A variant form of 3D-UNet for infant brain segmentation

Qamar, Saqib; Jin, Hai; Zheng, Ran; Ahmad, Parvez; Usama, Mohd

doi:10.1016/j.future.2019.11.021

Cited by 88 publications

(46 citation statements)

References 9 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…U-Net architectures are often used as a comparative baseline for other network architectures [11]. They have been widely used and adapted to clinical applications from detecting skin lesions [12], parotid glands [13], pulmonary nodules [14], segmented infant-brain MR-images [15], cardiac segmentation [16], as well as cell structures in light microscopy images [17]. ResNet architectures use residual connection and allow blocks to learn residual functions.…”

Section: Introductionmentioning

confidence: 99%

3D Automated Segmentation of Lower Leg Muscles Using Machine Learning on a Heterogeneous Dataset

et al. 2021

View full text Add to dashboard Cite

Quantitative MRI combines non-invasive imaging techniques to reveal alterations in muscle pathophysiology. Creating muscle-specific labels manually is time consuming and requires an experienced examiner. Semi-automatic and fully automatic methods reduce segmentation time significantly. Current machine learning solutions are commonly trained on data from healthy subjects using homogeneous databases with the same image contrast. While yielding high Dice scores (DS), those solutions are not applicable to different image contrasts and acquisitions. Therefore, the aim of our study was to evaluate the feasibility of automatic segmentation of a heterogeneous database. To create a heterogeneous dataset, we pooled lower leg muscle images from different studies with different contrasts and fields-of-view, containing healthy controls and diagnosed patients with various neuromuscular diseases. A second homogenous database with uniform contrasts was created as a subset of the first database. We trained three 3D-convolutional neuronal networks (CNN) on those databases to test performance as compared to manual segmentation. All networks, training on heterogeneous data, were able to predict seven muscles with a minimum average DS of 0.75. U-Net performed best when trained on the heterogeneous dataset (DS: 0.80 ± 0.10, AHD: 0.39 ± 0.35). ResNet and DenseNet yielded higher DS, when trained on a heterogeneous dataset (both DS: 0.86), as compared to a homogeneous dataset (ResNet DS: 0.83, DenseNet DS: 0.76). In conclusion, a CNN trained on a heterogeneous dataset achieves more accurate labels for predicting a heterogeneous database of lower leg muscles than a CNN trained on a homogenous dataset. We propose that a large heterogeneous database is needed, to make automated segmentation feasible for different kinds of image acquisitions.

show abstract

Section: Introductionmentioning

confidence: 99%

3D Automated Segmentation of Lower Leg Muscles Using Machine Learning on a Heterogeneous Dataset

et al. 2021

View full text Add to dashboard Cite

show abstract

“…The Dices on GW, WM, and CSF are 92.17%, 90.47%, and 95.60%, respectively, for our method. Compared to four other approaches [ 18 , 44 , 45 , 46 ], the performance has a higher average Dice score than [ 45 , 46 ]. Although the average Dice is lower than [ 18 ], the Dice on GM is higher; additionally, the optimal parameters are waiting to be found, and we will further exploit the potential of MP and MDP in future work.…”

Section: Resultsmentioning

confidence: 93%

“…Lei et al [ 44 ] proposed a dual aggregation network to adaptively aggregate different information of infant brain MRI modalities. Qamar et al [ 18 ] proposed to combine dense connection, residual connection, and inception module to achieve excellent results. Yu et al [ 45 ] developed a densely connected 3D-DenseVoxNet to preserve maximum information flow to ease the network training.…”

Section: Related Workmentioning

confidence: 99%

“…Recently, deep learning has been extensively applied in medical image segmentation; for example, segmenting local lesions such as tumors [ 14 , 15 , 16 ] and organs such as brain tissues [ 5 , 17 , 18 ]. By pooling features with different resolutions in the encoding path and recovering sharp object boundaries in the decoding path, the U-Net [ 19 ] can capture rich contextual information because of this encoding-decoding manner.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Learning U-Net Based Multi-Scale Features in Encoding-Decoding for MR Image Brain Tissue Segmentation

