A survey on U-shaped networks in medical image segmentations

Liu, Liangliang; Cheng, Jianhong; Quan, Quan; Wu, Fang‐Xiang; Wang, Yuping; Wang, Jianxin

doi:10.1016/j.neucom.2020.05.070

Cited by 187 publications

(84 citation statements)

References 71 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Recently, U-Net architecture is the most well-known deep learning architecture in medical image segmentation. Liu et al [ 28 ] provided a comprehensive literature review of U-shaped networks applied to medical image segmentation tasks. Several improvements have been made to U-Net architecture, e.g., UNet++ [ 21 ], Attention U-Net [ 22 ].…”

Section: Related Workmentioning

confidence: 99%

Edge-Sensitive Left Ventricle Segmentation Using Deep Reinforcement Learning

Xiong

Cheung

et al. 2021

Sensors

View full text Add to dashboard Cite

Deep reinforcement learning (DRL) has been utilized in numerous computer vision tasks, such as object detection, autonomous driving, etc. However, relatively few DRL methods have been proposed in the area of image segmentation, particularly in left ventricle segmentation. Reinforcement learning-based methods in earlier works often rely on learning proper thresholds to perform segmentation, and the segmentation results are inaccurate due to the sensitivity of the threshold. To tackle this problem, a novel DRL agent is designed to imitate the human process to perform LV segmentation. For this purpose, we formulate the segmentation problem as a Markov decision process and innovatively optimize it through DRL. The proposed DRL agent consists of two neural networks, i.e., First-P-Net and Next-P-Net. The First-P-Net locates the initial edge point, and the Next-P-Net locates the remaining edge points successively and ultimately obtains a closed segmentation result. The experimental results show that the proposed model has outperformed the previous reinforcement learning methods and achieved comparable performances compared with deep learning baselines on two widely used LV endocardium segmentation datasets, namely Automated Cardiac Diagnosis Challenge (ACDC) 2017 dataset, and Sunnybrook 2009 dataset. Moreover, the proposed model achieves higher F-measure accuracy compared with deep learning methods when training with a very limited number of samples.

show abstract

Section: Related Workmentioning

confidence: 99%

Edge-Sensitive Left Ventricle Segmentation Using Deep Reinforcement Learning

Xiong

Cheung

et al. 2021

Sensors

View full text Add to dashboard Cite

show abstract

“…We start from two popular segmentation networks, the preferred model for medical segmentation, U-Net, and a general purpose model, DeepLabV3+. Novel modifications and integrations to U-Net (like those proposed in [11][12][13]) will be explored in the future. In [14] a deep learning-based segmentation method that automatically configures itself (including preprocessing, network architecture, training, and post-processing), called nnU-net, is proposed for a large range of segmentation tasks in the biomedical domain.…”

Section: Introductionmentioning

confidence: 99%

Region-of-Interest-Based Cardiac Image Segmentation with Deep Learning

et al. 2021

View full text Add to dashboard Cite

Despite the promising results obtained by deep learning methods in the field of medical image segmentation, lack of sufficient data always hinders performance to a certain degree. In this work, we explore the feasibility of applying deep learning methods on a pilot dataset. We present a simple and practical approach to perform segmentation in a 2D, slice-by-slice manner, based on region of interest (ROI) localization, applying an optimized training regime to improve segmentation performance from regions of interest. We start from two popular segmentation networks, the preferred model for medical segmentation, U-Net, and a general-purpose model, DeepLabV3+. Furthermore, we show that ensembling of these two fundamentally different architectures brings constant benefits by testing our approach on two different datasets, the publicly available ACDC challenge, and the imATFIB dataset from our in-house conducted clinical study. Results on the imATFIB dataset show that the proposed approach performs well with the provided training volumes, achieving an average Dice Similarity Coefficient of the whole heart of 89.89% on the validation set. Moreover, our algorithm achieved a mean Dice value of 91.87% on the ACDC validation, being comparable to the second best-performing approach on the challenge. Our approach provides an opportunity to serve as a building block of a computer-aided diagnostic system in a clinical setting.

show abstract

“…U-net is particularly suitable for biomedical image segmentation. Several studies have reported superior segmentation performances using their models based on U-net [ 15 ]. Chen et al developed DeepLabv3+ by combining pyramidal pooling modules with an encoder-decoder model and demonstrated its state-of-the-art performance on cityscape images [ 16 ].…”

Section: Introductionmentioning

confidence: 99%

Model-Agnostic Method for Thoracic Wall Segmentation in Fetal Ultrasound Videos

et al. 2020

View full text Add to dashboard Cite

The application of segmentation methods to medical imaging has the potential to create novel diagnostic support models. With respect to fetal ultrasound, the thoracic wall is a key structure on the assessment of the chest region for examiners to recognize the relative orientation and size of structures inside the thorax, which are critical components in neonatal prognosis. In this study, to improve the segmentation performance of the thoracic wall in fetal ultrasound videos, we proposed a novel model-agnostic method using deep learning techniques: the Multi-Frame + Cylinder method (MFCY). The Multi-frame method (MF) uses time-series information of ultrasound videos, and the Cylinder method (CY) utilizes the shape of the thoracic wall. To evaluate the achieved improvement, we performed segmentation using five-fold cross-validation on 538 ultrasound frames in the four-chamber view (4CV) of 256 normal cases using U-net and DeepLabv3+. MFCY increased the mean values of the intersection over union (IoU) of thoracic wall segmentation from 0.448 to 0.493 for U-net and from 0.417 to 0.470 for DeepLabv3+. These results demonstrated that MFCY improved the segmentation performance of the thoracic wall in fetal ultrasound videos without altering the network structure. MFCY is expected to facilitate the development of diagnostic support models in fetal ultrasound by providing further accurate segmentation of the thoracic wall.

show abstract

A survey on U-shaped networks in medical image segmentations

Cited by 187 publications

References 71 publications

Edge-Sensitive Left Ventricle Segmentation Using Deep Reinforcement Learning

Edge-Sensitive Left Ventricle Segmentation Using Deep Reinforcement Learning

Region-of-Interest-Based Cardiac Image Segmentation with Deep Learning

Model-Agnostic Method for Thoracic Wall Segmentation in Fetal Ultrasound Videos

Contact Info

Product

Resources

About