Two-component Radiology-guided Autonomous Cascade Engine (TRACE) (TRACE)
Protocol for a Prospective Randomised Crossover Controlled Trial of the Artificial Intelligence-Assisted Decision-Making System for Gastric Cancer T-Staging (TRACE)
This study employed a prospective, randomised crossover trial design to evaluate the clinical utility of the TRACE artificial intelligence system for gastric cancer T-staging. A total of 54 radiologists from tertiary and non-tertiary hospitals, including both senior and junior practitioners, were enrolled. The study aimed to investigate whether AI-assisted diagnosis could improve the diagnostic accuracy of gastric cancer T-staging compared with independent interpretation by radiologists.
All participants were required to interpret 60 contrast-enhanced CT cases sequentially, completing two readings for each case: one without AI assistance and one with AI assistance; The order of the two readings was randomised, and a one-month washout period was observed between readings to eliminate memory bias. All cases were pathologically confirmed gastric cancer cases (stages T1-T4b), and the study simultaneously recorded the physicians' T-staging diagnostic results and the time taken per case. The 60 cases per radiologist were randomly selected from a pool of 1,000 histologically confirmed gastric cancer cases, stratified by pathological T stage T1-T4b. The reference standard was postoperative pathological T stage. The primary outcome was the change in T-staging accuracy between AI-assisted reading and standard (unaided) reading.The term "prospective" in this study refers to the prospective execution of radiologist enrollment, randomization, reading procedures, and data collection.
Studieoversikt
Status
Forhold
Intervensjon / Behandling
Detaljert beskrivelse
The TRACE trial is a prospective, randomized, crossover, controlled study evaluating an artificial intelligence (AI)-assisted decision system for T staging of gastric cancer based on CT images.
Background and rationale: Accurate preoperative T staging is critical for treatment planning in gastric cancer, but remains challenging due to reader variability and imaging limitations. The AI system was developed using deep learning with a large multi-center dataset to improve staging accuracy.
Study design: Eligible patients with pathologically confirmed gastric cancer will undergo preoperative contrast-enhanced CT. Each participant will be assessed twice in random order: once with AI assistance (AI arm) and once without (standard arm). A washout period will be applied between the two readings to minimize recall bias. Radiologists involved in the study are blinded to clinical and pathological reference standards.
Objective: To compare the T staging accuracy (primary outcome) between AI-assisted and standard reading, with secondary outcomes including inter-reader agreement, reading time, and diagnostic confidence.
Statistical methods: A crossover design will be used with a sample size calculated to detect a prespecified difference in overall accuracy. The primary analysis will employ a paired McNemar test or generalized estimating equation accounting for period and carryover effects. Subgroup analyses by tumor location, T category, and reader experience will be exploratory.
Data monitoring: No independent Data Monitoring Committee is required due to the low-risk nature of the diagnostic device. Adverse events related to the use of the software (e.g., workflow disruption) will be recorded and reported.
Ethics and dissemination: The protocol has been approved by the Ethics Committee of Liaoning Cancer Hospital & Institute. Written informed consent (online or paper-based) will be obtained from all participants. Results will be submitted for publication in peer-reviewed journals regardless of outcome.
Studietype
Registrering (Antatt)
Fase
- Ikke aktuelt
Kontakter og plasseringer
Studiekontakt
- Navn: Guoliang Zheng
- Telefonnummer: 13322400728
- E-post: zhengboren1@126.com
Studiesteder
-
-
Liaoning
-
Shenyang, Liaoning, Kina, 110024
- Rekruttering
- Cancer Hospital of Dalian University of Technology (Liaoning Cancer Hospital & Institute)
-
Ta kontakt med:
- Guoliang Zheng, doctor
- Telefonnummer: 13322400728
- E-post: zhengboren1@126.com
-
-
Deltakelseskriterier
Kvalifikasjonskriterier
Alder som er kvalifisert for studier
- Barn
- Voksen
- Eldre voksen
Tar imot friske frivillige
Beskrivelse
Inclusion Criteria (Imaging Data)
- Contrast-enhanced CT (CE-CT) images of gastric cancer patients from the Liaoning Cancer Hospital;
- Patients with a definitive postoperative pathological diagnosis of gastric cancer and a clear T-stage classification (T1-T4, including T4a and T4b);
- Imaging data must be complete and of sufficient quality to meet diagnostic and analytical requirements, with no significant artefacts or missing key data;
- Complete clinical and pathological information must be available to establish a diagnostic gold standard for comparison.
