Computational Analysis and Deep Learning for Medical Care. Группа авторов

Чтение книги онлайн.

СКАЧАТЬ achieves 90.64%. DenseNET produces approximately similar segmentations based on MASD, Mean Localisation Distance (MLD), and Mean Dice Similarity Coefficient (MDSC). Comparison result is shown in Table 1.12.

1.5 Conclusion

      In this Chapter, we had discussed about the various CNN architectural models and its parameters. In the first phase, various architectures such as LeNet, AlexNet, VGGnet, GoogleNet, ResNet, ResNeXt, SENet, and DenseNet and MobileNet are studied. In the second phase, the application of CNN for the segmentation of IVD is presented. The comparison with state-of-the-art of segmentation approaches for spine T2W images are also presented. From the experimental results, it is clear that 2.5D multi-scale FCN outperforms all other models. As a future study, this work modify any currents models to get optimized results.

Table 1.10 Comparison of DenseNet.

Figure 1.11 Architecture of MobileNets.

Table 1.11 Various parameters of MobileNets.

Type/Stride	Filter shape	Input size
Conv / s2	3 × 3 × 3 × 32	224 × 224 × 3
Conv dw / s1	3 × 3 × 32 dw	112 × 112 × 32
Conv / s1	1 × 1 × 32 × 64	112 × 112 × 32
Conv dw / s2	3 × 3 × 64 dw	112 × 112 × 64
Conv / s1	1 × 1 × 64 × 128	56 × 56 × 64
Conv dw / s1	3 × 3 × 128 dw	56 × 56 × 128
Conv / s1	1 × 1 × 128 × 128	56 × 56 × 128
Conv dw / s2	3 × 3 × 128 dw	56 × 56 × 128
Conv / s1	1 × 1 × 1 × 128 × 256	28 × 28 × 128
Conv dw / s1	3 × 3 × 256 dw	28 × 28 × 256
Conv / s1	1 × 1 × 256 × 256	28 × 28 × 256
Conv dw / s2	3 × 3 × 256 dw	28 × 28 × 256
Conv / s1	1 × 1 × 256 × 512	14 × 14 × 256
5 × Conv dw / s1 Conv / s1	3 × 3 × 512 dw	14 × 14 × 512
	1 × 1 × 512 × 512	14 × 14 × 512
Conv dw / s2	3 × 3 × 512 dw	14 × 14 × 512
Conv / s1	1 × 1 × 512 × 1024	7 × 7 × 512
Conv dw / s2	3 × 3 × 1,024 dw	7 × 7 × 1,024
Conv / s1	1 × 1 × 1,024 × 1024	7 × 7 × 1,024
Avg Pool / s1	Pool 7 × 7	7 × 7 × 1,024
FC / s1	1024 × 1,000	1 × 1 × 1,024
Softmax / s1	Classifier	1 × 1 × 1,000

Table 1.12 State-of-art of spine segmentation approaches.

Author	Method/Algorithm	Parameters
Mader [11]	V-Net	MDSC (%) = 89.4MASD (mm) = 0.45
Bateson [12]	Constrained domain adaptation employ ENet	MDSC (%) = 81.1HD (mm) = 1.09
Zeng [13]	CNN	MDSC (%)= 90.64MASD (mm) = 0.60
Chang Liu [14]	2.5D multi-scale FCN	MDSC (%) = 90.64MASD (mm) = 0.60MLD (mm) = 0.77
Gao [15]	2D CNN, DenseNet	MDSC (%) = 90.58MASD (mm) = 0.61MLD (mm) = 0.78
Jose [17]	HD-UNet asym	MDSC (%) = 89.67MASD (mm) = 0.65MLD (mm) = 0.964
Claudia Iriondo [16]	VNet-based 3D connected component analysis	MDSC (%) = 89.71MASD (mm) = 0.74MLD (mm) = 0.86

References

      1. LeCun, Y., Bottou, L., Bengio, Y., Haffner, P., Gradient-based learning applied to document recognition. Proc. IEEE, 86, 11, 2278–2323, 1998.

      2. Krizhevsky, A., Sutskever, I., Hinton, G.E., ImageNet classification with deep convolutional neural networks. Commun. ACM, 60, 6, СКАЧАТЬ