A hybrid attentional guidance network for tumors segmentation of breast ultrasound images

Lu, Yue; Jiang, Xiaosong; Zhou, Mengqiang; Zhi, Dengjiang; Qiu, Ruiyu; Ou, Zhanhong; Bai, Jieyun

doi:10.1007/s11548-023-02849-7

Cited by 5 publications

(7 citation statements)

References 26 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…However, Yang's method was not tested using the OASBUD database. The analysis of Table 3 indicates that the results obtained in OASBUD are significantly worse than in other databases, suggesting it is more difficult in the analysis (DI = 0.6 in Ru et al 29 and 0.78 in Lu et al 26 ). Since we combine the databases in training and testing, the OASBUD cases can influence the performance of our method.…”

Section: Comparison To the State-of-the-artmentioning

confidence: 90%

“…Table 3 shows our results compared with the existing solutions described in Section 1. For comparison, we selected only methods (1) described in the last two years (2022-2023) in recognized sources, (2) trained or tested using at least two of the three public US image databases used in this study [25][26][27][28][29] (Ru et al 29 employed all three databases). All methods rely on deep neural networks with architectures usually deeper and more advanced than those proposed in this paper; all apply the testing strategy within single databases.…”

Section: Comparison To the State-of-the-artmentioning

confidence: 99%

“…Before the expansion of deep learning approaches, breast tumors were extracted in US scans using various canonical methods based on thresholding, watersheds, graphs, clustering, active contours, region analysis, Markov random fields, and classical neural networks (valuable surveys can be found in 20,21 ), but their efficiency was limited in high-noise images. The current state-of-the-art segmentation methods are concentrated around deep networks [22][23][24][25][26][27][28][29] . Almajalid et al 22 employed a U-Net convolutional neural network (CNN) with some pre-and postprocessing and obtained a Dice similarity coefficient (Dice index) of 0.83 over a private set of 221 images.…”

Section: Introductionmentioning

confidence: 99%

“…In their SCFURNet model, they equipped a U-Net architecture with spatial-wise and channel-wise fuzzy blocks for uncertainty reduction, yielding a Dice index of 0.81 in both BUSI and Dataset B (plus 0.93 in BUSIS database and 0.82 in a multiclass task over a private collection). The hybrid attentional guidance HAG-Net model from Lu et al 26 used a multiscale guidance block to extract low-resolution lesion location data and a short multi-head self-attention with convolutional block attention module to analyze global features and long-range dependencies. The Dice index reached 0.83 in BUSI and 0.78 in OASBUD.…”

Section: Introductionmentioning

confidence: 99%

See 3 more Smart Citations

Breast tumor segmentation in ultrasound using distance-adapted fuzzy connectedness, convolutional neural network, and active contour

Biesok,

Juszczyk,

Badura

2024

Preprint

View full text Add to dashboard Cite

This study addresses computer-aided breast cancer diagnosis through a hybrid framework for breast tumor segmentation in ultrasound images. The core of the three-stage method is based on the autoencoder convolutional neural network. In the first stage, we prepare a hybrid pseudo-color image through multiple instances of fuzzy connectedness analysis with a novel distance-adapted fuzzy affinity. After the hybrid image is processed by the deep network, we adjust the segmentation outcome with the Chan-Vese active contour model. We find the idea of incorporating fuzzy connectedness into the input data preparation for deep-learning image analysis our main contribution to the study. The method is trained and validated using a combined dataset of 993 breast ultrasound images from three public collections. The experiments address essential settings and hyperparameters of the method, e.g., the network architecture, input image size, and active contour setup. The tumor segmentation reaches a median Dice index of 0.86 (mean at 0.79) over the combined database. We refer our results to the most recent state-of-the-art using the same datasets, finding our model comparable in segmentation performance.

show abstract

Section: Comparison To the State-of-the-artmentioning

confidence: 90%

Section: Comparison To the State-of-the-artmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Breast tumor segmentation in ultrasound using distance-adapted fuzzy connectedness, convolutional neural network, and active contour

Biesok,

Juszczyk,

Badura

2024

Preprint

View full text Add to dashboard Cite

show abstract

“…In [37,38], attention mechanisms and transfer learning methods are employed. Whereas multi-scale guidance block and attention module are used in [39]. In [19,40], the authors have used embedded ResNet-101 as the backbone network, whereas in [41] embedded SEResnext-50 is used as the backbone network.…”

Section: State-of-the-art Comparisonmentioning

confidence: 99%

DBU-Net: Dual branch U-Net for tumor segmentation in breast ultrasound images

Pramanik,

Schwenker

et al. 2023

PLoS ONE

View full text Add to dashboard Cite

Breast ultrasound medical images often have low imaging quality along with unclear target boundaries. These issues make it challenging for physicians to accurately identify and outline tumors when diagnosing patients. Since precise segmentation is crucial for diagnosis, there is a strong need for an automated method to enhance the segmentation accuracy, which can serve as a technical aid in diagnosis. Recently, the U-Net and its variants have shown great success in medical image segmentation. In this study, drawing inspiration from the U-Net concept, we propose a new variant of the U-Net architecture, called DBU-Net, for tumor segmentation in breast ultrasound images. To enhance the feature extraction capabilities of the encoder, we introduce a novel approach involving the utilization of two distinct encoding paths. In the first path, the original image is employed, while in the second path, we use an image created using the Roberts edge filter, in which edges are highlighted. This dual branch encoding strategy helps to extract the semantic rich information through a mutually informative learning process. At each level of the encoder, both branches independently undergo two convolutional layers followed by a pooling layer. To facilitate cross learning between the branches, a weighted addition scheme is implemented. These weights are dynamically learned by considering the gradient with respect to the loss function. We evaluate the performance of our proposed DBU-Net model on two datasets, namely BUSI and UDIAT, and our experimental results demonstrate superior performance compared to state-of-the-art models.

show abstract

RTSeg-net: A lightweight network for real-time segmentation of fetal head and pubic symphysis from intrapartum ultrasound images

Ou,

Bai,

Chen

et al. 2024

Computers in Biology and Medicine

View full text Add to dashboard Cite

A hybrid attentional guidance network for tumors segmentation of breast ultrasound images

Cited by 5 publications

References 26 publications

Breast tumor segmentation in ultrasound using distance-adapted fuzzy connectedness, convolutional neural network, and active contour

Breast tumor segmentation in ultrasound using distance-adapted fuzzy connectedness, convolutional neural network, and active contour

DBU-Net: Dual branch U-Net for tumor segmentation in breast ultrasound images

RTSeg-net: A lightweight network for real-time segmentation of fetal head and pubic symphysis from intrapartum ultrasound images

Contact Info

Product

Resources

About