We investigate the impacts of objective functions on the performance of deep-learning-based prostate magnetic resonance image segmentation. To this end, we first develop a baseline convolutional neural network (BCNN) for the prostate image segmentation, which consists of encoding, bridge, decoding, and classification modules. In the BCNN, we use 3D convolutional layers to consider volumetric information. Also, we adopt the residual feature forwarding and intermediate feature propagation techniques to make the BCNN reliably trainable for various objective functions. We compare six objective functions: Hamming distance, Euclidean distance, Jaccard index, dice coefficient, cosine similarity, and cross entropy. Experimental results on the PROMISE12 dataset demonstrate that the cosine similarity provides the best segmentation performance, whereas the cross entropy performs the worst.
|Title of host publication||2017 IEEE International Conference on Image Processing, ICIP 2017 - Proceedings|
|Publisher||IEEE Computer Society|
|Number of pages||5|
|Publication status||Published - 2017 Jul 2|
|Event||24th IEEE International Conference on Image Processing, ICIP 2017 - Beijing, China|
Duration: 2017 Sept 17 → 2017 Sept 20
|Name||Proceedings - International Conference on Image Processing, ICIP|
|Other||24th IEEE International Conference on Image Processing, ICIP 2017|
|Period||17/9/17 → 17/9/20|
Bibliographical noteFunding Information:
This work was supported partly by the National Research Foundation of Korea(NRF) grant funded by the Korea government(MSIP)(No. NRF-2015R1A2A1A10055037), and partly by the Agency for Defense Development (ADD) and Defense Acquisition Program Administration (DAPA) of Korea (UC160016FD).
© 2017 IEEE.
- 3D convolutional neural networks
- Medical image segmentation
- Objective functions
- Prostate segmentation
ASJC Scopus subject areas
- Computer Vision and Pattern Recognition
- Signal Processing