Physician Inclusion Criteria (Image Readers)
- Radiologists holding a valid medical licence;
- From the radiology department of a Grade A tertiary hospital or a non-Grade A tertiary hospital;
- Classified as senior or junior physicians based on clinical experience;
- Voluntarily participating in this study and completing both the non-AI-assisted and AI-assisted image interpretation tasks.
Case Exclusion Criteria
- Severe missing imaging data or quality failing to meet analysis requirements (e.g., severe motion artefacts);
- Lack of clear postoperative pathological T-staging results;
- Cases not involving gastric cancer or with incomplete pathological information;
- Cases of duplicate enrolment or inconsistent data recording.
Physician Exclusion Criteria
- Those unable to complete all image review tasks or demonstrating severe non-compliance;
- Those who withdraw during the study period and are unable to provide complete data for both phases of image review;
- Those who fail to complete the AI-assisted and non-AI-assisted interpretation processes as specified.
Withdrawal Criteria
- Physicians who voluntarily withdraw from the study for personal reasons (e.g., time, health or work commitments);
- Physicians who fail to complete the required image review tasks or have data missing in excess of the specified threshold;
- Cases where critical data errors are identified during subsequent verification or where pathological results cannot be traced; Data found during the study to be non-compliant with ethical or quality control requirements must be excluded.
Studieplan
Hvordan er studiet utformet?
Designdetaljer
- Primært formål: Diagnostisk
- Tildeling: Randomisert
- Intervensjonsmodell: Crossover-oppdrag
- Masking: Dobbelt
Våpen og intervensjoner
Deltakergruppe / Arm |
Intervensjon / Behandling |
|---|---|
|
Eksperimentell: Standard reading 1
Utilizing the TRACE model to assist radiologists in T-staging.
In this arm, participants receive TRACE model assistance in the first reading phase (AI-assisted), followed by independent reading without AI after a 1-month washout period.
The temporal order of the intervention is early application.
|
AI-assisted reading: Radiologists interpret preoperative contrast-enhanced CT images for gastric cancer T staging with the support of the TRACE artificial intelligence decision system.
The AI system provides a suggested T stage and relevant imaging features.
The radiologist makes the final staging decision after reviewing the AI output.
This intervention is used only during the AI-assisted reading session.
Participants are required to observe a washout period of at least 30 days between consecutive interventions/assessments.
|
|
Eksperimentell: Standard Reading 2
Utilizing the TRACE model to assist radiologists in T-staging.
In this arm, participants first perform independent reading without AI assistance, and after a 1-month washout period, they receive TRACE model assistance in the second reading phase.
The temporal order of the same intervention is delayed compared to Arm 1.
|
AI-assisted reading: Radiologists interpret preoperative contrast-enhanced CT images for gastric cancer T staging with the support of the TRACE artificial intelligence decision system.
The AI system provides a suggested T stage and relevant imaging features.
The radiologist makes the final staging decision after reviewing the AI output.
This intervention is used only during the AI-assisted reading session.
Participants are required to observe a washout period of at least 30 days between consecutive interventions/assessments.
|
Hva måler studien?
