Ignite Creation Date:
2025-12-24 @ 5:06 PM
Ignite Modification Date:
2025-12-25 @ 2:44 PM
Study NCT ID:
NCT07181850
Status:
COMPLETED
Last Update Posted:
2025-09-18
First Post:
2025-08-25
Is NOT Gene Therapy:
False
Has Adverse Events:
False
Brief Title:
Predicting Pathological Complete Response in Esophageal Squamous Cell Carcinoma Using a Multimodal Model Integrating Clinical, Radiomics, and Deep Learning Features
Sponsor:
Organization:
Raw JSON
{'hasResults': False, 'derivedSection': {'miscInfoModule': {'versionHolder': '2025-12-24'}, 'conditionBrowseModule': {'meshes': [{'id': 'D000077277', 'term': 'Esophageal Squamous Cell Carcinoma'}], 'ancestors': [{'id': 'D002294', 'term': 'Carcinoma, Squamous Cell'}, {'id': 'D002277', 'term': 'Carcinoma'}, {'id': 'D009375', 'term': 'Neoplasms, Glandular and Epithelial'}, {'id': 'D009370', 'term': 'Neoplasms by Histologic Type'}, {'id': 'D009369', 'term': 'Neoplasms'}, {'id': 'D018307', 'term': 'Neoplasms, Squamous Cell'}, {'id': 'D004938', 'term': 'Esophageal Neoplasms'}, {'id': 'D005770', 'term': 'Gastrointestinal Neoplasms'}, {'id': 'D004067', 'term': 'Digestive System Neoplasms'}, {'id': 'D009371', 'term': 'Neoplasms by Site'}, {'id': 'D006258', 'term': 'Head and Neck Neoplasms'}, {'id': 'D004066', 'term': 'Digestive System Diseases'}, {'id': 'D004935', 'term': 'Esophageal Diseases'}, {'id': 'D005767', 'term': 'Gastrointestinal Diseases'}]}}, 'protocolSection': {'designModule': {'studyType': 'OBSERVATIONAL', 'designInfo': {'timePerspective': 'RETROSPECTIVE', 'observationalModel': 'COHORT'}, 'enrollmentInfo': {'type': 'ACTUAL', 'count': 363}, 'patientRegistry': False}, 'statusModule': {'overallStatus': 'COMPLETED', 'startDateStruct': {'date': '2019-01-01', 'type': 'ACTUAL'}, 'expandedAccessInfo': {'hasExpandedAccess': False}, 'statusVerifiedDate': '2025-09', 'completionDateStruct': {'date': '2025-07-31', 'type': 'ACTUAL'}, 'lastUpdateSubmitDate': '2025-09-12', 'studyFirstSubmitDate': '2025-08-25', 'studyFirstSubmitQcDate': '2025-09-12', 'lastUpdatePostDateStruct': {'date': '2025-09-18', 'type': 'ESTIMATED'}, 'studyFirstPostDateStruct': {'date': '2025-09-18', 'type': 'ESTIMATED'}, 'primaryCompletionDateStruct': {'date': '2024-12-01', 'type': 'ACTUAL'}}, 'outcomesModule': {'primaryOutcomes': [{'measure': 'Pathological Complete Response (pCR) at Surgery', 'timeFrame': 'At time of surgery after neoadjuvant therapy (~6-8 weeks post-treatment).', 'description': 'pCR is defined as no residual viable tumor in the resected specimen (esophagus and regional lymph nodes) after neoadjuvant immunotherapy plus chemotherapy. pCR status is determined from the postoperative surgical pathology report. This is an observational cohort; treatments were standard-of-care and not assigned by protocol. pCR is abstracted from medical records for all eligible patients.'}], 'secondaryOutcomes': [{'measure': 'Diagnostic Performance of the Multimodal Model for Predicting pCR', 'timeFrame': 'From baseline CT (≤14 days before therapy start) to surgery (≈6-8 weeks post-therapy); analysis performed at study completion.', 'description': "Discrimination and diagnostic accuracy of the combined clinical+radiomics+2.5D MIL model to predict pathological complete response (AUC with 95% CI, sensitivity, specificity, PPV, NPV). Thresholds selected in training (e.g., Youden's J) are applied unchanged to validation and external cohorts; performance is computed on patient-level predictions."}]}, 'oversightModule': {'oversightHasDmc': False, 'isFdaRegulatedDrug': False, 'isFdaRegulatedDevice': False}, 'conditionsModule': {'keywords': ['Deep Learning', 'Multiple Instance Learning (MIL)'], 'conditions': ['Esophageal Squamous Cell Carcinoma', 'Pathological Complete Response']}, 'referencesModule': {'references': [{'pmid': '38890720', 'type': 'RESULT', 'citation': 'Fan L, Yang Z, Chang M, Chen Z, Wen Q. CT-based delta-radiomics nomogram to predict pathological complete response after neoadjuvant chemoradiotherapy in esophageal squamous cell carcinoma patients. J Transl Med. 2024 Jun 18;22(1):579. doi: 10.1186/s12967-024-05392-4.'