Prostate CancerGOPI-SegmNCT04191980
Deep Learning for Prostate Segmentation
An observational study of Prostate Cancer, run by Hospices Civils de Lyon at 1 site in France.
Trial summary
Because the diagnostic criteria for prostate cancer are different in the peripheral and the transition zone, prostate segmentation is needed for any computer-aided diagnosis system aimed at characterizing prostate lesions on magnetic resonance (MR) images. Read more about this study
- Who is it for?
- Ages 18 years and older, men only
- Conditions the study is for
- Prostate Cancer
- What is being tested?
- Comparison of prostate multi-zone segmentation obtained with an automatic deep learning-based algorithm and two expert radiologists
- How many people
- 62 participants
- Where
- 1 siteFrance
- Study dates
- 1 Feb 2019to Jun 2020
- Phase
- Observational
- Are there results?
- None posted in the registry
Key requirements
Who can take part, as listed by the sponsor. Only the study team can confirm whether you are eligible, so take this list to your doctor.
- Ages 18 years and older
- Men only
- No healthy volunteers
- Adult, Older adult
Study population: Random selection in the Picture Archiving and Communication System (PACS) of the Hospices Civils de Lyon among examinations performed between 2016 and 2019
Who may be able to join
- Prostate MRI contained in the PACS of the Hospices Civils de Lyon
- Performed in 2016-2019
Who cannot join
- MRIs from patients who already had treatment for prostate cancer
Trial locations and contacts
1 site in 1 country.
France1 site, 1 recruiting
- Recruiting
Hôpital Edouard Herriot
Lyon, 69008
Olivier ROUVIERE, Pr
About this study
Official title: Multi-zone Computer-aided Prostate Segmentation on MR Images Using a Deep Learning-based Approach
Because the diagnostic criteria for prostate cancer are different in the peripheral and the transition zone, prostate segmentation is needed for any computer-aided diagnosis system aimed at characterizing prostate lesions on magnetic resonance (MR) images. Manual segmentation is time consuming and may differ between radiologists with different expertise. We developed and trained a convolutional neural network algorithm for segmenting the whole prostate, the transition zone and the anterior fibromuscular stroma on T2-weighted images of 787 MRIs from an existing prospective radiological pathological correlation database containing prostate MRI of patients treated by prostatectomy between 2008 and 2014 (CLARA-P database).
The purpose of this study is to validate this algorithm on an independent cohort of patients.
- Conditions
- Prostate Cancer
- Being tested
- Comparison of prostate multi-zone segmentation obtained with an automatic deep learning-based algorithm and two expert radiologists
- Keywords
- prostate segmentation, MR images
- Medical subject headings
- Prostatic Neoplasms
What participants receive
What participants receive. In a randomised study each person is assigned to one group by chance.
Comparison of prostate multi-zone segmentation obtained with an automatic deep learning-based algorithm and two expert radiologistsOther
The algorithm is used to perform a multizone segmentation of the prostate including delineation of : the whole prostate contours, the transition zone contours, the anterior fibromuscular stroma.
The contours is independently corrected by 2 radiologists. The corrected contours of the different zones will be stored and for each zone 6 different metrics will be used to evaluate the difference between the initial and corrected contours:
- Mean Mesh Distance: Average Boundary Distance (ABD) for each point of the reference segmentation. The distance to the closest point of the compared segmentation is first computed. Then the average of all these distances is computed and gives the ABD
- General Hausdorff distance (HD)
- 95% percentile (P) of the HD and the 95th (P) of the asymmetric HD distribution
- 95% HD modified (HD95_1): different approach by first computing the 95th (P) of the asymmetric HD then taking the maximum
- Dice coefficient
- Difference in volumes
| Study group | Role | What they receive |
|---|---|---|
| Patients with a MRI on a 3 Tesla (T) unit | The total validation cohort is composed of axial T2-weighted images of the prostate obtained from 31 prostate MRIs on a 3T unit randomly chosen among the prostate MRIs performed at the Hospices Civils de Lyon in 20162015-2019 Receives: Other: Comparison of prostate multi-zone segmentation obtained with an automatic deep learning-based algorithm and two expert radiologists | |
| Patients with a MRI on a 1.5 Tesla unit | The total validation cohort is composed of axial T2-weighted images of the prostate obtained from 31 prostate MRIs on a 1.5T unit randomly chosen among the prostate MRIs performed at the Hospices Civils de Lyon in 20162015-2019 Receives: Other: Comparison of prostate multi-zone segmentation obtained with an automatic deep learning-based algorithm and two expert radiologists |
What is being measured
The primary outcome is the main question the study is designed to answer.
Mean Mesh Distance (Mean) between the contours of the whole prostate made by the algorithm and the two radiologists
The Mean Mesh Distance corresponds to the Average Boundary Distance (ABD) for each point of the reference segmentation. The distance to the closest point of the compared segmentation is first computed. Then the average of all these distances is computed and gives the ABD.
