Segmentation of intracranial arterial calcification with deeply supervised residual dropout networks

TY - GEN

T1 - Segmentation of intracranial arterial calcification with deeply supervised residual dropout networks

AU - Bortsova, Gerda

AU - van Tulder, Gijs

AU - Dubost, Florian

AU - Peng, Tingying

AU - Navab, Nassir

AU - van der Lugt, Aad

AU - Bos, Daniel

AU - de Bruijne, Marleen

N1 - Conference code: 20

PY - 2017

Y1 - 2017

N2 - Intracranial carotid artery calcification (ICAC) is a major risk factor for stroke, and might contribute to dementia and cognitive decline. Reliance on time-consuming manual annotation of ICAC hampers much demanded further research into the relationship between ICAC and neurological diseases. Automation of ICAC segmentation is therefore highly desirable, but difficult due to the proximity of the lesions to bony structures with a similar attenuation coefficient. In this paper, we propose a method for automatic segmentation of ICAC; the first to our knowledge. Our method is based on a 3D fully convolutional neural network that we extend with two regularization techniques. Firstly, we use deep supervision to encourage discriminative features in the hidden layers. Secondly, we augment the network with skip connections, as in the recently developed ResNet, and dropout layers, inserted in a way that skip connections circumvent them. We investigate the effect of skip connections and dropout. In addition, we propose a simple problem-specific modification of the network objective function that restricts the focus to the most important image regions and simplifies the optimization. We train and validate our model using 882 CT scans and test on 1,000. Our regularization techniques and objective improve the average Dice score by 7.1%, yielding an average Dice of 76.2% and 97.7% correlation between predicted ICAC volumes and manual annotations.

AB - Intracranial carotid artery calcification (ICAC) is a major risk factor for stroke, and might contribute to dementia and cognitive decline. Reliance on time-consuming manual annotation of ICAC hampers much demanded further research into the relationship between ICAC and neurological diseases. Automation of ICAC segmentation is therefore highly desirable, but difficult due to the proximity of the lesions to bony structures with a similar attenuation coefficient. In this paper, we propose a method for automatic segmentation of ICAC; the first to our knowledge. Our method is based on a 3D fully convolutional neural network that we extend with two regularization techniques. Firstly, we use deep supervision to encourage discriminative features in the hidden layers. Secondly, we augment the network with skip connections, as in the recently developed ResNet, and dropout layers, inserted in a way that skip connections circumvent them. We investigate the effect of skip connections and dropout. In addition, we propose a simple problem-specific modification of the network objective function that restricts the focus to the most important image regions and simplifies the optimization. We train and validate our model using 882 CT scans and test on 1,000. Our regularization techniques and objective improve the average Dice score by 7.1%, yielding an average Dice of 76.2% and 97.7% correlation between predicted ICAC volumes and manual annotations.

KW - Calcium scoring

KW - Deep learning

KW - Deep supervision

KW - Dropout

KW - Intracranial calcifications

KW - Residual networks

U2 - 10.1007/978-3-319-66179-7_41

DO - 10.1007/978-3-319-66179-7_41

M3 - Article in proceedings

AN - SCOPUS:85029535684

SN - 978-3-319-66178-0

T3 - Lecture notes in computer science

SP - 356

EP - 364

BT - Medical Image Computing and Computer-Assisted Intervention − MICCAI 2017

A2 - Descoteaux, Maxime

A2 - Maier-Hein, Lena

A2 - Franz, Alfred

A2 - Jannin, Pierre

A2 - Collins, D. Louis

A2 - Duchesne, Simon

PB - Springer

T2 - 20th International Conference on Medical Image Computing and Computer-Assisted Intervention

Y2 - 11 September 2017 through 13 September 2017

ER -