Object Segmentation with Deep Neural Nets Coupled with a Shape Prior, When Learning From a Training set of Limited Quality and Small Size
| Autor: | Suyash P. Awate, Saurabh J. Shigwan, Akshay V. Gaikwad |
|---|---|
| Rok vydání: | 2020 |
| Předmět: |
Training set
Artificial neural network Computer science business.industry media_common.quotation_subject Pattern recognition Object (computer science) 030218 nuclear medicine & medical imaging 03 medical and health sciences 0302 clinical medicine Quality (business) Segmentation State (computer science) Artificial intelligence business 030217 neurology & neurosurgery media_common |
| Zdroj: | ISBI |
| DOI: | 10.1109/isbi45749.2020.9098496 |
| Popis: | Statistical shape priors can be crucial in segmenting objects when the data differentiates poorly between the object and its surroundings. For reliable learning, while some methods need high-quality expert segmentations, other methods need large training sets, both of which can often be difficult to obtain in clinical deployment or scientific studies. We propose to couple deep neural networks with a pointset-based shape prior that can be learned effectively despite training sets having small size and imperfections in expert curation. The prior relies on sparse Riemannian modeling in Kendall shape space. Results on clinical brain magnetic resonance imaging data show that our framework improves over the state of the art in segmenting the thalamus and the caudate. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|