Accurate segmentation of breast tumors using AE U-net with HDC model in ultrasound images

Yan, Yu; Liu, Yangyang; Wu, Yiyun; Zhang, Hong; Zhang, Yameng; Meng, Lin

doi:10.1016/j.bspc.2021.103299

Cited by 45 publications

(17 citation statements)

References 16 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In this paper, U-net [5], SegNet [29], Att U-net [30], U-net++ [31], UNETR [32] five classical medical segmentation networks are used for comparison experiments. For the comparison of breast ultrasound, we also selected five specific segmentation methods, AE U-Net [17], STAN [33], RDAU-Net [34], MADU-net [10], SKU-net [21]. Similarly, we used three specific methods SDFNet [35], MBANet [36], and MSDSNet [37] for kidney ultrasound.…”

Section: Resultsmentioning

confidence: 99%

Asymmetric U-shaped network with hybrid attention mechanism for kidney ultrasound images segmentation

Chen

Zhao²,

Dai³

et al. 2023

Expert Systems with Applications

View full text Add to dashboard Cite

Section: Resultsmentioning

confidence: 99%

Asymmetric U-shaped network with hybrid attention mechanism for kidney ultrasound images segmentation

Chen

Zhao²,

Dai³

et al. 2023

Expert Systems with Applications

View full text Add to dashboard Cite

“…Originally designed for biomedical segmentation, U-Net has proven to be a useful machine learning network architecture and is widely applied to image restoration, classification, and quantification ( Ronneberger et al, 2015 ; Falk et al, 2019 ; Byra et al, 2020 ; Clowsley et al, 2020 ; Yan et al, 2022 ). To reconstruct a super-resolution image with the resolution similar to a standard DNA-PAINT image but with a much smaller number of blinking points (less raw data), the machine learning method U-PAINT derived from U-Net is developed.…”

Section: Resultsmentioning

confidence: 99%

DNA-PAINT Imaging Accelerated by Machine Learning

et al. 2022

View full text Add to dashboard Cite

DNA point accumulation in nanoscale topography (DNA-PAINT) is an easy-to-implement approach for localization-based super-resolution imaging. Conventional DNA-PAINT imaging typically requires tens of thousands of frames of raw data to reconstruct one super-resolution image, which prevents its potential application for live imaging. Here, we introduce a new DNA-PAINT labeling method that allows for imaging of microtubules with both DNA-PAINT and widefield illumination. We develop a U-Net-based neural network, namely, U-PAINT to accelerate DNA-PAINT imaging from a widefield fluorescent image and a sparse single-molecule localization image. Compared with the conventional method, U-PAINT only requires one-tenth of the original raw data, which permits fast imaging and reconstruction of super-resolution microtubules and can be adopted to analyze other SMLM datasets. We anticipate that this machine learning method enables faster and even live-cell DNA-PAINT imaging in the future.

show abstract

“…The network's receptive fields are adjusted using both a selective kernel and an attention mechanism to provide the fuse feature maps. Another CNN model was used to build an "attention enhanced U-net" for breast segmentation with improvements to the obtained results [17].…”

Section: Related Workmentioning

confidence: 99%

“…Over the years, the first attempt was devoted to computer-aided diagnostic systems, which are important tools in assisting the medical imaging professionals [2,3]. Nowadays, artificial intelligence (AI) is the leader in clinical practice, as it saves time and preforms tedious activities much faster, diminishes radiologist overload and helps less experiences practicians, in some cases [4][5][6][7][8][9][10][11][12][13][14][15][16][17]. AI includes machine learning and deep learning as efficient computational tools for biomedical big data storage, analysis and understanding.…”

Section: Introductionmentioning

confidence: 99%

Deep learning-based segmentation of breast masses using convolutional neural networks

Anghelache Nastase,

Moldovanu,

Moraru

2024

J. Phys.: Conf. Ser.

View full text Add to dashboard Cite

Automatic breast tumor segmentation based on convolutional neural networks (CNNs) is significant for the diagnosis and monitoring of breast cancers. CNNs have become an important method for early diagnosis of breast cancer and, thus, can help decrease the mortality rate. In order to assist medical professionals in breast cancer investigation a computerized system based on two encoder-decoder architectures for breast tumor segmentation has been developed. Two pre-trained DeepLabV3+ and U-Net models are proposed. The encoder generates a high-dimensional feature vector while the decoder analyses the low-resolution feature vector provided by the encoder and generates a semantic segmentation mask. Semantic segmentation based on deep learning techniques can overcome the limitations of traditional algorithms. To assess the efficiency of breast ultrasound image segmentation, we compare the segmentation results provided by CNNs against the Local Graph Cut technique (a semi-automatic segmentation method) in the Image Segmenter application. The output segmentation results have been evaluated by using the Dice similarity coefficient that compares the ground truth images provided by the specialists against the predicted segmentation results provided by the CNNs and Local Graph Cut algorithm. The proposed approach is validated on 780 breast ultrasonographic images of the BUSI public database of which 437 are benign and 210 are malignant. The BUSI database provides classification (benign or malignant) labels for ground truth in binary mask images. The average Dice scores computed between the ground truth images against CNNs were as follows: 0.9360 (malignant) and 0.9325 (benign) for the DeepLabV3+ architecture and of 0.6251 (malignant) and 0.6252 (benign) for the U-Net, respectively. When the segmentation results provided by CNNs were compared with the Local Graph Cut segmented images, the Dice scores were 0.9377 (malignant) and 0.9204 (benign) for DeepLabV3+ architecture and 0.6115 (malignant) and 0.6119 (benign) for U-Net, respectively. The results show that the DeepLabV3+ has significantly better segmentation performance and outperforms the U-Net network.

show abstract

Accurate segmentation of breast tumors using AE U-net with HDC model in ultrasound images

Cited by 45 publications

References 16 publications

Asymmetric U-shaped network with hybrid attention mechanism for kidney ultrasound images segmentation

Asymmetric U-shaped network with hybrid attention mechanism for kidney ultrasound images segmentation

DNA-PAINT Imaging Accelerated by Machine Learning

Deep learning-based segmentation of breast masses using convolutional neural networks

Contact Info

Product

Resources

About