Deep learning-based segmentation of multisite disease in ovarian cancer
© 2023. The Author(s)..
PURPOSE: To determine if pelvic/ovarian and omental lesions of ovarian cancer can be reliably segmented on computed tomography (CT) using fully automated deep learning-based methods.
METHODS: A deep learning model for the two most common disease sites of high-grade serous ovarian cancer lesions (pelvis/ovaries and omentum) was developed and compared against the well-established "no-new-Net" framework and unrevised trainee radiologist segmentations. A total of 451 CT scans collected from four different institutions were used for training (n = 276), evaluation (n = 104) and testing (n = 71) of the methods. The performance was evaluated using the Dice similarity coefficient (DSC) and compared using a Wilcoxon test.
RESULTS: Our model outperformed no-new-Net for the pelvic/ovarian lesions in cross-validation, on the evaluation and test set by a significant margin (p values being 4 × 10-7, 3 × 10-4, 4 × 10-2, respectively), and for the omental lesions on the evaluation set (p = 1 × 10-3). Our model did not perform significantly differently in segmenting pelvic/ovarian lesions (p = 0.371) compared to a trainee radiologist. On an independent test set, the model achieved a DSC performance of 71 ± 20 (mean ± standard deviation) for pelvic/ovarian and 61 ± 24 for omental lesions.
CONCLUSION: Automated ovarian cancer segmentation on CT scans using deep neural networks is feasible and achieves performance close to a trainee-level radiologist for pelvic/ovarian lesions.
RELEVANCE STATEMENT: Automated segmentation of ovarian cancer may be used by clinicians for CT-based volumetric assessments and researchers for building complex analysis pipelines.
KEY POINTS: • The first automated approach for pelvic/ovarian and omental ovarian cancer lesion segmentation on CT images has been presented. • Automated segmentation of ovarian cancer lesions can be comparable with manual segmentation of trainee radiologists. • Careful hyperparameter tuning can provide models significantly outperforming strong state-of-the-art baselines.
| Medienart: |
E-Artikel |
|---|
| Erscheinungsjahr: |
2023 |
|---|---|
| Erschienen: |
2023 |
| Enthalten in: |
Zur Gesamtaufnahme - volume:7 |
|---|---|
| Enthalten in: |
European radiology experimental - 7(2023), 1 vom: 07. Dez., Seite 77 |
| Sprache: |
Englisch |
|---|
| Beteiligte Personen: |
Buddenkotte, Thomas [VerfasserIn] |
|---|
| Links: |
|---|
| Themen: |
Deep learning |
|---|
| Anmerkungen: |
Date Completed 11.12.2023 Date Revised 20.03.2024 published: Electronic Citation Status MEDLINE |
|---|
| doi: |
10.1186/s41747-023-00388-z |
|---|
| funding: |
|
|---|---|
| Förderinstitution / Projekttitel: |
|
| PPN (Katalog-ID): |
NLM365485217 |
|---|
| LEADER | 01000caa a22002652 4500 | ||
|---|---|---|---|
| 001 | NLM365485217 | ||
| 003 | DE-627 | ||
| 005 | 20240320233737.0 | ||
| 007 | cr uuu---uuuuu | ||
| 008 | 231226s2023 xx |||||o 00| ||eng c | ||
| 024 | 7 | |a 10.1186/s41747-023-00388-z |2 doi | |
| 028 | 5 | 2 | |a pubmed24n1337.xml |
| 035 | |a (DE-627)NLM365485217 | ||
| 035 | |a (NLM)38057616 | ||
| 040 | |a DE-627 |b ger |c DE-627 |e rakwb | ||
| 041 | |a eng | ||
| 100 | 1 | |a Buddenkotte, Thomas |e verfasserin |4 aut | |
| 245 | 1 | 0 | |a Deep learning-based segmentation of multisite disease in ovarian cancer |
| 264 | 1 | |c 2023 | |
| 336 | |a Text |b txt |2 rdacontent | ||
| 337 | |a ƒaComputermedien |b c |2 rdamedia | ||
| 338 | |a ƒa Online-Ressource |b cr |2 rdacarrier | ||
| 500 | |a Date Completed 11.12.2023 | ||
| 500 | |a Date Revised 20.03.2024 | ||
| 500 | |a published: Electronic | ||
| 500 | |a Citation Status MEDLINE | ||
| 520 | |a © 2023. The Author(s). | ||
| 520 | |a PURPOSE: To determine if pelvic/ovarian and omental lesions of ovarian cancer can be reliably segmented on computed tomography (CT) using fully automated deep learning-based methods | ||