Long

Song

et al. 2021

Sensors

View full text Add to dashboard Cite

Accurate brain tissue segmentation of MRI is vital to diagnosis aiding, treatment planning, and neurologic condition monitoring. As an excellent convolutional neural network (CNN), U-Net is widely used in MR image segmentation as it usually generates high-precision features. However, the performance of U-Net is considerably restricted due to the variable shapes of the segmented targets in MRI and the information loss of down-sampling and up-sampling operations. Therefore, we propose a novel network by introducing spatial and channel dimensions-based multi-scale feature information extractors into its encoding-decoding framework, which is helpful in extracting rich multi-scale features while highlighting the details of higher-level features in the encoding part, and recovering the corresponding localization to a higher resolution layer in the decoding part. Concretely, we propose two information extractors, multi-branch pooling, called MP, in the encoding part, and multi-branch dense prediction, called MDP, in the decoding part, to extract multi-scale features. Additionally, we designed a new multi-branch output structure with MDP in the decoding part to form more accurate edge-preserving predicting maps by integrating the dense adjacent prediction features at different scales. Finally, the proposed method is tested on datasets MRbrainS13, IBSR18, and ISeg2017. We find that the proposed network performs higher accuracy in segmenting MRI brain tissues and it is better than the leading method of 2018 at the segmentation of GM and CSF. Therefore, it can be a useful tool for diagnostic applications, such as brain MRI segmentation and diagnosing.

show abstract

“…Another characteristic is to maintain high channel number of up-sampling so that relative position relation and detailed features can be fully combined and the quality of recognition is upgraded. The U-Net has been used in image segmentation, such as medical images [50][51] and remote sensing [52]; it can be also extended and enhanced to the 3D-UNet models, which have been applied in medical applications [53][54][55]. The network architecture with parameters is shown in Fig.…”

Section: ) 2d-unetmentioning

confidence: 99%

Surface Defect Detection of Wet-Blue Leather Using Hyperspectral Imaging

et al. 2021

View full text Add to dashboard Cite

Detection of surface defects on wet-blue leather is much more challenging than raw-hide leather. Since wet-blue leather turns blue and contains moisture after pre-treatment, it is a semi-product of the cowhide processing. At present, the defect detection of wet-blue leather is mostly carried out manually, and is time-consuming and labor-intensive for the professional inspectors. This paper is the first to use hyperspectral imaging (HSI) to implement the surface inspection of five wet-blue leather defects including brand masks, rotten grain, rupture, insect bites, and scratches in the pixel level detection. Hyperspectral Leather Defect Detection Algorithm (HLDDA) including Hyperspectral Target Detection (HTD) and Deep Learning (DL) techniques is proposed in this paper. In HTD, Weighted Background Suppression Constrained Energy Minimization (WBS-CEM) and WBS-Hierarchical CEM (WBS-hCEM) are developed in this paper by using weighting to suppress background and enhance the contrast between target and background. Experimental results show that the overall performance of WBS is better than the original CEM. In the DL part, 1D-Convolutional Neural Network (CNN), 2D-Unet and 3D-UNet architectures are designed to segment defect areas. For various characteristics of defects, 1D-CNN emphasizes defects with spectral features, 2D-Unet emphasizes defects with spatial features, and 3D-Unet can simultaneously process spatial and spectral information in HSI. Experimental results verified that the proposed HLDDA can effectively quantify and estimate the size of the defect, thereby accelerating the leather inspection process by professional inspectors and develop an automated leather grading towards Industry 4.0. INDEX TERMSConstrained Energy Minimization (CEM), Deep Learning (DL), Hyperspectral image (HSI)

show abstract

A variant form of 3D-UNet for infant brain segmentation

Cited by 88 publications

References 9 publications

3D Automated Segmentation of Lower Leg Muscles Using Machine Learning on a Heterogeneous Dataset

3D Automated Segmentation of Lower Leg Muscles Using Machine Learning on a Heterogeneous Dataset

Learning U-Net Based Multi-Scale Features in Encoding-Decoding for MR Image Brain Tissue Segmentation

Surface Defect Detection of Wet-Blue Leather Using Hyperspectral Imaging

Contact Info

Product

Resources

About