Dual parallel net: A novel deep learning model for rectal tumor segmentation via CNN and transformer with Gaussian Mixture prior

Zhang, Huiting; Xiao-lin, Yang; Li, Dengao; Cui, Yanfen; Zhao, Jumin; Qiu, Shuang

doi:10.1016/j.jbi.2023.104304

Cited by 6 publications

(2 citation statements)

References 18 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…While the network architecture undergoes continuous refinement, the backbone for feature engineering also evolves alongside the progression of computer vision technology. The journey starts with networks like AlexNet, 11 GoogLeNet, 12 VGG, 13 and DenseNet, 14 progresses with MobileNet, 15 ResNet, 16 and ShuffleNet, 17 and now includes networks such as ConvNeXt, 18 ResNeXt, 19 DullParNet, 20 ViT, 21 and Swin transformer. 22 With the advent of AlexNet, a paradigm shift in the development of feature extraction methods for convolutional neural networks takes place.…”

Section: Application Of Convolutional Neural Network In Medical Image...mentioning

confidence: 99%

A medical image segmentation method for rectal tumors based on multi‐scale feature retention and multiple attention mechanisms

Zhao,

Liu,

Yang

et al. 2024

Medical Physics

View full text Add to dashboard Cite

BackgroundWith the continuous development of deep learning algorithms in the field of medical images, models for medical image processing based on convolutional neural networks have made great progress. Since medical images of rectal tumors are characterized by specific morphological features and complex edges that differ from natural images, achieving good segmentation results often requires a higher level of enrichment through the utilization of semantic features.PurposeThe efficiency of feature extraction and utilization has been improved to some extent through enhanced hardware arithmetic and deeper networks in most models. However, problems still exist with detail loss and difficulty in feature extraction, arising from the extraction of high‐level semantic features in deep networks.MethodsIn this work, a novel medical image segmentation model has been proposed for Magnetic Resonance Imaging (MRI) image segmentation of rectal tumors. The model constructs a backbone architecture based on the idea of jump‐connected feature fusion and solves the problems of detail feature loss and low segmentation accuracy using three novel modules: Multi‐scale Feature Retention (MFR), Multi‐branch Cross‐channel Attention (MCA), and Coordinate Attention (CA).ResultsCompared with existing methods, our proposed model is able to segment the tumor region more effectively, achieving 97.4% and 94.9% in Dice and mIoU metrics, respectively, exhibiting excellent segmentation performance and computational speed.ConclusionsOur proposed model has improved the accuracy of both lesion region and tumor edge segmentation. In particular, the determination of the lesion region can help doctors identify the tumor location in clinical diagnosis, and the accurate segmentation of the tumor edge can assist doctors in judging the necessity and feasibility of surgery.

show abstract

Section: Application Of Convolutional Neural Network In Medical Image...mentioning

confidence: 99%

A medical image segmentation method for rectal tumors based on multi‐scale feature retention and multiple attention mechanisms

Zhao,

Liu,

Yang

et al. 2024

Medical Physics

View full text Add to dashboard Cite

show abstract

“…Convolutional neural networks (CNNs) excel in image segmentation. A coding-decoding framework, augmented by skip links, minimizes information loss, improving accuracy [ [18] , [19] , [20] , [21] ].Despite the CNN model's ability to produce highly accurate results, its performance relies on the training characteristics acquired from the dataset. However, precise segmentation and classification of liver cancer are challenging due to the ambiguity of anatomical liver boundaries.…”

Section: Introductionmentioning

confidence: 99%

Customized m-RCNN and hybrid deep classifier for liver cancer segmentation and classification

Khan,

Su,

Zaman

et al. 2024

Heliyon

View full text Add to dashboard Cite

RTAU-Net: A novel 3D rectal tumor segmentation model based on dual path fusion and attentional guidance

Li,

Wang,

Yang

et al. 2023

Computer Methods and Programs in Biomedicine

View full text Add to dashboard Cite

Dual parallel net: A novel deep learning model for rectal tumor segmentation via CNN and transformer with Gaussian Mixture prior

Cited by 6 publications

References 18 publications

A medical image segmentation method for rectal tumors based on multi‐scale feature retention and multiple attention mechanisms

A medical image segmentation method for rectal tumors based on multi‐scale feature retention and multiple attention mechanisms

Customized m-RCNN and hybrid deep classifier for liver cancer segmentation and classification

RTAU-Net: A novel 3D rectal tumor segmentation model based on dual path fusion and attentional guidance

Contact Info

Product

Resources

About