The Mean Mesh Distance between the contours of the whole prostate made by the algorithm and each radiologist will be used as primary outcome measure.
Measured: Month 11
Timeline
From the start of the study to its completion; the mark is today. Estimated dates are the sponsor’s plan.
- First posted10 Dec 2019
- Study start1 Feb 2019
- Primary completionJan 2020 (estimated)
- Study completionJun 2020 (estimated)
Resources
- Official record on ClinicalTrials.govThe registry entry this page is built from, with its full change history.
- Other trials for Prostate CancerStudies of the same condition, open and under way.
- More trials run by Hospices Civils de LyonThe sponsor's other registered studies.
- What the trial phases meanHow a treatment moves from first tests in people to approval.
More details
For doctors and researchers: how the study is designed, who runs it, and its registry IDs.
Study design
- Study type
- Observational
- Observational model
- Cohort
- Time perspective
- Retrospective
- Enrolment
- 62 participants (estimated)
Sponsor and investigators
- Lead sponsor
- Hospices Civils de Lyon
- Sponsor type
- University, hospital or other
- Responsible party
- Sponsor
IDs, dates and publications
- ClinicalTrials.gov ID
- NCT04191980
- Sponsor's protocol ID
- GOPI-Segmentation_2019
- Acronym
- GOPI-Segm
- Status last verified
- Dec 2019
- First submitted
- 6 Dec 2019
- Last updated
- 10 Dec 2019
- Results posted
- No
Study at a glance
From the registry record, last updated by the sponsor on 10 Dec 2019. Recruitment status is as the sponsor reported it: confirm with the study team.
- Official title
- Multi-zone Computer-aided Prostate Segmentation on MR Images Using a Deep Learning-based Approach
- ClinicalTrials.gov ID
- NCT04191980
- Acronym / sponsor ID
- GOPI-Segm / GOPI-Segmentation_2019
- Conditions
- Prostate Cancer
- Keywords
- prostate segmentation, MR images
- Study type
- Observational
- Recruitment status
- Unknown status
- Enrolment
- 62 participants (estimated)
- Lead sponsor
- Hospices Civils de LyonUniversity, hospital or other
- Study start
- 1 Feb 2019 (actual)
- Primary completion
- Jan 2020 (estimated)
- Study completion
- Jun 2020 (estimated)
- First posted
- 10 Dec 2019 (actual)
- Results
- Not posted in the source record
Clinical summary
The research question as the sponsor registered it. This describes what the study plans to test, not what it found.
Because the diagnostic criteria for prostate cancer are different in the peripheral and the transition zone, prostate segmentation is needed for any computer-aided diagnosis system aimed at characterizing prostate lesions on magnetic resonance (MR) images. Manual segmentation is time consuming and may differ between radiologists with different expertise. We developed and trained a convolutional neural network algorithm for segmenting the whole prostate, the transition zone and the anterior fibromuscular stroma on T2-weighted images of 787 MRIs from an existing prospective radiological pathological correlation database containing prostate MRI of patients treated by prostatectomy between 2008 and 2014 (CLARA-P database).
The purpose of this study is to validate this algorithm on an independent cohort of patients.
Study design
- Observational model
- Cohort
- Time perspective
- Retrospective
- Number of arms
- 2
| Arm | Type | Receives |
|---|---|---|
| Patients with a MRI on a 3 Tesla (T) unit | – | Other: Comparison of prostate multi-zone segmentation obtained with an automatic deep learning-based algorithm and two expert radiologistsThe total validation cohort is composed of axial T2-weighted images of the prostate obtained from 31 prostate MRIs on a 3T unit randomly chosen among the prostate MRIs performed at the Hospices Civils de Lyon in 20162015-2019 |
| Patients with a MRI on a 1.5 Tesla unit | – | Other: Comparison of prostate multi-zone segmentation obtained with an automatic deep learning-based algorithm and two expert radiologistsThe total validation cohort is composed of axial T2-weighted images of the prostate obtained from 31 prostate MRIs on a 1.5T unit randomly chosen among the prostate MRIs performed at the Hospices Civils de Lyon in 20162015-2019 |
Who may qualify
- Ages
- 18 years and older
- Sex
- Male only
- Healthy volunteers
- Not accepted
- Age groups
- Adult, Older adult
- Study population
- Random selection in the Picture Archiving and Communication System (PACS) of the Hospices Civils de Lyon among examinations performed between 2016 and 2019
Key inclusion criteria (2 listed)
- Prostate MRI contained in the PACS of the Hospices Civils de Lyon
- Performed in 2016-2019
Key exclusion criteria (1 listed)
- MRIs from patients who already had treatment for prostate cancer
Eligibility is decided by the study team after screening; this overview does not establish that a patient qualifies. Full inclusion and exclusion criteria.
