RadiologyNCT06874647
Chest X-Ray Image Diagnosis and Report Generation Dedicated Model Based on Deepseek
An observational study of Radiology and Artificial Intellegence, run by Union Hospital, Tongji Medical College, Huazhong University of Science and Technology at 3 sites in China.
Trial summary
The global shortage of radiologists is a pressing issue, particularly in regions with limited medical resources. Against this backdrop, making report generation the core objective of radiology AI systems not only aligns with the practical needs of radiologists but also better serves patient requirements. Read more about this study
- Who is it for?
- Any ageHealthy volunteers can take part
- Conditions the study is for
- Radiology, Artificial Intellegence, Large Language Model
- What is being tested?
- AI-generated report for reference
- How many people
- 300 participants
- Where
- 3 sitesChina
- Study dates
- 10 Mar 2025to 31 Mar 2025
- 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 Any age
- All sexes
- Healthy volunteers accepted
- Child, Adult, Older adult
Study population: Patients requiring chest X-ray
Who may be able to join
- Type of examination: standard digital orthopantomogram of the chest during the study period.
- Completeness of information: Medical records containing basic information, medical history, etc.
- Informed consent: written consent form signed by the patient or legal representative.
Who cannot join
- Anatomical abnormalities: congenital abnormalities of chest development, history of chest surgery, or severe scoliosis that interfere with image interpretation.
- Poor image quality: chest radiographs with severe artifacts, exposure abnormalities, or incomplete images.
- Acutely ill: life-threatening and unable to cooperate with the study process.
- Mental cognitive problems: suffering from severe mental illness or cognitive impairment, unable to understand the study and sign.
- Pregnant: Fetus is radiosensitive and physiological changes during pregnancy affect the images.
- Participation in other studies: concurrent participation in other programs that affect the results of this study.
Trial locations and contacts
3 sites in 1 country.
China3 sites
The First Affiliated Hospital of Henan University of science and technology
Luoyang, Henan, 471003
Union Hospital Affiliated to Tongji Medical College, Huazhong University of Science and Technology
Wuhan, Hubei, 430023
The First Affiliated Hospital of Zhengzhou University
Zhengzhou, Henan, 450002
About this study
Official title: Large Language Models for Chest X-Ray Image Diagnosis and Report Generation: A Stepwise, Multicenter, Early-Stage Clinical Validation Study
The global shortage of radiologists is a pressing issue, particularly in regions with limited medical resources. Against this backdrop, making report generation the core objective of radiology AI systems not only aligns with the practical needs of radiologists but also better serves patient requirements. With the development of multimodal large models, it has become possible to develop automatic report generation systems for medical images. Although ChatGPT 4o has demonstrated certain capabilities in multiple medical sub - fields, as a closed - source system, it has limitations. Its model generation mechanism is opaque, and issues such as hallucination exist. Recently, Deepseek's open - source multimodal large model, Janus - Pro, an "any to any" model, has the advantages of high performance, low cost, and open - source. Nature published three consecutive articles introducing its stunning features. After training and fine - tuning, Janus - Pro shows great potential in medical image diagnosis and report generation. However, currently, the application of Janus - Pro in image diagnosis has not been evaluated. Most existing models are highly versatile but lack optimization for specific domains, and there is a lack of systematic and multi - dimensional evaluation methods to determine the pros and cons of multimodal large models in medical radiology. Based on these current situations, the purpose of our research is to develop and verify the application value of large models dedicated to medical images in image diagnosis and radiology report generation.
- Conditions
- Radiology, Artificial Intellegence, Large Language Model, Chest X-ray for Clinical Evaluation
- Being tested
- AI-generated report for reference
- Keywords
- radiology, artificial intelligence, Large language model
What participants receive
What participants receive. In a randomised study each person is assigned to one group by chance.
AI-generated report for referenceOther
The Janus-Pro-CXR group has the AI-generated report for reference and can make changes to the AI-generated report. Another group completes the report independently.
| Study group | Role | What they receive |
|---|---|---|
| Janus-Pro-CXR | Not described Receives: Other: AI-generated report for reference | |
| SCP | Not described |
What is being measured
The primary outcome is the main question the study is designed to answer.
Report Quality Score and agreement score
The evaluation assessed the reports generated by the SCP group and the AI-assisted group, using a five-point Likert scale (5 being the best, 1 being the worst) to subjectively evaluate the capability of the large model in generating imaging reports. The RADPEER scoring system was used to assess the agreement between the original reports and the generated reports, including the clinical significance of any discrepancies.
