Share Email Print

Proceedings Paper

Assessment of optimal deep learning configuration for vertebrae segmentation from CT images
Author(s): Sandeep Dutta; Bipul Das; Sandeep Kaushik
Format Member Price Non-Member Price
PDF $17.00 $21.00

Paper Abstract

Automated segmentation of vertebral bone from diagnostic Computed Tomography (CT) images has become an important part of clinical workflow today. There is an increasing need for computer aided diagnosis applications of various spine disorders including scoliosis, fracture detection and even automated reporting. While modelbased methods have been widely used, recent deep Learning methods have shown a great potential in this area. However, choice of optimal configuration of the network to get the best segmentation performance is challenging. In this work, we explore the impact of different training and inference options, including dimensions, activation function, batch normalization, kernel size, filters, patch size and patch selection strategy in U-Net architecture. 20 publicly available CT Spine datasets from Spineweb repository was used in this study divided into training/test datasets. Training with different DL configurations were repeated with these datasets. We used the best weights corresponding to each configuration for inference on the independent test dataset. These results on the test dataset with the best weights for each configurations were compared. 3D models performed consistently better than 2D approaches. Overlapped patch based inference had a big impact on enhancing performance accuracy. The selection of training patch size was also found to be crucial in improving the model performance. Moreover, the need for an effective balance of positive and negative training patches was found. The best performance in our study was obtained by using overlapped patch inference, training with RELU activation and batch normalization in a 3D U-Net architecture with training patch size of 128×128×32 that resulted in average values of precision= 97%, sensitivity= 96% and F1 (Dice)= 96% for the test dataset.

Paper Details

Date Published: 15 March 2019
PDF: 8 pages
Proc. SPIE 10954, Medical Imaging 2019: Imaging Informatics for Healthcare, Research, and Applications, 109541A (15 March 2019); doi: 10.1117/12.2512636
Show Author Affiliations
Sandeep Dutta, GE Healthcare (United States)
Bipul Das, GE Global Research (India)
Sandeep Kaushik, GE Global Research (India)

Published in SPIE Proceedings Vol. 10954:
Medical Imaging 2019: Imaging Informatics for Healthcare, Research, and Applications
Po-Hao Chen; Peter R. Bak, Editor(s)

© SPIE. Terms of Use
Back to Top
Sign in to read the full article
Create a free SPIE account to get access to
premium articles and original research
Forgot your username?