Skip to main content

Table 4 Feature Extortion

From: The detection of lung cancer using massive artificial neural network based on soft tissue technique

S. No Feature Extortion Description
1 can.u Co-ordinates of a nodule candidate(horizontal)
2 can.v Co-ordinates of a nodule candidate(vertical)
3 can.Grad1 Co-ordinates of a nodule likelihood values
4 can.CV1 Computed by using gray level values
5 can.Grad2 Co-ordinates of a nodule likelihood values
6 can.CV2 Computed by using gray level values
7 Shape1 Area for a segmented nodule candidate(Aregion)
8 Shape2 Short and long axes of an ellipse which are robust to nodule candidate
9 Shape3 Aregion/Aconvex hull
10 Shape4 [dcandidate- center /squarero ot(Shape1/Л)]
11 Gray1 μregion – μsurround
The gray-level feature was estimated using fragmented candidates and their surrounding regions in both pre-processed image and nodule-enhanced image. A surrounding region was constructed by subtracting a candidate region from a dilated candidate region. μregion➔ Mean of a region
μsurround➔Mean
of a surrounding region
12 Gray2 σregion- σsurround
σregion➔Standard deviation of a region
σsurround➔Standard deviation of a surrounding region
13 Gray3 minregion-minsurround
minregion➔ Minimum value of a region
minsurround➔Minimum value of a surrounding region
14 Gray4 maxregion-maxsurround
maxregion ➔ Maximum value of a region
maxsurround➔Maximum value of a surrounding region
15 Gray5 Calculated using Gray1
16 Gray6 Calculated using Gray2
17 Gray7 Calculated using Gray3
18 Gray8 Calculated using Gray4
19 Grad1 \( \overline{\mathrm{Gr}}=\left(1/8\right)\sum \limits_{\mathrm{k}=0}^7{\mathrm{Gr}}^{\mathrm{h}} \)
\( {\displaystyle \begin{array}{c}{\mathrm{Gr}}^{\mathrm{h}}=\left[1/{\mathrm{N}}_{\mathrm{h}}\right]\sum \cos \kern0.28em {\alpha}_{\mathrm{mn}}\\ {}\mathrm{mn}\in {\mathrm{region}}_{\mathrm{h}}\\ {}{\mathrm{t}}_1\le {\mathrm{M}}_{\mathrm{mn}}\le {\mathrm{t}}_2\end{array}} \)
where Nh is number of pixels in segmented candidate area h and cos αmn denotes likelihood values used in two stage nodule enhancement method
20 Grad2 \( \upsigma =\surd \sum \limits_{\mathrm{k}=0}^7{\left({\mathrm{Gr}}^{\mathrm{h}}-\mathrm{Gr}\right)}^2 \)
21 Grad3 \( =\overline{\mathrm{Gr}}/\sigma \)
\( \overline{\mathrm{Gr}} \) denotes gradient feature
22 Surface1 λmin
Segmented candidate area in nodule enhanced image was robust to fourth order bivariate polynomial. The principal curvatures was computed at highest elevation point in the candidate region.
23 Surface2 λmax
24 Surface3 λmin λmax
25 Texture1 ∑ [C(i,j)2]
ij
C(i,j) ➔Co-occurrence matrix computed over neighboring pixel and a summation range from minimum to maximum pixel value in pre-processed image
26 Texture2 ∑ (i-j)2C(i,j)2
ij
C(i,j) ➔Co-occurrence matrix calculated over neighboring pixels and a summation range from the minimum to the maximum pixel value in the pre-processed image.
27 Texture3 Calculated based on Texture1 and Texture2
28 Texture4 Calculated based on Texture1 and Texture2
29 Texture5 Calculated based on Texture1 and Texture2
30 Texture6 Calculated based on Texture1 and Texture2
31 False Positive Loverlap / Lregion Where Lregion is length of boundary of a candidate area and Loverlap is number of pixels on boundary that overlap edge chain.