Deep Learning Model Predicts Pathological Complete Response of Lung Cancer Following Neoadjuvant Immunochemotherapy

NCT ID: NCT06285058

Last Updated: 2024-03-13

Basic Information

• Recruitment Status: NOT_YET_RECRUITING
• Total Enrollment: 1000 participants
• Study Classification: OBSERVATIONAL
• Study Start Date: 2024-03-31
• Study Completion Date: 2026-03-31

Brief Summary

This study presents the development and validation of an artificial intelligence (AI) prediction system that utilizes pre-neoadjuvant immunotherapy plain scans and enhanced multimodal CT scans to extract deep learning features. The aim is to predict the occurrence of pathological complete response in non-small cell lung cancer patients undergoing neoadjuvant immunochemotherapyy.

Detailed Description

This study retrospectively obtained non-contrast enhanced and contrast enhanced CT scans of patients with NSCLC who underwent surgery after receiving neoadjuvant immunochemotherapy. at multiple centers between August 2019 and February 2023. Deep learning features were extracted from both non-contract enhanced and contract enhanced CT scans to construct the predictive models (LUNAI-nCT model and LUNAI-eCT model), respectively. After feature fusion of these two types of features, a fused model (LUNAI-fCT model) was constructed. The performance of the model was evaluated using the area under the receiver operating characteristic curve (AUC), accuracy, sensitivity, specificity, positive predictive value (PPV), and negative predictive value (NPV). SHapley Additive exPlanations (SHAP) analysis was used to quantify the impact of CT imaging features on model prediction. To gain insights into how our model makes predictions, we employed Gradient-weighted Class Activation Mapping (Grad-CAM) to generate saliency heatmaps.

Conditions

Deep Learning Model; Pathological Complete Response; Non-small Cell Lung Cancer; Neoadjuvant Chemoimmunotherapy

Study Design

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

Study Groups

Training dataset

patients who were diagnosed with non-small cell carcinoma and undergo surgery after neoadjuvant chemoimmunotherapy treatment at hospital 1 (Tongji Medical College Affiliated Union Hospital)

No interventions

Intervention Type: DIAGNOSTIC_TEST

The high-throughput extraction of large amounts of quantitative image features from medical images

test dataset

patients who were diagnosed with non-small cell carcinoma and undergo surgery after neoadjuvant chemoimmunotherapy treatment at hospital (Zhengzhou University First Affiliated Hospital, Yichang Central Hospital, Anyang Cancer Hospital)

No interventions assigned to this group

Interventions

No interventions

The high-throughput extraction of large amounts of quantitative image features from medical images

Intervention Type: DIAGNOSTIC_TEST

Eligibility Criteria

Inclusion Criteria

1. Patients' with non-small cell lung cancer, diagnosed through biopsy pathology and clinically classified as stage IB to III;

2. Patients who receive at least two cycles of neoadjuvant immunotherapy combined with chemotherapy induction therapy;

3. According to the IASLC guidelines, postoperative pathological evaluation was performed on the treatment response of the tumor primary lesion and lymph nodes.

Exclusion Criteria

1. Missing or inadequate quality of CT;

2. Time interval between CT and start of treatment is greater than 1 month;

3. Incomplete clinicopathologic data.

• Minimum Eligible Age: 18 Years
• Maximum Eligible Age: 80 Years
• Eligible Sex: ALL
• Accepts Healthy Volunteers: No

Sponsors

Union Hospital, Tongji Medical College, Huazhong University of Science and Technology

OTHER

Sponsor Role: lead

Responsible Party

Responsibility Role: SPONSOR

References

Ye G, Wei Z, Han C, Wu G, Wong C, Liang Y, Chen X, Zhou W, Gao J, Liang C, Liao Y, Hendriks LEL, Wee L, De Ruysscher D, Dekker A, Zhou H, Qi Y, Liu Z, Shi Z. AI-derived longitudinal and multi-dimensional CT classifier for non-small cell lung cancer to optimize neoadjuvant chemoimmunotherapy decision: a multicentre retrospective study. EClinicalMedicine. 2025 Oct 7;89:103551. doi: 10.1016/j.eclinm.2025.103551. eCollection 2025 Nov.

Reference Type: DERIVED

PMID: 41127561 (View on PubMed)

Other Identifiers

LUNAI

Identifier Type: -

Identifier Source: org_study_id