DLTK: State of the Art Reference Implementations for Deep Learning on Medical Images

File Description SizeFormat 
1711.06853v1.pdfAccepted version487.3 kBAdobe PDFView/Open
Title: DLTK: State of the Art Reference Implementations for Deep Learning on Medical Images
Authors: Pawlowski, N
Ktena, SI
Lee, MCH
Kainz, B
Rueckert, D
Glocker, B
Rajchl, M
Item Type: Working Paper
Abstract: We present DLTK, a toolkit providing baseline implementations for efficient experimentation with deep learning methods on biomedical images. It builds on top of TensorFlow and its high modularity and easy-to-use examples allow for a low-threshold access to state-of-the-art implementations for typical medical imaging problems. A comparison of DLTK's reference implementations of popular network architectures for image segmentation demonstrates new top performance on the publicly available challenge data "Multi-Atlas Labeling Beyond the Cranial Vault". The average test Dice similarity coefficient of $81.5$ exceeds the previously best performing CNN ($75.7$) and the accuracy of the challenge winning method ($79.0$).
Issue Date: 31-Dec-2017
URI: http://hdl.handle.net/10044/1/54699
Copyright Statement: © The Authors
Sponsor/Funder: Microsoft Reseach
NVIDIA Corporation
Imperial College London
Funder's Grant Number: Imperial College Research Fellowship
Keywords: cs.CV
cs.LG
Notes: Submitted to Medical Imaging Meets NIPS 2017, Code at https://github.com/DLTK/DLTK
Appears in Collections:Faculty of Engineering
Computing
Department of Medicine
Faculty of Medicine



Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.

Creative Commons