Abstract
In order to detect lesions on medical images, deep learning models commonly require information about the size of the lesion, either through a bounding box or through the pixel-/voxel-wise annotation of the lesion, which is in turn extremely expensive to produce in most cases. In this paper, we aim at demonstrating that by having a single central point per lesion as ground truth for 3D ultrasounds, accurate deep learning models for lesion detection can be trained, leading to precise visualizations using Grad-CAM. From a set of breast ultrasound volumes, healthy and diseased patches were used to train a deep convolutional neural network. On the one hand, each diseased patch contained in its central area a lesion's center annotated by experts. On the other hand, healthy patches were extracted from random regions of ultrasounds taken from healthy patients. An AUC of 0.92 and an accuracy of 0.87 was achieved on test patches.
This is a preview of subscription content, log in via an institution.
Buying options
Tax calculation will be finalised at checkout
Purchases are for personal use only
Learn about institutional subscriptionsPreview
Unable to display preview. Download preview PDF.
References
Morrow M, Schnitt SJ, Norton L. Current management of lesions associated with an increased risk of breast cancer. Nature rev Clin oncol. 2015;12(4):227.
Cao Z, Duan L, Yang G, et al. An experimental study on breast lesion detection and classification from ultrasound images using deep learning architectures. BMC Med Imaging. 2019 Jul;19(1):51.
Torres F, Escalante-Ramirez B, Olveres J, et al. Lesion detection in breast ultrasound images using a machine learning approach and genetic Optimization. In: Iberian Conference on Pattern Recognition and Image Analysis. Springer; 2019. p. 289–301.
Redmon J, Divvala S, Girshick R, et al. You only look once: unified, real-time object detection. Proc IEEE CCVPR. 2016; p. 779–788.
Girshick R, Donahue J, Darrell T, et al. Rich feature hierarchies for accurate object detection and semantic segmentation. Proc IEEE CVPR. 2014; p. 580–587.
Chen LC, Papandreou G, Kokkinos I, et al. Deeplab: semantic image segmentation with deep convolutional nets, atrous convolution, and fully connected crfs. IEEE Trans Pattern Anal Mach Intell. 2017;40(4):834–848.
Liu S, Wang Y, Yang X, et al. Deep learning in medical ultrasound analysis: a review. Engineering. 2019;5(2):261–275.
He K, Zhang X, Ren S, et al. Deep residual learning for image recognition. Proc IEEE CVPR. 2016; p. 770–778.
Kingma DP, Ba J. Adam: a method for stochastic optimization. arXiv preprint arXiv:14126980. 2014;.
Selvaraju RR, Cogswell M, Das A, et al. Grad-CAM: visual explanations from deep networks via gradient-based localization. Proc IEEE ICCV. 2017; p. 618–626.
Seuret M, Limbach S,Weichselbaumer N, et al. Dataset of pages from early printed books with multiple font groups. In: Proceedings of the 5th InternationalWorkshop on Historical Document Imaging and Processing; 2019. p. 1–6.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2021 Der/die Autor(en), exklusiv lizenziert durch Springer Fachmedien Wiesbaden GmbH, ein Teil von Springer Nature
About this paper
Cite this paper
Rodríguez-Salas, D., Seuret, M., Vesal, S., Maier, A. (2021). Ultrasound Breast Lesion Detection using Extracted Attention Maps from a Weakly Supervised Convolutional Neural Network. In: Palm, C., Deserno, T.M., Handels, H., Maier, A., Maier-Hein, K., Tolxdorff, T. (eds) Bildverarbeitung für die Medizin 2021. Informatik aktuell. Springer Vieweg, Wiesbaden. https://doi.org/10.1007/978-3-658-33198-6_67
Download citation
DOI: https://doi.org/10.1007/978-3-658-33198-6_67
Published:
Publisher Name: Springer Vieweg, Wiesbaden
Print ISBN: 978-3-658-33197-9
Online ISBN: 978-3-658-33198-6
eBook Packages: Computer Science and Engineering (German Language)