| 520 | |a METHODS: A deep learning model for the two most common disease sites of high-grade serous ovarian cancer lesions (pelvis/ovaries and omentum) was developed and compared against the well-established "no-new-Net" framework and unrevised trainee radiologist segmentations. A total of 451 CT scans collected from four different institutions were used for training (n = 276), evaluation (n = 104) and testing (n = 71) of the methods. The performance was evaluated using the Dice similarity coefficient (DSC) and compared using a Wilcoxon test | ||
| 520 | |a RESULTS: Our model outperformed no-new-Net for the pelvic/ovarian lesions in cross-validation, on the evaluation and test set by a significant margin (p values being 4 × 10-7, 3 × 10-4, 4 × 10-2, respectively), and for the omental lesions on the evaluation set (p = 1 × 10-3). Our model did not perform significantly differently in segmenting pelvic/ovarian lesions (p = 0.371) compared to a trainee radiologist. On an independent test set, the model achieved a DSC performance of 71 ± 20 (mean ± standard deviation) for pelvic/ovarian and 61 ± 24 for omental lesions | ||
| 520 | |a CONCLUSION: Automated ovarian cancer segmentation on CT scans using deep neural networks is feasible and achieves performance close to a trainee-level radiologist for pelvic/ovarian lesions | ||
| 520 | |a RELEVANCE STATEMENT: Automated segmentation of ovarian cancer may be used by clinicians for CT-based volumetric assessments and researchers for building complex analysis pipelines | ||
| 520 | |a KEY POINTS: • The first automated approach for pelvic/ovarian and omental ovarian cancer lesion segmentation on CT images has been presented. • Automated segmentation of ovarian cancer lesions can be comparable with manual segmentation of trainee radiologists. • Careful hyperparameter tuning can provide models significantly outperforming strong state-of-the-art baselines | ||
| 650 | 4 | |a Journal Article | |
| 650 | 4 | |a Research Support, Non-U.S. Gov't | |
| 650 | 4 | |a Research Support, N.I.H., Extramural | |
| 650 | 4 | |a Deep learning | |
| 650 | 4 | |a Omentum | |
| 650 | 4 | |a Ovarian Neoplasms | |
| 650 | 4 | |a Pelvis | |
| 650 | 4 | |a Tomography (x-ray computed) | |
| 700 | 1 | |a Rundo, Leonardo |e verfasserin |4 aut | |
| 700 | 1 | |a Woitek, Ramona |e verfasserin |4 aut | |
| 700 | 1 | |a Escudero Sanchez, Lorena |e verfasserin |4 aut | |
| 700 | 1 | |a Beer, Lucian |e verfasserin |4 aut | |
| 700 | 1 | |a Crispin-Ortuzar, Mireia |e verfasserin |4 aut | |
| 700 | 1 | |a Etmann, Christian |e verfasserin |4 aut | |
| 700 | 1 | |a Mukherjee, Subhadip |e verfasserin |4 aut | |
| 700 | 1 | |a Bura, Vlad |e verfasserin |4 aut | |
| 700 | 1 | |a McCague, Cathal |e verfasserin |4 aut | |
| 700 | 1 | |a Sahin, Hilal |e verfasserin |4 aut | |
| 700 | 1 | |a Pintican, Roxana |e verfasserin |4 aut | |
| 700 | 1 | |a Zerunian, Marta |e verfasserin |4 aut | |
| 700 | 1 | |a Allajbeu, Iris |e verfasserin |4 aut | |
| 700 | 1 | |a Singh, Naveena |e verfasserin |4 aut | |
| 700 | 1 | |a Sahdev, Anju |e verfasserin |4 aut | |
| 700 | 1 | |a Havrilesky, Laura |e verfasserin |4 aut | |
| 700 | 1 | |a Cohn, David E |e verfasserin |4 aut | |
| 700 | 1 | |a Bateman, Nicholas W |e verfasserin |4 aut | |
| 700 | 1 | |a Conrads, Thomas P |e verfasserin |4 aut | |
| 700 | 1 | |a Darcy, Kathleen M |e verfasserin |4 aut | |
| 700 | 1 | |a Maxwell, G Larry |e verfasserin |4 aut | |
| 700 | 1 | |a Freymann, John B |e verfasserin |4 aut | |
| 700 | 1 | |a Öktem, Ozan |e verfasserin |4 aut | |
| 700 | 1 | |a Brenton, James D |e verfasserin |4 aut | |
| 700 | 1 | |a Sala, Evis |e verfasserin |4 aut | |
| 700 | 1 | |a Schönlieb, Carola-Bibiane |e verfasserin |4 aut | |
| 773 | 0 | 8 | |i Enthalten in |t European radiology experimental |d 2017 |g 7(2023), 1 vom: 07. Dez., Seite 77 |w (DE-627)NLM283556358 |x 2509-9280 |7 nnns |
| 773 | 1 | 8 | |g volume:7 |g year:2023 |g number:1 |g day:07 |g month:12 |g pages:77 |
| 856 | 4 | 0 | |u http://dx.doi.org/10.1186/s41747-023-00388-z |3 Volltext |
| 912 | |a GBV_USEFLAG_A | ||
| 912 | |a GBV_NLM | ||
| 951 | |a AR | ||
| 952 | |d 7 |j 2023 |e 1 |b 07 |c 12 |h 77 | ||