Combining seeded region growing and k-nearest neighbours for the segmentation of routinely acquired spatio-temporal image data

ConclusionsA Dice ’s coefficient of 0.80 for the area segmentation does not seem perfect. However, there are two main factors, besides true prediction errors, lowering the score: Segmentation mistakes on small areas lead to a rapid decrease in the score and labelling errors due to complex data. However, in combinat ion with the light-polluted data set and pollution area detection, these results can be considered successful and play a key role in our general goal: Exploiting NIR-FOI for the early detection of arthritis within hand joints.
Source: International Journal of Computer Assisted Radiology and Surgery - Category: Intensive Care Source Type: research