X-RayNCT07117266
Clinical Application of Automated Interpretation System for Chest X-Ray Images Based on Multimodal Large Models
A study testing radiologists reference AI reports in people with X-Ray and AI (Artificial Intelligence), run by Union Hospital, Tongji Medical College, Huazhong University of Science and Technology at 3 sites in China.
Trial summary
There's a global shortage of radiologists. Radiology AI's automatic reporting is key for boosting efficiency and meeting patient needs, especially in resource-poor areas. Multimodal large models enable medical image auto-reporting systems. Read more about this study
- Who is it for?
- Any ageHealthy volunteers can take part
- Conditions the study is for
- X-Ray, AI (Artificial Intelligence), Radiology
- What is being tested?
- radiologists reference AI reports
- Could I receive a placebo?
- No, everyone receives an active treatment
- How many people
- 296 participants
- Where
- 3 sitesChina
- Study dates
- 1 Aug 2025to 12 Aug 2025
- 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 Any age
- All sexes
- Healthy volunteers accepted
- Child, Adult, Older adult
Who may be able to join
- clinically suspected thoracic diseases (such as pneumonia, tuberculosis, or lung cancer) requiring CXR-assisted diagnosis;
- patients providing written informed consent for research data use;
- complete clinical records (including chief complaints, medical history, and laboratory test results);
- patients with no historical chest X-ray images and no need for comparison with previous chest X-ray images;
- Patients who underwent only posteroanterior (PA) chest X-rays without lateral chest X-rays.
Who cannot join
- substandard CXR image quality (including severe motion artifacts, over-/underexposure, or missing anatomical structures);
- pregnant or lactating women.
Trial locations and contacts
3 sites in 1 country.
China3 sites
The First Affiliated Hospital of Henan University of science and technology
Luoyang, 471003
Union Hospital Affiliated to Tongji Medical College, Huazhong University of Science and Technology
Wuhan, 430023
The First Affiliated Hospital of Zhengzhou University
Zhengzhou, 450002
About this study
Official title: A DeepSeek-Powered AI System for Automated Chest Radiograph Interpretation in Clinical Practice
There's a global shortage of radiologists. Radiology AI's automatic reporting is key for boosting efficiency and meeting patient needs, especially in resource-poor areas. Multimodal large models enable medical image auto-reporting systems. ChatGPT 4o can diagnose medical images but has issues like being closed-source and "hallucinations." The new open-source Janus Pro 1B-with strong performance, "any-to-any" capability, low cost, and open access-shows potential for medical imaging tasks with training. But little research explores its use here; most models are general, lacking field-specific optimization and systematic evaluation. This study will develop Janus Pro 1B-CXR (a medical image-specific model) via public data, test its value in diagnosis and reporting, and build an efficient automated system.
Read the detailed description
There is a global shortage of radiologists, and the automatic report generation function of radiology AI systems is crucial for improving medical efficiency and meeting patient needs, especially those in areas with scarce medical resources. Multimodal large models have made it possible to develop automatic report generation systems for medical images. Although ChatGPT 4o has certain capabilities in medical image diagnosis, it has issues such as being closed-source and hallucination. The recently launched open-source multimodal large model Janus-Pro has advantages including high performance, "Any to any", low cost, and open-source; after training and fine-tuning, it has the potential for medical image diagnosis and report generation. However, there is currently a lack of research on the application of Janus Pro 1B in image diagnosis; existing models are mostly general-purpose, lacking in-depth optimization for specific fields and systematic multi-dimensional evaluation methods. This study aims to develop a large model specialized in medical images, Janus Pro 1B-CXR, using public databases, verify its application value in image diagnosis and radiology report generation, and construct an efficient and accurate automated medical image analysis and diagnostic assistance system.
- Conditions
- X-Ray, AI (Artificial Intelligence), Radiology
- Being tested
- radiologists reference AI reports
- Keywords
- radiology, x-ray, AI
What participants receive
What participants receive. In a randomised study each person is assigned to one group by chance.
radiologists reference AI reportsOther
Radiologists generate reports with reference to AI reports
| Study group | Role | What they receive |
|---|---|---|
| AI-assisted group | Experimental | Radiologists generate reports with reference to AI reports Receives: Other: radiologists reference AI reports |
| Standard care group | No intervention | Radiologists generate reports independently without referencing AI reports, following standard clinical procedures. |
What is being measured
The primary outcome is the main question the study is designed to answer.
Report quality scores in the prospective study
In this prospective study, the quality of reports generated by junior radiologists was assessed using a 5-point Likert scale titled "Radiology Report Quality Assessment Scale", where the minimum value is 1 and the maximum value is 5, with higher scores indicating better report quality. These scores were compared between the AI-assisted group (junior radiologists using AI tools for report generation) and the standard care group (junior radiologists generating reports without AI assistance).
