MBFF-Net: Multi-Branch Feature Fusion Network for Carotid Plaque Segmentation in Ultrasound

Mi, Shiyu; Bao, Qiqi; Wei, Zhanghong; Xu, Fan; Yang, Wenming

doi:10.1007/978-3-030-87240-3_30

Cited by 5 publications

(2 citation statements)

References 24 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Some researchers have proposed innovative network structures as well as modules that can increase the ability of feature extraction and fusion. Mi et al [33] proposed a multi-branch feature fusion network (MBFF-Net). As shown in Fig.…”

Section: Segmentation Of the Plaque In Longitudinal Ultrasoundmentioning

confidence: 99%

Advances in Intelligent Segmentation and 3D/4D Reconstruction of Carotid Ultrasound Imaging

Cui¹,

Li²,

Lin³

2023

Advanced Ultrasound in Diagnosis and Therapy

View full text Add to dashboard Cite

Cardiovascular disease (CVD) is one of the ten leading causes of death worldwide. Atherosclerotic disease, which can lead to myocardial infarction and stroke, is the main cause of CVD. The two main ultrasound image phenotypes used to monitor atherosclerotic load are carotid intima-media thickness (IMT) and plaque area (PA). Early segmentation and measurement methods were based on manual or threshold segmentation, snake models, etc. Usually, these methods are semi-automatic and have poor repeatability and accuracy. Segmentation of the carotid intima-media complex (IMC) and plaque in ultrasound based on artificial intelligence can achieve good accuracy. Compared with two-dimensional ultrasound, three-dimensional/fourdimensional ultrasound can provide spatial dynamic vascular information, which is helpful for doctors to evaluate. This study reviews the progress of artificial intelligence (AI) segmentation methods based on machine learning (ML) and deep learning (DL) used in the segmentation of the IMC and plaque as well as the 3D / 4D reconstruction of carotid ultrasound.

show abstract

Section: Segmentation Of the Plaque In Longitudinal Ultrasoundmentioning

confidence: 99%

Advances in Intelligent Segmentation and 3D/4D Reconstruction of Carotid Ultrasound Imaging

Cui¹,

Li²,

Lin³

2023

Advanced Ultrasound in Diagnosis and Therapy

View full text Add to dashboard Cite

show abstract

“…These studies have shown that deep learning is stable and generalizable and can compensate for the diagnostic discrepancy among doctors with different levels of experience. To the best of our knowledge, there are no ultrasound-based radiomics studies for the differentiation between benign and malignant solid renal tumors ( Esteva et al, 2017 ; Kokil and Sudharson, 2019 ; Zabihollahy et al, 2020 ; Hu et al, 2021 ; Mi et al, 2021 ).…”

Section: Introductionmentioning

confidence: 99%

Multimodal ultrasound fusion network for differentiating between benign and malignant solid renal tumors

Zhu

et al. 2022

Front. Mol. Biosci.

View full text Add to dashboard Cite

Objective: We aim to establish a deep learning model called multimodal ultrasound fusion network (MUF-Net) based on gray-scale and contrast-enhanced ultrasound (CEUS) images for classifying benign and malignant solid renal tumors automatically and to compare the model’s performance with the assessments by radiologists with different levels of experience.Methods: A retrospective study included the CEUS videos of 181 patients with solid renal tumors (81 benign and 100 malignant tumors) from June 2012 to June 2021. A total of 9794 B-mode and CEUS-mode images were cropped from the CEUS videos. The MUF-Net was proposed to combine gray-scale and CEUS images to differentiate benign and malignant solid renal tumors. In this network, two independent branches were designed to extract features from each of the two modalities, and the features were fused using adaptive weights. Finally, the network output a classification score based on the fused features. The model’s performance was evaluated using five-fold cross-validation and compared with the assessments of the two groups of radiologists with different levels of experience.Results: For the discrimination between benign and malignant solid renal tumors, the junior radiologist group, senior radiologist group, and MUF-Net achieved accuracy of 70.6%, 75.7%, and 80.0%, sensitivity of 89.3%, 95.9%, and 80.4%, specificity of 58.7%, 62.9%, and 79.1%, and area under the receiver operating characteristic curve of 0.740 (95% confidence internal (CI): 0.70–0.75), 0.794 (95% CI: 0.72–0.83), and 0.877 (95% CI: 0.83–0.93), respectively.Conclusion: The MUF-Net model can accurately classify benign and malignant solid renal tumors and achieve better performance than senior radiologists.Key points: The CEUS video data contain the entire tumor microcirculation perfusion characteristics. The proposed MUF-Net based on B-mode and CEUS-mode images can accurately distinguish between benign and malignant solid renal tumors with an area under the receiver operating characteristic curve of 0.877, which surpasses senior radiologists’ assessments by a large margin.

show abstract

Anatomical-Functional Fusion Network for Lesion Segmentation Using Dual-View CEUS

Wan,

Liu,

Zhang

2023

Lecture Notes in Computer Science

View full text Add to dashboard Cite

MBFF-Net: Multi-Branch Feature Fusion Network for Carotid Plaque Segmentation in Ultrasound

Cited by 5 publications

References 24 publications

Advances in Intelligent Segmentation and 3D/4D Reconstruction of Carotid Ultrasound Imaging

Advances in Intelligent Segmentation and 3D/4D Reconstruction of Carotid Ultrasound Imaging

Multimodal ultrasound fusion network for differentiating between benign and malignant solid renal tumors

Anatomical-Functional Fusion Network for Lesion Segmentation Using Dual-View CEUS

Contact Info

Product

Resources

About