ClinicalTrials.gg
Enrolling by invitationNCT07373951DL-DriverBMUpdated Jan 29, 2026

Retrospective Multicenter Study of Patient-level T1CE/FLAIR MRI Deep Learning to Predict EGFR/ALK Driver Status in NSCLC Brain Metastases With External Validation and Survival Analysis

An observational study in Non-Small Cell Lung Cancer and Brain Metastases, sponsored by Ming Yang. Enrolling by invitation at 1 site in China. Open to participants aged 18 Years and older. Per ClinicalTrials.gov, last updated 2026-01-29.

Sponsored by Ming Yang · Observational

How we know

From the registry’s dates

  • Primary completion was expected by Apr 2026, 7 months ago, but the record still lists the study as enrolling by invitation.

Help build ClinicalTrials.gg — short surveys, remote interviews or testing, in your language. Take part →

Study type
Observational
Model
Cohort
Time perspective
Retrospective
Enrollment
380
Ages
18 Years and older
Sex
All
01

Where this study stands

Counted across the records on this site · 2026-11-22

Among 1,885 studies in Carcinoma, Non-Small-Cell Lung with a site in China — 763 open to participants now, 988 under way, 202 of them phase 3. Carcinoma, Non-Small-Cell Lung · China.

Planned enrollment
101st of 288
380 · median 200
Started
2025
with 207 others
Observational
288 of 1,885
114 open now
Primary completion
2026-04
later than 319 of 987 live
Registered
1,704th of 1,885
by date

Among the 1,885 studies in Carcinoma, Non-Small-Cell Lung with a site in China, this one is the 101st largest by planned enrollment of the 288 observational ones that give a count, is one of 208 that started in 2025, is one of 288 observational ones, reaches primary completion later than 319 of the 987 other live ones, and was the 1,704th registered.

Carcinoma, Non-Small-Cell Lung

7,639 studies on the registry are indexed under Carcinoma, Non-Small-Cell Lung; 1,838 are open to participants now.

Browse Carcinoma, Non-Small-Cell Lung studies →

Open to participants now

763 of the 1,885 studies in Carcinoma, Non-Small-Cell Lung with a site in China are open now. Recruiting first, the newest first:

758 more — sign in →

All 763 open studies →

A study can be open while its sites in China have not opened yet or have stopped. Only those recruiting at a site in China →

Who these studies take

Of the 1,324 Carcinoma, Non-Small-Cell Lung studies recruiting now, 987 (75%) set no upper age limit and 225 (17%) stop at 75 or younger; 34 take children under 18; 40 take healthy volunteers.

This study: 18 Years and older · all sexes · no healthy volunteers.

The full table on the hub →

This tab as a report to print or save as PDF → With an account.

Was this useful?
Get alerts for this landscapeDownload CSVNarrow it in search →With an account: a weekly mail of what changed among 1,885 studies in Carcinoma, Non-Small-Cell Lung with a site in China, or all of them as a file.
02

Study summary

This retrospective multicenter observational study aims to develop and externally validate a noninvasive deep learning model based on routine brain MRI to identify actionable driver alterations in patients with non-small cell lung cancer (NSCLC) brain metastases. The model uses contrast-enhanced T1-weighted imaging (T1CE) and FLAIR sequences to classify patients as driver-positive (EGFR mutation and/or ALK rearrangement/fusion) versus driver-negative (EGFR-negative and ALK-negative), using brain metastasis tissue next-generation sequencing as the reference standard. The development and internal validation cohorts are from the National Cancer Center (China). Two independent external test cohorts are used: one from the First Affiliated Hospital of Anhui Medical University (China) and one from a public de-identified dataset hosted by The Cancer Imaging Archive (TCIA). The primary endpoint is the patient-level area under the receiver operating characteristic curve (AUC) in the external test cohorts. Secondary analyses include model calibration and decision-curve analysis to estimate clinical utility, comparisons of 2D/2.5D/3D modeling strategies and multimodal fusion approaches, and exploratory associations between model outputs and overall survival (OS) and progression-free survival (PFS), calculated from the date of brain metastasis surgery to the event or last follow-up (data cutoff: May 1, 2026).