Measured: 1 week
Agreement evaluation in the prospective study
In this prospective study, the agreement between reports generated by junior radiologists and standard reports was assessed using the RADPEER scoring system-a peer review program established by the American College of Radiology (ACR) designed to evaluate the interpretation accuracy of radiologists-where the degree of concordance is measured by grading discrepancies and agreements according to specific criteria that also account for the clinical significance of differences. The RADPEER system uses a 5-category scale with a minimum value of 1 and a maximum value of 5, where higher scores indicate greater agreement between the generated reports and standard reports.
Measured: 1 week
Pairwise preference tests in the prospective study
In this prospective study, the preference between reports generated by junior radiologists in the AI-assisted group versus the standard care group was evaluated using the "Expert Pairwise Preference Assessment Tool", a structured measurement tool designed to quantify expert consensus on report superiority. The assessment was conducted by a panel of 5 independent radiology experts, who reviewed paired reports (one from the AI-assisted group and one from the standard-care group for the same clinical case) and individually indicated their preference for which report was more clinically valuable, accurate, or comprehensive. The unit of measure for this outcome is the "Percentage of paired cases with majority expert preference", defined as cases where ≥3 out of 5 experts expressed a clear preference for either the AI-assisted or standard care report.
Measured: 1 week
Reading Time in the prospective study
The time from when radiologists began examining chest radiographs to the completion of final reports, comparing efficiency between the AI-assisted and Standard-care groups.
Measured: 1 week
Secondary outcomes (3)
Report Quality Score in the retrospective study
In this retrospective study, the quality of reports generated by Janus-Pro-CXR, Janus-Pro, and ChatGPT 4o (compared to standard reports) was assessed using the 5-point Likert scale titled "Radiology Report Quality Assessment Scale". The scale has a minimum value of 1 and a maximum value of 5, with higher scores indicating better report quality.
Measured: 1 week
Agreement Evaluation in the retrospective study
In this retrospective study, the agreement between reports generated by Janus-Pro-CXR, Janus-Pro, and ChatGPT 4o and standard reports was assessed using the measurement tool titled "RADPEER Scoring System"-a structured peer review system established by the American College of Radiology (ACR) for evaluating radiological interpretation accuracy. The RADPEER system uses a 5-category scale with a minimum value of 1 and a maximum value of 5, where higher scores indicate greater agreement between the generated reports and standard reports.
Measured: 1 week
Pairwise preference tests in the retrospective study
In this retrospective study, the preference between reports generated by Janus-Pro-CXR, Janus-Pro, and ChatGPT 4o (compared to standard reports) was evaluated using the "Expert Pairwise Preference Assessment Tool"-a structured measurement tool designed to quantify expert consensus on report superiority. The assessment was conducted by a panel of 5 independent radiology experts, who reviewed paired reports (matching reports from a model-generated report vs. a standard report for the same clinical case) and individually indicated their preference based on predefined criteria including clinical accuracy, completeness, clarity, and diagnostic utility. The unit of measure for this outcome is the "Percentage of paired cases with majority expert preference", defined as cases where ≥3 out of 5 experts expressed a clear preference for one report over the other.
Measured: 1 week
Timeline
From the start of the study to its completion; the mark is today. Estimated dates are the sponsor’s plan.
- First posted12 Aug 2025
- Study start1 Aug 2025
- Primary completion12 Aug 2025
- Study completion12 Aug 2025
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 X-RayStudies of the same condition, open and under way.
- More trials run by Union Hospital, Tongji Medical College, Huazhong University of Science and TechnologyThe 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
- Interventional
- Phase
- Phase N/A
- Primary purpose
- Diagnosis
- Allocation
- Randomised
- Intervention model
- Parallel groups
- Masking
- Double blind
- Who is masked
- Participant, Outcomes assessor
- Enrolment
- 296 participants (actual)
Sponsor and investigators
- Sponsor type
- University, hospital or other
- Collaborators
- The First Affiliated Hospital of Zhengzhou University, The First Affiliated Hospital of Henan University of Science and Technology
- Responsible party
- Principal investigator, Yaowei Bai, Union Hospital, Tongji Medical College, Huazhong University of Science and Technology
IDs, dates and publications
- ClinicalTrials.gov ID
- NCT07117266
- Sponsor's protocol ID
- Janus Pro 1B-CXR
- Status last verified
- Aug 2025
- First submitted
- 10 Jul 2025
- Last updated
- 12 Sep 2025
- Results posted
- No
- Data monitoring committee
- Yes
- FDA-regulated drug
- No
- FDA-regulated device
- No
- Individual data sharing
- Undecided
Publications
Choi Y. Leveraging GPT-4 as a Proofreader: Addressing the Growing Workload of Radiologists. Radiology. 2025 Jan;314(1):e243859. doi: 10.1148/radiol.243859. No abstract available.
