T-AutoML: Automated Machine Learning for Lesion Segmentation using Transformers in 3D Medical Imaging

TL;DR

This paper introduces T-AutoML, an automated machine learning framework that uses transformers to optimize neural architecture, hyper-parameters, and data augmentation for lesion segmentation in 3D medical imaging, achieving state-of-the-art results.

Contribution

The paper presents a novel T-AutoML method that automates the design of neural networks, hyper-parameters, and data augmentation strategies specifically for lesion segmentation tasks.

Findings

Achieves state-of-the-art performance on multiple large-scale datasets.

Utilizes transformers to effectively explore the search space.

Automates the entire model development process for medical image segmentation.

Abstract

Lesion segmentation in medical imaging has been an important topic in clinical research. Researchers have proposed various detection and segmentation algorithms to address this task. Recently, deep learning-based approaches have significantly improved the performance over conventional methods. However, most state-of-the-art deep learning methods require the manual design of multiple network components and training strategies. In this paper, we propose a new automated machine learning algorithm, T-AutoML, which not only searches for the best neural architecture, but also finds the best combination of hyper-parameters and data augmentation strategies simultaneously. The proposed method utilizes the modern transformer model, which is introduced to adapt to the dynamic length of the search space embedding and can significantly improve the ability of the search. We validate T-AutoML on several large-scale public lesion segmentation data-sets and achieve state-of-the-art performance.