Share Email Print
cover

Proceedings Paper

End-to-end breast ultrasound lesions recognition with a deep learning approach
Author(s): Moi Hoon Yap; Manu Goyal; Fatima Osman; Ezak Ahmad; Robert Martí; Erika Denton; Arne Juette; Reyer Zwiggelaar
Format Member Price Non-Member Price
PDF $17.00 $21.00

Paper Abstract

Existing methods for automated breast ultrasound lesions detection and recognition tend to be based on multi-stage processing, such as preprocessing, filtering/denoising, segmentation and classification. The performance of these processes is dependent on the prior stages. To improve the current state of the art, we have proposed an end-to-end breast ultrasound lesions detection and recognition using a deep learning approach. We implemented a popular semantic segmentation framework, i.e. Fully Convolutional Network (FCN-AlexNet) for our experiment. To overcome data deficiency, we used a pre-trained model based on ImageNet and transfer learning. We validated our results on two datasets, which consist of a total of 113 malignant and 356 benign lesions. We assessed the performance of the model using the following split: 70% for training data, 10% for validation data, and 20% testing data. The results show that our proposed method performed better on benign lesions, with a Dice score of 0.6879, when compared to the malignant lesions with a Dice score of 0.5525. When considering the number of images with Dice score > 0.5, 79% of the benign lesions were successfully segmented and correctly recognised, while 65% of the malignant lesions were successfully segmented and correctly recognised. This paper provides the first end-to-end solution for breast ultrasound lesion recognition. The future challenges for the proposed approaches are to obtain additional datasets and customize the deep learning framework to improve the accuracy of this method.

Paper Details

Date Published: 12 March 2018
PDF: 8 pages
Proc. SPIE 10578, Medical Imaging 2018: Biomedical Applications in Molecular, Structural, and Functional Imaging, 1057819 (12 March 2018); doi: 10.1117/12.2293498
Show Author Affiliations
Moi Hoon Yap, Manchester Metropolitan Univ. (United Kingdom)
Manu Goyal, Manchester Metropolitan Univ. (United Kingdom)
Fatima Osman, Sudan Univ. of Science and Technology (Sudan)
Ezak Ahmad, Manchester Metropolitan Univ. (United Kingdom)
Robert Martí, Univ. de Girona (Spain)
Erika Denton, Norfolk and Norwich Univ. Hospital Foundation Trust (United Kingdom)
Arne Juette, Norfolk and Norwich Univ. Hospital Foundation Trust (United Kingdom)
Reyer Zwiggelaar, Aberystwyth Univ. (United Kingdom)


Published in SPIE Proceedings Vol. 10578:
Medical Imaging 2018: Biomedical Applications in Molecular, Structural, and Functional Imaging
Barjor Gimi; Andrzej Krol, Editor(s)

© SPIE. Terms of Use
Back to Top