Name
Abstract | ||
|---|---|---|
We address the problem of instance label stability in multiple instance learning MIL classifiers. These classifiers are trained only on globally annotated images bags, but often can provide fine-grained annotations for image pixels or patches instances. This is interesting for computer aided diagnosis CAD and other medical image analysis tasks for which only a coarse labeling is provided. Unfortunately, the instance labels may be unstable. This means that a slight change in training data could potentially lead to abnormalities being detected in different parts of the image, which is undesirable from a CAD point of view. Despite MIL gaining popularity in the CAD literature, this issue has not yet been addressed. We investigate the stability of instance labels provided by several MIL classifiers on 5 different datasets, of which 3 are medical image datasets breast histopathology, diabetic retinopathy and computed tomography lung images. We propose an unsupervised measure to evaluate instance stability, and demonstrate that a performance-stability trade-off can be made when comparing MIL classifiers. |
Year | DOI | Venue |
|---|---|---|
2017 | 10.1007/978-3-319-24553-9_66 | Proceedings of the 18th International Conference on Medical Image Computing and Computer-Assisted Intervention -- MICCAI 2015 - Volume 9349 |
DocType | Volume | ISSN |
Journal | abs/1703.04986 | 0302-9743 |
Citations | PageRank | References |
2 | 0.38 | 16 |
Authors | ||
5 | ||
Name | Order | Citations | PageRank |
|---|---|---|---|
| Veronika Cheplygina | 1 | 171 | 15.31 |
| Lauge Sørensen | 2 | 215 | 17.78 |
| David M. J. Tax | 3 | 2071 | 148.87 |
| Marleen de Bruijne | 4 | 976 | 78.84 |
| Marco Loog | 5 | 1796 | 154.31 |