Primære resultatmål
Resultatmål |
Tiltaksbeskrivelse |
Tidsramme |
|---|---|---|
|
Accuracy
Tidsramme: Within 40 days after the first radiologist initiates image reading.
|
Accuracy of radiologists' interpretation of T staging
|
Within 40 days after the first radiologist initiates image reading.
|
Sekundære resultatmål
Resultatmål |
Tiltaksbeskrivelse |
Tidsramme |
|---|---|---|
|
Accuracy Change by Physician Experience Level
Tidsramme: Within 40 days after the first radiologist initiates image reading.
|
Changes in diagnostic accuracy of radiologists with different experience levels before and after AI assistance.
|
Within 40 days after the first radiologist initiates image reading.
|
|
Stratified diagnostic accuracy of different T-stages
Tidsramme: Within 40 days after the first radiologist initiates image reading.
|
Stratified diagnostic accuracy for different T-stages (T1-T4, including T4a and T4b).
|
Within 40 days after the first radiologist initiates image reading.
|
|
Agreement between physician diagnosis and pathological gold standard
Tidsramme: Within 40 days after the first radiologist initiates image reading.
|
Agreement between radiologists' diagnostic results and the pathological gold standard (e.g., Kappa value).
|
Within 40 days after the first radiologist initiates image reading.
|
|
Agreement between AI model and physician interpretation
Tidsramme: Within 40 days after the first radiologist initiates image reading.
|
Agreement analysis between AI model prediction results and radiologists' interpretations.
|
Within 40 days after the first radiologist initiates image reading.
|
|
Effect of AI assistance on reading efficiency
Tidsramme: Within 40 days after the first radiologist initiates image reading.
|
Changes in average reading time for diagnosis with and without AI assistance.
|
Within 40 days after the first radiologist initiates image reading.
|
Andre resultatmål
Resultatmål |
Tiltaksbeskrivelse |
Tidsramme |
|---|---|---|
|
Influence of case characteristics on AI assistance effect
Tidsramme: Within 40 days after the first radiologist initiates image reading.
|
Influence of different case characteristics (e.g., tumor location, size) on the performance of AI assistance.
|
Within 40 days after the first radiologist initiates image reading.
|
|
Impact of individual physician differences on AI assistance effect
Tidsramme: Within 40 days after the first radiologist initiates image reading.
|
Impact of individual differences among physicians on the performance of AI assistance.
|
Within 40 days after the first radiologist initiates image reading.
|
|
Value of AI assistance in reducing diagnostic discrepancy
Tidsramme: Within 40 days after the first radiologist initiates image reading.
|
Potential value of AI assistance in reducing diagnostic differences and improving reading agreement.
|
Within 40 days after the first radiologist initiates image reading.
|
|
Impact of model probability information on physician decisions
Tidsramme: Within 40 days after the first radiologist initiates image reading.
|
Preliminary analysis of the impact of probability output from AI model on physician decision-making behavior.
|
Within 40 days after the first radiologist initiates image reading.
|
Samarbeidspartnere og etterforskere
Etterforskere
- Hovedetterforsker: Guoliang Zheng, Cancer Hospital of Dalian University of Technology (Liaoning Cancer Hospital & Institute)
Studierekorddatoer
Studer hoveddatoer
Studiestart (Antatt)
Primær fullføring (Antatt)
Studiet fullført (Antatt)
Datoer for studieregistrering
Først innsendt
Først innsendt som oppfylte QC-kriteriene
Først lagt ut (Faktiske)
Oppdateringer av studieposter
Sist oppdatering lagt ut (Faktiske)
Siste oppdatering sendt inn som oppfylte QC-kriteriene
Sist bekreftet
Mer informasjon
Begreper knyttet til denne studien
Ytterligere relevante MeSH-vilkår
Andre studie-ID-numre
- KY20260512
Plan for individuelle deltakerdata (IPD)
Planlegger du å dele individuelle deltakerdata (IPD)?
IPD-planbeskrivelse
Legemiddel- og utstyrsinformasjon, studiedokumenter
Studerer et amerikansk FDA-regulert medikamentprodukt
Studerer et amerikansk FDA-regulert enhetsprodukt
Denne informasjonen ble hentet direkte fra nettstedet clinicaltrials.gov uten noen endringer. Hvis du har noen forespørsler om å endre, fjerne eller oppdatere studiedetaljene dine, vennligst kontakt register@clinicaltrials.gov. Så snart en endring er implementert på clinicaltrials.gov, vil denne også bli oppdatert automatisk på nettstedet vårt. .