Skip to main content

Advertisement

Table 4 Mean Structural Similarity (MSSIM) before and after the BAE algorithm processing

From: An artifacts removal post-processing for epiphyseal region-of-interest (EROI) localization in automated bone age assessment (BAA)

Bands MSSIM Bands MSSIM
Row Column Before After Row Column Before After
2 2-10 0.8345 0.9324 11 2-10 0.8640 0.9223
3 2-10 0.8423 0.9431 12 2-10 0.8595 0.9343
4 2-10 0.8355 0.9341 13 2-10 0.8420 0.9243
5 2-10 0.8785 0.9125 14 2-10 0.8298 0.9089
6 2-10 0.8523 0.9256 15 2-10 0.8482 0.9423
7 2-10 0.8397 0.9543 16 2-10 0.8210 0.9432
8 2-10 0.8450 0.9354 17 2-10 0.8323 0.9502
9 2-10 0.8574 0.9445 18 2-10 0.8489 0.9357
10 2-10 0.8259 0.9213 19 2-10 0.8518 0.9389
  1. This table compares the MSSIM of each image tested in previous table 3 to evaluate the structural preserving ability of BAE. The result shows that the MSSIM before BAE algorithm is consistently lower than the MSSIM after performing BAE algorithm. This indicates that the BAE algorithm has contributed in preserving detail of the image. The MSSIM is improved averagely 10.49% after performing the BAE algorithm on the adaptive segmented hand radiograph.