文章修改 以及 文献修改

[thebear213]

Introduction最后一段

but the traditional feature selection methods have great limitations. Nowadays, some people also use the deep learning method[18][19] to directly study medical images instead of firstly extracting features. In this way, our cross contrast neural networks choose

后面的文献编号，全部加2

其中添加的
18.
@Article{litjens2017survey,
title={A survey on deep learning in medical image analysis},
author={Litjens, Geert and Kooi, Thijs and Bejnordi, Babak Ehteshami and Setio, Arnaud Arindra Adiyoso and Ciompi, Francesco and Ghafoorian, Mohsen and van der Laak, Jeroen AWM and Van Ginneken, Bram and S{'a}nchez, Clara I},
journal={Medical image analysis},
volume={42},
pages={60--88},
year={2017},
publisher={Elsevier}
}

@misc{criminisi2016machine,
title={Machine learning for medical images analysis},
author={Criminisi, Antonio},
year={2016},
publisher={Elsevier}
}