Efficient multi-scale 3D CNN with fully connected CRF for accurate brain lesion segmentation

Kamnitsas, Konstantinos; Ledig, Christian; Newcombe, Virginia; Simpson, Joanna; Kane, Andrew D.; Menon, David; Rueckert, Daniel; Glocker, Ben

doi:10.1016/j.media.2016.10.004

Cited by 2,949 publications

(2,158 citation statements)

References 62 publications

Supporting

Mentioning

2,136

Contrasting

Unclassified

Order By: Relevance

“…Given the nature of MR imaging, we have developed a network architecture that uses 3D convolutions , which are appropriate when dealing with fully volumetric images. Recently, 3D convolutional neural networks have been also proposed for Alzheimer's disease classification (Payan and Montana, 2015;Sarraf and Tofighi, 2016), brain lesion segmentation (Kamnitsas et al, 2016) and skull stripping .…”

Section: Convolutional Neural Networkmentioning

confidence: 99%

Predicting brain age with deep learning from raw imaging data results in a reliable and heritable biomarker

et al. 2017

View full text Add to dashboard Cite

Machine learning analysis of neuroimaging data can accurately predict chronological age in healthy people and deviations from healthy brain ageing have been associated with cognitive impairment and disease. Here we sought to further establish the credentials of 'brainpredicted age' as a biomarker of individual differences in the brain ageing process, using a predictive modelling approach based on deep learning, and specifically convolutional neural networks (CNN), and applied to both pre-processed and raw T1-weighted MRI data.Firstly, we aimed to demonstrate the accuracy of CNN brain-predicted age using a large dataset of healthy adults (N = 2001). Next, we sought to establish the heritability of brainpredicted age using a sample of monozygotic and dizygotic female twins (N = 62). Thirdly, we examined the test-retest and multi-centre reliability of brain-predicted age using two samples (within-scanner N = 20; between-scanner N = 11). CNN brain-predicted ages were generated and compared to a Gaussian Process Regression (GPR) approach, on all datasets. Input data were grey matter (GM) or white matter (WM) volumetric maps generated by Statistical Parametric Mapping (SPM) or raw data. CNN accurately predicted chronological age using GM (correlation between brain-predicted age and chronological age r = 0.96, mean absolute error [MAE] = 4.16 years) and raw (r = 0.94, MAE = 4.65 years) data. This was comparable to GPR brain-predicted age using GM data (r = 0.95, MAE = 4.66 years). Brain-predicted age was a significantly heritable phenotype for all models and input data (h 2 = 0.50-0.84). Brain-predicted age showed high test-retest reliability (intraclass correlation coefficient [ICC] = 0.90-0.98). Multi-centre reliability was more variable within high ICCs for GM (0.83-0.96) and poor-moderate levels for WM and raw data (0.51-0.77).2 Brain-predicted age represents an accurate, highly reliable and genetically-valid phenotype, that has potential to be used as a biomarker of brain ageing. Moreover, age predictions can be accurately generated on raw T1-MRI data, substantially reducing computation time for novel data, bringing the process closer to giving real-time information on brain health in clinical settings.

show abstract

Section: Convolutional Neural Networkmentioning

confidence: 99%

Predicting brain age with deep learning from raw imaging data results in a reliable and heritable biomarker

et al. 2017

View full text Add to dashboard Cite

show abstract

“…Ronneberger et al (2015); Moeskops et al (2016); Havaei et al (2017)), hence, we employ a CNN to automatically segment the LV myocardium. To combine the analysis of local texture with distal spatial information, multiscale CNN is used (de Brebisson and Montana, 2015;Moeskops et al, 2016;Kamnitsas et al, 2016;Havaei et al, 2017).…”

Section: Myocardium Segmentationmentioning

confidence: 99%

Deep learning analysis of the myocardium in coronary CT angiography for identification of patients with functionally significant coronary artery stenosis