PubMed 39873608Rimmer A. Radiologist shortage leaves patient care at risk, warns royal college. BMJ. 2017 Oct 11;359:j4683. doi: 10.1136/bmj.j4683. No abstract available.
PubMed 29021184Afshari Mirak S, Tirumani SH, Ramaiya N, Mohamed I. The Growing Nationwide Radiologist Shortage: Current Opportunities and Ongoing Challenges for International Medical Graduate Radiologists. Radiology. 2025 Mar;314(3):e232625. doi: 10.1148/radiol.232625.
PubMed 40035678
Study at a glance
From the registry record, last updated by the sponsor on 12 Sep 2025. Recruitment status is as the sponsor reported it: confirm with the study team.
- Official title
- A DeepSeek-Powered AI System for Automated Chest Radiograph Interpretation in Clinical Practice
- ClinicalTrials.gov ID
- NCT07117266
- Acronym / sponsor ID
- Janus Pro 1B-CXR
- Conditions
- X-Ray, AI (Artificial Intelligence), Radiology
- Keywords
- radiology, x-ray, AI
- Study type
- Interventional
- Recruitment status
- Completed
- Enrolment
- 296 participants (actual)
- Lead sponsor
- Union Hospital, Tongji Medical College, Huazhong University of Science and TechnologyUniversity, hospital or other
- Collaborators
- The First Affiliated Hospital of Zhengzhou University, The First Affiliated Hospital of Henan University of Science and Technology
- Study start
- 1 Aug 2025 (actual)
- Primary completion
- 12 Aug 2025 (actual)
- Study completion
- 12 Aug 2025 (actual)
- First posted
- 12 Aug 2025 (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.
There's a global shortage of radiologists. Radiology AI's automatic reporting is key for boosting efficiency and meeting patient needs, especially in resource-poor areas. Multimodal large models enable medical image auto-reporting systems. ChatGPT 4o can diagnose medical images but has issues like being closed-source and "hallucinations." The new open-source Janus Pro 1B-with strong performance, "any-to-any" capability, low cost, and open access-shows potential for medical imaging tasks with training. But little research explores its use here; most models are general, lacking field-specific optimization and systematic evaluation. This study will develop Janus Pro 1B-CXR (a medical image-specific model) via public data, test its value in diagnosis and reporting, and build an efficient automated system.
Detailed description
There is a global shortage of radiologists, and the automatic report generation function of radiology AI systems is crucial for improving medical efficiency and meeting patient needs, especially those in areas with scarce medical resources. Multimodal large models have made it possible to develop automatic report generation systems for medical images. Although ChatGPT 4o has certain capabilities in medical image diagnosis, it has issues such as being closed-source and hallucination. The recently launched open-source multimodal large model Janus-Pro has advantages including high performance, "Any to any", low cost, and open-source; after training and fine-tuning, it has the potential for medical image diagnosis and report generation. However, there is currently a lack of research on the application of Janus Pro 1B in image diagnosis; existing models are mostly general-purpose, lacking in-depth optimization for specific fields and systematic multi-dimensional evaluation methods. This study aims to develop a large model specialized in medical images, Janus Pro 1B-CXR, using public databases, verify its application value in image diagnosis and radiology report generation, and construct an efficient and accurate automated medical image analysis and diagnostic assistance system.
Study design
- Primary purpose
- Diagnosis
- Allocation
- Randomised
- Intervention model
- Parallel groups
- Masking
- Double blind (participant, outcomes assessor)
- Number of arms
- 2
| Arm | Type | Receives |
|---|---|---|
| AI-assisted group | Experimental | Other: radiologists reference AI reportsRadiologists generate reports with reference to AI reports |
| Standard care group | No intervention | –Radiologists generate reports independently without referencing AI reports, following standard clinical procedures. |
Who may qualify
- Sex
- All
- Healthy volunteers
- Accepted
- Age groups
- Child, Adult, Older adult
Key inclusion criteria (5 listed)
- clinically suspected thoracic diseases (such as pneumonia, tuberculosis, or lung cancer) requiring CXR-assisted diagnosis;
- patients providing written informed consent for research data use;
- complete clinical records (including chief complaints, medical history, and laboratory test results);
- patients with no historical chest X-ray images and no need for comparison with previous chest X-ray images;
- Patients who underwent only posteroanterior (PA) chest X-rays without lateral chest X-rays.
Key exclusion criteria (2 listed)
- substandard CXR image quality (including severe motion artifacts, over-/underexposure, or missing anatomical structures);
- pregnant or lactating women.
