DiNTS: Differentiable Neural Network Topology Search for 3D Medical Image Segmentation
Recently, neural architecture search (NAS) has been applied to automatically search high-performance networks for medical image segmentation. The NAS search space usually contains a network topology level (controlling connections among cells with different spatial scales) and a cell level (operations within each cell). Existing methods either require long searching time for large-scale 3D image datasets, or are limited to pre-defined topologies (such as U-shaped or single-path). In this work, we focus on three important aspects of NAS in 3D medical image segmentation: flexible multi-path network topology, high search efficiency, and budgeted GPU memory usage. A novel differentiable search framework is proposed to support fast gradient-based search within a highly flexible network topology search space. The discretization of the searched optimal continuous model in differentiable scheme may produce a sub-optimal final discrete model (discretization gap). Therefore, we propose a topology loss to alleviate this problem. In addition, the GPU memory usage for the searched 3D model is limited with budget constraints during search. Our Differentiable Network Topology Search scheme (DiNTS) is evaluated on the Medical Segmentation Decathlon (MSD) challenge, which contains ten challenging segmentation tasks. Our method achieves the state-of-the-art performance and the top ranking on the MSD challenge leaderboard.
Code (1)
Tasks
GPUImage SegmentationMedical Image SegmentationNeural Architecture SearchSegmentationSemantic SegmentationSimilar Papers 제목 키워드 기반
DOTS: Decoupling Operation and Topology in Differentiable Architecture Search
Differentiable Architecture Search (DARTS) has attracted extensive attention due to its efficiency in searching for cell structures. DARTS mainly focuses on the operation search and derives the cell topology from the ope…
Cortex-Synth: Differentiable Topology-Aware 3D Skeleton Synthesis with Hierarchical Graph Attention
We present Cortex Synth, a novel end-to-end differentiable framework for joint 3D skeleton geometry and topology synthesis from single 2D images. Our architecture introduces three key innovations: (1) A hierarchical grap…
Explicit Learning Topology for Differentiable Neural Architecture Search
Differentiable neural architecture search (NAS) has gained much success in discovering more flexible and diverse cell types. Current methods couple the operations and topology during search, and simply derive optimal topo…
Neural Architecture SearchTopology-Preserving Deep Image Segmentation
Segmentation algorithms are prone to make topological errors on fine-scale structures, e.g., broken connections. We propose a novel method that learns to segment with correct topology. In particular, we design a continuo…
Image SegmentationSegmentationSemantic SegmentationManifold Topological Deep Learning for Biomedical Data
Recently, topological deep learning (TDL), which integrates algebraic topology with deep neural networks, has achieved tremendous success in processing point-cloud data, emerging as a promising paradigm in data science. …
Deep Learning