Gastric CancerNCT04040374
Artificial Intelligence Versus Expert Endoscopists for Diagnosis of Gastric Cancer
A study testing AI-based diagnosis and The expert endoscopists-based diagnosis in people with Gastric Cancer, run by Tokyo University at 1 site in Japan.
Trial summary
Title: A single-center, retrospective randomized controlled trial of artificial intelligence (AI) versus expert endoscopists for diagnosis of gastric cancer in patients who underwent upper gastrointestinal endoscopy. Read more about this study
- Who is it for?
- Ages 20 years and older
- Conditions the study is for
- Gastric Cancer
- What is being tested?
- AI-based diagnosis and The expert endoscopists-based diagnosis
- Could I receive a placebo?
- No, everyone receives an active treatment
- How many people
- 500 participants
- Where
- 1 siteJapan
- Study dates
- 1 Jul 2019to 16 Nov 2019
- Phase
- Interventional
- 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 20 years and older
- All sexes
- No healthy volunteers
- Adult, Older adult
Who may be able to join
- Males or females aged ≥ 20 years who underwent upper gastrointestinal endoscopy at Tokyo University Hospital during 2018.
- Informed optout consent, obtained from each patient before completion of the study.
Who cannot join
- Patients who underwent gastrectomy.
- Patients who underwent transnasal upper gastrointestinal endoscopy.
Trial locations and contacts
1 site in 1 country.
Japan1 site
Department of Gastroenterology, Graduate School of Medicine, The University of Tokyo
Tokyo, 1138655
About this study
Official title: A Single-center, Retrospective, Open Label, Randomized Controlled Trial of Artificial Intelligence Versus Expert Endoscopists for Diagnosis of Gastric Cancer in Patients Who Underwent Upper Gastrointestinal Endoscopy
Title: A single-center, retrospective randomized controlled trial of artificial intelligence (AI) versus expert endoscopists for diagnosis of gastric cancer in patients who underwent upper gastrointestinal endoscopy.
Précis: this single-center, retrospective randomized controlled trial will include 500 outpatients who underwent upper gastrointestinal endoscopy for gastric cancer screening and will compare the diagnostic detection rate for gastric cancer of AI and expert endoscopists.
Read more
Objectives Primary Objective: to evaluate the diagnostic detection rate for gastric cancer of AI and expert endoscopists.
Secondary Objectives: to determine whether AI is not inferior to expert endoscopists in terms of the number of images analyzed for diagnosis of gastric cancer and intersection over union (IOU), and the detection rate of diagnosis of early and advanced gastric cancer.
Endpoints Primary Endpoint: diagnosis of gastric cancer. Secondary Endpoints: image based diagnosis of gastric cancer and IOU. Population: in total, 500 males and females aged ≥ 20 years who underwent upper gastrointestinal endoscopy for screening of gastric cancer at a single hospital in Japan.
Describe the Intervention: AI-based diagnosis of gastric cancer based on upper gastrointestinal endoscopy images.
Study Duration: 3 months.
Read the detailed description
Prior to Study: Total 500: Screen potential subjects by inclusion and exclusion criteria; obtain endoscopy images.
Randomization was performed.
Intervention: AI diagnosis was performed for 250 patients using upper gastrointestinal endoscopy images, and Expert endoscopists diagnosis was performed for 250 patients by same methods.
Primary analysis: Perform primary analysis of primary and secondary endpoints for 250 patients in each group
Cross over diagnosis between AI and expert endoscopists was performed.
Perform secondary analysis of agreement of gastric cancer diagnosis per images and IOU between AI and expert endoscopists for 500 patients.
- Conditions
- Gastric Cancer
- Being tested
- AI-based diagnosis, The expert endoscopists-based diagnosis
- Keywords
- artificial intelligence, gastric cancer
- Medical subject headings
- Stomach Neoplasms
What participants receive
What participants receive. In a randomised study each person is assigned to one group by chance.
AI-based diagnosisDiagnostic test
AI-based diagnosis will be performed based on analysis of endoscopic images (Olympus Optical, Tokyo, Japan). The investigators will use the Single Shot MultiBox Detector (SSD), a deep neural network architecture (https://arxiv.org/abs/1512.02325), and an optimal diagnostic cutoff from a prior report2. The AI system reviewed endoscopy images and reported those in which gastric cancer was detected, together with the coordinates (X, Y) of the lesions.
