Student beats the teacher: deep neural networks for lateral ventricles segmentation in brain MR

@inproceedings{Ghafoorian2018StudentBT,
  title={Student beats the teacher: deep neural networks for lateral ventricles segmentation in brain MR},
  author={Mohsen Ghafoorian and Jonas Teuwen and Rashindra Manniesing and F.‐E. Leeuw and Bram van Ginneken and Nico Karssemeijer and Bram Platel},
  booktitle={Medical Imaging},
  year={2018}
}
Ventricular volume and its progression are known to be linked to several brain diseases such as dementia and schizophrenia. Therefore accurate measurement of ventricle volume is vital for longitudinal studies on these disorders, making automated ventricle segmentation algorithms desirable. In the past few years, deep neural networks have shown to outperform the classical models in many imaging domains. However, the success of deep networks is dependent on manually labeled data sets, which are… Expand
Brain ventricle parcellation using a deep neural network: Application to patients with ventriculomegaly
TLDR
A modified 3D U-Net method to perform accurate ventricular parcellation, even with grossly enlarged ventricles, from magnetic resonance images (MRIs) is proposed and provides a tool that enables computation of novel imaging biomarkers for dilated ventricular spaces that characterize the ventricular system. Expand
Learning to Segment the Lung Volume from CT Scans Based on Semi-Automatic Ground-Truth
TLDR
This work proposes to train a 3D CNN to solve the lung volume segmentation task based on semi-automatically generated annotations, and introduces an extension of the well-known V-Net architecture that can handle higher-dimensional input data. Expand
Machine Learning for Quantification of Small Vessel Disease Imaging Biomarkers
TLDR
This thesis is devoted to developing fully automated methods for quantification of small vessel disease imaging bio-markers, namely WMHs and lacunes, using machine learning/deep learning and computer vision techniques, using biologically inspired methods combined with deep neural networks. Expand
CT-ORG, a new dataset for multiple organ segmentation in computed tomography
TLDR
This work developed a diverse dataset of 140 CT scans containing six organ classes: liver, lungs, bladder, kidney, bones and brain, and trained a deep neural network which requires only 4.3 s to simultaneously segment all the organs in a case. Expand
Hippocampus segmentation in CT using deep learning: impact of MR versus CT-based training contours
TLDR
CT-based training contours for CT hippocampus segmentation cannot replace propagated MR-based contours without significant loss in performance, however, if MR- based contours are used, the resulting segmentations outperform experts in contouring the hippocampus on CT. Expand
Automated Image Registration Quality Assessment Utilizing Deep-learning based Ventricle Extraction in Clinical Data
TLDR
The utility of an automated tool for assessing image registration quality in clinical scans could ultimately assist in the translation of automated neuroimaging pipelines to the clinic. Expand
CT organ segmentation using GPU data augmentation, unsupervised labels and IOU loss
TLDR
It is shown that simple models can achieve competitive accuracy for organ segmentation on CT images when trained with extensive data augmentation, which leverages existing graphics hardware to quickly apply geometric and photometric transformations to 3D image data. Expand
Multi-atlas image registration of clinical data with automated quality assessment using ventricle segmentation
TLDR
The utility of an automated tool for assessing image registration quality in clinical scans could ultimately assist in the translation of automated neuroimaging pipelines to the clinic. Expand
Clinical feasibility of brain quantitative susceptibility mapping.
TLDR
Brain QSM images of various neurological diseases have reliable diagnostic quality in clinical MRI, with MEDI+0 providing susceptibility values automatically referenced to CSF in longitudinal and cross-center studies. Expand
Challenges for machine learning in clinical translation of big data imaging studies
TLDR
Issues relating to data availability, interpretability, evaluation and logistical challenges, and the challenges still to be overcome are focused on to enable the full success of big data deep learning approaches to be experienced outside of the research field. Expand
...
1
2
...

References

SHOWING 1-10 OF 31 REFERENCES
Location Sensitive Deep Convolutional Neural Networks for Segmentation of White Matter Hyperintensities
TLDR
This paper applies and compares the proposed architectures for segmentation of white matter hyperintensities in brain MR images on a large dataset and observes that the CNNs that incorporate location information substantially outperform a conventional segmentation method with handcrafted features as well asCNNs that do not integrate location information. Expand
U-Net: Convolutional Networks for Biomedical Image Segmentation
TLDR
It is shown that such a network can be trained end-to-end from very few images and outperforms the prior best method (a sliding-window convolutional network) on the ISBI challenge for segmentation of neuronal structures in electron microscopic stacks. Expand
Automated detection of white matter hyperintensities of all sizes in cerebral small vessel disease.
TLDR
The authors have developed a CAD system with all its ingredients being optimized for a better detection of WMHs of all size, which shows performance close to an independent reader. Expand
Deep multi-scale location-aware 3D convolutional neural networks for automated detection of lacunes of presumed vascular origin
TLDR
An automated two-stage method using deep convolutional neural networks (CNN) to detect initial candidates of presumed vascular origin and equip the network with contextual information using multi-scale analysis and integration of explicit location features is proposed. Expand
3D U-Net: Learning Dense Volumetric Segmentation from Sparse Annotation
TLDR
The proposed network extends the previous u-net architecture from Ronneberger et al. by replacing all 2D operations with their 3D counterparts and performs on-the-fly elastic deformations for efficient data augmentation during training. Expand
A survey on deep learning in medical image analysis
TLDR
This paper reviews the major deep learning concepts pertinent to medical image analysis and summarizes over 300 contributions to the field, most of which appeared in the last year, to survey the use of deep learning for image classification, object detection, segmentation, registration, and other tasks. Expand
Development and Validation of a Deep Learning Algorithm for Detection of Diabetic Retinopathy in Retinal Fundus Photographs.
TLDR
An algorithm based on deep machine learning had high sensitivity and specificity for detecting referable diabetic retinopathy and diabetic macular edema in retinal fundus photographs from adults with diabetes. Expand
Longitudinal changes in lateral ventricular volume in Datients with dementia of the Alzheimer type
TLDR
The rate of total lateral ventricular enlargement accompanying DAT is due to continuous, pathologic cell loss, significantly greater than cell loss due to the healthy aging process. Expand
Causes and consequences of cerebral small vessel disease. The RUN DMC study: a prospective cohort study. Study rationale and protocol
TLDR
The follow up of the RUN DMC study has the potential to further unravel the causes and possibly better predict the consequences of changes in white matter integrity in elderly with SVD by using relatively new imaging techniques. Expand
New reconstruction algorithm for digital breast tomosynthesis: better image quality for humans and computers
TLDR
The new algorithm provides DBT volumes with better contrast and image quality, fewer artifacts, and improved visibility of calcifications for human observers, as well as improved detection performance with deep-learning algorithms. Expand
...
1
2
3
4
...