VMC‐UNet: A Vision Mamba‐CNN U‐Net for Tumor Segmentation in Breast Ultrasound Image DOI
Dongyue Wang, Weiyu Zhao, Kangping Cui

et al.

International Journal of Imaging Systems and Technology, Journal Year: 2024, Volume and Issue: 34(6)

Published: Nov. 1, 2024

ABSTRACT Breast cancer remains one of the most significant health threats to women, making precise segmentation target tumors critical for early clinical intervention and postoperative monitoring. While numerous convolutional neural networks (CNNs) vision transformers have been developed segment breast from ultrasound images, both architectures encounter difficulties in effectively modeling long‐range dependencies, which are essential accurate segmentation. Drawing inspiration Mamba architecture, we introduce Vision Mamba‐CNN U‐Net (VMC‐UNet) tumor This innovative hybrid framework merges dependency capabilities with detailed local representation power CNNs. A key feature our approach is implementation a residual connection method within utilizing visual state space (VSS) module extract features maps effectively. Additionally, better integrate texture structural features, designed bilinear multi‐scale attention (BMSA), significantly enhances network's ability capture utilize intricate details across multiple scales. Extensive experiments conducted on three public datasets demonstrate that proposed VMC‐UNet surpasses other state‐of‐the‐art methods segmentation, achieving Dice coefficients 81.52% BUSI, 88.00% BUS, 88.96% STU. The source code accessible at https://github.com/windywindyw/VMC‐UNet .

Language: Английский

The Application of ResNet-34 Model Integrating Transfer Learning in the Recognition and Classification of Overseas Chinese Frescoes DOI Open Access
Le Gao, Xin Zhang, Yang Tian

et al.

Electronics, Journal Year: 2023, Volume and Issue: 12(17), P. 3677 - 3677

Published: Aug. 31, 2023

The unique characteristics of frescoes on overseas Chinese buildings can attest to the integration and historical background Western cultures. Reasonable analysis preservation provide sustainable development for culture history. This research adopts image technology based artificial intelligence proposes a ResNet-34 model method integrating transfer learning. deep learning identify classify source emigrants, effectively deal with problems such as small number fresco images emigrants’ buildings, poor quality, difficulty in feature extraction, similar pattern text style. experimental results show that training process proposed this article is stable. On constructed Jiangmen Haikou JHD datasets, final accuracy 98.41%, recall rate 98.53%. above evaluation indicators are superior classic models AlexNet, GoogLeNet, VGGNet. It be seen has strong generalization ability not prone overfitting. cultural connotations regions frescoes.

Language: Английский

Citations

6
Beyond pixel: Superpixel-based MRI segmentation through traditional machine learning and graph convolutional network DOI Creative Commons
Zakia Khatun, Halldór Jónsson,

Mariella Tsirilaki

et al.

Computer Methods and Programs in Biomedicine, Journal Year: 2024, Volume and Issue: 256, P. 108398 - 108398

Published: Aug. 28, 2024

Tendon segmentation is crucial for studying tendon-related pathologies like tendinopathy, tendinosis, etc. This step further enables detailed analysis of specific tendon regions using automated or semi-automated methods. study specifically aims at the Achilles tendon, largest in human body.

Language: Английский

Citations

1
A fundus vessel segmentation method based on double skip connections combined with deep supervision DOI Creative Commons
Qingyou Liu, Fen Zhou, Jianxin Shen

et al.

Frontiers in Cell and Developmental Biology, Journal Year: 2024, Volume and Issue: 12

Published: Oct. 3, 2024

Fundus vessel segmentation is vital for diagnosing ophthalmic diseases like central serous chorioretinopathy (CSC), diabetic retinopathy, and glaucoma. Accurate provides crucial morphology details, aiding the early detection intervention of diseases. However, current algorithms struggle with fine maintaining sensitivity in complex regions. Challenges also stem from imaging variability poor generalization across multimodal datasets, highlighting need more advanced clinical practice.

Language: Английский

Citations

0
Recognition of Diabetic Retinopathy Grades Based on Data Augmentation and Attention Mechanisms DOI

X. Li,

Li Wen,

FANYU DU

et al.

International Journal of Imaging Systems and Technology, Journal Year: 2024, Volume and Issue: 34(6)

Published: Oct. 22, 2024

ABSTRACT Diabetic retinopathy is a complication of diabetes and one the leading causes vision loss. Early detection treatment are essential to prevent Deep learning has been making great strides in field medical image processing can be used as an aid for practitioners. However, unbalanced datasets, sparse focal areas, small differences between adjacent disease grades, varied manifestations same grade challenge deep model training. Generalization performance robustness inadequate. To address problem sample numbers classes dataset, this work proposes using VQ‐VAE reconstructing affine transformed images enrich balance dataset. Test results show model's average reconstruction error 0.0001, mean structural similarity reconstructed original 0.967. This proves differ from originals yet belong category, expanding diversifying Addressing issues area sparsity disparity, utilizes ResNeXt50 backbone network constructs diverse attention networks by modifying structure embedding different modules. Experiments demonstrate that convolutional outperforms terms Precision, Sensitivity, Specificity, F1 Score, Quadratic Weighted Kappa Coefficient, Accuracy, against Salt Pepper noise, Gaussian gradient perturbation. Finally, heat maps each recognizing fundus were plotted Grad‐CAM method. The attentional more effective than non‐attentional at attending image.

Language: Английский

Citations

0
VMC‐UNet: A Vision Mamba‐CNN U‐Net for Tumor Segmentation in Breast Ultrasound Image DOI
Dongyue Wang, Weiyu Zhao, Kangping Cui

et al.

International Journal of Imaging Systems and Technology, Journal Year: 2024, Volume and Issue: 34(6)

Published: Nov. 1, 2024

ABSTRACT Breast cancer remains one of the most significant health threats to women, making precise segmentation target tumors critical for early clinical intervention and postoperative monitoring. While numerous convolutional neural networks (CNNs) vision transformers have been developed segment breast from ultrasound images, both architectures encounter difficulties in effectively modeling long‐range dependencies, which are essential accurate segmentation. Drawing inspiration Mamba architecture, we introduce Vision Mamba‐CNN U‐Net (VMC‐UNet) tumor This innovative hybrid framework merges dependency capabilities with detailed local representation power CNNs. A key feature our approach is implementation a residual connection method within utilizing visual state space (VSS) module extract features maps effectively. Additionally, better integrate texture structural features, designed bilinear multi‐scale attention (BMSA), significantly enhances network's ability capture utilize intricate details across multiple scales. Extensive experiments conducted on three public datasets demonstrate that proposed VMC‐UNet surpasses other state‐of‐the‐art methods segmentation, achieving Dice coefficients 81.52% BUSI, 88.00% BUS, 88.96% STU. The source code accessible at https://github.com/windywindyw/VMC‐UNet .

Language: Английский

Citations

0