Breast mass segmentation in ultrasound with selective kernel U-Net convolutional neural network

•Convolutional neural networks can efficiently segment breast masses in ultrasound.•Segmentation network's receptive field can be adjusted with an attention mechanism.•Segmentation performance assessment based on multiple datasets. In this work, we propose a deep learning method for breast mass...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Veröffentlicht in:Biomedical signal processing and control Jg. 61; S. 102027
Hauptverfasser: Byra, Michal, Jarosik, Piotr, Szubert, Aleksandra, Galperin, Michael, Ojeda-Fournier, Haydee, Olson, Linda, O’Boyle, Mary, Comstock, Christopher, Andre, Michael
Format: Journal Article
Sprache:Englisch
Veröffentlicht: England Elsevier Ltd 01.08.2020
Schlagworte:
Attention mechanism
Breast mass segmentation
Convolutional neural networks
Deep learning
Receptive field
Ultrasound imaging
Deep learning
Attention mechanism
Receptive field
Breast mass segmentation
Convolutional neural networks
Ultrasound imaging
ISSN:1746-8094
Online-Zugang:Volltext
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
Beschreibung
Zusammenfassung:•Convolutional neural networks can efficiently segment breast masses in ultrasound.•Segmentation network's receptive field can be adjusted with an attention mechanism.•Segmentation performance assessment based on multiple datasets. In this work, we propose a deep learning method for breast mass segmentation in ultrasound (US). Variations in breast mass size and image characteristics make the automatic segmentation difficult. To address this issue, we developed a selective kernel (SK) U-Net convolutional neural network. The aim of the SKs was to adjust network's receptive fields via an attention mechanism, and fuse feature maps extracted with dilated and conventional convolutions. The proposed method was developed and evaluated using US images collected from 882 breast masses. Moreover, we used three datasets of US images collected at different medical centers for testing (893 US images). On our test set of 150 US images, the SK-U-Net achieved mean Dice score of 0.826, and outperformed regular U-Net, Dice score of 0.778. When evaluated on three separate datasets, the proposed method yielded mean Dice scores ranging from 0.646 to 0.780. Additional fine-tuning of our better-performing model with data collected at different centers improved mean Dice scores by ∼6%. SK-U-Net utilized both dilated and regular convolutions to process US images. We found strong correlation, Spearman's rank coefficient of 0.7, between the utilization of dilated convolutions and breast mass size in the case of network's expansion path. Our study shows the usefulness of deep learning methods for breast mass segmentation. SK-U-Net implementation and pre-trained weights can be found at github.com/mbyr/bus_seg.
Bibliographie:ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 23
Authors’ contribution
Michal Byra: conceptualization, methodology, software, formal analysis, investigation, resources, data curation, writing – original draft, writing - review & editing, visualization. Piotr Jarosik: conceptualization, writing - review & editing. Aleksandra Szubert: data curation. Michael Galperin: investigation, resources, data curation, funding acquisition. Haydee Ojeda-Fournier: investigation, resources, data curation. Mary O’Boyle: investigation, resources, data curation. Christopher Comstock: investigation, resources, data curation. Michael Andre: conceptualization, investigation, resources, writing – original draft, writing – review & editing, supervision, project administration funding acquisition.
ISSN:1746-8094
DOI:10.1016/j.bspc.2020.102027