Read the detailed description

Rationale and Objectives Actionable driver alterations such as EGFR mutations and ALK rearrangements/fusions are key determinants of treatment selection in NSCLC. In patients with brain metastases, tissue acquisition may be limited by surgical risk, lesion location, and time constraints. Routine brain MRI provides rich phenotypic information that may capture imaging correlates of molecular drivers. This study is designed to develop and externally validate a patient-level deep learning model that leverages multimodal MRI (T1CE and FLAIR) to noninvasively identify driver-positive status (EGFR mutation and/or ALK rearrangement/fusion) versus driver-negative status (EGFR-negative and ALK-negative).

Study Design and Data Sources This is a retrospective multicenter observational cohort study. Model development (training and internal validation) will be performed using data from the National Cancer Center (China). External validation will be conducted in two independent cohorts: (1) a clinical cohort from the First Affiliated Hospital of Anhui Medical University (China) and (2) a public de-identified cohort obtained from The Cancer Imaging Archive (TCIA). The TCIA cohort is used as an independent test set and is not involved in model training, hyperparameter tuning, or threshold selection.

Reference Standard and Driver Definition Driver status will be determined by next-generation sequencing performed on resected brain metastasis tissue. Driver-positive is defined as EGFR mutation and/or ALK rearrangement/fusion detected on brain metastasis tissue testing. Driver-negative is defined as both EGFR-negative and ALK-negative.

Imaging Inputs and Preprocessing Eligible patients must have preoperative brain MRI including at minimum T1CE and FLAIR sequences with acceptable image quality. Imaging data will be de-identified and standardized for analysis. Preprocessing will include harmonized spatial resampling to a common voxel spacing, intensity normalization, and co-registration between modalities when needed. Lesion localization/segmentation will be performed using manual, semi-automated, or automated approaches with quality control by trained reviewers, depending on data availability. For patients with multiple brain metastases, lesion-level representations will be aggregated to produce a patient-level prediction using a predefined pooling strategy (e.g., attention pooling or multiple-instance learning).

Model Development and External Validation The primary model will use multimodal inputs (T1CE + FLAIR) and a fusion strategy (including transformer-based fusion as a prespecified approach). Comparative analyses will evaluate 2D, 2.5D, and 3D modeling strategies and alternative fusion schemes (e.g., early vs late fusion) under a consistent evaluation framework. All model selection and threshold determination will be completed using the National Cancer Center development data. The finalized model and prespecified thresholds will then be locked and evaluated once in each external cohort without any additional training or recalibration.

Outcomes and Statistical Analysis The primary endpoint is discrimination performance assessed by patient-level AUC in the external test cohorts, with 95% confidence intervals. Secondary endpoints include sensitivity, specificity, positive predictive value (PPV), negative predictive value (NPV), calibration (calibration curves and Brier score), and decision-curve analysis to estimate net benefit across clinically relevant thresholds. Subgroup analyses may be performed by center, imaging acquisition characteristics, and single versus multiple metastases. In a subset with follow-up data, exploratory analyses will evaluate associations between model outputs and OS/PFS using Kaplan-Meier methods and Cox proportional hazards models. OS and PFS will be calculated from the date of brain metastasis surgery to death/progression or last follow-up; the data cutoff date is May 1, 2026.

Ethics and Privacy This study uses retrospective clinical data that will be de-identified prior to analysis. Institutional review board approval and/or waiver of informed consent will be obtained as required by participating institutions. The TCIA cohort consists of public de-identified data and does not involve direct participant contact.

03

Conditions studied

  • Non-Small Cell Lung Cancer
  • Brain Metastases

Keywords

  • Magnetic Resonance Imaging
  • Deep Learning
  • Multimodal MRI
  • T1-weighted Contrast-Enhanced (T1CE)
  • FLAIR
  • Transformer
  • EGFR
  • ALK
04

Who can participate

Ages eligible
18 Years and older
Sexes eligible
All
Accepts healthy volunteers
No
Sampling method
Non-probability sample

Study population

Retrospective multicenter cohorts of adult patients with non-small cell lung cancer (NSCLC) brain metastases who underwent brain metastasis surgery and had preoperative brain MRI including T1CE and FLAIR. EGFR and ALK status are determined by next-generation sequencing (NCG/NGS) performed on resected brain metastasis tissue. The development/internal validation cohort is from the National Cancer Center (China). Two independent external test cohorts are from the First Affiliated Hospital of Anhui Medical University (China) and a de-identified public dataset from The Cancer Imaging Archive (TCIA). Overall survival and progression-free survival are calculated from the date of brain metastasis surgery to the event or last follow-up (data cutoff: May 1, 2026).

