nn-TransUNet: An Automatic Deep Learning Pipeline for Heart MRI Segmentation

Abstract

Cardiovascular disease (CVD) is a disease with high mortality in modern times. The segmentation task for MRI to extract the related organs for CVD is essential for diagnosis. Currently, a large number of deep learning methods are designed for medical image segmentation tasks. However, the design of segmentation algorithms tends to have more focus on deepening the network architectures and tuning the parameters and hyperparameters manually, which not only leads to a high time and effort consumption, but also causes the problem that the architectures and setting designed for a single task only performs well in a single dataset, but have low performance in other cases. In this paper, nn-TransUNet, an automatic deep learning pipeline for MRI segmentation of the heart is proposed to combine the experiment planning of nnU-net and the network architecture of TransUNet. nn-TransUNet uses vision transformers and convolution layers in the design of the encoder and takes up convolution layers as decoder. With the adaptive preprocessing and network training plan generated by the proposed automatic experiment planning pipeline, nn-TransUNet is able to fulfill the target of medical image segmentation in heart MRI tasks. nn-TransUNet achieved state-of-the-art level in heart MRI segmentation task on Automatic Cardiac Diagnosis Challenge (ACDC) Dataset. It also saves the effort and time to manually tune the parameters and hyperparameters, which can reduce the burden on researchers.

A Lightweight Deep Learning Based Microwave Brain Image Network Model for Brain Tumor Classification Using Reconstructed Microwave Brain (RMB) Images

“…In the last couple of years, deep learning-based transformer architecture has been employed for classifying medical images instead of CNN models. An nn-TransUNet model has been used for MRI medical image segmentation tasks [41]. The model used vision transformers and convolution layers in the encoder for enhancing the segmentation and classification performance.…”

Accurate segmentation algorithm of acoustic neuroma in the cerebellopontine angle based on ACP-TransUNet

“…In TransAttUnet ( Chen et al, 2021 ), multilevel guided attention and multiscale skip connection were co-developed to effectively improve the functionality and flexibility of the traditional U-shaped architecture. Zhao et al proposed an automatic deep learning pipeline nn-TransUNet ( Zhao et al, 2022 ) for cardiac MRI segmentation by combining the experimental planning of nn-UNet and the network architecture of TransUNet. EG-TransUNet ( Pan et al, 2023 ) used progressive enhancement module, channel spatial attention, and semantic guidance attention to be able to capture object variability on different biomedical datasets.…”

Semi-supervised learning based on uncertainty estimation and image segmentation of left ventricle MRI in cardiac clinical diagnosis

“…For example, Roshan et al [15] proposed SegAN, an adversarial neural network architecture for left ventricle segmentation from cardiac MRI data, demonstrating the effectiveness of machine learning in 2D segmentation of medical cardiac images. Li et al [16] further proposed nn-TransUNet for automatic deep learning-based cardiac MRI segmentation, saving the effort and time required for manual parameter and hyperparameter tuning, showcasing its superiority in handling various high-resolution feature medical images for 3D cardiac image segmentation tasks, and demonstrating the potential of deep learning in the field of 3D cardiac medical image segmentation.…”