}, {'pmid': '38263134', 'type': 'RESULT', 'citation': 'Liu Y, Wang Y, Wang X, Xue L, Zhang H, Ma Z, Deng H, Yang Z, Sun X, Men Y, Ye F, Men K, Qin J, Bi N, Wang Q, Hui Z. MR radiomics predicts pathological complete response of esophageal squamous cell carcinoma after neoadjuvant chemoradiotherapy: a multicenter study. Cancer Imaging. 2024 Jan 23;24(1):16. doi: 10.1186/s40644-024-00659-x.'}, {'pmid': '40105813', 'type': 'RESULT', 'citation': 'Guo X, Chen C, Zhao J, Wang C, Mei X, Shen J, Lv H, Han Y, Wang Q, Lv J, Chen H, Yan X, Liu Z, Zhang Z, Zhong Q, Jiang Y, Xu L, Li X, Qian D, Ma D, Ye M, Wang C, Wang Z, Lin J, Tian Z, Leng X, Li Z. Neoadjuvant Chemoradiotherapy vs Chemoimmunotherapy for Esophageal Squamous Cell Carcinoma. JAMA Surg. 2025 May 1;160(5):565-574. doi: 10.1001/jamasurg.2025.0220.'}, {'pmid': '39221992', 'type': 'RESULT', 'citation': 'Zheng Y, Liang G, Yuan D, Liu X, Ba Y, Qin Z, Shen S, Li Z, Sun H, Liu B, Gao Q, Li P, Wang Z, Liu S, Zhu J, Wang H, Ma H, Liu Z, Zhao F, Zhang J, Zhang H, Wu D, Qu J, Ma J, Zhang P, Ma W, Yan M, Yu Y, Li Q, Zhang J, Xing W. Perioperative toripalimab plus neoadjuvant chemotherapy might improve outcomes in resectable esophageal cancer: an interim analysis of a phase III randomized clinical trial. Cancer Commun (Lond). 2024 Oct;44(10):1214-1227. doi: 10.1002/cac2.12604. Epub 2024 Sep 2.'}]}, 'descriptionModule': {'briefSummary': 'This multicenter, retrospective cohort study reviews the medical records and CT scans of adults with esophageal squamous cell carcinoma (ESCC) who received neoadjuvant immunotherapy plus chemotherapy before surgery at three hospitals in China. The goal is to develop and validate a computer-assisted model that predicts which patients achieve a pathological complete response (pCR)-meaning no residual tumor is found at surgery-after preoperative treatment. Accurate pCR prediction may help clinicians personalize care and avoid unnecessary treatments in likely non-responders.\n\nThe study includes 363 patients. For each patient, routinely collected clinical information and preoperative venous-phase chest CT images were analyzed. From CT images, both radiomics features and features learned by a "2.5D" deep learning approach with multiple-instance learning (MIL) were extracted. These were combined with clinical variables to create a multimodal prediction model. Model performance will be evaluated using standard metrics and validated in internal and external cohorts.\n\nPatients typically received two cycles of taxane-platinum chemotherapy (paclitaxel with cisplatin or carboplatin) combined with camrelizumab every 2-3 weeks before surgery; CT scans were performed within 14 days prior to starting therapy. Surgery (R0 resection) was performed 6-8 weeks after treatment, and pCR was determined by the postoperative pathology report.\n\nThis is an observational study; no treatments are assigned by protocol. The study was approved by the Ethics Committee of Nanjing Medical University, with informed consent waived due to the retrospective design.', 'detailedDescription': 'Design and Setting. Multicenter, retrospective cohort study conducted at three affiliated hospitals in China. A total of 363 consecutive ESCC patients met eligibility criteria and were split into a training cohort (n=107), internal validation cohort (n=45), and two external test cohorts (n=129 and n=82).