Automatic segmentation of sub-acute ischemic stroke lesion by using DTCWT and DBN with parameter fine tuning

Background and purposeInfarct volume is a valuable outcome measure in treatment trials of acute ischemic stroke and is strongly associated with functional outcome. Its manual volumetric assessment is, however, too demanding to be implemented in clinical practice.ObjectiveTo assess the value of convolutional neural networks (CNNs) in the automatic segmentation of infarct volume in follow-up CT images in a large population of patients with acute ischemic stroke.Materials and methodsWe included CT images of 1026 patients from a large pooling of patients with acute ischemic stroke. A reference standard for the infarct segmentation was generated by manual delineation. We introduce three CNN models for the segmentation of subtle, intermediate, and severe hypodense lesions. The fully automated infarct segmentation was defined as the combination of the results of these three CNNs. The results of the three-CNNs approach were compared with the results from a single CNN approach and with the reference standard segmentations.ResultsThe median infarct volume was 48 mL (IQR 15–125 mL). Comparison between the volumes of the three-CNNs approach and manually delineated infarct volumes showed excellent agreement, with an intraclass correlation coefficient (ICC) of 0.88. Even better agreement was found for severe and intermediate hypodense infarcts, with ICCs of 0.98 and 0.93, respectively. Although the number of patients used for training in the single CNN approach was much larger, the accuracy of the three-CNNs approach strongly outperformed the single CNN approach, which had an ICC of 0.34.ConclusionConvolutional neural networks are valuable and accurate in the quantitative assessment of infarct volumes, for both subtle and severe hypodense infarcts in follow-up CT images. Our proposed three-CNNs approach strongly outperforms a more straightforward single CNN approach.

Download Full-text

Effect of MRI Images Based on Semi-Automatic Volume Segmentation in Patients with Acute Ischemic Stroke

Journal of Medical Imaging and Health Informatics ◽

10.1166/jmihi.2021.3430 ◽

2021 ◽

Vol 11 (1) ◽

pp. 223-229

Author(s):

Peng Ji ◽

Limin Jiang ◽

Xiangdong Guo ◽

Yajing Sun ◽

Xueping Qu ◽

...

Keyword(s):

Ischemic Stroke ◽

Acute Ischemic Stroke ◽

Automatic Segmentation ◽

Diagnostic Value ◽

Processing Method ◽

Segmentation Method ◽

Adc Value ◽

Conventional Mri ◽

Infarct Area ◽

Signal Characteristics

Objective: To study the MRI and CT characteristics of different periods of acute ischemic stroke and evaluate its diagnostic value by using semi-automatic mention segmentation method. Methods: CT, conventional MRI and DWI were performed in 64 patients with acute ischemic stroke. The average ADC value and average relative ADC (rADC) value of infarct lesions were measured and statistically analyzed. Results: There were no significant differences in CT, conventional MRI, and DWI signal characteristics between 1 and 7 days after the onset of acute ischemic stroke. The average ADC value and the average rADC value decreased, but the average rADC in the infarct area increased with time. The rADC value was statistically significant with the onset of 1d, 2d, 3d, and 4d (P < 0.05), but not statistically significant with the onset of 5d and 6d (P > 0.05). Conclusion: In the image processing method of semi-automatic segmentation method, the characteristics of CT, conventional MRI, and DWI signals combined with the evolution of rADC values over time can help to judge the pathophysiological changes of acute ischemic stroke, which is ischemic. Stroke staging and treatment guidance are provided.

Download Full-text

Acute Ischemic Stroke Lesion Measurement on Diffusion-weighted Imaging–Important Considerations in Designing Acute Stroke Trials With Magnetic Resonance Imaging

Journal of Stroke and Cerebrovascular Diseases ◽

10.1016/j.jstrokecerebrovasdis.2006.11.003 ◽

2007 ◽

Vol 16 (2) ◽

pp. 64-70 ◽

Cited By ~ 27

Author(s):

Carly S. Rivers ◽

Joanna M. Wardlaw ◽

Paul A. Armitage ◽

Mark E. Bastin ◽

Peter J. Hand ◽

...

Keyword(s):

Magnetic Resonance Imaging ◽

Ischemic Stroke ◽

Magnetic Resonance ◽

Acute Stroke ◽

Acute Ischemic Stroke ◽

Diffusion Weighted Imaging ◽

Resonance Imaging ◽

Diffusion Weighted ◽

Stroke Lesion

Download Full-text

Deep Learning-Based Acute Ischemic Stroke Lesion Segmentation Method on Multimodal MR Images Using a Few Fully Labeled Subjects

Computational and Mathematical Methods in Medicine ◽

10.1155/2021/3628179 ◽

2021 ◽

Vol 2021 ◽

pp. 1-13

Author(s):

Bin Zhao ◽

Zhiyang Liu ◽

Guohua Liu ◽

Chen Cao ◽

Song Jin ◽

...

Keyword(s):

Ischemic Stroke ◽

Acute Ischemic Stroke ◽

Segmentation Method ◽

Lesion Segmentation ◽

Resonance Imaging ◽

Mr Images ◽

Dice Coefficient ◽

Automatic Methods ◽

Stroke Lesion ◽

Magnetic Resonance Imaging Mri

Acute ischemic stroke (AIS) has been a common threat to human health and may lead to severe outcomes without proper and prompt treatment. To precisely diagnose AIS, it is of paramount importance to quantitatively evaluate the AIS lesions. By adopting a convolutional neural network (CNN), many automatic methods for ischemic stroke lesion segmentation on magnetic resonance imaging (MRI) have been proposed. However, most CNN-based methods should be trained on a large amount of fully labeled subjects, and the label annotation is a labor-intensive and time-consuming task. Therefore, in this paper, we propose to use a mixture of many weakly labeled and a few fully labeled subjects to relieve the thirst of fully labeled subjects. In particular, a multifeature map fusion network (MFMF-Network) with two branches is proposed, where hundreds of weakly labeled subjects are used to train the classification branch, and several fully labeled subjects are adopted to tune the segmentation branch. By training on 398 weakly labeled and 5 fully labeled subjects, the proposed method is able to achieve a mean dice coefficient of 0.699 ± 0.128 on a test set with 179 subjects. The lesion-wise and subject-wise metrics are also evaluated, where a lesion-wise F1 score of 0.886 and a subject-wise detection rate of 1 are achieved.

Download Full-text