motion artifacts compared with conventional SVR in synthetic experiments. Furthermore, we have evaluated our method qualitatively and quantitatively on real fetal MRI data subject to maternal breathing and sudden fetal movements. We evaluate peak-signal-to-noise ratio, structural similarity index, and cross correlation with respect to the originally acquired data and provide a method for visual inspection of reconstruction uncertainty. We further evaluate the distance error for selected anatomical landmarks in the fetal head, as well as calculating the mean and maximum displacements resulting from automatic non-rigid registration to a motion-free ground truth image. These experiments demonstrate a successful application of PVR motion compensation to the whole fetal body, uterus, and placenta.

show abstract

“…Related work: To the best of our knowledge, fully automatic segmentation of the placenta from MRI has not been investigated before. Most previous work in fetal MRI was focused on brain segmentation [2] and very recently has been extended to localize other fetal organs [6]. These methods rely on engineering visual features for training a classifier such as random forests.…”

Section: Introductionmentioning

confidence: 99%

Fast Fully Automatic Segmentation of the Human Placenta from Motion Corrupted MRI

Alansary

Kamnitsas

Davidson

et al. 2016

Lecture Notes in Computer Science

Self Cite

View full text Add to dashboard Cite

Abstract. Recently, magnetic resonance imaging has revealed to be important for the evaluation of placenta's health during pregnancy. Quantitative assessment of the placenta requires a segmentation, which proves to be challenging because of the high variability of its position, orientation, shape and appearance. Moreover, image acquisition is corrupted by motion artifacts from both fetal and maternal movements. In this paper we propose a fully automatic segmentation framework of the placenta from structural T2-weighted scans of the whole uterus, as well as an extension in order to provide an intuitive pre-natal view into this vital organ. We adopt a 3D multi-scale convolutional neural network to automatically identify placental candidate pixels. The resulting classification is subsequently refined by a 3D dense conditional random field, so that a high resolution placental volume can be reconstructed from multiple overlapping stacks of slices. Our segmentation framework has been tested on 66 subjects at gestational ages 20-38 weeks achieving a Dice score of 71.95 ± 19.79% for healthy fetuses with a fixed scan sequence and 66.89 ± 15.35% for a cohort mixed with cases of intrauterine fetal growth restriction using varying scan parameters.

show abstract

Automated Localization of Fetal Organs in MRI Using Random Forests with Steerable Features

Cited by 17 publications

References 10 publications

Learning clinically useful information from images: Past, present and future

Learning clinically useful information from images: Past, present and future

PVR: Patch-to-Volume Reconstruction for Large Area Motion Correction of Fetal MRI

Fast Fully Automatic Segmentation of the Human Placenta from Motion Corrupted MRI

Contact Info

Product

Resources

About