Pulmonary NodulesGGN-TrajectoryNCT07647692
Deep Learning Time-Series Prediction of Long-Term Growth Patterns of Pulmonary Ground-Glass Nodules Using Serial CT
An observational study of Pulmonary Nodules and Lung Neoplasms, run by Peking University People's Hospital at 1 site in China.
Trial summary
Pulmonary ground-glass nodules (GGNs) are commonly found on chest CT scans. Some stay stable for years, while others slowly or rapidly turn into lung cancer. Doctors currently follow these nodules with repeated CT scans, but it is difficult to tell ahead of time which nodules will progress, how fast they will… Read more about this study
- Who is it for?
- Ages 18 years and older
- Conditions the study is for
- Pulmonary Nodules, Lung Neoplasms, Adenocarcinoma of Lung
- What is being tested?
- Serial Thin-Slice Chest CT
- How many people
- 4,750 participants
- Where
- 1 siteChina
- Study dates
- 1 Jun 2026to 1 Jun 2031
- How long will I take part?
- 5 Years
- Phase
- Observational
- Are there results?
- Not yet: the study is under way
Key requirements
Who can take part, as listed by the sponsor. Only the study team can confirm whether you are eligible, so take this list to your doctor.
- Ages 18 years and older
- All sexes
- No healthy volunteers
- Adult, Older adult
Study population: Adult patients (≥ 18 years) with a persistent pulmonary ground-glass nodule who underwent routine chest CT surveillance at the participating centers. Three retrospective cohorts (surgical development, surgical internal test, non-surgical internal test) are identified from the institutional PACS and clinical records of Peking University People's Hospital; one prospective multi-center cohort is enrolled consecutively after the AI model is locked.
Who may be able to join
- Age ≥ 18 years.
- Persistent pulmonary ground-glass nodule (pGGN or mGGN, 5-30 mm) on thin-slice chest CT (slice thickness ≤ 1.5 mm).
- Baseline and follow-up thin-slice chest CTs of sufficient quality for 3D segmentation and registration.
- Minimum interval between any two consecutive CTs > 1 month.
- Complete baseline clinical data available (age, sex, smoking history, family history of malignancy, relevant comorbidities).
- Cohort-specific inclusion
Show all 10Show fewer
- Group 1 (Development): surgical resection of the target GGN at PKUPH between Jan 2007 - Jun 2025, with ≥ 2 pre-operative thin-slice CTs available.
- Group 2 (Surgical internal test): surgical resection at PKUPH between Jul 2025 - Jan 2026, with ≥ 2 pre-operative thin-slice CTs available.
- Group 3 (Non-surgical internal test): non-operative management at PKUPH between Jan 2020 - Dec 2025, with ≥ 3 thin-slice CTs of the target GGN available.
- Group 4 (Prospective external validation): prospective enrollment after model lock at participating centers, baseline CT plus ≥ 2 planned routine follow-up thin-slice CTs.
Who cannot join
- Coexisting severe pulmonary disease that obscures evaluation of the target GGN (e.g., active pulmonary tuberculosis, severe interstitial lung disease).
- Prior history of any other thoracic malignancy, or active extrathoracic malignancy under treatment within 5 years, that would confound interpretation of the target GGN.
- CT image quality insufficient for registration and feature extraction (severe motion artifact, slice thickness > 1.5 mm at any required timepoint, or extensive metallic artifact projecting over the target GGN).
- Pure solid nodule with no ground-glass component.
- Target GGN already received treatment (resection, ablation, or radiotherapy) prior to the baseline CT used in this study.
Trial locations and contacts
1 site in 1 country. Contact the study team or a site near you to ask about taking part.
