2.3 Merge Texture Features
Deep neural network can directly classify images, but it does not use the underlying
features of images. Considering that there are a large number of underlying features
such as texture in medical images, this paper integrates the original image and texture
features and then sends them into the deep neural network for classification.
2.3.1 Extract the LBP Texture Features of the Image
The local binary mode is a texture metric in the gray range. In order to improve the
limitations of the original LBP, it is impossible to extract the texture features of largesize structures. Ojala et al. [7] modified the LBP to obtain the LBP value that uniquely
represents the local texture features:
LBP P;R ¼
X PÀ1
i¼0
s g i À g c
ð
Þ2
i
ð1Þ
where SðÁÞ is defined as:
s(x) ¼
1; x ! 0
0; x\0
ð2Þ
Fig. 3. DenseNet structure
Abnormality Diagnosis of Musculoskeletal Radiographs Combined …
483