Go through the criteria one by one — yes, no or not sure — and take the list to your doctor or the study team. Kept in this browser only.

Inclusion criteria

Age ≥ 18 years at the time of surgery. confirmed non-small cell lung cancer (NSCLC). Brain metastasis treated with surgical resection (index date for survival analyses).

Preoperative brain MRI is available, including, at minimum, contrast-enhanced T1-weighted imaging (T1CE) and FLAIR.

EGFR and ALK status are available from next-generation sequencing (NCG/NGS) performed on resected brain metastasis tissue (+/-).

MRI quality sufficient for analysis (adequate brain coverage and no severe artifacts).

Exclusion criteria

Exclusion Criteria:

Missing required MRI sequences (T1CE or FLAIR) or non-diagnostic image quality due to severe artifacts/motion.

Missing or unverifiable molecular testing results for EGFR and/or ALK from tissue.

Uncertain primary tumor origin or non-NSCLC histology. Prior intracranial therapy that substantially alters lesion appearance before the index MRI and cannot be reliably ascertained or adjusted for (e.g., radiotherapy immediately before the MRI), as determined by study investigators.

Terms in these criteria, in plain language(2)

Underlined terms in the criteria open these too. Explained by clinicaltrials.gg, not part of the registry record. The study team decides who can take part.

Brain metastases

Cancer deposits in the brain from a cancer that started elsewhere in the body (CNS metastases include the spinal cord).

Studies differ: some leave out any brain metastases, some accept ones treated and stable for some weeks. Check what this study allows.

Histologically or cytologically confirmed

The diagnosis was confirmed by looking at a sample under a microscope: tissue from a biopsy or surgery (histology), or cells from a fluid or needle sample (cytology).

Your pathology report is the document that shows this.

05

Study design

Observational model
Cohort
Time perspective
Retrospective
Enrollment
380 participants (estimated)
Patient registry
No

Groups and cohorts

  • National Cancer Center (NCC) Development Cohort

    Retrospective cohort of NSCLC brain metastasis patients from the National Cancer Center (China) with preoperative brain MRI including T1CE and FLAIR and brain metastasis tissue NGS (NCG/NGS) results for EGFR and ALK. This cohort is used for model development and internal validation, including prespecified threshold selection.

  • Anhui Medical University 1st Affiliated Hospital External Test Cohort

    Independent retrospective external validation cohort from the First Affiliated Hospital of Anhui Medical University (China) with preoperative T1CE and FLAIR MRI and brain metastasis tissue NGS results for EGFR and ALK. No model training or threshold tuning is performed in this cohort; it is used for locked external testing.

  • TCIA Public External Test Cohort

    Independent external validation cohort obtained from The Cancer Imaging Archive (TCIA), consisting of de-identified public brain MRI data (including T1CE and FLAIR when available) from NSCLC brain metastasis patients. This cohort is used only for locked external testing and is not involved in any model training, tuning, or threshold selection.

06

What researchers measure

Primary outcomes

  1. Patient-level AUC for driver status (External Validation)

    The deep learning model uses preoperative brain MRI (T1CE and FLAIR) to output a patient-level probability of driver-positive status. Performance will be evaluated primarily in two independent external test cohorts (First Affiliated Hospital of Anhui Medical University and TCIA). AUC with 95% confidence intervals will be reported.

    Time frame: Retrospective analysis through data cutoff (May 1, 2026)

Secondary outcomes

  1. Sensitivity and specificity at prespecified thresholds (External Validation)

    Prespecified thresholds (e.g., screening-oriented high-sensitivity threshold and/or confirmation-oriented high-specificity threshold) will be determined using the National Cancer Center development cohort and then locked. Sensitivity and specificity will be reported in external test cohorts.