The expert endoscopists-based diagnosisDiagnostic test
The expert endoscopists are two physicians with experience of more than 20,000 endoscopies. The expert endoscopists will review the endoscopy images of each patient for 5 min. They will then report endoscopy images in which gastric cancer was detected and manually annotate the lesions in those images.
| Study group | Role | What they receive |
|---|---|---|
| AI-based diagnosis | Experimental | • AI-based diagnosis will be performed based on analysis of endoscopic images (Olympus Optical, Tokyo, Japan). The investigators will use the Single Shot MultiBox Detector (SSD), a deep neural network architecture (https://arxiv.org/abs/1512.02325), and an optimal diagnostic cutoff from a prior report2. The AI system reviewed endoscopy images and reported those in which gastric cancer was detected, together with the coordinates (X, Y) of the lesions. Receives: Diagnostic Test: AI-based diagnosis |
| Expert endoscopist diagnosis | Active comparator | The expert endoscopists are two physicians with experience of more than 20,000 endoscopies. The expert endoscopists will review the endoscopy images of each patient for 5 min. They will then report endoscopy images in which gastric cancer was detected and manually annotate the lesions in those images. Receives: Diagnostic Test: The expert endoscopists-based diagnosis |
What is being measured
The primary outcome is the main question the study is designed to answer.
Per patient diagnosis of gastric cancer
Number of Participants
Measured: Up to 6 weeks from study start
Secondary outcomes (5)
Number of images analyzed for diagnosis of gastric cancer
Number of upper gastrointestinal endoscopy images
Measured: Up to 6 weeks from study start
Intersection over union (IOU) of gastric lesions
A value between 0 and 1
Measured: Up to 6 weeks from study start
Diagnosis of advanced gastric cancer
Number of Participants diagnosed with advanced gastric cancer
Measured: Up to 6 weeks from study start
Diagnosis of early gastric cancer
Number of Participants diagnosed with early gastric cancer
Measured: Up to 6 weeks from study start
Agreement on image and IOU based diagnosis of gastric cancer between AI and expert endoscopists
Number of images and IOU value (between 0 and 1)
Measured: Up to 12 weeks from study start
Timeline
From the start of the study to its completion; the mark is today. Estimated dates are the sponsor’s plan.
- First posted31 Jul 2019
- Study start1 Jul 2019
- Primary completion1 Oct 2019
- Study completion16 Nov 2019
Resources
- Official record on ClinicalTrials.govThe registry entry this page is built from, with its full change history.
- Publications (3)Papers the sponsor has linked to this study.
- Other trials for Gastric CancerStudies of the same condition, open and under way.
- 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
- Interventional
- Phase
- Phase N/A
- Primary purpose
- Diagnosis
- Allocation
- Randomised
- Intervention model
- Parallel groups
- Masking
- None (open label)
- Enrolment
- 500 participants (actual)
Sponsor and investigators
- Lead sponsor
- Tokyo University
- Sponsor type
- University, hospital or other
- Responsible party
- Principal investigator, Ryota Niikura, Tokyo University
- Investigators
- Ryota Niikura, MD, Principal investigator, Tokyo University
IDs, dates and publications
- ClinicalTrials.gov ID
- NCT04040374
- Sponsor's protocol ID
- 11931-(1)
- Status last verified
- Nov 2019
- First submitted
- 19 Jul 2019
- Last updated
- 20 Nov 2019
- Results posted
- No
- Data monitoring committee
- No
- FDA-regulated drug
- No
- FDA-regulated device
- No
- Individual data sharing
- No
Publications
Cancer Genome Atlas Research Network. Comprehensive molecular characterization of gastric adenocarcinoma. Nature. 2014 Sep 11;513(7517):202-9. doi: 10.1038/nature13480. Epub 2014 Jul 23.
PubMed 25079317Hirasawa T, Aoyama K, Tanimoto T, Ishihara S, Shichijo S, Ozawa T, Ohnishi T, Fujishiro M, Matsuo K, Fujisaki J, Tada T. Application of artificial intelligence using a convolutional neural network for detecting gastric cancer in endoscopic images. Gastric Cancer. 2018 Jul;21(4):653-660. doi: 10.1007/s10120-018-0793-2. Epub 2018 Jan 15.
PubMed 29335825Niikura R, Aoki T, Shichijo S, Yamada A, Kawahara T, Kato Y, Hirata Y, Hayakawa Y, Suzuki N, Ochi M, Hirasawa T, Tada T, Kawai T, Koike K. Artificial intelligence versus expert endoscopists for diagnosis of gastric cancer in patients who have undergone upper gastrointestinal endoscopy. Endoscopy. 2022 Aug;54(8):780-784. doi: 10.1055/a-1660-6500. Epub 2022 May 4.
PubMed 34607377
Study at a glance
From the registry record, last updated by the sponsor on 20 Nov 2019. Recruitment status is as the sponsor reported it: confirm with the study team.
