Can ovarian cancer detection be improved using AI-driven diagnostic support applied to ultrasound images?
ISRCTN | ISRCTN88222986 |
---|---|
DOI | https://doi.org/10.1186/ISRCTN88222986 |
Secondary identifying numbers | OV-AID-20230326 |
- Submission date
- 26/03/2023
- Registration date
- 01/04/2023
- Last edited
- 28/05/2024
- Recruitment status
- Recruiting
- Overall study status
- Ongoing
- Condition category
- Cancer
Plain English Summary
Background and study aims
Ovarian tumors are common and their management is dependent on the risk of malignancy. Patients with malignant ovarian tumors benefit from being referred to a gynecologic oncologist for debulking surgery, indicating higher survival rates. On the other hand, benign cysts should be handled conservatively with ultrasound follow-up or with minimally invasive surgery, while preserving fertility and avoiding unnecessary suffering. Transvaginal ultrasound assessment has a central role in the diagnostics of ovarian tumors as it has high accuracy, at least in the hands of ultrasound experts. There is currently a shortage of sonographers with enough experience though, as malignant tumors are relatively uncommon. Thus, there is a need to find alternatives to improve the diagnostics of ovarian tumors. In other medical fields, researchers have been able to develop automated imaging tools to improve diagnostic accuracy, for example when searching for breast cancer and bone fractures. Recent advances in computerized image analysis have been powered by deep neural networks (DNNs), which are computational versions mimicking the biological nervous system. Recently, researchers have developed and validated a DNN model (Ovry-Dx) to discriminate benign from malignant ovarian tumors based on 3077 ultrasound images from 758 patients. Ovry-Dx had a diagnostic accuracy comparable to human expert assessment. Further validating studies are needed to explore the generalizability and robustness of DNN models, and the clinical benefits in the hands of less experienced examiners. This study aims to compare the accuracy in differentiating benign from malignant masses using DNN models as compared to subjective assessment using pattern recognition or the IOTA-ADNEX model, by examiners of different levels of expertise.
Who can participate?
Women aged 15 years and over with a recently detected ovarian tumor, planned for either surgery or long time (at least 21 months) follow-up
What does the study involve?
Subjective assessment using pattern recognition and the IOTA-ADNEX model score will be compared to the DNN-model assessment. The histological outcome from surgery or long-time ultrasound follow-up (minimum 21 months) serves as the gold standard.
What are the possible benefits and risks of participating?
There are neither any benefits nor any risks as the DNN model outcome will not be shown to the examiner. The images will not be analysed by the DNN model until all patients have been examined. Therefore, participation will not affect the management of the patient.
Where is the study run from?
Karolinska Institutet (Sweden)
When is the study starting and how long is it expected to run for?
January 2020 to June 2026
Who is funding the study?
1. Swedish Research Council (Sweden)
2. Swedish Cancer Society (Sweden)
3. Stockholms Läns Landsting (Sweden)
4. Radiumhemmets Forskningsfonder (Sweden)
Who is the main contact?
Elisabeth Epstein, elisabeth.epstein@ki.se
Contact information
Principal Investigator
Sjukhusbacken 10
Stockholm
11883
Sweden
0000-0003-2298-7785 | |
Phone | +46 (0)706699019 |
elisabeth.epstein@ki.se |
Study information
Study design | Prospective multicenter diagnostic accuracy study |
---|---|
Primary study design | Observational |
Secondary study design | Cohort study |
Study setting(s) | Hospital |
Study type | Diagnostic |
Participant information sheet | Not available in web format, please use contact details to request a participant information sheet |
Scientific title | Diagnostic accuracy of computerized ultrasound image analysis using deep neural network models as compared to subjective assessment using pattern recognition or IOTA-ADNEX model - a prospective multi-centre trial |
Study acronym | OV-AID, Phase I |
Study hypothesis | The accuracy in differentiating benign from malignant masses using deep neural network (DNN) models is superior to subjective assessment using pattern recognition or the IOTA-ADNEX model, by non-expert examiners. |
Ethics approval(s) | Approved 02/02/2021, Etikprövningsmyndigheten (Sjukhusbacken 10, Uppsala, 750 02 Uppsala, Sweden; +46 (0)104750800; registrator@etikprovning.se), ref: 2020-07200, 2021-04549, 2021-06367-02, 2023-01834-02 |
Condition | Ovarian cancer |
Intervention | Current interventions as of 28/05/2024: A prospective study including >700 patients with ovarian tumors, assessed by examiners with varying expertise (at least 400 assessments by non-experts, and 300 by expert examiners). Subjective assessment using pattern recognition and the IOTA-ADNEX model score will be compared to DNN-model assessment. The histological outcome from surgery or long-time ultrasound follow-up (minimum 9 months, with scans after 3 and 6 months) serves as the gold standard. For every case: over four grayscale (at least two without callipers), two power Doppler still images and two video clips (with and without Doppler), should be collected. Previous interventions: A prospective study including >400 patients (at least 150 malignant) with ovarian tumors, assessed by examiners with varying expertise (at least 200 assessments by non-experts). Subjective assessment using pattern recognition and the IOTA-ADNEX model score will be compared to DNN-model assessment. The histological outcome from surgery or long-time ultrasound follow-up (minimum 21 months, with scans after 3, 6 and 12 months) serves as the gold standard. For every case: over four grayscale (at least two without callipers), two power Doppler still images and two video clips (with and without Doppler), should be collected. |