Interventions
| Intervention | Type | Arms |
|---|---|---|
| Comparison of prostate multi-zone segmentation obtained with an automatic deep learning-based algorithm and two expert radiologistsThe algorithm is used to perform a multizone segmentation of the prostate including delineation of : the whole prostate contours, the transition zone contours, the anterior fibromuscular stroma. The contours is independently corrected by 2 radiologists. The corrected contours of the different zones will be stored and for each zone 6 different metrics will be used to evaluate the difference between the initial and corrected contours: * Mean Mesh Distance: Average Boundary Distance (ABD) for each point of the reference segmentation. The distance to the closest point of the compared segmentation is first computed. Then the average of all these distances is computed and gives the ABD * General Hausdorff distance (HD) * 95% percentile (P) of the HD and the 95th (P) of the asymmetric HD distribution * 95% HD modified (HD95_1): different approach by first computing the 95th (P) of the asymmetric HD then taking the maximum * Dice coefficient * Difference in volumes | Other | Patients with a MRI on a 1.5 Tesla unit, Patients with a MRI on a 3 Tesla (T) unit |
Primary outcome
Mean Mesh Distance (Mean) between the contours of the whole prostate made by the algorithm and the two radiologists
Time frame: Month 11
The Mean Mesh Distance corresponds to the Average Boundary Distance (ABD) for each point of the reference segmentation. The distance to the closest point of the compared segmentation is first computed. Then the average of all these distances is computed and gives the ABD. The Mean Mesh Distance between the contours of the whole prostate made by the algorithm and each radiologist will be used as primary outcome measure.
Results and safety
Results are not available in the source record.
Research links
- Official record on ClinicalTrials.govLast updated by the sponsor 10 Dec 2019.
Related trials for Prostate Cancer
RecruitingPhase 1/2
Docetaxel and SX-682 in Recurrent/Metastatic Head and Neck Squamous Cell Carcinoma, Salivary Gland Carcinoma, and Advanced Prostate Cancer
Head and Neck Cancer, Head and Neck Squamous Cell Carcinoma
Enrolling by invitationObservational study
Natural History Study of Early Life Exposures in Agriculture (ELEA)
Prostate Cancer, Leukemia
RecruitingPhase 2
Testing the Effectiveness of Two Immunotherapy Drugs (Nivolumab and Ipilimumab) With One Anti-cancer Targeted Drug (Cabozantinib) for Rare Genitourinary Tumors
Bladder Adenocarcinoma, Bladder Clear Cell Adenocarcinoma
RecruitingObservational study
cfDNA Assay Prospective Observational Validation for Early Cancer Detection and Minimal Residual Disease
Brain Cancer, Breast Cancer
RecruitingPhase 3
Diagnostic Performance of [18F]PSMA-1007 PET/CT Imaging in Patients With Newly-Diagnosed Prostate Cancer
Prostate Cancer
Referral and contact
AzTrials does not enrol participants or take referrals. Contact the study team or a site listed below; they decide who can take part. This study is not recruiting at the moment.
1 site in 1 country: see every site and its status.
Questions about this trial
What is this clinical trial studying?
An observational study of Prostate Cancer, run by Hospices Civils de Lyon at 1 site in France.
The full registered description is in the About this study section and the official record.
Who may be eligible to take part?
The sponsor lists 2 inclusion and 1 exclusion criteria. Eligibility is decided by the study team after screening, so read the full criteria and contact a listed site.
Is this clinical trial currently recruiting?
The record says: status not confirmed, as of the sponsor's last update on 10 Dec 2019. Status can change between updates, so confirm with the study contact before making plans.
Where is the study taking place?
The record lists 1 site in France. Whether a site is taking part right now should be confirmed with that site. See every site.
What are the possible benefits and risks?
They depend on the study and the treatment, and no study can promise a benefit. The study team explains the known risks during informed consent, before anyone joins; the record itself does not list them.
Are results available for this study?
Results are not available in the source record.
How can a doctor refer a patient or contact the research team?
Contact Olivier ROUVIERE, Pr (472 11 61 67 ext. +33, Olivier.rouviere@chu-lyon.fr), or a site near the patient. AzTrials does not enrol participants or take referrals.
What does the primary outcome measure?
Mean Mesh Distance (Mean) between the contours of the whole prostate made by the algorithm and the two radiologists (time frame: Month 11). It is what the study was designed to measure, not a finding.
Where can I read the original study information?
Does a listing mean the treatment is approved or proven to work?
No. A listing means the study is registered. It does not show that the treatment is safe, works, or is approved by a regulator.
How often is this information updated?
AzTrials copies changed records from ClinicalTrials.gov every night and reloads the whole registry every week. The sponsor last updated this record on 10 Dec 2019.