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
Prospectively registered
Protocol
Statistical analysis plan
Results
Individual participant data
Record updated in last year

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

Prof Elisabeth Epstein
Principal Investigator

Sjukhusbacken 10
Stockholm
11883
Sweden

ORCiD logoORCID ID 0000-0003-2298-7785
Phone +46 (0)706699019
Email elisabeth.epstein@ki.se

Study information

Study designProspective multicenter diagnostic accuracy study
Primary study designObservational
Secondary study designCohort study
Study setting(s)Hospital
Study typeDiagnostic
Participant information sheet Not available in web format, please use contact details to request a participant information sheet
Scientific titleDiagnostic 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 acronymOV-AID, Phase I
Study hypothesisThe 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
ConditionOvarian cancer
InterventionCurrent 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 typeOther
Primary outcome measureDiagnostic 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 measuresAccuracy 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 date01/01/2020
Overall study end date06/06/2026

Eligibility

Participant type(s)Patient
Age groupMixed
Lower age limit15 Years
SexFemale
Target number of participantsMinimum 700 participants, and at least 400 assessments are performed by non-experts.
Participant inclusion criteria1. Women aged ≥15 years
2. Newly detected ovarian tumor
3. Capable of understanding the study information and accepts participation
Participant exclusion criteria1. Aged <15 years
2. Patients who are not capable of understanding the study information or don't accept participation
Recruitment start date01/03/2021
Recruitment end date31/12/2025

Locations

Countries of recruitment

  • Czech Republic
  • Italy
  • Lithuania
  • Philippines
  • Poland
  • Spain
  • Sweden

Study participating centres

Södersjukhuset
Department of Obstetrics and Gynecology
Stockholm
11883
Sweden
Centrallasarettet Växjö
Department of Obstetrics and Gynecology
Växsjö
35234
Sweden
Karolinska University Hospital, Huddinge
Division of Gynecology and Reproduction
Huddinge
14186
Sweden
Aleris UltraGyn, Sabbatsbergs Hospital
Sabbatsbergs Hospital
Stockholm
11361
Sweden
Uppsala University Hospital
Department of Obstetrics and Gynecology
Uppsala
75185
Sweden
University Hospital Linköping
Department of Obstetrics and Gynecology
Linköping
58191
Sweden
Skåne University Hospital
Department of Obstetrics and Gynecology
Lund
22242
Sweden
Östra Hospital, Sahlgrenska University Hospital
Department of Obstetrics and Gynecology
Gothenburg
41685
Sweden
Hallands Hospital
Department of Obstetrics and Gynecology
Halmstad
30233
Sweden
Danderyds Hospital
Department of Obstetrics and Gynecology
Danderyd
18288
Sweden
GynStockholm, Cevita Care
Gynecology Clinic
Stockholm
11281
Sweden
Nyköpings Hospital
Department of Obstetrics and Gynecology
Nyköping
61139
Sweden
NÄL Hospital Trollhättan
Department of Obstetrics and Gynecology
Trollhättan
46173
Sweden
Örebro University Hospital
Department of Obstetrics and Gynecology
Örebro
70185
Sweden
Skåne University Hospital
Department of Obstetrics and Gynecology
Malmö
21428
Sweden
Karlstad Central Hospital
Department of Obstetrics and Gynecology
Karlstad
65230
Sweden
Endogyn
Stockholm
131 31
Sweden
Institute for the Care of Mother and Child
Prague
147 00
Czech Republic
I.R.C.C.S. Burlo Garofolo Institute for Maternal and Child Health,
Trieste
341 37
Italy
IRCCS San Gerardo Dei Tintori
Department of Obstetrics and Gynecology
Monza
20900
Italy
University of Milano-Bicocca
Department of Medicine and Surgery
Milan
20126
Italy
Fondazione Poliambulanza Istituto Ospedaliero
Department of Obstetrics and Gynecology
Brescia
25124
Italy
Forlì and Faenza Hospitals
Obstetrics and Gynecology Unit
Romagna
48018
Italy
Mater Olbia Hospital
Gynecology and Breast Care Center
Olbia
07026
Italy
Medical University of Lublin
Lublin
20059
Poland
Medical University of Silesia
Katowice
40055
Poland
Rizal Medical Center
Department of Obstetrics and Gynecology
Metro Manila
1600
Philippines
Hospital Universitario Dexeus
Department of Obstetrics, Gynecology, and Reproduction
Barcelona
08028
Spain
Lithuanian University of Health Sciences
Department of Obstetrics and Gynaecology
Kaunas
44307
Lithuania

Sponsor information

Karolinska Institute
University/education

Sjukhusbacken 10
Stockholm
11883
Sweden

Phone +46 (0)8 524 800 00
Email annsofie.wall@ki.se
Website https://ki.se/kisos
ROR logo "ROR" https://ror.org/056d84691

Funders

Funder type

Government

Vetenskapsrådet
Government organisation / National government
Alternative name(s)
Swedish Research Council, VR
Location
Sweden
Cancerfonden
Private sector organisation / Trusts, charities, foundations (both public and private)
Alternative name(s)
Swedish Cancer Society
Location
Sweden
Stockholms Läns Landsting
Government organisation / Local government
Alternative name(s)
Stockholm County Council
Location
Sweden
Radiumhemmets Forskningsfonder

No information available

Results and Publications

Intention to publish date30/06/2026
Individual participant data (IPD) Intention to shareYes
IPD sharing plan summaryAvailable on request
Publication and dissemination planPlanned publication in a high-impact peer reviewed journal
IPD sharing planData 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

ISRCTN88222986 Prospective_Study_Protocol_v1.pdf
ISRCTN88222986_PROTOCOL_V2.pdf

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).