Name
Abstract | ||
|---|---|---|
HighlightsA new method for identifying fat droplets in histological images is presented.Adjacency statistics are utilized as shape features.Fat droplets are identified with high sensitivity and specificity.Adjacency statistics greatly improve the identification of clustered fat droplets.The method can be quickly executed on standard computers. Background and objectiveThe accurate identification of fat droplets is a prerequisite for the automatic quantification of steatosis in histological images. A major challenge in this regard is the distinction between clustered fat droplets and vessels or tissue cracks. MethodsWe present a new method for the identification of fat droplets that utilizes adjacency statistics as shape features. Adjacency statistics are simple statistics on neighbor pixels. ResultsThe method accurately identified fat droplets with sensitivity and specificity values above 90%. Compared with commonly-used shape features, adjacency statistics greatly improved the sensitivity toward clustered fat droplets by 29% and the specificity by 17%. On a standard personal computer, megapixel images were processed in less than 0.05s. ConclusionsThe presented method is simple to implement and can provide the basis for the fast and accurate quantification of steatosis. |
Year | DOI | Venue |
|---|---|---|
2015 | 10.1016/j.cmpb.2015.05.009 | Computer Methods and Programs in Biomedicine |
Keywords | Field | DocType |
Steatosis quantification,Histological image analysis,Shape features,Texture features | Adjacency list,Computer vision,Computer science,Personal computer,Artificial intelligence,Pixel | Journal |
Volume | Issue | ISSN |
121 | 2 | 0169-2607 |
Citations | PageRank | References |
1 | 0.37 | 4 |
Authors | ||
6 | ||
Name | Order | Citations | PageRank |
|---|---|---|---|
| André Homeyer | 1 | 53 | 6.60 |
| Andrea Schenk | 2 | 310 | 31.12 |
| Janine Arlt | 3 | 6 | 1.68 |
| Uta Dahmen | 4 | 23 | 4.84 |
| Olaf Dirsch | 5 | 19 | 2.97 |
| Horst K. Hahn | 6 | 450 | 72.61 |