Segmentation of human aorta using 3D nnU-net-oriented deep learning

Abstract

Computed tomography angiography (CTA) has become the main imaging technique for cardiovascular diseases. Before performing the transcatheter aortic valve intervention operation, segmenting images of the aortic sinus and nearby cardiovascular tissue from enhanced images of the human heart is essential for auxiliary diagnosis and guiding doctors to make treatment plans. This paper proposes a nnU-Net (no-new-Net) framework based on deep learning (DL) methods to segment the aorta and the heart tissue near the aortic valve in cardiac CTA images, and verifies its accuracy and effectiveness. A total of 130 sets of cardiac CTA image data (88 training sets, 22 validation sets, and 20 test sets) of different subjects have been used for the study. The advantage of the nnU-Net model is that it can automatically perform preprocessing and data augmentation according to the input image data, can dynamically adjust the network structure and parameter configuration, and has a high model generalization ability. Experimental results show that the DL method based on nnU-Net can accurately and effectively complete the segmentation task of cardiac aorta and cardiac tissue near the root on the cardiac CTA dataset, and achieves an average Dice similarity coefficient of 0.9698 ± 0.0081. The actual inference segmentation effect basically meets the preoperative needs of the clinic. Using the DL method based on the nnU-Net model solves the problems of low accuracy in threshold segmentation, bad segmentation of organs with fuzzy edges, and poor adaptability to different patients’ cardiac CTA images. nnU-Net will become an excellent DL technology in cardiac CTA image segmentation tasks.

Esophageal cancer detection via non-contrast CT and deep learning

“…In previous research, the nnU-Net has been widely used for the segmentation of the aorta ( 28 ), carotid artery ( 29 ), liver ( 30 ), and fetal brain ( 31 ), with promising performance in terms of accuracy, reliability, and efficiency. Accordingly, the nnU-Net is employed for the segmentation of the esophagus in the CT images with the evaluation metrics of Dice coefficient and Hausdorff Distance.…”

“…For instance, in terms of preprocessing and post-processing, the nnU-Net applies various methods such as denoising, enhancement, cropping, thresholding, and fusion to improve image quality and segmentation results, while also enhancing the visualization and interpretability of segmentation outcomes. For model optimization, the nnU-Net employs an optimizer with adaptive learning rate and momentum to In previous research, the nnU-Net has been widely used for the segmentation of the aorta (28), carotid artery (29), liver (30), and fetal brain (31), with promising performance in terms of accuracy, reliability, and efficiency. Accordingly, the nnU-Net is employed for the segmentation of the esophagus in the CT images with the evaluation metrics of Dice coefficient and Hausdorff Distance.…”

A Deformable Constraint Transport Network for Optimal Aortic Segmentation From CT Images

“…Feiger proposes a novel variant network, SU-net, to solve some of the limitations of Unet [19]. 3D U-Net, which retains spatial contextual information between slices [22]- [24], improves spatial continuity. However, 3D models require a large memory for long-sequence images [25].…”

“…To demonstrate the superiority of our DCTN, we have compared it with the existing methods of aortic segmentation, including Xiong [21], Sieren [27], Li [24], Feiger [19], Wobben [23], Song [34], Hahn [28], Abdolmanafi [47], Chen [26], Lyu [48], Zhao [36] , Deng [32], Yu [49], Cheng [50], and Cao [22]. We visualize the segmentation results of DCTN and other top seven comparison methods in Fig.…”

IoT Agricultural Pest Identification Based on Multiple Convolutional Models

“…The original images often contain a lot of useless information, and preprocessing the dataset is an important task to weaken the influence of useless information on the network model. The statistical analysis of the seven types of datasets used in this paper shows that the datasets have a limited amount of data and have the problem of unbalanced data distribution, and some samples with too little data will hurt the training of the model [26][27]. this section, reasonable pre-processing operations are performed on the existing datasets, and the datasets are trimmed employing image cropping and inverse color transformations.…”