Silent Evaluation of DeepTRG for Assessing Tumor Response After Preoperative Treatment in Stomach and Gastroesophageal Junction Cancer
Trial statusRecruiting
Trial phaseNot listed
Trial typeObservational
Biological sexAll
Age18+
SponsorQun Zhao
About this trial
This study will evaluate whether an artificial intelligence (AI) system called DeepTRG can reliably assess cancer tissue removed during surgery after treatment given before surgery. It will include adults with stomach cancer or cancer at the junction between the stomach and the food pipe who have received treatment before surgery.
Pathologists are doctors who examine tissue to diagnose disease. After cancer surgery, they assess how much living cancer remains and whether cancer is present in nearby lymph nodes. DeepTRG analyzes digital images of tissue slides to measure remaining cancer and describe tissue changes, such as scarring and inflammation. It combines information from the original tumor site and lymph nodes to produce a structured assessment.
The main question is:
\* How often can DeepTRG complete the required assessment and produce a clear result without a person correcting the AI analysis?
The study will also examine:
* How closely the system's measurements agree with assessments made by independent expert pathologists. * How accurately it detects remaining cancer, including small amounts of cancer and cancer in lymph nodes. * How long the analysis takes and how often it fails or produces an uncertain result. * Whether its performance differs across treatment types and cancer tissue types.
This study will take place at the Fourth Hospital of Hebei Medical University in China. Eligible patients will be enrolled consecutively. Researchers will use tissue collected during the patients' planned surgery. No additional surgery or biopsy is required for this study.
DeepTRG will run in the background in "silent mode." The doctors responsible for the patients' routine pathology reports and treatment decisions will not receive its results. Patients will continue to receive usual care. The AI model and its grading rules will be fixed before validation begins.
Independent expert pathologists will assess the tissue without seeing the AI results. Researchers will then compare the expert assessments, routine pathology reports, and DeepTRG outputs. Cases with poor-quality images, failed analyses, or uncertain outputs will remain part of the assessment of how reliably the system works.
Researchers will also collect information about subsequent treatment, cancer recurrence, and survival during follow-up. The initial analysis will focus on feasibility and measurement performance. A separate future study would be needed to determine whether using DeepTRG in clinical care improves doctors' decisions or patient outcomes.
Eligibility criteria
This trial does not accept healthy volunteersQualifiers
Age 18 years or older.
Histologically confirmed adenocarcinoma of the stomach or gastroesophageal junction (Siewert type II or III), diagnosed before neoadjuvant treatment.
Received neoadjuvant anticancer treatment before planned surgical resection.
Scheduled to undergo surgical resection with curative intent at the Fourth Hospital of Hebei Medical University, with routine pathological examination of the primary tumor site and regional lymph nodes.
Disqualifiers
Non-adenocarcinoma malignancies, including squamous cell carcinoma, lymphoma, gastrointestinal stromal tumor, or neuroendocrine carcinoma.
Surgery for recurrent gastric or gastroesophageal junction cancer.
Previous inclusion of the patient's tissue or data in DeepTRG model training, grading-rule development, or parameter tuning.
Trial population
Consecutive adults with histologically confirmed gastric or Siewert type II or III gastroesophageal junction adenocarcinoma who have received neoadjuvant treatment and are scheduled for surgical resection with curative intent at the Fourth Hospital of Hebei Medical University, China. Eligible patients will be approached consecutively during the recruitment period, before postoperative pathological response is known. Routinely collected primary tumor and regional lymph node specimens will be evaluated. DeepTRG will operate in silent mode, with its outputs withheld from routine reporting pathologists and treating clinicians. Technical failures and unassessable cases will be retained in the feasibility analysis.
Trial design
Design model
Cohort
Time perspective
Prospective
Treatments tested in this trial
AI-Based Digital Pathology Assessment of Treatment Response (DeepTRG)
Diagnostic testDeepTRG is an AI-based digital pathology system applied to whole-slide images of routinely collected hematoxylin and eosin-stained tissue from the primary tumor site and regional lymph nodes after neoadjuvant therapy and surgical resection. It quantifies residual viable tumor and treatment-related tissue changes and generates a patient-level pathological response grade with quality and uncertainty indicators. The model and grading rules will be locked before prospective validation. The system will operate in silent mode: outputs will be stored for research and withheld from treating clinicians and routine reporting pathologists. Results will be compared with routine pathology reports and independent expert assessments. Processing time, analysis failures, and uncertain outputs will be recorded. No additional biopsy or change in treatment will be required.
Treatment groups
No treatment groups listed
Trial outcomes
Primary outcomes
1
Patient-Level Complete Automated Assessment Rate
Percentage of enrolled patients undergoing surgical resection for whom DeepTRG generates a complete patient-level pathological response assessment within the specified assessment window, without manual correction of AI-generated segmentations, measurements, or grades. A successful assessment must include the final DeepTRG grade and all required primary tumor and regional lymph node outputs, meet prespecified quality criteria, and have no unresolved uncertainty requiring manual adjudication. The AI model, grading rules, required outputs, and quality criteria will be locked before enrollment. The denominator will include all enrolled patients undergoing eligible surgical resection, including those with unavailable or inadequate slides, digitization failures, processing failures, or unassessable or uncertain outputs. These cases will be counted as unsuccessful assessments. The rate will be reported with a 95% confidence interval.
Time frame
Within 14 days after receipt of the surgical specimen by the pathology department.Sponsors and contacts
Click on the lead sponsor to view all of their trials.
Qun Zhao
Lead sponsor
Hebei Medical University
Sponsor institution
Source ClinicalTrials.gov