Adaptive channel and multiscale spatial context network for breast mass segmentation in full-field mammograms

Zhao, Wan‐Ming; Lou, Meng; Qi, Yunliang; Wang, Yiming; Xu, Chunbo; Deng, Xiangyu; Ma, Yide

doi:10.1007/s10489-021-02297-3

Cited by 11 publications

(4 citation statements)

References 53 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The new upsampling block could effectively extract important information from high-level and low-level features, while a channelattention approach was used to refine these features. Zhao et al 39 tried to embed an adaptive channel and multiscale spatial context module (ACMSC) in the ResNet-backbone U-Net. The ACMSC module took advantage of the self -attention mechanism to adaptively highlight information-rich channels.…”

Section: Mass Segmentation Methods Based On Cnnsmentioning

confidence: 99%

TrEnD: A transformer‐based encoder‐decoder model with adaptive patch embedding for mass segmentation in mammograms

Liu

et al. 2023

Medical Physics

View full text Add to dashboard Cite

Background: Breast cancer is one of the most prevalent malignancies diagnosed in women. Mammogram inspection in the search and delineation of breast tumors is an essential prerequisite for a reliable diagnosis. However, analyzing mammograms by radiologists is time-consuming and prone to errors. Therefore, the development of computer-aided diagnostic (CAD) systems to automate the mass segmentation procedure is greatly expected. Purpose: Accurate breast mass segmentation in mammograms remains challenging in CAD systems due to the low contrast, various shapes, and fuzzy boundaries of masses. In this paper, we propose a fully automatic and effective mass segmentation model based on deep learning for improving segmentation performance. Methods:We propose an effective transformer-based encoder-decoder model (TrEnD). Firstly, we introduce a lightweight method for adaptive patch embedding (APE) of the transformer, which utilizes superpixels to adaptively adjust the size and position of each patch. Secondly, we introduce a hierarchical transformer-encoder and attention-gated-decoder structure, which is beneficial for progressively suppressing interference feature activations in irrelevant background areas. Thirdly, a dual-branch design is employed to extract and fuse globally coarse and locally fine features in parallel, which could capture the global contextual information and ensure the relevance and integrity of local information. The model is evaluated on two public datasets CBIS-DDSM and INbreast. To further demonstrate the robustness of TrEnD, different cropping strategies are applied to these datasets, termed tight, loose, maximal, and mixframe.Finally,ablation analysis is performed to assess the individual contribution of each module to the model performance. Results:The proposed segmentation model provides a high Dice coefficient and Intersection over Union (IoU) of 92.20% and 85.81% on the mix-frame CBIS-DDSM, while 91.83% and 85.29% for the mix-frame INbreast, respectively. The segmentation performance outperforms the current state-of -the-art approaches. By adding the APE and attention-gated module, the Dice and IoU have improved by 6.54% and 10.07%. Conclusion: According to extensive qualitative and quantitative assessments, the proposed network is effective for automatic breast mass segmentation, and has adequate potential to offer technical assistance for subsequent clinical diagnoses.

show abstract

Section: Mass Segmentation Methods Based On Cnnsmentioning

confidence: 99%

TrEnD: A transformer‐based encoder‐decoder model with adaptive patch embedding for mass segmentation in mammograms

Liu

et al. 2023

Medical Physics

View full text Add to dashboard Cite

show abstract

“…We compared the performance achieved by the proposed EU-Net with the existing approaches, namely ARF-Net [31], FS-Unet [32], Li et al [10], ACMSCNet [33], Connected ResUNets [34], and DS U-Net [12] on the INBreast, and CBIS-DDSM datasets. These approaches employed different evaluation protocols: ARF-Net [31], Li et al [10], and DS U-Net [12] employed the official train/test split provided in the dataset, whereas FS-Unet [32], ACMSCNet [33], Connected ResUNets [34] employed customs data-splits. Therefore we re-evaluated our model with those evaluation protocols for a fair comparison.…”

Section: Comparison With Existing Approachesmentioning

confidence: 99%

EU-Net: Enhanced U-shaped Network for Breast Mass Segmentation

Chowdary¹,

Yoagarajah²

2024

IEEE J. Biomed. Health Inform.

