TY - GEN
T1 - Context-aware convolutional neural networks for stroke sign detection in non-contrast CT scans
AU - Lisowska, Aneta
AU - O’Neil, Alison
AU - Dilys, Vismantas
AU - Daykin, Matthew
AU - Beveridge, Erin
AU - Muir, Keith
AU - McLaughlin, Stephen
AU - Poole, Ian
PY - 2017/6/22
Y1 - 2017/6/22
N2 - Detection of acute stroke signs in non-contrast CT images is a challenging task. The intensity and texture variations in pathological regions are subtle and can be confounded by normal physiological changes or by old lesions. In this paper we investigate the use of contextual information for stroke sign detection. In particular, the appearance of the contralateral anatomy and the atlas-encoded spatial location are incorporated into a Convolutional Neural Network (CNN) architecture. CNNs are trained separately for the detection of dense vessels and of ischaemia. The network performance is evaluated on 170 datasets by cross-validation. We find that atlas location is important for dense vessel detection, but is less useful for ischaemia, whereas bilateral comparison is crucial for detection of ischaemia.
AB - Detection of acute stroke signs in non-contrast CT images is a challenging task. The intensity and texture variations in pathological regions are subtle and can be confounded by normal physiological changes or by old lesions. In this paper we investigate the use of contextual information for stroke sign detection. In particular, the appearance of the contralateral anatomy and the atlas-encoded spatial location are incorporated into a Convolutional Neural Network (CNN) architecture. CNNs are trained separately for the detection of dense vessels and of ischaemia. The network performance is evaluated on 170 datasets by cross-validation. We find that atlas location is important for dense vessel detection, but is less useful for ischaemia, whereas bilateral comparison is crucial for detection of ischaemia.
UR - http://www.scopus.com/inward/record.url?scp=85022204242&partnerID=8YFLogxK
U2 - 10.1007/978-3-319-60964-5_43
DO - 10.1007/978-3-319-60964-5_43
M3 - Conference contribution
AN - SCOPUS:85022204242
SN - 9783319609638
T3 - Communications in Computer and Information Science
SP - 494
EP - 505
BT - Medical Image Understanding and Analysis
A2 - Valdés Hernández, María
A2 - González-Castro, Víctor
PB - Springer
T2 - 21st Annual Conference on Medical Image Understanding and Analysis 2017
Y2 - 11 July 2017 through 13 July 2017
ER -