Desktop version

Home arrow Engineering arrow Cellular Image Classification

Experimental Results on the ICIP2013 Training Dataset

Based on the ICIP2013 training dataset, the classification performance of different algorithms at the cell level and the image level is shown in Table 5.4. Our proposed LLDC method achieves the best performance. Particularly, LLC-(sift+ldv) can achieve better classification performance than LSC-(sift+ldv). In summary, LLC- related features perform better for the ICIP2013 training dataset while LSC-related features is more suitable for the ICPR2012 dataset.

Table 5.5 shows the confusion matrix at the cell level by the proposed LLDC method using the LLC strategy on the concatenated image representation. Nuclear membrane pattern gets the highest classification accuracy rate, followed by homogeneous pattern as they have distinguished characteristic compared with other patterns. Golgi pattern is often mistaken for nucleolar pattern, because some golgi pattern have large speckles within the nucleoli while some only have several cluster of irregular granules, which is just similar to nucleolar pattern. Table5.6 illustrates the confusion matrix at the image level. The proposed LLDC method obtains the classification accuracy of 90.2 % at the image level, which means that 37 slide images are correctly identified while there are 41 slide images in the test set. Nucleolar and nuclear membrane patterns particularly obtain 100% of the image-level accuracy. It is evident that golgi pattern is wrongly classified as nucleolar, which is very common at the cell level.

ho (%)

sp (%)

nu (%)

ce (%)

nm (%)

go (%)

ho

84.6

11.4

2.2

0.0

1.6

0.2

sp

  • 00

73.9

7.8

8.4

0.8

0.3

nu

1.4

5.1

80.5

6.6

3.2

3.2

ce

1.7

15.9

2.4

79.9

0.1

0.0

nm

3.7

4.5

0.6

0.5

87.0

3.7

go

7.7

1.4

35.6

0.3

3.9

51.1

Table 5.6 The confusion matrix for the image level classification on the ICIP2013 training dataset

ho (%)

sp (%)

nu (%)

ce (%)

nm (%)

go (%)

ho

87.5

12.5

0.0

0.0

0.0

0.0

sp

0.0

87.5

0.0

12.5

0.0

0.0

nu

0.0

0.0

100.0

0.0

0.0

0.0

ce

0.0

12.5

0.0

87.5

0.0

0.0

nm

0.0

0.0

0.0

0.0

100.0

0.0

go

0.0

0.0

50.0

0.0

0.0

50.0

 
Source
< Prev   CONTENTS   Source   Next >

Related topics