Abstract
Deep learning-based breast lesion detection in ultrasound images has demonstrated
great potential to provide objective suggestions for radiologists and improve their
accuracy in diagnosing breast diseases. However, the lack of an effective feature
enhancement approach limits the performance of deep learning models. Therefore, in
this study, we propose a novel dual global attention neural network (DGANet) to improve
the accuracy of breast lesion detection in ultrasound images. Specifically, we designed
a bilateral spatial attention module and a global channel attention module to enhance
features in spatial and channel dimensions, respectively. The bilateral spatial attention
module enhances features by capturing supporting information in regions neighboring
breast lesions and reducing integration of noise signal. The global channel attention
module enhances features of important channels by weighted calculation, where the
weights are decided by the learned interdependencies among all channels. To verify
the performance of the DGANet, we conduct breast lesion detection experiments on our
collected data set of 7040 ultrasound images and a public data set of breast ultrasound
images. YOLOv3, RetinaNet, Faster R-CNN, YOLOv5, and YOLOX are used as comparison
models. The results indicate that DGANet outperforms the comparison methods by 0.2%–5.9%
in total mean average precision.
Key Words
To read this article in full you will need to make a payment
Purchase one-time access:
Academic & Personal: 24 hour online accessCorporate R&D Professionals: 24 hour online accessOne-time access price info
- For academic or personal research use, select 'Academic and Personal'
- For corporate R&D use, select 'Corporate R&D Professionals'
Subscribe:
Subscribe to Ultrasound in Medicine and BiologyAlready a print subscriber? Claim online access
Already an online subscriber? Sign in
Register: Create an account
Institutional Access: Sign in to ScienceDirect
References
- Dataset of breast ultrasound images.Data Brief. 2019; 28104863
- Molecular imaging of breast cancer: Present and future directions.Front Chem. 2014; 2: 112
- Breast tumor detection in ultrasound images using deep learning.in: Wu G Munsell B Zhan Y Bai W Sanroma G Coupé P Patch-based Techniques in Medical Imaging. Patch-MI 2017. Springer, Cham2017 (Lecture Notes Comput Sci10530:121–128)
- Gcnet: Non-local networks meet squeeze-excitation networks and beyond.in: 2019 IEEE/CVF International Conference on Computer Vision Workshop (ICCVW), New York: IEEE2019: 1971-1980
- Global context networks.IEEE Trans Pattern Anal Mach Intell. 2020; (Published online December 24)
- Yolov3: An incremental improvement.Computer Vision and Pattern Recognition. Springer, Springer Berlin/Heidelberg2018 (1804–1802)
- Dual attention network for scene segmentation.in: 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition, New York: IEEE2019: 3146-3154
- Yolox: Exceeding YOLO series in 2021.in: arXiv preprint, 2021https://arxiv.org/abs/2107.08430
- Breast image analysis for risk assessment, detection, diagnosis, and treatment of cancer.Annu Rev Biomed Eng. 2013; 15: 327-357
Guan Q, Huang Y, Zhong Z, Zheng Z, Zheng L, Yang Y. Diagnose like a radiologist: Attention guided convolutional neural network for thorax disease classification. arXiv preprint arXiv:1801.09927, 2018.
- Deep learning and handcrafted method fusion: Higher diagnostic accuracy for melanoma dermoscopy images.IEEE J Biomed Health Inform. 2019; 23: 1385-1391
- Deep residual learning for image recognition.in: IEEE Conference on Computer Vision and Pattern Recognition. IEEE, New York2016: 770-778
- Squeeze-and-excitation networks.in: IEEE Conference on Computer Vision and Pattern Recognition. IEEE, New York2018: 7132-7141
- Risk stratification of lung nodules using 3D CNN-based multi-task learning.Springer, Cham2017
- Stochastic gradient descent.Deep learning with Python. Springer, Cham2017: 113-132
- Transformer with Gaussian-weighted self-attention for speech enhancement.in: 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), New York: IEEE2020: 6649-6653
- A large-scale database and a CNN model for attention-based glaucoma detection.IEEE Trans Med Imaging. 2019; 39: 413-424
- Automatic identification of breast ultrasound image based on supervised block-based region segmentation algorithm and features combination migration deep learning model.IEEE J Biomed Health Inform. 2020; 24: 984-993
- Breast imaging reporting and data system (bi-rads).Radiol Clin. 2002; 40: 409-430
- Focal loss for dense object detection.in: IEEE International Conference on Computer Vision, New York: IEEE2017: 2980-2988
- Characterization of a class of sigmoid functions with applications to neural networks.Neural Networks. 1996; 9: 819-835
- Center-focusing multitask CNN with injected features for classification of glioma nuclear images.in: 2017 IEEE Winter Conference on Applications of Computer Vision (WACV), New York: IEEE2017: 834-841
- Rectified linear units improve restricted Boltzmann machines.in: 27th International Conference on International Conference on Machine Learning, IMLS2010: 807-814
- Transfusion: Understanding transfer learning for medical imaging.in: 33rd Conference on Neural Information Processing Systems (NeurIPS 2019), Vancouver, BC, Canada2019
- Yolo9000: Better, faster, stronger.in: IEEE Conference on Computer Vision and Pattern Recognition, New York: IEEE2017: 7263-7271
- Faster R-CNN: Towards real-time object detection with region proposal networks.IEEE Trans Pattern Anal Mach Intell. 2017; 39: 1137-1149
- Generalized intersection over union: A metric and a loss for bounding box regression.in: IEEE/CVF Conference on Computer Vision and Pattern Recognition, New York: IEEE2019
- Brain tumor detection using fusion of hand crafted and deep learning features.Cogn Syst Res. 2020; 59: 221-230
- Computer-aided diagnosis for breast ultrasound using computerized bi-rads features and machine learning methods.Ultrasound Med Biol. 2016; 42: 980-988
- Joint weakly and semi-supervised deep learning for localization and classification of masses in breast ultrasound images.IEEE Trans Med Imaging. 2019; 38: 762-774
- Expert knowledge-infused deep learning for automatic lung nodule detection.J X-Ray Sci Technol. 2019; 27: 17-35
- Non-local neural networks.in: IEEE Conference on Computer Vision and Pattern Recognition, New York: IEEE2018: 7794-7803
- Cbam: Convolutional block attention module.in: Ferrari V Hebert M Sminchisescu C Weiss Y Computer Vision—ECCV 2018. Springer, Cham2018 (Lecture Notes Comput Sci 2018;11211:3–19)
- Using BI-RADS stratifications as auxiliary information for breast masses classification in ultrasound images.IEEE J Biomed Health Inform. 2021; 25: 2058-2070
- Automated breast ultrasound lesions detection using convolutional neural networks.IEEE J Biomed Health Inform. 2017; 22: 1218-1226
- End-to-end breast ultrasound lesions recognition with a deep learning approach.in: Medical Imaging 2018: Biomedical Applications in Molecular, Structural, and Functional Imaging. Proc SPIE. 10578. 20181057819
- Breast ultrasound region of interest detection and lesion localisation.Artif Intell Medic. 2020; 107101880
Article info
Publication history
Published online: October 03, 2022
Accepted:
July 13,
2022
Received in revised form:
June 20,
2022
Received:
December 31,
2021
Identification
Copyright
© 2022 World Federation for Ultrasound in Medicine & Biology. All rights reserved.
