Fig. 1. Flow chart of GAN

Fig. 2. Framework of SSGAN

Fig. 3. Generation network structure of SSGAN

Fig. 4. Structure of discriminator D in SSGAN

Fig. 5. Training sample images

Fig. 6. Comparison of histogram equalization images. (a)(b)(c) Original X-ray images; (d)(e)(f) histogram equalization X-ray images

Fig. 7. Variaiton of loss function. (a) Loss of discriminator network; (b) loss of generator network

Fig. 8. Trend of classification results for samples with different number of labeled data

Fig. 9. Generated images of SSGAN and original images. (a) Generated images; (b) original images