    Time frame: Retrospective analysis through May 1, 2026

  2. Predictive values (PPV/NPV) (External Validation)

    PPV and NPV will be calculated in each external test cohort using the locked thresholds defined in the development cohort.

    Time frame: Retrospective analysis through May 1, 2026

  3. Model calibration (External Validation)

    Calibration of predicted probabilities will be evaluated in external test cohorts using calibration curves and Brier score (and/or calibration intercept/slope as applicable).

    Time frame: Retrospective analysis through May 1, 2026

  4. Decision-curve analysis (Clinical utility)

    Decision-curve analysis will be used to estimate clinical utility across a range of threshold probabilities, comparing model-guided triage strategies with default strategies (e.g., testing all vs testing none).

    Time frame: Retrospective analysis through May 1, 2026

  5. Overall survival (OS) association (Exploratory)

    OS will be defined from the date of brain metastasis surgery to death from any cause or last follow-up. Exploratory analyses will evaluate associations between model outputs (continuous probability and/or risk groups) and OS using Kaplan-Meier and Cox proportional hazards models in the subset with available follow-up data.

    Time frame: From date of brain metastasis surgery to death or last follow-up (up to May 1, 2026)

  6. Progression-free survival (PFS) association (Exploratory)

    PFS will be defined from the date of brain metastasis surgery to radiographic or clinical progression, death, or last follow-up. Exploratory analyses will evaluate associations between model outputs (continuous probability and/or risk groups) and PFS using Kaplan-Meier and Cox models in the subset with available follow-up data.

    Time frame: From date of brain metastasis surgery to progression/death or last follow-up (up to May 1, 2026)

07

Study locations

1 site
  • National Cancer Center/National Clinical Research Center for Cancer/Cancer Hospital, Chinese Academy of Medical Sciences and Peking Union Medical College
    Beijing, Beijing Municipality 100021, China
08

References and documents

Publications

  • Chadha, S., Sritharan, D., Dolezal, D., Chande, S., Hager, T., Bousabarah, K., Aboian, M., chiang, v., Lin, M., Nguyen, D., Aneja, S. (2025). MR Imaging and Segmentations with Matched Brain Biopsy Pathology Slides from Patients with Brain Metastases from Primary Lung Cancer (Brain-Mets-Lung-MRI-Path-Segs) (Version 2) [dataset]. The Cancer Imaging Archive. https://doi.org/10.7937/k0sm-y874
  • Zwanenburg A, Vallieres M, Abdalah MA, Aerts HJWL, Andrearczyk V, Apte A, Ashrafinia S, Bakas S, Beukinga RJ, Boellaard R, Bogowicz M, Boldrini L, Buvat I, Cook GJR, Davatzikos C, Depeursinge A, Desseroit MC, Dinapoli N, Dinh CV, Echegaray S, El Naqa I, Fedorov AY, Gatta R, Gillies RJ, Goh V, Gotz M, Guckenberger M, Ha SM, Hatt M, Isensee F, Lambin P, Leger S, Leijenaar RTH, Lenkowicz J, Lippert F, Losnegard A, Maier-Hein KH, Morin O, Muller H, Napel S, Nioche C, Orlhac F, Pati S, Pfaehler EAG, Rahmim A, Rao AUK, Scherer J, Siddique MM, Sijtsema NM, Socarras Fernandez J, Spezi E, Steenbakkers RJHM, Tanadini-Lang S, Thorwarth D, Troost EGC, Upadhaya T, Valentini V, van Dijk LV, van Griethuysen J, van Velden FHP, Whybra P, Richter C, Lock S. The Image Biomarker Standardization Initiative: Standardized Quantitative Radiomics for High-Throughput Image-based Phenotyping. Radiology. 2020 May;295(2):328-338. doi: 10.1148/radiol.2020191145. Epub 2020 Mar 10. PubMed 32154773 ↗
  • Collins GS, Moons KGM, Dhiman P, Riley RD, Beam AL, Van Calster B, Ghassemi M, Liu X, Reitsma JB, van Smeden M, Boulesteix AL, Camaradou JC, Celi LA, Denaxas S, Denniston AK, Glocker B, Golub RM, Harvey H, Heinze G, Hoffman MM, Kengne AP, Lam E, Lee N, Loder EW, Maier-Hein L, Mateen BA, McCradden MD, Oakden-Rayner L, Ordish J, Parnell R, Rose S, Singh K, Wynants L, Logullo P. TRIPOD+AI statement: updated guidance for reporting clinical prediction models that use regression or machine learning methods. BMJ. 2024 Apr 16;385:e078378. doi: 10.1136/bmj-2023-078378. PubMed 38626948 ↗
  • Mongan J, Moy L, Kahn CE Jr. Checklist for Artificial Intelligence in Medical Imaging (CLAIM): A Guide for Authors and Reviewers. Radiol Artif Intell. 2020 Mar 25;2(2):e200029. doi: 10.1148/ryai.2020200029. eCollection 2020 Mar. No abstract available. PubMed 33937821 ↗
  • Clark K, Vendt B, Smith K, Freymann J, Kirby J, Koppel P, Moore S, Phillips S, Maffitt D, Pringle M, Tarbox L, Prior F. The Cancer Imaging Archive (TCIA): maintaining and operating a public information repository. J Digit Imaging. 2013 Dec;26(6):1045-57. doi: 10.1007/s10278-013-9622-7. PubMed 23884657 ↗