\n\nPopulation. Inclusion criteria: biopsy-confirmed ESCC; locally advanced disease by AJCC 8th edition (cT1N1-T3N0-3M0) on contrast-enhanced CT; completion of standardized neoadjuvant chemo-immunotherapy; availability of high-quality venous-phase chest CT (slice thickness ≤5 mm) within 14 days before therapy; R0 resection 6-8 weeks post-treatment; and a definitive postoperative pathology report documenting pCR. Key exclusions: non-squamous histology, distant metastasis, synchronous malignancies, poor/no venous-phase imaging, slice thickness \\>5 mm, severe artifacts, incomplete tumor visualization, incomplete treatment, or missing endpoints.\n\nNeoadjuvant Regimen and Imaging. Patients generally received two cycles of taxane-platinum chemotherapy (paclitaxel plus cisplatin or carboplatin) combined with camrelizumab every 2-3 weeks prior to surgery. CT imaging was standardized to venous-phase contrast with 1-5 mm slices; scans without venous phase or \\>5 mm thickness were excluded. Tumor volumes were delineated by two radiologists; disagreements were adjudicated by a senior radiologist, and features were harmonized via resampling and intensity normalization.\n\nFeature Extraction and Modeling. The pipeline integrated: (1) clinical variables; (2) conventional CT radiomics features (shape, first-order, GLCM, GLRLM, GLSZM, etc.); and (3) 2.5D deep learning slice embeddings aggregated to the patient level using multiple-instance learning (MIL). The 2.5D approach uses adjacent slices in axial/sagittal/coronal planes with ResNet backbones; attention-based MIL plus histogram/BoW-TF-IDF descriptors summarized slice-level predictions. Feature selection used univariate filters, correlation screening, mRMR, and LASSO before training classifiers (logistic regression, SVM, Random Forest, Extra-Trees, LightGBM).\n\nOutcomes and Analysis.\n\nPrimary outcome: pCR at surgery (yes/no).\n\nSecondary outcomes: model performance (AUC, sensitivity, specificity, PPV/NPV, calibration) and clinical utility by decision-curve analysis; disease-free survival by Kaplan-Meier analysis.\n\nEthics. Approved by the Ethics Committee of Nanjing Medical University; informed consent was waived given the retrospective design and use of de-identified data.'}, 'eligibilityModule': {'sex': 'ALL', 'stdAges': ['ADULT', 'OLDER_ADULT'], 'minimumAge': '18 Years', 'samplingMethod': 'NON_PROBABILITY_SAMPLE', 'studyPopulation': "Adults with biopsy-confirmed ESCC treated at three participating centers in China. Patients received standard neoadjuvant chemo-immunotherapy (e.g., camrelizumab with paclitaxel and cisplatin or carboplatin), had pre-treatment venous-phase chest CT within 14 days, and underwent R0 resection 6-8 weeks post-therapy. pCR status was determined from surgical pathology. Sites include: The Affiliated Huai'an No. 1 People's Hospital of Nanjing Medical University; Nanjing Medical University Affiliated Cancer Hospital \\& Jiangsu Cancer Hospital \\& Jiangsu Institute of Cancer Research; and Nanjing Drum Tower Hospital.", 'healthyVolunteers': False, 'eligibilityCriteria': 'Inclusion Criteria:\n\nBiopsy-confirmed esophageal squamous cell carcinoma (ESCC). Locally advanced disease per AJCC 8th ed. (cT1N1-T3N0-3M0) on contrast-enhanced CT.\n\nCompleted standardized neoadjuvant chemo-immunotherapy (e.g., paclitaxel + cisplatin/carboplatin with camrelizumab every 2-3 weeks) prior to surgery.\n\nHigh-quality venous-phase chest CT (slice thickness ≤5 mm) obtained within 14 days before therapy start.\n\nUnderwent R0 resection 6-8 weeks after therapy. Availability of a definitive postoperative pathology report to ascertain pCR status.\n\nExclusion Criteria:\n\nNon-squamous histology; distant metastasis (M1); synchronous malignancies. Inadequate imaging quality (no venous phase, slice thickness \\>5 mm, severe artifacts, or incomplete tumor visualization).