Measured: No more than 1 week
Pairwise preference
For each evaluator, they must select the better report between the one generated by the large model and the published report. The proportion of cases where three or more evaluators agreed that the AI-assisted group's reports were superior to those of the SCP group was calculated.
Measured: No more than 1 week
Reading Time
To evaluate the impact of the large model on workflow efficiency, the reading time-defined as the duration from when a radiologist begins reviewing a chest X-ray to the completion of the final radiology report-was measured and automatically recorded by the system.
Measured: No more than 1 week
Timeline
From the start of the study to its completion; the mark is today. Estimated dates are the sponsor’s plan.
- First posted13 Mar 2025
- Study start10 Mar 2025
- Primary completion31 Mar 2025
- Study completion31 Mar 2025
Resources
- Official record on ClinicalTrials.govThe registry entry this page is built from, with its full change history.
- Publications (1)Papers the sponsor has linked to this study.
- Other trials for RadiologyStudies 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
- Observational
- Observational model
- Cohort
- Time perspective
- Prospective
- Enrolment
- 300 participants (actual)
Sponsor and investigators
- Lead sponsor
- Union Hospital, Tongji Medical College, Huazhong University of Science and Technology
- Sponsor type
- University, hospital or other
- Responsible party
- Sponsor
IDs, dates and publications
- ClinicalTrials.gov ID
- NCT06874647
- Sponsor's protocol ID
- Janus-Pro-CXR
- Status last verified
- Mar 2025
- First submitted
- 9 Mar 2025
- Last updated
- 23 Apr 2025
- Results posted
- No
- Data monitoring committee
- No
- FDA-regulated drug
- No
- FDA-regulated device
- No
- Individual data sharing
- No
Publications
Tanno R, Barrett DGT, Sellergren A, Ghaisas S, Dathathri S, See A, Welbl J, Lau C, Tu T, Azizi S, Singhal K, Schaekermann M, May R, Lee R, Man S, Mahdavi S, Ahmed Z, Matias Y, Barral J, Eslami SMA, Belgrave D, Liu Y, Kalidindi SR, Shetty S, Natarajan V, Kohli P, Huang PS, Karthikesalingam A, Ktena I. Collaboration between clinicians and vision-language models in radiology report generation. Nat Med. 2025 Feb;31(2):599-608. doi: 10.1038/s41591-024-03302-1. Epub 2024 Nov 7.
PubMed 39511432
Study at a glance
From the registry record, last updated by the sponsor on 23 Apr 2025. Recruitment status is as the sponsor reported it: confirm with the study team.
- Official title
- Large Language Models for Chest X-Ray Image Diagnosis and Report Generation: A Stepwise, Multicenter, Early-Stage Clinical Validation Study
- ClinicalTrials.gov ID
- NCT06874647
- Acronym / sponsor ID
- Janus-Pro-CXR
- Conditions
- Radiology, Artificial Intellegence, Large Language Model, Chest X-ray for Clinical Evaluation
- Keywords
- radiology, artificial intelligence, Large language model
- Study type
- Observational
- Recruitment status
- Completed
- Enrolment
- 300 participants (actual)
- Lead sponsor
- Union Hospital, Tongji Medical College, Huazhong University of Science and TechnologyUniversity, hospital or other
- Study start
- 10 Mar 2025 (actual)
- Primary completion
- 31 Mar 2025 (actual)
- Study completion
- 31 Mar 2025 (actual)
- First posted
- 13 Mar 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.
The global shortage of radiologists is a pressing issue, particularly in regions with limited medical resources. Against this backdrop, making report generation the core objective of radiology AI systems not only aligns with the practical needs of radiologists but also better serves patient requirements. With the development of multimodal large models, it has become possible to develop automatic report generation systems for medical images. Although ChatGPT 4o has demonstrated certain capabilities in multiple medical sub - fields, as a closed - source system, it has limitations. Its model generation mechanism is opaque, and issues such as hallucination exist. Recently, Deepseek's open - source multimodal large model, Janus - Pro, an "any to any" model, has the advantages of high performance, low cost, and open - source. Nature published three consecutive articles introducing its stunning features. After training and fine - tuning, Janus - Pro shows great potential in medical image diagnosis and report generation. However, currently, the application of Janus - Pro in image diagnosis has not been evaluated. Most existing models are highly versatile but lack optimization for specific domains, and there is a lack of systematic and multi - dimensional evaluation methods to determine the pros and cons of multimodal large models in medical radiology. Based on these current situations, the purpose of our research is to develop and verify the application value of large models dedicated to medical images in image diagnosis and radiology report generation.