View full text Add to dashboard Cite

Segmentation of breast masses in digital mammograms is very challenging due to its complexity. The recent U-shaped encoder-decoder networks achieved remarkable performance in medical image segmentation. However, these networks have some limitations: a) The multi-scale context information is required to accurately segment mass but is not effectively extracted and utilized. b) The global context information is often ignored by the skip connection. To overcome these limitations and achieve better segmentation, we propose an Enhanced U-shaped Network (EU-Net). The proposed EU-Net comprises of 3 novel components: 1) dense block, which is employed in the encoder and the decoder in place of convolutional layers to achieve the multi-scale features. 2) Multi-Scale Feature Extraction and Fusion, which is used in the junction between the encoder and the decoder for further extracting and fusing the multi-scale context information. 3) Skip Connection Reconstruction, which is inserted between the encoder and the decoder at each stage, to redesign the skip connection and emphasize the global context information. Extensive experimental results under different settings show that the proposed EU-Net achieves superior performances than the previous state-of-the-art segmentation models, and other existing approaches on IN-Breast and CBIS-DDSM mammogram datasets. The generalization ability of the proposed EU-Net is evidenced through crossdataset and ternary dataset evaluation performance. In the ternary dataset evaluation, the model is trained and evaluated on the UDIAT breast ultrasound dataset without finetuning. The EU-Net achieves higher generalization performance in both evaluation experiments. These experiments collectively indicate the efficiency and high generalization ability of the proposed EU-Net.

show abstract

Section: Comparison With Existing Approachesmentioning

confidence: 99%

EU-Net: Enhanced U-shaped Network for Breast Mass Segmentation

Chowdary¹,

Yogarajah²

2022

Preprint

View full text Add to dashboard Cite

<p>Segmentation of breast masses in digital mammograms is very challenging due to its complexity. The recent U-shaped encoder-decoder networks achieved remarkable performance in medical image segmentation. However, these networks have some limitations: a) The multi-scale context information is required to accurately segment mass but is not effectively extracted and utilized. b) The global context information is often ignored by the skip connection. To overcome these limitations and achieve better segmentation, we propose an Enhanced U-shaped Network (EU-Net). The proposed EU-Net comprises of 3 novel components: 1) dense block, which is employed in the encoder and the decoder in place of convolutional layers to achieve the multi-scale features. 2) Multi-Scale Feature Extraction and Fusion, which is used in the junction between the encoder and the decoder for further extracting and fusing the multi-scale context information. 3) Skip Connection Reconstruction, which is inserted between the encoder and the decoder at each stage, to redesign the skip connection and emphasize the global context information. Extensive experimental results under different settings show that the proposed EU-Net achieves superior performances than the previous state-of-the-art segmentation models, and other existing approaches on IN-Breast and CBIS-DDSM mammogram datasets. The generalization ability of the proposed EU-Net is evidenced through crossdataset and ternary dataset evaluation performance. In the ternary dataset evaluation, the model is trained and evaluated on the UDIAT breast ultrasound dataset without finetuning. The EU-Net achieves higher generalization performance in both evaluation experiments. These experiments collectively indicate the efficiency and high generalization ability of the proposed EU-Net.</p>

show abstract

Adaptive channel and multiscale spatial context network for breast mass segmentation in full-field mammograms

Cited by 11 publications

References 53 publications

TrEnD: A transformer‐based encoder‐decoder model with adaptive patch embedding for mass segmentation in mammograms

TrEnD: A transformer‐based encoder‐decoder model with adaptive patch embedding for mass segmentation in mammograms

EU-Net: Enhanced U-shaped Network for Breast Mass Segmentation

EU-Net: Enhanced U-shaped Network for Breast Mass Segmentation

Contact Info

Product

Resources

About