- Official title
- A Single-center, Retrospective, Open Label, Randomized Controlled Trial of Artificial Intelligence Versus Expert Endoscopists for Diagnosis of Gastric Cancer in Patients Who Underwent Upper Gastrointestinal Endoscopy
- ClinicalTrials.gov ID
- NCT04040374
- Acronym / sponsor ID
- 11931-(1)
- Conditions
- Gastric Cancer
- Keywords
- artificial intelligence, gastric cancer
- Study type
- Interventional
- Recruitment status
- Completed
- Enrolment
- 500 participants (actual)
- Lead sponsor
- Tokyo UniversityUniversity, hospital or other
- Study start
- 1 Jul 2019 (actual)
- Primary completion
- 1 Oct 2019 (actual)
- Study completion
- 16 Nov 2019 (actual)
- First posted
- 31 Jul 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.
Title: A single-center, retrospective randomized controlled trial of artificial intelligence (AI) versus expert endoscopists for diagnosis of gastric cancer in patients who underwent upper gastrointestinal endoscopy.
Précis: this single-center, retrospective randomized controlled trial will include 500 outpatients who underwent upper gastrointestinal endoscopy for gastric cancer screening and will compare the diagnostic detection rate for gastric cancer of AI and expert endoscopists.
Objectives Primary Objective: to evaluate the diagnostic detection rate for gastric cancer of AI and expert endoscopists.
Secondary Objectives: to determine whether AI is not inferior to expert endoscopists in terms of the number of images analyzed for diagnosis of gastric cancer and intersection over union (IOU), and the detection rate of diagnosis of early and advanced gastric cancer.
Endpoints Primary Endpoint: diagnosis of gastric cancer. Secondary Endpoints: image based diagnosis of gastric cancer and IOU. Population: in total, 500 males and females aged ≥ 20 years who underwent upper gastrointestinal endoscopy for screening of gastric cancer at a single hospital in Japan.
Describe the Intervention: AI-based diagnosis of gastric cancer based on upper gastrointestinal endoscopy images.
Study Duration: 3 months.
Detailed description
Prior to Study: Total 500: Screen potential subjects by inclusion and exclusion criteria; obtain endoscopy images.
Randomization was performed.
Intervention: AI diagnosis was performed for 250 patients using upper gastrointestinal endoscopy images, and Expert endoscopists diagnosis was performed for 250 patients by same methods.
Primary analysis: Perform primary analysis of primary and secondary endpoints for 250 patients in each group
Cross over diagnosis between AI and expert endoscopists was performed.
Perform secondary analysis of agreement of gastric cancer diagnosis per images and IOU between AI and expert endoscopists for 500 patients.
Study design
- Primary purpose
- Diagnosis
- Allocation
- Randomised
- Intervention model
- Parallel groups
- Masking
- None (open label)
- Number of arms
- 2
| Arm | Type | Receives |
|---|---|---|
| AI-based diagnosis | Experimental | Diagnostic Test: AI-based diagnosis• AI-based diagnosis will be performed based on analysis of endoscopic images (Olympus Optical, Tokyo, Japan). The investigators will use the Single Shot MultiBox Detector (SSD), a deep neural network architecture (https://arxiv.org/abs/1512.02325), and an optimal diagnostic cutoff from a prior report2. The AI system reviewed endoscopy images and reported those in which gastric cancer was detected, together with the coordinates (X, Y) of the lesions. |
| Expert endoscopist diagnosis | Active comparator | Diagnostic Test: The expert endoscopists-based diagnosisThe expert endoscopists are two physicians with experience of more than 20,000 endoscopies. The expert endoscopists will review the endoscopy images of each patient for 5 min. They will then report endoscopy images in which gastric cancer was detected and manually annotate the lesions in those images. |
Who may qualify
- Ages
- 20 years and older
- Sex
- All
- Healthy volunteers
- Not accepted
- Age groups
- Adult, Older adult
Key inclusion criteria (2 listed)
- Males or females aged ≥ 20 years who underwent upper gastrointestinal endoscopy at Tokyo University Hospital during 2018.
- Informed optout consent, obtained from each patient before completion of the study.
Key exclusion criteria (2 listed)
- Patients who underwent gastrectomy.
- Patients who underwent transnasal upper gastrointestinal endoscopy.