Study design
- Observational model
- Cohort
- Time perspective
- Prospective
- Number of arms
- 2
| Arm | Type | Receives |
|---|---|---|
| Janus-Pro-CXR | – | Other: AI-generated report for reference |
| SCP | – | – |
Who may qualify
- Sex
- All
- Healthy volunteers
- Accepted
- Age groups
- Child, Adult, Older adult
- Study population
- Patients requiring chest X-ray
Key inclusion criteria (3 listed)
- Type of examination: standard digital orthopantomogram of the chest during the study period.
- Completeness of information: Medical records containing basic information, medical history, etc.
- Informed consent: written consent form signed by the patient or legal representative.
Key exclusion criteria (6 listed)
- Anatomical abnormalities: congenital abnormalities of chest development, history of chest surgery, or severe scoliosis that interfere with image interpretation.
- Poor image quality: chest radiographs with severe artifacts, exposure abnormalities, or incomplete images.
- Acutely ill: life-threatening and unable to cooperate with the study process.
- Mental cognitive problems: suffering from severe mental illness or cognitive impairment, unable to understand the study and sign.
- Pregnant: Fetus is radiosensitive and physiological changes during pregnancy affect the images.
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-generated report for referenceThe Janus-Pro-CXR group has the AI-generated report for reference and can make changes to the AI-generated report. Another group completes the report independently. | Other | Janus-Pro-CXR |
Primary outcome
Report Quality Score and agreement score
Time frame: No more than 1 week
The evaluation assessed the reports generated by the SCP group and the AI-assisted group, using a five-point Likert scale (5 being the best, 1 being the worst) to subjectively evaluate the capability of the large model in generating imaging reports. The RADPEER scoring system was used to assess the agreement between the original reports and the generated reports, including the clinical significance of any discrepancies.
Pairwise preference
Time frame: No more than 1 week
For each evaluator, they must select the better report between the one generated by the large model and the published report. The proportion of cases where three or more evaluators agreed that the AI-assisted group's reports were superior to those of the SCP group was calculated.
Reading Time
Time frame: No more than 1 week
To evaluate the impact of the large model on workflow efficiency, the reading time-defined as the duration from when a radiologist begins reviewing a chest X-ray to the completion of the final radiology report-was measured and automatically recorded by the system.
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 23 Apr 2025.
- Results publication: PubMed 39511432Tanno R, Barrett DGT, Sellergren A, Ghaisas S, Dathathri S, See A, Welbl J, Lau C, Tu T, Azizi S, Singhal K, Schaekermann M, May R, Lee R, Man S, Mahdavi S, Ahmed Z, Matias Y, Barral J, Eslami SMA, Belgrave D, Liu Y, Kalidindi SR, Shetty S, Natarajan V, Kohli P, Huang PS, Karthikesalingam A, Ktena I. Collaboration between clinicians and vision-language models in radiology report generation. Nat Med. 2025 Feb;31(2):599-608. doi: 10.1038/s41591-024-03302-1. Epub 2024 Nov 7.
- Individual participant dataSharing planned: No
Related trials for Radiology
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
Not yet recruitingObservational study
Diagnostic Accuracy of Large Language Models for Peri-Implant Marginal Bone Loss on Panoramic Radiographs
Peri-implantitis, Alveolar Bone Loss
Active, not recruitingObservational study
Development and Evaluation of Techniques for Computer Aided Detection and Diagnosis From Existing Radiologic Images
Radiology Information Systems
Not yet recruitingObservational study
Impact of a Radiologic and Immunologic Signature on Cerebral Efficacy of Treatments in Lung Cancers With Brain Metastasis
Carcinoma, Non-Small-Cell Lung
Not yet recruiting
Prostatic Artery Embolization Using Histoacryl as a Novel Embolizing Agent for Treatment of BPH
Benign Prostatic Hyperplasia, Lower Urinary Tract Symptoms
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?
An observational study of Radiology and Artificial Intellegence, 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 3 inclusion and 6 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 23 Apr 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 Score and agreement score (time frame: No more than 1 week). The study lists 3 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 NCT06874647, which also lists 1 linked publication.
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 23 Apr 2025.