UXNet: Searching Multi-level Feature Aggregation for 3D Medical Image Segmentation

by   Yuanfeng Ji, et al.

Aggregating multi-level feature representation plays a critical role in achieving robust volumetric medical image segmentation, which is important for the auxiliary diagnosis and treatment. Unlike the recent neural architecture search (NAS) methods that typically searched the optimal operators in each network layer, but missed a good strategy to search for feature aggregations, this paper proposes a novel NAS method for 3D medical image segmentation, named UXNet, which searches both the scale-wise feature aggregation strategies as well as the block-wise operators in the encoder-decoder network. UXNet has several appealing benefits. (1) It significantly improves flexibility of the classical UNet architecture, which only aggregates feature representations of encoder and decoder in equivalent resolution. (2) A continuous relaxation of UXNet is carefully designed, enabling its searching scheme performed in an efficient differentiable manner. (3) Extensive experiments demonstrate the effectiveness of UXNet compared with recent NAS methods for medical image segmentation. The architecture discovered by UXNet outperforms existing state-of-the-art models in terms of Dice on several public 3D medical image segmentation benchmarks, especially for the boundary locations and tiny tissues. The searching computational complexity of UXNet is cheap, enabling to search a network with the best performance less than 1.5 days on two TitanXP GPUs.


Scalable Neural Architecture Search for 3D Medical Image Segmentation

In this paper, a neural architecture search (NAS) framework is proposed ...

Mixed-Block Neural Architecture Search for Medical Image Segmentation

Deep Neural Networks (DNNs) have the potential for making various clinic...

Resource Optimized Neural Architecture Search for 3D Medical Image Segmentation

Neural Architecture Search (NAS), a framework which automates the task o...

V-NAS: Neural Architecture Search for Volumetric Medical Image Segmentation

Deep learning algorithms, in particular 2D and 3D fully convolutional ne...

DiNTS: Differentiable Neural Network Topology Search for 3D Medical Image Segmentation

Recently, neural architecture search (NAS) has been applied to automatic...

Leveraging Image Complexity in Macro-Level Neural Network Design for Medical Image Segmentation

Recent progress in encoder-decoder neural network architecture design ha...

Voxel-level Siamese Representation Learning for Abdominal Multi-Organ Segmentation

Recent works in medical image segmentation have actively explored variou...