Name
Title | ||
|---|---|---|
Assessment of the relationship between lesion segmentation accuracy and computer-aided diagnosis scheme performance |
Abstract | ||
|---|---|---|
In this study we randomly select 250 malignant and 250 benign mass regions as a training dataset. The boundary contours of these regions were manually identified and marked. Twelve image features were computed for each region. An artificial neural network (ANN) was trained as a classifier. To select a specific testing dataset, we applied a topographic multi-layer region growth algorithm to detect boundary contours of 1,903 mass regions in an initial pool of testing regions. All processed regions are sorted based on a size difference ratio between manual and automated segmentation. We selected a testing dataset involving 250 malignant and 250 benign mass regions with larger size difference ratios. Using the area under ROC curve (A(Z) value) as performance index we investigated the relationship between the accuracy of mass segmentation and the performance of a computer-aided diagnosis (CAD) scheme. CAD performance degrades as the size difference ratio increases. Then, we developed and tested a hybrid region growth algorithm that combined the topographic region growth with an active contour approach. In this hybrid algorithm, the boundary contour detected by the topographic region growth is used as the initial contour of the active contour algorithm. The algorithm iteratively searches for the optimal region boundaries. A CAD likelihood score of the growth region being a true-positive mass is computed in each iteration. The region growth is automatically terminated once the first maximum CAD score is reached. This hybrid region growth algorithm reduces the size difference ratios between two areas segmented automatically and manually to less than +/- 15% for all testing regions and the testing A(Z) value increases to from 0.63 to 0.90. The results indicate that CAD performance heavily depends on the accuracy of mass segmentation. In order to achieve robust CAD performance, reducing lesion segmentation error is important. |
Year | DOI | Venue |
|---|---|---|
2008 | 10.1117/12.768705 | PROCEEDINGS OF THE SOCIETY OF PHOTO-OPTICAL INSTRUMENTATION ENGINEERS (SPIE) |
Keywords | Field | DocType |
computer-aided diagnosis,region growth,active contour algorithm,mammography,performance assessment | Active contour model,CAD,Computer vision,Hybrid algorithm,Pattern recognition,Segmentation,Feature (computer vision),Topographic map,Computer science,Computer-aided diagnosis,Image processing,Artificial intelligence | Conference |
Volume | ISSN | Citations |
6915 | 0277-786X | 2 |
PageRank | References | Authors |
0.42 | 4 | 5 |
Name | Order | Citations | PageRank |
|---|---|---|---|
| Bin Zheng | 1 | 135 | 28.83 |
| Jiantao Pu | 2 | 277 | 23.12 |
| Sang Cheol Park | 3 | 154 | 10.39 |
| margarita l zuley | 4 | 2 | 2.78 |
| David Gur | 5 | 120 | 31.52 |