Deep Radiomics-based Fusion Model Predicting Bevacizumab Treatment Response and Outcome in Patients With Colorectal Liver Metastases

NCT ID: NCT06023173

Last Updated: 2023-09-14

Basic Information

• Recruitment Status: COMPLETED
• Total Enrollment: 307 participants
• Study Classification: OBSERVATIONAL
• Study Start Date: 2013-10-01
• Study Completion Date: 2023-01-01

Brief Summary

This multi-modal deep radiomics model, using PET/CT, clinical and histopathological data, was able to identify patients with bevacizumab-sensitive unresectable colorectal cancer liver metastases, providing a favorable approach for precise patient treatment.

Detailed Description

Accurately predicting tumor response to targeted therapies is essential for guiding personalized conversion therapy in patients with unresectable colorectal cancer liver metastases (CRLM). Currently, tumor response evaluation criteria are based on assessments made after at least 2-months treatment. Consequently, there is a compelling need to develop baseline tools that can be used to guide therapy selection. Herein, the investigators proposed a deep radiomics-based fusion model which demonstrates high accuracy in predicting the efficacy of bevacizumab in CRLM patients. Further, the investigators observed a significant and positive association between the predicted-responders and longer progression-free survival as well as longer overall survival in CRLM patients treated with bevacizumab. Moreover, the model exhibits high negative prediction value, indicating its potential to accurately identify individuals who are unresponsive to bevacizumab. Thus, our model provides a valuable baseline method for specifically identifying bevacizumab-sensitive CRLM patients, which is offering a clinically convenient approach to guide precise patient treatment.

Conditions

The Patients With CRLM Who Benefit More From Bevacizumab

Study Design

• Observational Model Type: COHORT
• Study Time Perspective: RETROSPECTIVE

Study Groups

Training Cohort

This cohort was derived from Arm A (treated with FOLFOX + bevacizumab) of the BECOME studyand was used for model construction.

Deep radiomics-based fusion model

Intervention Type: DIAGNOSTIC_TEST

This multi-modal deep radiomics model, using PET/CT, clinical and histopathological data, was able to identify patients with bevacizumab-sensitive CRLM, providing a favorable approach for precise patient treatment.

Negative Validation Cohort

The cohort was derived from Arm B (treated with FOLFOX) of the BECOME study , which demonstrated that the model specifically predicted the efficacy of bevacizumab.

Deep radiomics-based fusion model

Intervention Type: DIAGNOSTIC_TEST

This multi-modal deep radiomics model, using PET/CT, clinical and histopathological data, was able to identify patients with bevacizumab-sensitive CRLM, providing a favorable approach for precise patient treatment.

Internal Validation Cohort

The cohort was derived from an independent Zhongshan Hospital cohort with the same treatment team and imaging instrumentation as the BECOME study, differing only in patient period, and was used for internal validation of the model.

Deep radiomics-based fusion model

Intervention Type: DIAGNOSTIC_TEST

This multi-modal deep radiomics model, using PET/CT, clinical and histopathological data, was able to identify patients with bevacizumab-sensitive CRLM, providing a favorable approach for precise patient treatment.

External Validation Cohort

The cohort was obtained from the Zhongshan Hospital - Xiamenand the First Affiliated Hospital of Wenzhou Medical University for external validation of the model.

Deep radiomics-based fusion model

Intervention Type: DIAGNOSTIC_TEST

This multi-modal deep radiomics model, using PET/CT, clinical and histopathological data, was able to identify patients with bevacizumab-sensitive CRLM, providing a favorable approach for precise patient treatment.

Interventions

Deep radiomics-based fusion model

This multi-modal deep radiomics model, using PET/CT, clinical and histopathological data, was able to identify patients with bevacizumab-sensitive CRLM, providing a favorable approach for precise patient treatment.

Intervention Type: DIAGNOSTIC_TEST

Other Intervention Names

deep learning model

Eligibility Criteria

Inclusion Criteria

1. Age ≥ 18 years and ≤75 years;

2. Patients were histologically confirmed for colorectal adenocarcinoma with unresectable liver-limited or liver-dominant metastases

3. PET/CT at baseline were available

4. First line treated with FOLFOX+ bevacizumab.

Exclusion Criteria

1. Resectable liver metastases;

2. Wide-type KRAS/NRAS;

3. No measurable liver metastasis;

4. No efficacy assessment;

5. No follow-up information.

• Minimum Eligible Age: 18 Years
• Maximum Eligible Age: 75 Years
• Eligible Sex: ALL
• Accepts Healthy Volunteers: No

Sponsors

Fudan University

OTHER

Sponsor Role: lead

Responsible Party

Xu jianmin

Head of Colorectal Surgery

Responsibility Role: PRINCIPAL_INVESTIGATOR

Principal Investigators

Jianmin Xu, MD

Role: PRINCIPAL_INVESTIGATOR

Fudan University

Locations

Department of General Surgery, Zhongshan Hospital, Fudan University

Shanghai, , China

Countries

China

Other Identifiers

DERBY

Identifier Type: -

Identifier Source: org_study_id