HASA: Hybrid Architecture Search with Aggregation Strategy for Echinococcosis Classification and Ovary Segmentation in Ultrasound Images
This work addresses the computational cost and instability of neural architecture search for medical imaging applications, specifically ultrasound analysis of echinococcosis and ovaries.
The authors tackled the problem of automating network architecture design for ultrasound image analysis by proposing a hybrid neural architecture search framework that combines pre-trained backbones with searched cells. Their method achieved state-of-the-art performance on echinococcosis classification (9 classes, 9566 images) and ovary segmentation (3204 images) tasks while reducing model parameters.
Different from handcrafted features, deep neural networks can automatically learn task-specific features from data. Due to this data-driven nature, they have achieved remarkable success in various areas. However, manual design and selection of suitable network architectures are time-consuming and require substantial effort of human experts. To address this problem, researchers have proposed neural architecture search (NAS) algorithms which can automatically generate network architectures but suffer from heavy computational cost and instability if searching from scratch. In this paper, we propose a hybrid NAS framework for ultrasound (US) image classification and segmentation. The hybrid framework consists of a pre-trained backbone and several searched cells (i.e., network building blocks), which takes advantage of the strengths of both NAS and the expert knowledge from existing convolutional neural networks. Specifically, two effective and lightweight operations, a mixed depth-wise convolution operator and a squeeze-and-excitation block, are introduced into the candidate operations to enhance the variety and capacity of the searched cells. These two operations not only decrease model parameters but also boost network performance. Moreover, we propose a re-aggregation strategy for the searched cells, aiming to further improve the performance for different vision tasks. We tested our method on two large US image datasets, including a 9-class echinococcosis dataset containing 9566 images for classification and an ovary dataset containing 3204 images for segmentation. Ablation experiments and comparison with other handcrafted or automatically searched architectures demonstrate that our method can generate more powerful and lightweight models for the above US image classification and segmentation tasks.