An efficient two-step multi-organ registration on abdominal CT via deep-learning based segmentation

Yang, Shaodi; Zhao, Yuqian; Zhang, Fan; Liao, Miao; Yang, Zhongguo; Wang, Yan-jin; Yu, Lingli

doi:10.1016/j.bspc.2021.103027

Cited by 5 publications

(4 citation statements)

References 44 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Although brain MRI registration is a challenging task, the brain images do not contain any background information, thus, existing methods can use global-level intensity similarity to conduct registration. However, for the images with abundant background information (such as prostate MRI/transrectal ultrasound images [40][41][42] and abdominal CT images 32,43 ), it might not be the optimal solution to calculate the intensity similarity in the whole image domain to supervise the registration. As shown in Tables 1 -3, the unsupervised networks 15,22,23 using global-level intensity similarity failed to provide accurate registration for abdominal CT images.…”

Section: Discussionmentioning

confidence: 99%

Salient deformable network for abdominal multiorgan registration

2022

View full text Add to dashboard Cite

Background: Image registration has long been an active research area in the society of medical image computing, which is to perform spatial transformation between a pair of images and establish a point-wise correspondence to achieve spatial consistency. Purpose: Previous work mainly focused on learning complicated deformation fields by maximizing the global-level (i.e., foreground plus background) image similarity.We argue that taking the background similarity into account may not be a good solution, if we only seek the accurate alignment of target organs/regions in real clinical practice. Methods: We, therefore, propose a novel concept of Salient Registration and introduce a novel deformable network equipped with a saliency module. Specifically, a multitask learning-based saliency module is proposed to discriminate the salient regions-of -registration in a semisupervised manner. Then, our deformable network analyzes the intensity and anatomical similarity of salient regions, and finally conducts the salient deformable registration. Results: We evaluate the efficacy of the proposed network on challenging abdominal multiorgan CT scans. The experimental results demonstrate that the proposed registration network outperforms other state-of -the-art methods, achieving a mean Dice similarity coefficient (DSC) of 40.2%,Hausdorff distance (95 HD) of 20.8 mm, and average symmetric surface distance (ASSD) of 4.58 mm. Moreover, even by training using one labeled data, our network can still attain satisfactory registration performance, with a mean DSC of 39.2%, 95 HD of 21.2 mm, and ASSD of 4.78 mm. Conclusions:The proposed network provides an accurate solution for multiorgan registration and has the potential to be used for improving other registration applications. The code is publicly available at https://github.com/Rrrfrr/Salient-Deformable-Network.

show abstract

Section: Discussionmentioning

confidence: 99%

Salient deformable network for abdominal multiorgan registration

2022

View full text Add to dashboard Cite

show abstract

“…In recent years, there has been growing literature on multi-organ segmentation. [24][25][26][27] There are several large-scale datasets, while they are task-specific to segment only one type of organ or tumor. Segmentation of multiple organs or tumors on partially labeled datasets remains a challenge.…”

Section: Fully Supervised Methodsmentioning

confidence: 99%

“…In recent years, there has been growing literature on multi‐organ segmentation 24‐27 . There are several large‐scale datasets, while they are task‐specific to segment only one type of organ or tumor.…”

Section: Related Workmentioning

confidence: 99%

Learning multi‐organ and tumor segmentation from partially labeled datasets by a conditional dynamic attention network

Li,

Lian,

Lin

et al. 2023

Concurrency and Computation

View full text Add to dashboard Cite

SummaryMulti‐organ segmentation is a critical prerequisite for many clinical applications. Deep learning‐based approaches have recently achieved promising results on this task. However, they heavily rely on massive data with multi‐organ annotated, which is labor‐ and expert‐intensive and thus difficult to obtain. In contrast, single‐organ datasets are easier to acquire, and many well‐annotated ones are publicly available. It leads to the partially labeled issue: How to learn a unified multi‐organ segmentation model from several single‐organ datasets? Pseudo‐label‐based methods and conditional information‐based methods make up the majority of existing solutions, where the former largely depends on the accuracy of pseudo‐labels, and the latter has a limited capacity for task‐related features. In this paper, we propose the Conditional Dynamic Attention Network (CDANet). Our approach is designed with two key components: (1) multisource parameter generator, fusing the conditional and multiscale information to better distinguish among different tasks, and (2) dynamic attention module, promoting more attention to task‐related features. We have conducted extensive experiments on seven partially labeled challenging datasets. The results show that our method achieved competitive results compared with the advanced approaches, with an average Dice score of 75.08%. Additionally, the Hausdorff Distance is 26.31, which is a competitive result.

show abstract

“…In recent years, there has been a great deal of interest in developing computed tomography (CT) based auto‐segmentation methods for organ‐at‐risk (OAR) regions in radiotherapy. 1 , 2 , 3 Not only does this approach significantly reduce the time required for contour delineation and review, but it also improves work efficiency. 4 However, current auto‐segmentation models still rely heavily on large, high‐quality image collections and annotation data.…”

Section: Introductionmentioning

confidence: 99%

Semi‐supervised auto‐segmentation method for pelvic organ‐at‐risk in magnetic resonance images based on deep‐learning

Li,

Jia,

Lin

et al. 2024

J Applied Clin Med Phys

View full text Add to dashboard Cite

Background and purposeIn radiotherapy, magnetic resonance (MR) imaging has higher contrast for soft tissues compared to computed tomography (CT) scanning and does not emit radiation. However, manual annotation of the deep learning‐based automatic organ‐at‐risk (OAR) delineation algorithms is expensive, making the collection of large‐high‐quality annotated datasets a challenge. Therefore, we proposed the low‐cost semi‐supervised OAR segmentation method using small pelvic MR image annotations.MethodsWe trained a deep learning‐based segmentation model using 116 sets of MR images from 116 patients. The bladder, femoral heads, rectum, and small intestine were selected as OAR regions. To generate the training set, we utilized a semi‐supervised method and ensemble learning techniques. Additionally, we employed a post‐processing algorithm to correct the self‐annotation data. Both 2D and 3D auto‐segmentation networks were evaluated for their performance. Furthermore, we evaluated the performance of semi‐supervised method for 50 labeled data and only 10 labeled data.ResultsThe Dice similarity coefficient (DSC) of the bladder, femoral heads, rectum and small intestine between segmentation results and reference masks is 0.954, 0.984, 0.908, 0.852 only using self‐annotation and post‐processing methods of 2D segmentation model. The DSC of corresponding OARs is 0.871, 0.975, 0.975, 0.783, 0.724 using 3D segmentation network, 0.896, 0.984, 0.890, 0.828 using 2D segmentation network and common supervised method.ConclusionThe outcomes of our study demonstrate that it is possible to train a multi‐OAR segmentation model using small annotation samples and additional unlabeled data. To effectively annotate the dataset, ensemble learning and post‐processing methods were employed. Additionally, when dealing with anisotropy and limited sample sizes, the 2D model outperformed the 3D model in terms of performance.

show abstract

An efficient two-step multi-organ registration on abdominal CT via deep-learning based segmentation

Cited by 5 publications

References 44 publications

Salient deformable network for abdominal multiorgan registration

Salient deformable network for abdominal multiorgan registration

Learning multi‐organ and tumor segmentation from partially labeled datasets by a conditional dynamic attention network

Semi‐supervised auto‐segmentation method for pelvic organ‐at‐risk in magnetic resonance images based on deep‐learning

Contact Info

Product

Resources

About