Abstract | ||
---|---|---|
Accurate automatic algorithms for the segmentation of brain tumours have the potential of improving disease diagnosis, treatment planning, as well as enabling large-scale studies of the pathology. In this work we employ DeepMedic [1], a 3D CNN architecture previously presented for lesion segmentation, which we further improve by adding residual connections. We also present a series of experiments on the BRATS 2015 training database for evaluating the robustness of the network when less training data are available or less filters are used, aiming to shed some light on requirements for employing such a system. Our method was further benchmarked on the BRATS 2016 Challenge, where it achieved very good performance despite the simplicity of the pipeline. |
Year | DOI | Venue |
---|---|---|
2016 | 10.1007/978-3-319-55524-9_14 | Lecture Notes in Computer Science |
Field | DocType | Volume |
Conditional random field,Training set,Residual,Pattern recognition,Convolutional neural network,Segmentation,Computer science,Brain tumor segmentation,Robustness (computer science),Artificial intelligence,Lesion segmentation | Conference | 10154 |
ISSN | Citations | PageRank |
0302-9743 | 3 | 0.40 |
References | Authors | |
0 | 8 |
Name | Order | Citations | PageRank |
---|---|---|---|
Konstantinos Kamnitsas | 1 | 361 | 15.18 |
Enzo Ferrante | 2 | 174 | 13.61 |
Sarah Parisot | 3 | 147 | 14.13 |
Christian Ledig | 4 | 489 | 27.08 |
Aditya V. Nori | 5 | 945 | 50.97 |
Antonio Criminisi | 6 | 6801 | 394.29 |
Daniel Rueckert | 7 | 9338 | 637.58 |
Ben Glocker | 8 | 2157 | 119.81 |