Title | ||
---|---|---|
Nonlinear Adaptively Learned Optimization For Object Localization In 3d Medical Images |
Abstract | ||
---|---|---|
Precise localization of anatomical structures in 3D medical images can support several tasks such as image registration, organ segmentation, lesion quantification and abnormality detection. This work proposes a novel method, based on deep reinforcement learning, to actively learn to localize an object in the volumetric scene. Given the parameterization of the sought object, an intelligent agent learns to optimize the parameters by performing a sequence of simple control actions. We show the applicability of our method by localizing boxes (9 degrees of freedom) on a set of acquired MRI scans of the brain region. We achieve high speed and high accuracy detection results, with robustness to challenging cases. This method can be applied to a broad range of problems and easily generalized to other type of imaging modalities. |
Year | DOI | Venue |
---|---|---|
2018 | 10.1007/978-3-030-00889-5_29 | DEEP LEARNING IN MEDICAL IMAGE ANALYSIS AND MULTIMODAL LEARNING FOR CLINICAL DECISION SUPPORT, DLMIA 2018 |
Keywords | Field | DocType |
Deep reinforcement learning, Nonlinear parameter optimization, 3D medical images, Object localization | Computer vision,Intelligent agent,Nonlinear system,Segmentation,Computer science,Robustness (computer science),Artificial intelligence,Anatomical structures,Abnormality detection,Image registration,Reinforcement learning | Conference |
Volume | ISSN | Citations |
11045 | 0302-9743 | 0 |
PageRank | References | Authors |
0.34 | 0 | 9 |
Name | Order | Citations | PageRank |
---|---|---|---|
Mayalen Etcheverry | 1 | 0 | 1.01 |
Bogdan Georgescu | 2 | 1638 | 138.49 |
Benjamin L. Odry | 3 | 3 | 0.82 |
Thomas J. Re | 4 | 0 | 0.34 |
Shivam Kaushik | 5 | 0 | 0.34 |
Bernhard Geiger | 6 | 0 | 0.34 |
Mariappan S. Nadar | 7 | 77 | 10.18 |
Sasa Grbic | 8 | 82 | 13.77 |
Dorin Comaniciu | 9 | 8389 | 601.83 |