Dual‐Path Attention Compensation U‐Net for Stroke Lesion Segmentation

Hui, Haisheng; Zhang, Xueying; Wu, Zelin; Li, Fenlian

doi:10.1155/2021/7552185

Cited by 12 publications

(8 citation statements)

References 32 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…in slice segmentation, combining an Attention ResUnet and an Attention Unet in patch segmentation (step 1) and an Attention ResUnet in slice segmentation (step 2). [11] 0.593 TOMITA, Naofumi et al, 2020 [7] 0.640 Proposed Method 0.8070…”

Section: Overall Resultsmentioning

confidence: 99%

Automatic segmentation of stroke lesions in T1-weighted magnetic resonance images with convolutional neural networks

Sousa¹,

Arruda²,

Krieger³

et al. 2023

Medical Imaging 2023: Computer-Aided Diagnosis

View full text Add to dashboard Cite

Stroke is a major cause of death and permanent disability. Magnetic resonance imaging (MRI) is often the modality for evaluating lesion extension, affected brain, area and classification between hemorrhagic or ischemic, which are critical for treatment and rehabilitation decisions. MRI manual evaluation and lesion delineation is time-consuming and subject to inter-and intra-observer variation. Although promising, convolutional neural network (CNN) approaches face challenges in dealing with small-size lesions, irregular morphology, and idiosyncrasy. The best-published segmentation approaches based on the ATLAS dataset and CNNs are either fully 3D, or use up to eight anatomically specific 2D CNNs, incurring high computation costs and limited deployment feasibility. We developed a more straightforward segmentation method using only three CNNs. First, an Attention UNet and an Attention ResUNet are trained only on a lesion-wise balanced sample of slice patches. By working on the patch level, these networks learn to segment lesions' texture and shape irregularities. Then, another Attention ResUNet uses the previous two CNNs output patches reassembled and stacked along with the original slice. By having the broader slice context available, this second step combines the first step segmentations, handling disagreements while keeping the segmentation coherence on the slice level. We validated the method on 239 exams from the multicenter ATLAS dataset, using a 5-fold cross-validation. In the test set of 45,171 slices, we observed a mean slice Dice coefficient of 0.8070±0.05, a state-of-the-art result in this dataset, showing generalization capacity on different centers and acquisition conditions.

show abstract

Section: Overall Resultsmentioning

confidence: 99%

Automatic segmentation of stroke lesions in T1-weighted magnetic resonance images with convolutional neural networks

Sousa¹,

Arruda²,

Krieger³

et al. 2023

Medical Imaging 2023: Computer-Aided Diagnosis

View full text Add to dashboard Cite

show abstract

“…In addition to the simple geometric estimation method by ABC/2, previous studies had applied methods like deep learning for medical image segmentation and have achieved good results. Among them, the U-net was a widely proven effective method ( 30 , 31 , 33 ). Therefore, this study also compared the RG-WP algorithm with U-net.…”

Section: Discussionmentioning

confidence: 99%

Segmentation of Spontaneous Intracerebral Hemorrhage on CT With a Region Growing Method Based on Watershed Preprocessing

et al. 2022

View full text Add to dashboard Cite

Intracerebral hemorrhage (ICH) poses a great threat to human life due to its high incidence and poor prognosis. Identification of the bleeding location and quantification of the volume based on CT images are of great significance for assisting the diagnosis and treatment of ICH. In this study, a region-growing algorithm based on watershed preprocessing (RG-WP) was proposed to segment and quantify the hemorrhage. The lowest points yielded by the watershed algorithm were used as seed points for region growing and then hemorrhage was segmented based on the region growing method. At the same time, to integrate the rich experience of clinicians with the algorithm, manual selection of seed points on the basis of watershed segmentation was performed. With the application of segmentation on CT images of 55 patients with ICH, the performance of the RG-WP algorithm was evaluated by comparing it with manual segmentations delineated by professional clinicians as well as the traditional ABC/2 method and the deep learning algorithm U-net. The mean deviation of hemorrhage volume of the RG-WP algorithm from manual segmentation was −0.12 ml (range: −1.05–1.16), while that of the ABC/2 from the manual was 1.05 ml (range: −0.77–9.57). Strong agreement of the algorithm and the manual was confirmed with a high intraclass correlation coefficient (ICC) (0.998, 95% CI: 0.997–0.999), which was superior to that of the ABC/2 and the manual (0.972, 95% CI: 0.953–0.984). The sensitivity (Sen), positive predictive value (PPV), dice similarity index (DSI), and Jaccard index (JI) of the RG-WP algorithm compared to the manual were 0.92 ± 0.04, 0.95 ± 0.04, 0.93 ± 0.02, and 0.88 ± 0.04, respectively, showing high consistency. Besides, the accuracy of the algorithm was also comparable to that of the deep learning method U-net, with Sen, PPV, DSI, and JI being 0.91 ± 0.09, 0.91 ± 0.06, 0.91 ± 0.05, and 0.91 ± 0.06, respectively.

show abstract

“…Attention U-Net was published in 2018 [ 20 ]; it was verified to perform well in several medical image segmentation tasks [ 21 , 22 ], but it has not yet been employed in brain hematoma segmentation.…”

Section: Methodsmentioning

confidence: 99%

Automatic and Efficient Prediction of Hematoma Expansion in Patients with Hypertensive Intracerebral Hemorrhage Using Deep Learning Based on CT Images

Wang

Gao

et al. 2022

JPM

View full text Add to dashboard Cite

Patients with hypertensive intracerebral hemorrhage (ICH) have a high hematoma expansion (HE) incidence. Noninvasive prediction HE helps doctors take effective measures to prevent accidents. This study retrospectively analyzed 253 cases of hypertensive intraparenchymal hematoma. Baseline non-contrast-enhanced CT scans (NECTs) were collected at admission and compared with subsequent CTs to determine the presence of HE. An end-to-end deep learning method based on CT was proposed to automatically segment the hematoma region, region of interest (ROI) feature extraction, and HE prediction. A variety of algorithms were employed for comparison. U-Net with attention performs best in the task of segmenting hematomas, with the mean Intersection overUnion (mIoU) of 0.9025. ResNet-34 achieves the most robust generalization capability in HE prediction, with an area under the receiver operating characteristic curve (AUC) of 0.9267, an accuracy of 0.8827, and an F1 score of 0.8644. The proposed method is superior to other mainstream models, which will facilitate accurate, efficient, and automated HE prediction.

show abstract

Dual‐Path Attention Compensation U‐Net for Stroke Lesion Segmentation

Cited by 12 publications

References 32 publications

Automatic segmentation of stroke lesions in T1-weighted magnetic resonance images with convolutional neural networks

Automatic segmentation of stroke lesions in T1-weighted magnetic resonance images with convolutional neural networks

Segmentation of Spontaneous Intracerebral Hemorrhage on CT With a Region Growing Method Based on Watershed Preprocessing

Automatic and Efficient Prediction of Hematoma Expansion in Patients with Hypertensive Intracerebral Hemorrhage Using Deep Learning Based on CT Images

Contact Info

Product

Resources

About