China1 site
Peking University People's Hospital
Beijing, Beijing Municipality, 100044
Hao Li, 13051713494, haolipkuph@pkuph.edu.cn
About this study
Official title: Development and Multi-Cohort Validation of a Deep Learning Spatiotemporal Model for Predicting Long-Term Progression of Pulmonary Ground-Glass Nodules Using Serial Thoracic CT
Pulmonary ground-glass nodules (GGNs) are commonly found on chest CT scans. Some stay stable for years, while others slowly or rapidly turn into lung cancer. Doctors currently follow these nodules with repeated CT scans, but it is difficult to tell ahead of time which nodules will progress, how fast they will progress, and which ones can be safely monitored rather than immediately treated.
This observational study aims to develop and validate an artificial intelligence (AI) model that uses each patient's series of CT scans over time to predict the long-term growth behavior of a GGN. The research team will collect three retrospective single-center cohorts from Peking University People's Hospital (a development cohort and two internal test cohorts, one from surgically resected patients and one from non-operated patients followed by serial CT) as well as a prospective multi-center validation cohort enrolled after the AI model is locked.
Read more
For every patient, each GGN is automatically segmented in three dimensions on every CT scan. A deep learning model extracts imaging features at each timepoint and feeds the sequence of features, together with the actual times between scans, into a time-aware sequence model. The model is trained to predict (i) whether the nodule will show radiological progression at 1, 3, and 5 years after baseline, and (ii) which of four long-term growth patterns the nodule will follow: stable, slow progression, slow-then-rapid progression, or rapid progression. In patients who were ultimately resected, the histopathological diagnosis serves as a secondary reference standard.
This is an observational study. No experimental treatment is given. All CT scans and clinical visits are part of routine clinical care.
Read the detailed description
Pulmonary ground-glass nodules (GGNs), including pure ground-glass nodules (pGGN) and mixed ground-glass nodules (mGGN), span a biological spectrum from atypical adenomatous hyperplasia and adenocarcinoma in situ to invasive lung adenocarcinoma. Current management guidelines (Fleischner Society, BTS, NCCN) rely primarily on cross-sectional CT features (diameter, density, consolidation-to-tumor ratio); these features do not capture the non-linear long-term behavior of GGNs. Long-term cohorts show that a meaningful fraction of GGNs remain indolent for years and then accelerate, demonstrating the limits of single-timepoint assessment.
Existing GGN management algorithms emphasize cross-sectional features measured on a single CT scan. Cross-sectional features alone are known to lose discriminative performance at longer (3-5 year) prediction horizons, where the relevant signal is increasingly carried by how the nodule changes over time rather than how it looks at any single moment. The present study is designed around this observation. It shifts the modeling target from static single-CT classification to a long-term spatiotemporal deep-learning framework that explicitly encodes the full trajectory of the nodule across the entire available serial-CT record.
This study uses a mixed retrospective-prospective design and is reported under TRIPOD guidance. Four cohorts are pre-specified:
- Development Cohort (Cohort 1): n ≈ 2,700. Surgically resected patients at Peking University People's Hospital from January 2007 to June 2025, with ≥ 2 pre-operative thin-slice chest CT scans available for the resected GGN.
- Internal Test Cohort A (Cohort 2): n ≈ 350. Surgically resected patients at Peking University People's Hospital from July 2025 to January 2026, with ≥ 2 pre-operative thin-slice chest CT scans available for the resected GGN.
- Internal Test Cohort B (Cohort 3): n ≈ 1,200. Non-operated patients at Peking University People's Hospital from January 2020 to December 2025, with ≥ 3 thin-slice chest CT scans of the target GGN.
- Prospective External Validation Cohort (Cohort 4): n ≈ 500. Patients (operated or non-operated) prospectively enrolled at Peking University People's Hospital and additional co-sites after the AI model is locked, with serial thin-slice chest CT performed as part of routine surveillance. This cohort serves as independent external (in-time and multi-center) validation and is not used for any model training or hyperparameter tuning.