\n\nDid not complete the full treatment course or had missing endpoints (e.g., no pathological response record or lost to follow-up).'}, 'identificationModule': {'nctId': 'NCT07181850', 'acronym': 'pCR-ESCC', 'briefTitle': 'Predicting Pathological Complete Response in Esophageal Squamous Cell Carcinoma Using a Multimodal Model Integrating Clinical, Radiomics, and Deep Learning Features', 'organization': {'class': 'OTHER', 'fullName': 'Nanjing Medical University'}, 'officialTitle': 'Integration of Clinical, Radiomics, and 2.5D Deep Learning-Based Multiple Instance Learning Features for Predicting Pathological Complete Response in Esophageal Squamous Cell Carcinoma Following Neoadjuvant Immunotherapy and Chemotherapy: A Multicenter Comparative Study', 'orgStudyIdInfo': {'id': 'KY-2024-373-01'}, 'secondaryIdInfos': [{'id': '81903992', 'type': 'OTHER_GRANT', 'domain': 'National Natural Science Foundation of China'}]}, 'armsInterventionsModule': {'armGroups': [{'label': 'ESCC nIT+nCT Surgical Resection Cohort (Multicenter, China)', 'description': 'Adults with biopsy-confirmed esophageal squamous cell carcinoma treated at three centers in China who received standardized neoadjuvant immunotherapy plus taxane-platinum chemotherapy (e.g., camrelizumab with paclitaxel and cisplatin or carboplatin) before surgery. Pre-treatment venous-phase chest CT (1-5 mm slices) within 14 days of therapy start was analyzed to extract radiomics and 2.5D deep-learning/MIL features. All patients underwent R0 resection 6-8 weeks post-therapy; pathological complete response (pCR) was determined on surgical specimens. This is an observational cohort used to build and externally validate a multimodal model predicting pCR; no biospecimens are retained and no treatments are assigned by protocol.', 'interventionNames': ['Other: Standard-of-Care Neoadjuvant Immunochemotherapy (nIT+nCT)']}], 'interventions': [{'name': 'Standard-of-Care Neoadjuvant Immunochemotherapy (nIT+nCT)', 'type': 'OTHER', 'description': 'Adults with biopsy-confirmed ESCC received standard neoadjuvant immunochemotherapy before surgery (e.g., camrelizumab with paclitaxel plus cisplatin or carboplatin, typically 2 cycles every 2-3 weeks). Treatments were routine clinical care at participating centers and were not assigned by study protocol; this record captures the exposure for observational modeling of pathological complete response (pCR). Surgery (R0) occurred \\~6-8 weeks after therapy.', 'armGroupLabels': ['ESCC nIT+nCT Surgical Resection Cohort (Multicenter, China)']}]}, 'contactsLocationsModule': {'locations': [{'zip': '223000', 'city': "Huai'an", 'state': 'Jiangsu', 'country': 'China', 'facility': "The Affiliated Huai'an No. 1 People's Hospital of Nanjing Medical University", 'geoPoint': {'lat': 33.58861, 'lon': 119.01917}}]}, 'ipdSharingStatementModule': {'ipdSharing': 'NO', 'description': 'IPD will not be shared because the study received ethics approval with a waiver of informed consent for retrospective use within participating centers, and broad external sharing was not contemplated. In addition, raw imaging data pose re-identification risks, and cross-institutional data-sharing agreements are not in place.'}, 'sponsorCollaboratorsModule': {'leadSponsor': {'name': 'Nanjing Medical University', 'class': 'OTHER'}, 'collaborators': [{'name': 'The Affiliated cancer hospital of Nanjing Medical University', 'class': 'UNKNOWN'}, {'name': 'The Affiliated Nanjing Drum Tower Hospital of Nanjing University Medical School', 'class': 'OTHER'}], 'responsibleParty': {'type': 'PRINCIPAL_INVESTIGATOR', 'investigatorTitle': 'Professor of Thoracic Surgery', 'investigatorFullName': 'Zhiyun Xu', 'investigatorAffiliation': 'Nanjing Medical University'}}}}