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 |
|---|---|---|
| radiologists reference AI reportsRadiologists generate reports with reference to AI reports | Other | AI-assisted group |
Primary outcome
Report quality scores in the prospective study
Time frame: 1 week
In this prospective study, the quality of reports generated by junior radiologists was assessed using a 5-point Likert scale titled "Radiology Report Quality Assessment Scale", where the minimum value is 1 and the maximum value is 5, with higher scores indicating better report quality. These scores were compared between the AI-assisted group (junior radiologists using AI tools for report generation) and the standard care group (junior radiologists generating reports without AI assistance).
Agreement evaluation in the prospective study
Time frame: 1 week
In this prospective study, the agreement between reports generated by junior radiologists and standard reports was assessed using the RADPEER scoring system-a peer review program established by the American College of Radiology (ACR) designed to evaluate the interpretation accuracy of radiologists-where the degree of concordance is measured by grading discrepancies and agreements according to specific criteria that also account for the clinical significance of differences. The RADPEER system uses a 5-category scale with a minimum value of 1 and a maximum value of 5, where higher scores indicate greater agreement between the generated reports and standard reports.
Pairwise preference tests in the prospective study
Time frame: 1 week
In this prospective study, the preference between reports generated by junior radiologists in the AI-assisted group versus the standard care group was evaluated using the "Expert Pairwise Preference Assessment Tool", a structured measurement tool designed to quantify expert consensus on report superiority. The assessment was conducted by a panel of 5 independent radiology experts, who reviewed paired reports (one from the AI-assisted group and one from the standard-care group for the same clinical case) and individually indicated their preference for which report was more clinically valuable, accurate, or comprehensive. The unit of measure for this outcome is the "Percentage of paired cases with majority expert preference", defined as cases where ≥3 out of 5 experts expressed a clear preference for either the AI-assisted or standard care report.
Reading Time in the prospective study
Time frame: 1 week
The time from when radiologists began examining chest radiographs to the completion of final reports, comparing efficiency between the AI-assisted and Standard-care groups.
3 secondary outcomes
Report Quality Score in the retrospective study
Time frame: 1 week
Agreement Evaluation in the retrospective study
Time frame: 1 week
Pairwise preference tests in the retrospective study
Time frame: 1 week
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 12 Sep 2025.
- Results publication: PubMed 39873608Choi Y. Leveraging GPT-4 as a Proofreader: Addressing the Growing Workload of Radiologists. Radiology. 2025 Jan;314(1):e243859. doi: 10.1148/radiol.243859. No abstract available.
- Results publication: PubMed 29021184Rimmer A. Radiologist shortage leaves patient care at risk, warns royal college. BMJ. 2017 Oct 11;359:j4683. doi: 10.1136/bmj.j4683. No abstract available.
- Results publication: PubMed 40035678Afshari Mirak S, Tirumani SH, Ramaiya N, Mohamed I. The Growing Nationwide Radiologist Shortage: Current Opportunities and Ongoing Challenges for International Medical Graduate Radiologists. Radiology. 2025 Mar;314(3):e232625. doi: 10.1148/radiol.232625.
- Individual participant dataSharing planned: Undecided
Related trials for X-Ray
Not yet recruitingObservational study
Accuracy of AI in Positional Classification Between Lower Third Molar and Mandibular Canal
As a Decision-support Tool During Preoperative Assessment
RecruitingPhase 3
First-line Immunotherapy-based Standard of Care and Local Ablative Treatments for Oligometastatic Non-small Cell Lung Cancer Patients.
Oligometastatic Non-small Cell Lung Cancer (NSCLC)
RecruitingObservational study
Multimodal Assessment of Sarcopenia Using Shear Wave Elastography, Dual-Energy X-ray Absorptiometry, Bioelectrical Impedance Analysis, and Physical Performance Measures
Sacropenia
Not yet recruiting
Study of Monochromatic X-ray Mammography System
Breast Imaging, Breast Cancer
Recruiting
More Than Just X-Rays - Imaging of Chemotherapy-induced Morphological and Functional Cardiovascular and Lung Changes After Childhood ALL and Other Cancers - a Monocentric Late Effects Study (MaximALL)
Acute Lymphatic Leukemia, Lymphoma
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.
The record lists no contact. Use the official record to reach the sponsor.
3 sites in 1 country: see every site and its status.
Questions about this trial
What is this clinical trial studying?
A study testing radiologists reference AI reports in people with X-Ray and AI (Artificial Intelligence), run by Union Hospital, Tongji Medical College, Huazhong University of Science and Technology at 3 sites in China.
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 5 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 12 Sep 2025. Status can change between updates, so confirm with the study contact before making plans.
Where is the study taking place?
The record lists 3 sites in China. 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?
Report quality scores in the prospective study (time frame: 1 week). The study lists 4 primary outcomes in all. 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 NCT07117266, 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 12 Sep 2025.