After resampling to 1 × 1 × 1 mm and lung-window normalization, serial CTs are spatiotemporally registered (rigid + deformable) to baseline. For each timepoint, two regions of interest (ROIs) are derived for every target GGN: (i) the intratumoral ROI, defined as the full 3D extent of the nodule itself, automatically segmented using a pre-trained 3D U-Net with expert review; and (ii) the peritumoral ROI, defined as the shell of lung parenchyma extending 5 mm outward from the segmented nodule boundary, with intervening vessels, airways, and pleural surfaces masked out, to capture the perinodular lung microenvironment around the nodule. Radiomic features (per the Image Biomarker Standardization Initiative, IBSI) are extracted separately from each ROI, and deep features are extracted by a 3D convolutional neural network (e.g., 3D ResNet) applied independently to the intratumoral and peritumoral volumes. The two feature streams are concatenated at each timepoint to capture both intra-lesional heterogeneity and the perilesional microenvironment, which prior work from our team has shown to be informative.
The ordered sequence of per-timepoint feature vectors, together with the actual inter-scan time intervals, is fed into a time-aware sequence model (LSTM, GRU, or continuous-time Transformer) to model growth dynamics. Clinical covariates (age, sex, smoking history, family history of malignancy, emphysema score) are fused into a multimodal network. Temporal-attention maps and Shapley values are used for interpretability, with separate attribution reported for the intratumoral and peritumoral feature streams.
Model performance is reported with AUC and 95% CI for binary 1-, 3-, and 5-year progression endpoints, with DeLong testing against a single-baseline-CT radiomics benchmark; multi-class performance for the four-pattern trajectory task is reported with weighted / macro / micro F1 plus per-class precision and recall. Class imbalance, in particular the slow-then-rapid subgroup, is addressed with ADASYN oversampling and focal loss. For the subset of patients ultimately resected (Cohorts 1, 2, and the operated subset of Cohort 4), histopathological diagnosis serves as a secondary reference standard against which the imaging endpoints and the AI-predicted trajectory are compared.
- Conditions
- Pulmonary Nodules, Lung Neoplasms, Adenocarcinoma of Lung
- Being tested
- Serial Thin-Slice Chest CT
- Keywords
- Ground Glass Opacity, Ground-Glass Nodule, Longitudinal CT, Time-Series Analysis, Growth Trajectory, Volume Doubling Time, Deep Learning, Radiomics
- Medical subject headings
- Multiple Pulmonary Nodules, Lung Neoplasms, Adenocarcinoma of Lung
What participants receive
What participants receive. In a randomised study each person is assigned to one group by chance.
Serial Thin-Slice Chest CTDiagnostic test
Routine-care thin-slice non-contrast chest CT (slice thickness ≤ 1.5 mm, lung-window reconstruction) acquired at baseline and at subsequent clinical follow-up timepoints (minimum inter-scan interval > 1 month). Images are resampled to 1 × 1 × 1 mm and intensity-normalized before analysis. No additional imaging, radiation exposure, or procedures are performed for this study; all imaging is part of routine clinical care.