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 |
|---|---|---|
| AI-based diagnosisAI-based diagnosis will be performed based on analysis of endoscopic images (Olympus Optical, Tokyo, Japan). The investigators will use the Single Shot MultiBox Detector (SSD), a deep neural network architecture (https://arxiv.org/abs/1512.02325), and an optimal diagnostic cutoff from a prior report2. The AI system reviewed endoscopy images and reported those in which gastric cancer was detected, together with the coordinates (X, Y) of the lesions. | Diagnostic test | AI-based diagnosis |
| The expert endoscopists-based diagnosisThe expert endoscopists are two physicians with experience of more than 20,000 endoscopies. The expert endoscopists will review the endoscopy images of each patient for 5 min. They will then report endoscopy images in which gastric cancer was detected and manually annotate the lesions in those images. | Diagnostic test | Expert endoscopist diagnosis |
Primary outcome
Per patient diagnosis of gastric cancer
Time frame: Up to 6 weeks from study start
Number of Participants
5 secondary outcomes
Number of images analyzed for diagnosis of gastric cancer
Time frame: Up to 6 weeks from study start
Intersection over union (IOU) of gastric lesions
Time frame: Up to 6 weeks from study start
Diagnosis of advanced gastric cancer
Time frame: Up to 6 weeks from study start
Diagnosis of early gastric cancer
Time frame: Up to 6 weeks from study start
Agreement on image and IOU based diagnosis of gastric cancer between AI and expert endoscopists
Time frame: Up to 12 weeks from study start
Results and safety
The study is completed, but results are not available in the source record. That does not mean the treatment did or did not work.
Research links
- Official record on ClinicalTrials.govLast updated by the sponsor 20 Nov 2019.
- Background: PubMed 25079317Cancer Genome Atlas Research Network. Comprehensive molecular characterization of gastric adenocarcinoma. Nature. 2014 Sep 11;513(7517):202-9. doi: 10.1038/nature13480. Epub 2014 Jul 23.
- Background: PubMed 29335825Hirasawa T, Aoyama K, Tanimoto T, Ishihara S, Shichijo S, Ozawa T, Ohnishi T, Fujishiro M, Matsuo K, Fujisaki J, Tada T. Application of artificial intelligence using a convolutional neural network for detecting gastric cancer in endoscopic images. Gastric Cancer. 2018 Jul;21(4):653-660. doi: 10.1007/s10120-018-0793-2. Epub 2018 Jan 15.
- Derived from this study: PubMed 34607377Niikura R, Aoki T, Shichijo S, Yamada A, Kawahara T, Kato Y, Hirata Y, Hayakawa Y, Suzuki N, Ochi M, Hirasawa T, Tada T, Kawai T, Koike K. Artificial intelligence versus expert endoscopists for diagnosis of gastric cancer in patients who have undergone upper gastrointestinal endoscopy. Endoscopy. 2022 Aug;54(8):780-784. doi: 10.1055/a-1660-6500. Epub 2022 May 4.
- Individual participant dataSharing planned: No
Related trials for Gastric Cancer
RecruitingPhase 1/2
Study of INBRX-106 and INBRX-106 in Combination With Pembrolizumab (Keytruda®) in Subjects With Locally Advanced or Metastatic Solid Tumors (Hexavalent OX40 Agonist)
Solid Tumor, Non-Small Cell Lung Cancer
RecruitingPhase 2/3
Multicenter Validation Trial of [18F]AlF-FAPI-74 for PET Imaging of Cancer-associated Fibroblasts Through Fibroblast Activation Protein Inhibitors (FAPI) in Different Tumor Types
Oesophageal Cancer, Gastric Cancer
Not yet recruitingPhase 1
GK01 Cell Therapy in Gastric Cancer With Peritoneal Metastasis
Gastric Cancer (GC)
RecruitingPhase 3
A Study of Neoadjuvant-adjuvant Durvalumab and FLOT Chemotherapy Followed by Adjuvant Durvalumab in Chinese Patients With Resectable GC/GEJC.
Gastric, Esophagogastric Junction
Active, not recruitingEarly Phase 1
Iomab-ACT: A Pilot Study of 131-I Apamistamab Followed by CD19-Targeted CAR T-Cell Therapy for Patients With Relapsed or Refractory B-Cell Acute Lymphoblastic Leukemia or Diffuse Large B-Cell Lymphoma
B-ALL, DLBCL
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.
Ryota Niikura, MD principal investigator
Tokyo University
1 site in 1 country: see every site and its status.
Questions about this trial
What is this clinical trial studying?
A study testing AI-based diagnosis and The expert endoscopists-based diagnosis in people with Gastric Cancer, run by Tokyo University at 1 site in Japan.
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 2 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: finished, as of the sponsor's last update on 20 Nov 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 Japan. 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?
The study is completed, but results are not available in the source record. That does not mean the treatment did or did not work.
How can a doctor refer a patient or contact the research team?
The record lists no contact. The official record names the sponsor, who can be asked directly. AzTrials does not enrol participants or take referrals.
What does the primary outcome measure?
Per patient diagnosis of gastric cancer (time frame: Up to 6 weeks from study start). It is what the study was designed to measure, not a finding.
Where can I read the original study information?
On the ClinicalTrials.gov record for NCT04040374, which also lists 3 linked publications.
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 20 Nov 2019.