Automated Localization of Fetal Organs in MRI Using Random Forests with Steerable Features (Miccai 2015 poster)
1 like200 views
This document presents a method for automatically localizing fetal organs in MRI scans using random forests with steerable features. The method first normalizes fetal size, then uses a classification and regression pipeline with random forests to assign voxels to organs and vote for organ centers. Features are steered based on detected landmarks like the brain to account for unknown fetal orientation. Evaluation on two datasets found the heart was localized within 10mm of ground truth in 90% of cases, suggesting it could initialize motion correction. Future work will use the detections for slice-by-slice segmentation to improve motion correction quality.
![Automated Localization of Fetal Organs in MRI
Using Random Forests with Steerable Features
K. Keraudren1
, B. Kainz1
, O. Oktay1
, V. Kyriakopoulou2
,
M. Rutherford2
, J.V. Hajnal2
, D. Rueckert1
1
Biomedical Image Analysis Group, Imperial College London, 2
Centre for the Developing Brain, King’s College London
Size normalization
Due to fetal motion, fetal MRI is typically ac-
quired as stacks of 2D slices of real-time MRI,
freezing in-plane motion. Motion correction
methods can subsequently be applied to cor-
rect the misalignment between slices and pro-
vide consistent 3D data1
. Such methods perform
slice-to-volume registration and require the fetal
anatomy to be isolated from surrounding mater-
nal tissues. We thus propose a method to auto-
matically localize the fetal heart, lungs and liver.
u0u0
w0w0
v0v0
brainbrain
heartheart
Sagittal plane
v0v0
w0w0
u0u0
heartheart
rightright
lunglung
Transverse plane
Average image of the training data after
size normalization.
To reduce the variability due to fetal develop-
ment, we normalize the size of all fetuses by re-
sampling the images to an isotropic voxel size
sga that is a function of the gestational age, so
that a fetus of 30 weeks is resampled to a voxel
size s30: sga = CRLga/CRL30 × s30 where CRL
denotes the crown-rump length.
Organ localization pipeline
Inspired by Hough Forests2
, the proposed method performs classification (a,c) and regression (b,d)
steps using Random Forests in order to assign voxels to a certain organ then vote for the location of
the organ center. A set of organ candidates is generated, then scored based on their relative position.
(a) (b) (c) (d)
Proposed pipeline for the automated localization of fetal organs in MRI.
The center of the brain3
is first used to steer features when detecting the heart, which then fixes an
axis when detecting the lungs and liver. Knowing the location of the brain, the search for the heart
only needs to explore the image region contained between two spheres. The search for the lungs and
liver can similarly be restricted to a sphere around the heart.
Steerable features
In order to cope with the unknown orientation
of the fetus, image features are extracted in a
local coordinate system. At training time, the
coordinate system (u0, v0, w0) is defined by land-
marks on the fetal anatomy. At test time, the
coordinate system (u, v, w) is estimated as or-
gans are detected: first the brain, which fixes a
point, then the heart, which fixes an axis, and
finally the liver and both lungs.
uu
vv
uu
vv
uu
vv
At test time, features are steered toward
the center of the brain.
Results
The method was evaluated on two datasets of T2 MRI, a first dataset without motion artifacts and
a second with artifacts, with gestational ages (GA) ranging from 20 to 38 weeks. Thanks to the size
normalization, the same trained detector can be used across all GA. A similar performance of the
detector across GA was observed. In 90% of cases, the detected heart center is within 10mm of the
ground truth, which suggests that the proposed method could provide an automated initialization
for the motion correction of the chest4
. The asymmetry in the performance of the detector between
the left and right lungs can be explained by the presence of the liver below the right lung, leading to
a stronger geometric constraint when ranking organ candidates.
Left
lung
Right
lung
Heart Liver
0
5
10
15
20
25
30
35
40
Distanceerror(mm)
1st
dataset: healthy
Left
lung
Right
lung
Heart Liver
0
5
10
15
20
25
30
35
40
1st
dataset: IUGR
Left
lung
Right
lung
Heart Liver Brain
0
5
10
15
20
25
30
35
40
2nd
dataset
Distance error between the predicted organ centers and their ground truth for the first
dataset (30 healthy and 25 IUGR fetuses) and the second dataset (64 healthy fetuses).
References
[1] M. Kuklisova-Murgasova, G. Quaghebeur,
M. Rutherford, J. Hajnal, and J. Schnabel,
“Reconstruction of Fetal Brain MRI with Inten-
sity Matching and Complete Outlier Removal,”
Medical Image Analysis, 2012.
[2] J. Gall and V. Lempitsky, “Class-specific Hough
Forests for Object Detection,” in CVPR, 2009.
[3] K. Keraudren, V. Kyriakopoulou, M. Ruther-
ford, J. V. Hajnal, and D. Rueckert, “Localisa-
tion of the Brain in Fetal MRI Using Bundled
SIFT Features,” in MICCAI, 2013.
[4] B. Kainz, C. Malamateniou, M. Murgasova,
K. Keraudren, M. Rutherford, J. V. Hajnal, and
D. Rueckert, “Motion Corrected 3D Reconstruc-
tion of the Fetal Thorax from Prenatal MRI,” in
MICCAI, 2014.
Conclusion & Future work
AcquisitionMotioncorrection
Sagittal Coronal Transverse
We presented a pipeline which, in combination
with automated brain detection3
, enables the au-
tomated localization of the lungs, heart and liver
in fetal MRI. The localization results can be used
to initialize a segmentation or motion correction,
and to orient the 3D volume with respect to the
fetal anatomy to facilitate clinical diagnosis.