Zreik

Leßmann

Hamersvelt

et al. 2018

Medical Image Analysis

171

124

View full text Add to dashboard Cite

In patients with coronary artery stenoses of intermediate severity, the functional significance needs to be determined. Fractional flow reserve (FFR) measurement, performed during invasive coronary angiography (ICA), is most often used in clinical practice. To reduce the number of ICA procedures, we present a method for automatic identification of patients with functionally significant coronary artery stenoses, employing deep learning analysis of the left ventricle (LV) myocardium in rest coronary CT angiography (CCTA).The study includes consecutively acquired CCTA scans of 166 patients who underwent invasive FFR measurements. To identify patients with a functionally significant coronary artery stenosis, analysis is performed in several stages. First, the LV myocardium is segmented using a multiscale convolutional neural network (CNN). To characterize the segmented LV myocardium, it is subsequently encoded using unsupervised convolutional autoencoder (CAE). As ischemic changes are expected to appear locally, the LV myocardium is divided into a number of spatially connected clusters, and statistics of the encodings are computed as features. Thereafter, patients are classified according to the presence of functionally significant stenosis using an SVM classifier based on the extracted features.Quantitative evaluation of LV myocardium segmentation in 20 images resulted in an average Dice coefficient of 0.91 and an average mean absolute distance between the segmented and reference LV boundaries of 0.7 mm. Twenty CCTA images were used to train the LV myocardium encoder. Classification of patients was evaluated in the remaining 126 CCTA scans in 50 10-fold cross-validation experiments and resulted in an area under the receiver operating characteristic curve of 0.74 ± 0.02. At sensitivity levels 0.60, 0.70 and 0.80, the corresponding specificity was 0.77, 0.71 and 0.59, respectively.The results demonstrate that automatic analysis of the LV myocardium in a single CCTA scan acquired at rest, without assessment of the anatomy of the coronary arteries, can be used to identify patients with functionally significant coronary artery stenosis. This might reduce the number of patients undergoing unnecessary invasive FFR measurements.

show abstract

“…This includes automatic segmentation of brain lesions [2,10], tumors [9,15,21], and neuroanatomy [14,22,3], using voxelwise network architectures [14,9,17], and more recently using 3D voxelwise networks [3,10], and fully convolutional networks (FCNs) [4,13,17]. Compared to voxelwise methods, FCNs are fast in testing and training, and use the entire samples to learn local and global image features.…”

Section: Introductionmentioning

confidence: 99%

Tversky Loss Function for Image Segmentation Using 3D Fully Convolutional Deep Networks

Salehi

Erdoğmuş

Gholipour

2017

Lecture Notes in Computer Science

727

380

View full text Add to dashboard Cite

Abstract. Fully convolutional deep neural networks carry out excellent potential for fast and accurate image segmentation. One of the main challenges in training these networks is data imbalance, which is particularly problematic in medical imaging applications such as lesion segmentation where the number of lesion voxels is often much lower than the number of non-lesion voxels. Training with unbalanced data can lead to predictions that are severely biased towards high precision but low recall (sensitivity), which is undesired especially in medical applications where false negatives are much less tolerable than false positives. Several methods have been proposed to deal with this problem including balanced sampling, two step training, sample re-weighting, and similarity loss functions. In this paper, we propose a generalized loss function based on the Tversky index to address the issue of data imbalance and achieve much better trade-off between precision and recall in training 3D fully convolutional deep neural networks. Experimental results in multiple sclerosis lesion segmentation on magnetic resonance images show improved F2 score, Dice coefficient, and the area under the precision-recall curve in test data. Based on these results we suggest Tversky loss function as a generalized framework to effectively train deep neural networks.

show abstract

Efficient multi-scale 3D CNN with fully connected CRF for accurate brain lesion segmentation

Cited by 2,949 publications

References 62 publications

Predicting brain age with deep learning from raw imaging data results in a reliable and heritable biomarker

Predicting brain age with deep learning from raw imaging data results in a reliable and heritable biomarker

Deep learning analysis of the myocardium in coronary CT angiography for identification of patients with functionally significant coronary artery stenosis

Tversky Loss Function for Image Segmentation Using 3D Fully Convolutional Deep Networks

Contact Info

Product

Resources

About