Efficient neural architecture search on low-dimensional data for OCT image segmentation

Typically, deep learning architectures are handcrafted for their respective learning problem. As an alternative, neural architecture search (NAS) has been proposed where the architectureś structure is learned in an additional optimization step. For the medical imaging domain, this approach is very promising as there are diverse problems and imaging modalities that require architecture design. However, NAS is very time-consuming and medical learning problems often involve high-dimensional data with high computational requirements. We propose an efficient approach for NAS in the context of medical, image-based deep learning problems by searching for architectures on low-dimensional data which are subsequently transferred to high-dimensional data. For OCT-based layer segmentation, we demonstrate that a search on 1D data reduces search time by 87.5% compared to a search on 2D data while the final 2D models achieve similar performance

DDC Class

004: Informatik

600: Technik

610: Medizin

More Funding Information

TUHH I3-Labs initiative

Lizenz

https://creativecommons.org/licenses/by/4.0/

Name

efficient_neural_architecture_search_on_low_dimensional_data_for_oct_image_segmentation.pdf

Size

234.84 KB

Format

Adobe PDF

Options

Efficient neural architecture search on low-dimensional data for OCT image segmentation