Ultrasound Breast Lesion Detection using Extracted Attention Maps from a Weakly Supervised Convolutional Neural Network

Rodriguez Salas D, Seuret M, Vesal S, Maier A (2021)

Publication Language: English

Publication Type: Conference contribution, Original article

Publication year: 2021

Publisher: Springer Fachmedien Wiesbaden

City/Town: Wiesbaden

Pages Range: 282-287

Conference Proceedings Title: Bildverarbeitung für die Medizin 2021

Event location: Regensburg DE

ISBN: 978-3-658-33198-6

DOI: 10.1007/978-3-658-33198-6

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.

Authors with CRIS profile

Dalia Rodriguez Salas Lehrstuhl für Informatik 5 (Mustererkennung) Mathias Seuret Lehrstuhl für Informatik 5 (Mustererkennung) Sulaiman Vesal Lehrstuhl für Informatik 5 (Mustererkennung) Andreas Maier Lehrstuhl für Informatik 5 (Mustererkennung)

How to cite

APA:

Rodriguez 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, Christoph; Deserno, Thomas M.; Handels, Heinz;Maier, Andreas; Maier-Hein, Klaus;Tolxdorff, Thomas. (Eds.), Bildverarbeitung für die Medizin 2021 (pp. 282-287). Regensburg, DE: Wiesbaden: Springer Fachmedien Wiesbaden.

MLA:

Rodriguez Salas, Dalia, et al. "Ultrasound Breast Lesion Detection using Extracted Attention Maps from a Weakly Supervised Convolutional Neural Network." Proceedings of the Bildverarbeitung für die Medizin 2021, Regensburg Ed. Palm, Christoph; Deserno, Thomas M.; Handels, Heinz;Maier, Andreas; Maier-Hein, Klaus;Tolxdorff, Thomas., Wiesbaden: Springer Fachmedien Wiesbaden, 2021. 282-287.

BibTeX: Download