AUNet: attention-guided dense-upsampling networks for breast mass segmentation in whole mammograms

Sun, Hui; Li, Cheng; Liu, Boqiang; Liu, Zaiyi; Wang, Meiyun; Zheng, Hairong; Feng, David Dagan; Wang, Shanshan

doi:10.1088/1361-6560/ab5745

Cited by 116 publications

(66 citation statements)

References 76 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…On the other hand, metric val-ues from the state-of-the-art breast mass segmentation model are also shown in Table 2. It can be seen that both sensitivity and dice in our model are higher than the method proposed by Sun et al [39].…”

Section: E Results On Cbis-ddsm Datasetcontrasting

confidence: 60%

“…Benefiting from the adversarial training mode, cGAN outstrips the two aforementioned methods with an obvious improvement in terms of sensitivity and dice similarity coefficient. Although Sun et al [39] got the state of the art result by incorporating attention mechanism, our proposed model gives better metric values, whether its dice or sensitivity. An interesting point is that no matter which model the results come from, both specificity and accuracy maintain at a very high level with values of over 98%.…”

Section: Results On Inbreast Datasetmentioning

confidence: 84%

See 1 more Smart Citation

A Novel Multi-Scale Adversarial Networks for Precise Segmentation of X-Ray Breast Mass

Chen

Wang

et al. 2020

IEEE Access

View full text Add to dashboard Cite

With the constant changes of people's lifestyle and living environment, the morbidity of breast cancer is increasing year by year. It is highly imperative to develop an effective breast mass segmentation method for early breast cancer diagnosis. However, segmenting breast masses in mammograms is still one hot issue with enormous challenges because of masses' irregular shapes and various sizes. In this study, we propose multi-adversarial learning to capture multi-scale image information for accurate breast mass segmentation. To effectively reinforce higher-order consistency in the segmentation results, the proposed network introduces the idea of adversarial networks, mainly consisting of a segmentation network and a discrimination network. An improved U-Net is introduced as the segmentation network to generate masks of the suspicious regions, while the discrimination network combines three convolutional critic networks that operate at different scales to discriminate the input masks. To weaken the unbalanced class problem and produce fine-grained segmentation results, weighted cross entropy loss and Earth-Mover distance are jointly used as an integrated loss function to guide the optimization process. Furthermore, the spectral normalization is adopted to the critics to alleviate the instability of training. The effectiveness of the proposed method is evaluated on two public datasets (INbreast and CBIS-DDSM). Experimental results empirically demonstrate that our method outperforms FCNs-based methods and the state-of-the-art method with dice of 81.64% for INbreast and 82.16% for CBIS-DDSM.

show abstract

Section: E Results On Cbis-ddsm Datasetcontrasting

confidence: 60%

Section: Results On Inbreast Datasetmentioning

confidence: 84%

A Novel Multi-Scale Adversarial Networks for Precise Segmentation of X-Ray Breast Mass

Chen

Wang

et al. 2020

IEEE Access

View full text Add to dashboard Cite

show abstract

“…The dataset comprises of FFDM images along with the segmentation mask and the cropped ROI for every suspicious finding in DICOM format. For the experiments, a curated set of 689 images is used for training and a set of 168 images is used for testing 27 . There are multiple ROI detections in an image which are provided as separate masks in the dataset.…”

Section: Methodsmentioning

confidence: 99%

Deeply supervisedU‐Netfor mass segmentation in digital mammograms

Vidhyapriya

Elango

et al. 2020

Int J Imaging Syst Tech

View full text Add to dashboard Cite

Mass detection is a critical process in the examination of mammograms. The shape and texture of the mass are key parameters used in the diagnosis of breast cancer. To recover the shape of the mass, semantic segmentation is found to be more useful rather than mere object detection (or) localization. The main challenges involved in the mass segmentation include: (a) low signal to noise ratio (b) indiscernible mass boundaries, and (c) more false positives. These problems arise due to the significant overlap in the intensities of both the normal parenchymal region and the mass region. To address these challenges, deeply supervised U‐Net model (DS U‐Net) coupled with dense conditional random fields (CRFs) is proposed. Here, the input images are preprocessed using CLAHE and a modified encoder‐decoder‐based deep learning model is used for segmentation. In general, the encoder captures the textual information of various regions in an input image, whereas the decoder recovers the spatial location of the desired region of interest. The encoder‐decoder‐based models lack the ability to recover the non‐conspicuous and spiculated mass boundaries. In the proposed work, deep supervision is integrated with a popular encoder‐decoder model (U‐Net) to improve the attention of the network toward the boundary of the suspicious regions. The final segmentation map is also created as a linear combination of the intermediate feature maps and the output feature map. The dense CRF is then used to fine‐tune the segmentation map for the recovery of definite edges. The DS U‐Net with dense CRF is evaluated on two publicly available benchmark datasets CBIS‐DDSM and INBREAST. It provides a dice score of 82.9% for CBIS‐DDSM and 79% for INBREAST.

show abstract

“…Recent works [46,35,20] apply deep neural network model based on U-Net to medical image segmentation. Zhou et al [46] proposed a new architecture named D-UNet for chronic stroke lesion segmentation, which combines 2D and 3D convolution innovatively in the encoding stage.…”

mentioning

confidence: 99%

“…Zhou et al [46] proposed a new architecture named D-UNet for chronic stroke lesion segmentation, which combines 2D and 3D convolution innovatively in the encoding stage. Sun et al [35] proposed a novel attention-guided dense-upsampling network named AUNet for accurate breast mass segmentation. Liu et al [20] proposed a multi-scale deep fusion network named MSDF-Net for stroke lesion segmentation.…”

mentioning

confidence: 99%

Automatic segmentation of the femur and tibia bones from X-ray images based on pure dilated residual U-Net

Shen¹,

Xu²,

Zhang³

et al. 2021

IPI

View full text Add to dashboard Cite

X-ray images of the lower limb bone are the most commonly used imaging modality for clinical studies, and segmentation of the femur and tibia in an X-ray image is helpful for many medical studies such as diagnosis, surgery and treatment. In this paper, we propose a new approach based on pure dilated residual U-Net for the segmentation of the femur and tibia bones. The proposed approach employs dilated convolution completely to increase the receptive field, in this way, we can make full use of the advantages of dilated convolution. We conducted experiments and evaluations on datasets provided by Tianjin hospital. Comparison with the classical U-net and FusionNet, our method has fewer parameters, higher accuracy, and converges more rapidly, which means the high performance of the proposed method.

show abstract

AUNet: attention-guided dense-upsampling networks for breast mass segmentation in whole mammograms

Cited by 116 publications

References 76 publications

A Novel Multi-Scale Adversarial Networks for Precise Segmentation of X-Ray Breast Mass

A Novel Multi-Scale Adversarial Networks for Precise Segmentation of X-Ray Breast Mass

Deeply supervisedU‐Netfor mass segmentation in digital mammograms

Automatic segmentation of the femur and tibia bones from X-ray images based on pure dilated residual U-Net

Contact Info

Product

Resources

About