| Title: | Deeply-supervised 3D convolutional neural networks for automated ovary and follicle detection from ultrasound volumes |
|---|
| Authors: | ID Potočnik, Božidar (Author)
ID Šavc, Martin (Author) |
|---|
| Files: |  applsci-12-01246.pdf (1,28 MB)
MD5: 9BB06D60D77966BAF074E78C8B335BCC
 https://www.mdpi.com/2076-3417/12/3/1246
|
|---|
| Language: | English |
|---|
| Work type: | Article |
|---|
| Typology: | 1.01 - Original Scientific Article |
|---|
| Organization: | FERI - Faculty of Electrical Engineering and Computer Science
|
|---|
| Abstract: | Automated detection of ovarian follicles in ultrasound images is much appreciated when
its effectiveness is comparable with the experts’ annotations. Today’s best methods estimate follicles
notably worse than the experts. This paper describes the development of two-stage deeply-supervised
3D Convolutional Neural Networks (CNN) based on the established U-Net. Either the entire U-Net
or specific parts of the U-Net decoder were replicated in order to integrate the prior knowledge into
the detection. Methods were trained end-to-end by follicle detection, while transfer learning was
employed for ovary detection. The USOVA3D database of annotated ultrasound volumes, with its
verification protocol, was used to verify the effectiveness. In follicle detection, the proposed methods
estimate follicles up to 2.9% more accurately than the compared methods. With our two-stage CNNs
trained by transfer learning, the effectiveness of ovary detection surpasses the up-to-date automated
detection methods by about 7.6%. The obtained results demonstrated that our methods estimate
follicles only slightly worse than the experts, while the ovaries are detected almost as accurately as
by the experts. Statistical analysis of 50 repetitions of CNN model training proved that the training
is stable, and that the effectiveness improvements are not only due to random initialisation. Our
deeply-supervised 3D CNNs can be adapted easily to other problem domains.
|
|---|
| Keywords: | 3D deep neural networks, 3D ultrasound images of ovaries, deep supervision, detection of follicles and ovaries, U-Net based architecture |
|---|
| Publication status: | Published |
|---|
| Publication version: | Version of Record |
|---|
| Submitted for review: | 28.12.2021 |
|---|
| Article acceptance date: | 20.01.2022 |
|---|
| Publication date: | 25.01.2022 |
|---|
| Publisher: | MDPI AG |
|---|
| Year of publishing: | 2022 |
|---|
| Number of pages: | 21 str. |
|---|
| Numbering: | Vol. 12, iss. 3 |
|---|
| PID: | 20.500.12556/DKUM-92286  |
|---|
| UDC: | 004.5:61 |
|---|
| ISSN on article: | 2076-3417 |
|---|
| COBISS.SI-ID: | 94961923 |
|---|
| DOI: | 10.3390/app12031246 |
|---|
| Copyright: | © 2022 by the authors |
|---|
| Publication date in DKUM: | 27.03.2025 |
|---|
| Views: | 148 |
|---|
| Downloads: | 18 |
|---|
| Metadata: |    |
|---|
| Categories: | Misc.
|
|---|
|
:
|
Copy citation |
|---|
| | | | Average score: | (0 votes) |
|---|
| Your score: | Voting is allowed only for logged in users. |
|---|
| Share: |  |
|---|
Hover the mouse pointer over a document title to show the abstract or click
on the title to get all document metadata. |
