Multi-scale Gradational-Order Fusion Framework for Breast Lesions Classification Using Ultrasound Images

Ning, Zhenyuan; Tu, Chao; Xiao, Qing; Luo, Jiaxiu; Yu, Zhengtao

doi:10.1007/978-3-030-59725-2_17

Cited by 10 publications

(12 citation statements)

References 11 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…On dataset UDIAT, we compare the proposed FMRNet with three existing methods, including the representative ensemble model based on peritumoral regions which are conducted with US images in the breast tumor and the thyroid cancer, 29,33 MsGoFNet, 23 and a method proposed by Byra et al 47 . As for the implementation of the ensemble model, we chose Resnet‐34 as the backbone network of three networks, and its inputs are the intratumoral images, peritumoral images, and combined‐tumoral images, which are shown in Figure 1b, d, f .…”

Section: Resultsmentioning

confidence: 99%

“…As for the implementation of the ensemble model, we chose Resnet‐34 as the backbone network of three networks, and its inputs are the intratumoral images, peritumoral images, and combined‐tumoral images, which are shown in Figure 1b, d, f . The results of MsGoFNet and the method of Byra et al.are taken from the results in the original paper 23 …”

Section: Resultsmentioning

confidence: 99%

“…The results of MsGoFNet and the method of Byra et alare taken from the results in the original paper. 23 The detailed results are shown in Table 3. As can be seen, the proposed FMRNet achieves the best performance.Compared to the method of Byra et al, 47 the proposed method yields overall improved results in all evaluation metrics.…”

Section: Competing Methodsmentioning

confidence: 99%

“…They built the model on a private dataset and tested it on the public dataset BUSI, and the results illustrated a good performance. Ning et al 23 proposed a multiscale gradational-order fusion (MsGoF) framework, which has achieved state-of -the-art performance on the public dataset UDIAT. 19 In this method, the multiscale patches are first extracted from the annotated lesions as the multichannel inputs, followed by several fusion blocks to comprehensively capture morphological characteristics of breast lesions.…”

Section: Introductionmentioning

confidence: 99%

“…They built the model on a private dataset and tested it on the public dataset BUSI, and the results illustrated a good performance. Ning et al 23 . proposed a multiscale gradational‐order fusion (MsGoF) framework, which has achieved state‐of‐the‐art performance on the public dataset UDIAT 19 .…”

Section: Introductionmentioning

confidence: 99%

See 4 more Smart Citations

FMRNet: A fused network of multiple tumoral regions for breast tumor classification with ultrasound images

et al. 2021

View full text Add to dashboard Cite

Purpose Recent studies have illustrated that the peritumoral regions of medical images have value for clinical diagnosis. However, the existing approaches using peritumoral regions mainly focus on the diagnostic capability of the single region and ignore the advantages of effectively fusing the intratumoral and peritumoral regions. In addition, these methods need accurate segmentation masks in the testing stage, which are tedious and inconvenient in clinical applications. To address these issues, we construct a deep convolutional neural network that can adaptively fuse the information of multiple tumoral‐regions (FMRNet) for breast tumor classification using ultrasound (US) images without segmentation masks in the testing stage. Methods To sufficiently excavate the potential relationship, we design a fused network and two independent modules to extract and fuse features of multiple regions simultaneously. First, we introduce two enhanced combined‐tumoral (EC) region modules, aiming to enhance the combined‐tumoral features gradually. Then, we further design a three‐branch module for extracting and fusing the features of intratumoral, peritumoral, and combined‐tumoral regions, denoted as the intratumoral, peritumoral, and combined‐tumoral module. Especially, we design a novel fusion module by introducing a channel attention module to adaptively fuse the features of three regions. The model is evaluated on two public datasets including UDIAT and BUSI with breast tumor ultrasound images. Two independent groups of experiments are performed on two respective datasets using the fivefold stratified cross‐validation strategy. Finally, we conduct ablation experiments on two datasets, in which BUSI is used as the training set and UDIAT is used as the testing set. Results We conduct detailed ablation experiments about the proposed two modules and comparative experiments with other existing representative methods. The experimental results show that the proposed method yields state‐of‐the‐art performance on both two datasets. Especially, in the UDIAT dataset, the proposed FMRNet achieves a high accuracy of 0.945 and a specificity of 0.945, respectively. Moreover, the precision (PRE = 0.909) even dramatically improves by 21.6% on the BUSI dataset compared with the existing method of the best result. Conclusion The proposed FMRNet shows good performance in breast tumor classification with US images, and proves its capability of exploiting and fusing the information of multiple tumoral‐regions. Furthermore, the FMRNet has potential value in classifying other types of cancers using multiple tumoral‐regions of other kinds of medical images.

show abstract

Section: Resultsmentioning

confidence: 99%

Section: Resultsmentioning

confidence: 99%