ASS-GAN: Asymmetric semi-supervised GAN for breast ultrasound image segmentation

Zhai, Donghai; Hu, Bijie; Gong, Xun; Zou, Haipeng; Luo, Jun

doi:10.1016/j.neucom.2022.04.021

Cited by 34 publications

(16 citation statements)

References 19 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The two generators may supervise each other, generating reliable segmentation predicted masks as advice for each other in the absence of labels. The experimental findings demonstrate that the suggested strategy performs well even when there are a limited number of tagged photos [88]. To obtain more accurate medical picture segmentation, x-Net, a novel deep model, is presented.…”

Section: Neurosciencementioning

confidence: 88%

Image Segmentation Using Hybrid Optimization Algorithms: Review

Hemeida¹,

Yahya

Al-Sanary

2022

Aswan University Journal of Sciences and Technology

View full text Add to dashboard Cite

Image segmentation, often based on the properties of image pixels, is a widely used method in digital image processing and analysis to divide an image into multiple parts or areas. The main goal of image segmentation is to simplify the image for easier analysis. It would be very difficult to implement computer vision without performing image segmentation. An important component of computer vision is image segmentation, which has numerous commercial applications. Google and others Image-based search engines use image segmentation algorithms to identify the objects in your image and match their results to the relevant images they find to present you with search results.

show abstract

Section: Neurosciencementioning

confidence: 88%

Image Segmentation Using Hybrid Optimization Algorithms: Review

Hemeida¹,

Yahya

Al-Sanary

2022

Aswan University Journal of Sciences and Technology

View full text Add to dashboard Cite

show abstract

“…Multiple attention mechanisms, as well as a sequential training strategy using a weakly-supervised learning scheme, are employed to improve both classification and localization performance on partially annotated datasets. Future studies will be conducted to comprehensively investigate innovative methods to further improve model performance, such as advanced attention module design 7,17 and representation learning via self-supervised learning. 18,19…”

Section: Discussionmentioning

confidence: 99%

An auxiliary attention-based network for joint classification and localization of breast tumor on ultrasound images

Fan

Gong

Tang

et al. 2023

Medical Imaging 2023: Image Processing

View full text Add to dashboard Cite

Ultrasound imaging is an effective screening tool for early diagnosis of breast tumor to decrease the mortality rate. However, differentiation of tumor type based on ultrasound images remains challenging in the field of medical imaging due to the inherent noise and speckles. Thus, obtaining additional information for lesion localization could better support the decision-making by clinicians and improve diagnosis fidelity. Recently, multi-task learning (MTL) methods have been proposed for joint tumor classification and localization, where promising results were demonstrated. However, most MTL methods trained independent network branches for the two different tasks, which might cause conflicts in optimizing features due to their different purposes. In addition, these methods usually require fully-segmented datasets for model training, which poses a heavy burden in data annotation. To overcome these limitations, we propose a novel MTL framework for joint breast tumor classification and localization, motivated by the idea of attention mechanism and weakly-supervised learning strategy. Our method has three major advantages. First, an auxiliary lesion-aware network (LA-Net) with multiple attention modules for lesion localization was designed on top of a pre-defined classification network. In this way, the extracted features for classification were directly augmented by the region of interest (ROI) predicted by the LA-Net, alleviating the potential conflicts between the two tasks. Second, a sequential training strategy with a weakly-supervised learning scheme was employed to train the LA-Net and the classification network iteratively, which allows the model to be trained on the partially-segmented datasets and reduces the burden on data annotation. Third, the LA-Net and classification network design are modularized so that both architectures can be flexibly adjusted for various applications. Results from experiments performed on two breast ultrasound image datasets demonstrated the effectiveness of the proposed method.Recently, attention mechanisms have attracted lots of attention in the research community of BUS image analysis. 7 Attention mechanisms allow the network to focus more on the important ROIs of the image so that the extracted feature

show abstract

“…The application of the proposed model implied the viability of a dual intended automated system with segmentation and extraction of low-dimensional deep radiomics from ROI. The proposed model exhibited relatively considerable accuracy compared to the state-of-art models, i.e., ASS-GANs [ 54 ], and W-Net [ 55 ], yet the combination of concurrent low-dimensional radiomics increases the contribution of this model, which significantly reduces the training process and required data compared cascading multiple models. Similarly, our model exhibited considerable growth in model performance for classifying breast cancer patients from benign cases ( Figure 7 , and Table 2 ).…”

Section: Discussionmentioning

confidence: 99%

Dual-Intended Deep Learning Model for Breast Cancer Diagnosis in Ultrasound Imaging

Vigil

Barry

Amini

et al. 2022

Cancers

View full text Add to dashboard Cite

Automated medical data analysis demonstrated a significant role in modern medicine, and cancer diagnosis/prognosis to achieve highly reliable and generalizable systems. In this study, an automated breast cancer screening method in ultrasound imaging is proposed. A convolutional deep autoencoder model is presented for simultaneous segmentation and radiomic extraction. The model segments the breast lesions while concurrently extracting radiomic features. With our deep model, we perform breast lesion segmentation, which is linked to low-dimensional deep-radiomic extraction (four features). Similarly, we used high dimensional conventional imaging throughputs and applied spectral embedding techniques to reduce its size from 354 to 12 radiomics. A total of 780 ultrasound images—437 benign, 210, malignant, and 133 normal—were used to train and validate the models in this study. To diagnose malignant lesions, we have performed training, hyperparameter tuning, cross-validation, and testing with a random forest model. This resulted in a binary classification accuracy of 78.5% (65.1–84.1%) for the maximal (full multivariate) cross-validated model for a combination of radiomic groups.

show abstract

ASS-GAN: Asymmetric semi-supervised GAN for breast ultrasound image segmentation

Cited by 34 publications

References 19 publications

Image Segmentation Using Hybrid Optimization Algorithms: Review

Image Segmentation Using Hybrid Optimization Algorithms: Review

An auxiliary attention-based network for joint classification and localization of breast tumor on ultrasound images

Dual-Intended Deep Learning Model for Breast Cancer Diagnosis in Ultrasound Imaging

Contact Info

Product

Resources

About