Moving Medical Image Analysis to GPU Embedded Systems: Application to Brain Tumor Segmentation

Figures & data

Table 1. Nvidia Jetson AGX Xavier specifications.

	Jetson AGX Xavier Module
CPU	8-core ARM v8.2 64-bit CPU, 8MB L2 + 4MB L3
GPU	512-core Volta GPU with Tensor Cores
Memory	16GB 256-Bit LPDDR4x | 137GB/s
Weight	630 grams
Dimension	100 mm x 87 mm x 16 mm
Storage	32GB eMMC 5.1

Figure 1. The Nvidia deep learning accelerator architecture. Nvdla.org.

Figure 2. Modified separable convolution block replacing each of the U-net regular and transposed convolutions.

Figure 3. Composition of a separable convolution block.

Figure 4. Our compressed U-net architecture. It consists of MobileNetV2-like separable convolution blocks coupled with max-pooling for downsampling in the encoding part of the network and bilinear upsampling in the decoding part.

Figure 5. Four sequences and ground truth of an LGG case and two HGG cases taken from the BRaTS 2015 dataset.

Table 2. Nvidia Jetson AGX Xavier power modes.

	MAXN	10 W	15 W	30W_ALL
CPU Cores	8	2	4	8
CPU Max Freq. (MHz)	1377	520	6700	900
GPU Max Freq. (MHz)	2265.6	1200	1200	1200
Memory Max Freq. (MHz)	2133.6	1066	1333	1600

Table 3. Results of our proposed approach compared to other similar deep learning based brain tumor segmentation methods.

	Dice Score
Method	Complete	Core	Enhancing
Proposed	0.81	0.77	0.53
Zhao (Zhao et al. 2018)	0.82	0.72	0.62
Pereira (Pereira et al. 2016)	0.84	0.72	0.62
Dong (Dong et al. 2017)	0.86	0.86	0.65

Figure 6. Example of tumor segmentation results. With a 128x128x4 input slice in A, its associated ground truth in B and the compressed model output in C.

Zhao, X., Y. Wu, G. Song, Z. Li, Y. Zhang, and Y. Fan. 2018. A deep learning model integrating fcnns and crfs for brain tumor seg- mentation. Medical Image Analysis 43:98–111. http://www.sciencedirect.com/science/article/pii/S136184151730141X.

 PubMed Web of Science ®Google Scholar

Pereira, S., A. Pinto, V. Alves, and C. A. Silva. May 2016. Brain tumor segmentation using convolutional neural networks in mri images. IEEE Transactions On Medical Imaging 35 (5):1240–51. doi: 10.1109/TMI.2016.2538465.

 PubMed Web of Science ®Google Scholar

Dong, H., G. Yang, F. Liu, Y. Mo, and Y. Guo. 2017. Automatic brain tumor detection and segmentation using u-net based fully convolutional networks. Medical Image Understanding and Analysis 506–17. https://doi.10.1007/978-3-319-60964-544

 Google Scholar