Preliminary work used the rough segmentation
produced by the detection process to generate a
mask for the fetal trunk, with morphological op-
erations and a region growing algorithm. Future
work will focus on a slice-by-slice segmentation
in order to increase the quality of the motion cor-
rected volume.](https://image.slidesharecdn.com/miccai-2015poster-161022133511/85/Automated-Localization-of-Fetal-Organs-in-MRI-Using-Random-Forests-with-Steerable-Features-Miccai-2015-poster-1-320.jpg)
Automated Localization of Fetal Organs in MRI Using Random Forests with Steerable Features (Miccai 2015 poster)
- 1. Automated Localization of Fetal Organs in MRI Using Random Forests with Steerable Features K. Keraudren1 , B. Kainz1 , O. Oktay1 , V. Kyriakopoulou2 , M. Rutherford2 , J.V. Hajnal2 , D. Rueckert1 1 Biomedical Image Analysis Group, Imperial College London, 2 Centre for the Developing Brain, King’s College London Size normalization Due to fetal motion, fetal MRI is typically ac- quired as stacks of 2D slices of real-time MRI, freezing in-plane motion. Motion correction methods can subsequently be applied to cor- rect the misalignment between slices and pro- vide consistent 3D data1 . Such methods perform slice-to-volume registration and require the fetal anatomy to be isolated from surrounding mater- nal tissues. We thus propose a method to auto- matically localize the fetal heart, lungs and liver. u0u0 w0w0 v0v0 brainbrain heartheart Sagittal plane v0v0 w0w0 u0u0 heartheart rightright lunglung Transverse plane Average image of the training data after size normalization. To reduce the variability due to fetal develop- ment, we normalize the size of all fetuses by re- sampling the images to an isotropic voxel size sga that is a function of the gestational age, so that a fetus of 30 weeks is resampled to a voxel size s30: sga = CRLga/CRL30 × s30 where CRL denotes the crown-rump length. Organ localization pipeline Inspired by Hough Forests2 , the proposed method performs classification (a,c) and regression (b,d) steps using Random Forests in order to assign voxels to a certain organ then vote for the location of the organ center. A set of organ candidates is generated, then scored based on their relative position. (a) (b) (c) (d) Proposed pipeline for the automated localization of fetal organs in MRI. The center of the brain3 is first used to steer features when detecting the heart, which then fixes an axis when detecting the lungs and liver. Knowing the location of the brain, the search for the heart only needs to explore the image region contained between two spheres. The search for the lungs and liver can similarly be restricted to a sphere around the heart. Steerable features In order to cope with the unknown orientation of the fetus, image features are extracted in a local coordinate system. At training time, the coordinate system (u0, v0, w0) is defined by land- marks on the fetal anatomy. At test time, the coordinate system (u, v, w) is estimated as or- gans are detected: first the brain, which fixes a point, then the heart, which fixes an axis, and finally the liver and both lungs. uu vv uu vv uu vv At test time, features are steered toward the center of the brain. Results The method was evaluated on two datasets of T2 MRI, a first dataset without motion artifacts and a second with artifacts, with gestational ages (GA) ranging from 20 to 38 weeks. Thanks to the size normalization, the same trained detector can be used across all GA. A similar performance of the detector across GA was observed. In 90% of cases, the detected heart center is within 10mm of the ground truth, which suggests that the proposed method could provide an automated initialization for the motion correction of the chest4 . The asymmetry in the performance of the detector between the left and right lungs can be explained by the presence of the liver below the right lung, leading to a stronger geometric constraint when ranking organ candidates. Left lung Right lung Heart Liver 0 5 10 15 20 25 30 35 40 Distanceerror(mm) 1st dataset: healthy Left lung Right lung Heart Liver 0 5 10 15 20 25 30 35 40 1st dataset: IUGR Left lung Right lung Heart Liver Brain 0 5 10 15 20 25 30 35 40 2nd dataset Distance error between the predicted organ centers and their ground truth for the first dataset (30 healthy and 25 IUGR fetuses) and the second dataset (64 healthy fetuses). References [1] M. Kuklisova-Murgasova, G. Quaghebeur, M. Rutherford, J. Hajnal, and J. Schnabel, “Reconstruction of Fetal Brain MRI with Inten- sity Matching and Complete Outlier Removal,” Medical Image Analysis, 2012. [2] J. Gall and V. Lempitsky, “Class-specific Hough Forests for Object Detection,” in CVPR, 2009. [3] K. Keraudren, V. Kyriakopoulou, M. Ruther- ford, J. V. Hajnal, and D. Rueckert, “Localisa- tion of the Brain in Fetal MRI Using Bundled SIFT Features,” in MICCAI, 2013. [4] B. Kainz, C. Malamateniou, M. Murgasova, K. Keraudren, M. Rutherford, J. V. Hajnal, and D. Rueckert, “Motion Corrected 3D Reconstruc- tion of the Fetal Thorax from Prenatal MRI,” in MICCAI, 2014. Conclusion & Future work AcquisitionMotioncorrection Sagittal Coronal Transverse We presented a pipeline which, in combination with automated brain detection3 , enables the au- tomated localization of the lungs, heart and liver in fetal MRI. The localization results can be used to initialize a segmentation or motion correction, and to orient the 3D volume with respect to the fetal anatomy to facilitate clinical diagnosis. Preliminary work used the rough segmentation produced by the detection process to generate a mask for the fetal trunk, with morphological op- erations and a region growing algorithm. Future work will focus on a slice-by-slice segmentation in order to increase the quality of the motion cor- rected volume.