Adnexal mass segmentation with ultrasound data synthesis
OA Location
Author(s)
Type
Chapter
Abstract
Ovarian cancer is the most lethal gynaecological malignancy. The disease is most commonly asymptomatic at its early stages and its diagnosis relies on expert evaluation of transvaginal ultrasound images. Ultrasound is the first-line imaging modality for characterising adnexal masses, it requires significant expertise and its analysis is subjective and labour-intensive, therefore open to error. Hence, automating processes to facilitate and standardise the evaluation of scans is desired in clinical practice. Using supervised learning, we have demonstrated that segmentation of adnexal masses is possible, however, prevalence and label imbalance restricts the performance on under-represented classes. To mitigate this we apply a novel pathology-specific data synthesiser. We create synthetic medical images with their corresponding ground truth segmentations by using Poisson image editing to integrate less common masses into other samples. Our approach achieves the best performance across all classes, including an improvement of up to 8% when compared with nnU-Net baseline approaches.
Editor(s)
Aylward, S
Noble, JA
Hu, Y
Lee, SL
Baum, Z
Min, Z
Date Issued
2022-09-15
Citation
Simplifying Medical Ultrasound, 2022, 13565, pp.106-116
ISBN
978-3-031-16901-4
Publisher
Springer Nature Switzerland AG
Start Page
106
End Page
116
Journal / Book Title
Simplifying Medical Ultrasound
Lecture Notes in Computer Science
Volume
13565
Copyright Statement
© 2022 The Author(s), under exclusive license to Springer Nature Switzerland AG.
Identifier
https://www.webofscience.com/api/gateway?GWVersion=2&SrcApp=PARTNER_APP&SrcAuth=LinksAMR&KeyUT=WOS:000869762300011&DestLinkType=FullRecord&DestApp=ALL_WOS&UsrCustomerID=a2bf6146997ec60c407a63945d4e92bb
Subjects
Acoustics
Computer Science
Computer Science, Artificial Intelligence
Life Sciences & Biomedicine
Radiology, Nuclear Medicine & Medical Imaging
Science & Technology
Technology
Publication Status
Published
Date Publish Online
2022-09-15