SMU-Net: Saliency-Guided Morphology-Aware U-Net for Breast Lesion Segmentation in Ultrasound Image

Ning, Zhenyuan; Zhong, Shengzhou; Feng, Qianjin; Chen, Wufan; Yu, Zhengtao

doi:10.1109/tmi.2021.3116087

Cited by 72 publications

(27 citation statements)

References 57 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…With the great success of DL, especially CNN architectures, in the image processing and computer vision domains, few recent years have witnessed a vast emergence of DL to address various challenging tasks of medical image analysis because of the requirement of much more specialized knowledge from technicians and medical experts if compared with natural image analysis [142], [143]. For lesion segmentation in breast ultrasound (BUS) images, the work [144] studied an advanced network, namely saliency-guided morphology-aware U-Net (SMU-Net), by involving an additional middle feature learning stream and an auxiliary network. The coarse-to-fine representative features from the auxiliary network were fused with other features (e.g., background-assisted, shape-aware, edge-aware, and position-aware) to effectively discriminate morphological texture in BUS images.…”

Section: A Healthcarementioning

confidence: 99%

“…Replying on a deep encoder-decoder architecture, the network can learn image similarity and motion smoothness without ground truth information in a patch-wise manner to save computing resources significantly instead of a regular volume-wise manner. To overcome the obstacle of increasing network size and computation of 3D CNNs in mining complicated patterns in 3D images [144], 2D neuroevolutionary networks were investigated for 3D medical image segmentation [146], in which an optimal evolutionary 3D CNN was renovated to reduce computational cost without sacrificing accuracy. With AI in use as the core technology for data ana- RNNs and LSTM networks with the attention mechanisms.…”

Section: A Healthcarementioning

confidence: 99%

“…Hierarchical DL framework with CNNs for learning models at local devices and global cloud center. [144] Lesion segmentation in breast ultrasound images for detecting abnormalities.…”

Section: Gamingmentioning

confidence: 99%

See 2 more Smart Citations

Artificial Intelligence for the Metaverse: A Survey

Huynh‐The¹,

Pham²,

Pham³

et al. 2022

Preprint

View full text Add to dashboard Cite

Along with the massive growth of the Internet from the 1990s until now, various innovative technologies have been created to bring users breathtaking experiences with more virtual interactions in cyberspace. Many virtual environments with thousands of services and applications, from social networks to virtual gaming worlds, have been developed with immersive experience and digital transformation, but most are incoherent instead of being integrated into a platform. In this context, metaverse, a term formed by combining meta and universe, has been introduced as a shared virtual world that is fueled by many emerging technologies, such as fifth-generation networks and beyond, virtual reality, and artificial intelligence (AI). Among such technologies, AI has shown the great importance of processing big data to enhance immersive experience and enable humanlike intelligence of virtual agents. In this survey, we make a beneficial effort to explore the role of AI in the foundation and development of the metaverse. We first deliver a preliminary of AI, including machine learning algorithms and deep learning architectures, and its role in the metaverse. We then convey a comprehensive investigation of AI-based methods concerning six technical aspects that have potentials for the metaverse: natural language processing, machine vision, blockchain, networking, digital twin, and neural interface, and being potential for the metaverse. Subsequently, several AI-aided applications, such as healthcare, manufacturing, smart cities, and gaming, are studied to be deployed in the virtual worlds. Finally, we conclude the key contribution of this survey and open some future research directions in AI for the metaverse.

show abstract

Section: A Healthcarementioning

confidence: 99%

Section: A Healthcarementioning

confidence: 99%

See 1 more Smart Citation

Artificial Intelligence for the Metaverse: A Survey

Huynh‐The¹,

Pham²,

Pham³

et al. 2022

Preprint

View full text Add to dashboard Cite

show abstract

“…It is necessary to extract the diseased nodule from the normal tissue region to provide input data for the next classification operation. At present, the main algorithms proposed by domestic and foreign scholars in the research of ultrasound image segmentation are threshold and edge method, region method, graph theory and clustering method, energy functional method, and neural network method [ 8 ].…”

Section: Related Researchesmentioning

confidence: 99%

Breast Tumor Ultrasound Image Segmentation Method Based on Improved Residual U-Net Network

Zhao

Dai

2022

Computational Intelligence and Neuroscience

View full text Add to dashboard Cite

In order to achieve efficient and accurate breast tumor recognition and diagnosis, this paper proposes a breast tumor ultrasound image segmentation method based on U-Net framework, combined with residual block and attention mechanism. In this method, the residual block is introduced into U-Net network for improvement to avoid the degradation of model performance caused by the gradient disappearance and reduce the training difficulty of deep network. At the same time, considering the features of spatial and channel attention, a fusion attention mechanism is proposed to be introduced into the image analysis model to improve the ability to obtain the feature information of ultrasound images and realize the accurate recognition and extraction of breast tumors. The experimental results show that the Dice index value of the proposed method can reach 0.921, which shows excellent image segmentation performance.

show abstract

“…Using these weak annotations, a fully supervised model is trained iteratively. However, this approach carries many downsides, such as no control over initial segmentation error propagation in the iterative training, requires many manual parameterization during weak annotation generation, and lack of grasping fuzzy, low-contrast and complex boundaries of the objects [44,45]. Segmentation error propagation through iterations can adversely impact model performance, especially in areas requiring sophisticated domain expertise.…”

Section: Proposed Sspa Approachmentioning

confidence: 99%

Semantic Image Segmentation Using Scant Pixel Annotations

Chakravarthy

Abeyrathna

Subramaniam

et al. 2022

MAKE

View full text Add to dashboard Cite

The success of deep networks for the semantic segmentation of images is limited by the availability of annotated training data. The manual annotation of images for segmentation is a tedious and time-consuming task that often requires sophisticated users with significant domain expertise to create high-quality annotations over hundreds of images. In this paper, we propose the segmentation with scant pixel annotations (SSPA) approach to generate high-performing segmentation models using a scant set of expert annotated images. The models are generated by training them on images with automatically generated pseudo-labels along with a scant set of expert annotated images selected using an entropy-based algorithm. For each chosen image, experts are directed to assign labels to a particular group of pixels, while a set of replacement rules that leverage the patterns learned by the model is used to automatically assign labels to the remaining pixels. The SSPA approach integrates active learning and semi-supervised learning with pseudo-labels, where expert annotations are not essential but generated on demand. Extensive experiments on bio-medical and biofilm datasets show that the SSPA approach achieves state-of-the-art performance with less than 5% cumulative annotation of the pixels of the training data by the experts.

show abstract

SMU-Net: Saliency-Guided Morphology-Aware U-Net for Breast Lesion Segmentation in Ultrasound Image

Cited by 72 publications

References 57 publications

Artificial Intelligence for the Metaverse: A Survey

Artificial Intelligence for the Metaverse: A Survey

Breast Tumor Ultrasound Image Segmentation Method Based on Improved Residual U-Net Network

Semantic Image Segmentation Using Scant Pixel Annotations

Contact Info

Product

Resources

About