Intervention type | Other |
Primary outcome measure | Diagnostic accuracy in differentiating benign from malignant ovarian tumors measured by comparing the outcomes from subjective assessment, IOTA-ADNEX model scoring and previously developed deep neural network (DNN) models at one timepoint |
Secondary outcome measures | Accuracy in differentiating benign from malignant ovarian tumors measured by comparing the outcomes from subjective assessment, IOTA-ADNEX model scoring and previously developed DNN models - stratified by user experience (expert examiners versus non-expert examiners) at one timepoint |
Overall study start date | 01/01/2020 |
Overall study end date | 06/06/2026 |
Eligibility
Participant type(s) | Patient |
---|---|
Age group | Mixed |
Lower age limit | 15 Years |
Sex | Female |
Target number of participants | Minimum 700 participants, and at least 400 assessments are performed by non-experts. |
Participant inclusion criteria | 1. Women aged ≥15 years 2. Newly detected ovarian tumor 3. Capable of understanding the study information and accepts participation |
Participant exclusion criteria | 1. Aged <15 years 2. Patients who are not capable of understanding the study information or don't accept participation |
Recruitment start date | 01/03/2021 |
Recruitment end date | 31/12/2025 |
Locations
Countries of recruitment
- Czech Republic
- Italy
- Lithuania
- Philippines
- Poland
- Spain
- Sweden
Study participating centres
Stockholm
11883
Sweden
Växsjö
35234
Sweden
Huddinge
14186
Sweden
Stockholm
11361
Sweden
Uppsala
75185
Sweden
Linköping
58191
Sweden
Lund
22242
Sweden
Gothenburg
41685
Sweden
Halmstad
30233
Sweden
Danderyd
18288
Sweden
Stockholm
11281
Sweden
Nyköping
61139
Sweden
Trollhättan
46173
Sweden
Örebro
70185
Sweden
Malmö
21428
Sweden
Karlstad
65230
Sweden
131 31
Sweden
147 00
Czech Republic
341 37
Italy
Monza
20900
Italy
Milan
20126
Italy
Brescia
25124
Italy
Romagna
48018
Italy
Olbia
07026
Italy
20059
Poland
40055
Poland
Metro Manila
1600
Philippines
Barcelona
08028
Spain
Kaunas
44307
Lithuania
Sponsor information
University/education
Sjukhusbacken 10
Stockholm
11883
Sweden
Phone | +46 (0)8 524 800 00 |
---|---|
annsofie.wall@ki.se | |
Website | https://ki.se/kisos |
https://ror.org/056d84691 |
Funders
Funder type
Government
Government organisation / National government
- Alternative name(s)
- Swedish Research Council, VR
- Location
- Sweden
Private sector organisation / Trusts, charities, foundations (both public and private)
- Alternative name(s)
- Swedish Cancer Society
- Location
- Sweden
Government organisation / Local government
- Alternative name(s)
- Stockholm County Council
- Location
- Sweden
No information available
Results and Publications
Intention to publish date | 30/06/2026 |
---|---|
Individual participant data (IPD) Intention to share | Yes |
IPD sharing plan summary | Available on request |
Publication and dissemination plan | Planned publication in a high-impact peer reviewed journal |
IPD sharing plan | Data from the analysis will be available upon request from Elisabeth Epstein (elisabeth.epstein@ki.se). Anonymized clinical data will be shared after publication; images and videos will not be available. All patients gave their informed consent to participate, but not specifically that data would be shared. All data have been anonymized only the PI of the study has access to the anonymization key. |
Study outputs
Output type | Details | Date created | Date added | Peer reviewed? | Patient-facing? |
---|---|---|---|---|---|
Protocol file | version 1 | 06/11/2023 | No | No | |
Protocol file | version 2 | 28/05/2024 | No | No |
Additional files
Editorial Notes
28/05/2024: The following changes were made to the study record:
1. Uploaded protocol.
2. The acronym was changed from 'OV-AID' to 'OV-AID, Phase I'.
3. Ethics approval details added.
4. The target number of participants was changed from 'Minimum 600 participants, where at least 150 tumors are malignant, and at least 200 assessments are performed by non-experts' to 'Minimum 700 participants, and at least 400 assessments are performed by non-experts'.
5. Endogyn, Institute for the Care of Mother and Child, I.R.C.C.S. Burlo Garofolo Institute for Maternal and Child Health, Department of Obstetrics and Gynecology, IRCCS San Gerardo Dei Tintori, Department of Medicine and Surgery, University of Milano-Bicocca, Department of Obstetrics and Gynecology Fondazione Poliambulanza Istituto Ospedaliero, Obstetrics and Gynecology Unit, Forlì and Faenza Hospitals, Gynecology and Breast Care Center, Mater Olbia Hospital, Medical University of Lublin, Medical University of Silesia, Department of Obstetrics and Gynecology, Rizal Medical Center, Department of Obstetrics, Gynecology, and Reproduction, Hospital Universitario Dexeus, Department of Obstetrics and Gynaecology, Lithuanian University of Health Sciences were added to the study participating centres.
6. The interventions were updated.
7. Czech Republic, Italy, Poland, Philippines, Spain and Lithuania were added to the countries of recruitment.
06/11/2023: Uploaded protocol (not peer-reviewed) as an additional file.
8. Radiumhemmets Forskningsfonder was added to the funders.
9. The intention to publish date was changed from 01/03/2026 to 30/06/2026.
31/03/2023: Trial's existence confirmed by Swedish Cancer Society (Cancerfonden).