V-NAS: Neural Architecture Search for Volumetric Medical Image Segmentation
This addresses the challenge of balancing spatial information and computational efficiency in medical image segmentation for healthcare applications, though it is incremental as it builds on existing neural architecture search techniques.
The paper tackled the problem of volumetric medical image segmentation by proposing V-NAS, a neural architecture search method that automatically chooses between 2D, 3D, or Pseudo-3D convolutions, resulting in consistent outperformance of state-of-the-art methods on public datasets like NIH Pancreas and MSD Lung and Pancreas tumors.
Deep learning algorithms, in particular 2D and 3D fully convolutional neural networks (FCNs), have rapidly become the mainstream methodology for volumetric medical image segmentation. However, 2D convolutions cannot fully leverage the rich spatial information along the third axis, while 3D convolutions suffer from the demanding computation and high GPU memory consumption. In this paper, we propose to automatically search the network architecture tailoring to volumetric medical image segmentation problem. Concretely, we formulate the structure learning as differentiable neural architecture search, and let the network itself choose between 2D, 3D or Pseudo-3D (P3D) convolutions at each layer. We evaluate our method on 3 public datasets, i.e., the NIH Pancreas dataset, the Lung and Pancreas dataset from the Medical Segmentation Decathlon (MSD) Challenge. Our method, named V-NAS, consistently outperforms other state-of-the-arts on the segmentation task of both normal organ (NIH Pancreas) and abnormal organs (MSD Lung tumors and MSD Pancreas tumors), which shows the power of chosen architecture. Moreover, the searched architecture on one dataset can be well generalized to other datasets, which demonstrates the robustness and practical use of our proposed method.