Individual participant data

Plan to share: Undecided — A definitive IPD sharing plan has not yet been determined at the time of registration. Because the study involves retrospective multi-institutional clinical imaging, tissue-based molecular testing, and survival follow-up, any data sharing must comply with IRB approvals, privacy regulations, and participating institutions' data governance policies. The study team anticipates evaluating controlled-access sharing of de-identified derived datasets and model outputs after publication, subject to appropriate agreements and approvals.

09

Timeline

Tracking since Sep 25, 2026
ElapsedEstimatedEstimated, not yet reached

Started Nov 2025 (actual). Primary completion is estimated for Apr 2026, 5 months after the start.

How these figures are worked out, and which studies are left out of them.

Registered
Jan 21, 2026
First posted
Jan 28, 2026
StartActual
Nov 1, 2025
Primary completionEst.
Apr 1, 2026
CompletionEst.
May 1, 2026
Last update
Jan 29, 2026
What these dates mean
Start.
When the first participant enrolled; while estimated, when the study expects to open to recruitment.
Primary completion.
When the last participant was examined or treated to collect data for the study's main question, its primary outcome. A study that stopped early gives the date its data collection stopped.
Completion.
When the last participant's last visit took place, for every outcome, secondary ones and side effects included: the end of the study. Often later than primary completion, sometimes the same day.
Actual and Est.
Actual means the registry says the date has happened. Est. (estimated) is a date the sponsor plans or expects. It can still move, and the sponsor is expected to change it to actual once it has passed.
No changes since tracking began. The registry record was last updated on Jan 29, 2026, before this site started recording changes on Sep 25, 2026. Its history is on ClinicalTrials.gov ↗
10

Registry details

Key details

Study ID
NCT07373951
Lead sponsor
Ming Yang
Responsible party
Ming Yang (Clinical Professor, Cancer Institute and Hospital, Chinese Academy of Medical Sciences) — Sponsor-investigator
First posted
Jan 28, 2026
Start date
Nov 1, 2025
Primary completion
Apr 1, 2026 (estimated)
Completion
May 1, 2026 (estimated)
Last update
Jan 29, 2026

Oversight

Data monitoring committee
Yes
FDA-regulated drug
No
FDA-regulated device
No
View the source record on ClinicalTrials.gov ↗

Interested in this study?

Eligibility is decided by the study team. Share this record with your doctor or contact the team directly.

No contact was published for this record. The registry link below has the sponsor’s details.

Follow this study

Get an email when the registry record changes — status, dates, results — or when someone posts here.

Sign in to follow

Discussion

Questions and observations about this study, from anyone following it. Not medical advice, and not a channel to the study team — their contact details are on the registry record.

Sign in to join the discussion. Reading takes no account; posting does. You choose a display name, and a pseudonym is the default.

Nothing here yet. If you are running this trial, taking part in it, or weighing whether to, this is the place to say so.

Start the discussion