| Study group | Role | What they receive |
|---|---|---|
| Retrospective Surgical Development Cohort (Training) | Anticipated n: 2,700. Enrollment period: January 2007 - June 2025. Adults aged 18 years or older who underwent surgical resection for a pulmonary ground-glass nodule (pGGN or mGGN, 5-30 mm) at Peking University People's Hospital between January 2007 and 30 June 2025, with at least two pre-operative thin-slice chest CT scans (slice thickness ≤ 1.5 mm) of the resected nodule available. Imaging and clinical data from this cohort are used exclusively for model development (training and hyperparameter tuning). Surgical histopathology is collected and used as the secondary reference standard. Receives: Diagnostic Test: Serial Thin-Slice Chest CT | |
| Retrospective Surgical Internal Test Cohort | Anticipated n: 350. Enrollment period: July 2025 - January 2026. Adults aged 18 years or older who underwent surgical resection for a pulmonary ground-glass nodule at Peking University People's Hospital between 1 July 2025 and 31 January 2026, with at least two pre-operative thin-slice chest CT scans of the resected nodule available. This cohort is held out from model development and used exclusively for internal testing on operated patients. Surgical histopathology is available as the secondary reference standard. Receives: Diagnostic Test: Serial Thin-Slice Chest CT | |
| Retrospective Non-Surgical Internal Test Cohort | Anticipated n: 1,200. Enrollment period: January 2020 - December 2025. Adults aged 18 years or older with a persistent pulmonary ground-glass nodule at Peking University People's Hospital between 1 January 2020 and 31 December 2025 who were managed non-operatively with serial CT surveillance, with at least three thin-slice chest CT scans of the target GGN available. This cohort is held out from model development and used exclusively for internal testing in the non-operated population. Histopathology is not available; the primary imaging endpoints are used as the reference standard. Receives: Diagnostic Test: Serial Thin-Slice Chest CT | |
| Prospective Multi-Center External Validation Cohort | Anticipated n: 500. Enrollment period: June 2026 onward. Adults aged 18 years or older newly identified with a persistent pulmonary ground-glass nodule (5-30 mm) at participating centers, prospectively enrolled after the AI model is locked. Both operated and non-operated patients are eligible; a baseline thin-slice chest CT is required, and at least two additional thin-slice follow-up CTs are obtained as part of routine clinical care. Imaging and clinical data from this cohort are used exclusively for external (in-time and multi-center) validation of the locked model and are not used for any model training or hyperparameter tuning. Histopathology, where available from clinical resection, is used as the secondary reference standard. Receives: Diagnostic Test: Serial Thin-Slice Chest CT |
What is being measured
The primary outcome is the main question the study is designed to answer.
Radiological Progression of the Target Ground-Glass Nodule at 1 Year
Radiological progression is defined as meeting either of the following on a follow-up thin-slice CT compared with the baseline CT, based on 3D automated segmentation with expert adjudication: (a) increase of the overall maximum diameter of the nodule by ≥ 2 mm; OR (b) the appearance of a new solid component, or the increase in maximum diameter of an existing solid component, by ≥ 2 mm. The solid component is defined as regions with an attenuation value greater than -300 HU. Each participant is classified as a progression event at the 1-year timepoint if either criterion is met on a CT performed within the ± 3-month window around 12 months after baseline. Applies to all four cohorts.
Measured: 12 months from baseline CT (± 3-month window)
Radiological Progression of the Target Ground-Glass Nodule at 3 Years
Same progression definition as Primary Outcome 1, assessed on a CT performed within the ± 6-month window around 36 months after baseline. Ascertained where the available follow-up duration permits. Applies to all four cohorts.
Measured: 36 months from baseline CT (± 6-month window)
Radiological Progression of the Target Ground-Glass Nodule at 5 Years
Same progression definition as Primary Outcome 1, assessed on a CT performed within the ± 6-month window around 60 months after baseline. Ascertained where the available follow-up duration permits. Applies to all four cohorts.
Measured: 60 months from baseline CT (± 6-month window)
Long-Term Growth Trajectory Classification of the Target GGN
Each participant's target GGN is assigned, based on the full serial CT record, to exactly one of four mutually exclusive trajectory classes: (1) Stable - no progression event during follow-up; (2) Slow progression - continuous, approximately constant slow growth or slow increase of the solid component; (3) Slow-then-rapid progression - stable or minimally changing for an early period (e.g., 1-3 years) followed by abrupt acceleration (e.g., marked shortening of volume doubling time or new prominent solid component); (4) Rapid progression - aggressive growth evident early in follow-up. Classification is performed by two senior chest radiologists reading independently on the 3D automated outputs, with a third senior radiologist adjudicating disagreements.
Measured: Assessed across the full serial CT record, up to 60 months from baseline
Secondary outcomes (1)
Histopathological Diagnosis at Surgical Resection
For participants who undergo surgical resection of the target GGN as part of routine clinical care (all participants in Group 1, all in Group 2, and the operated subset of Group 4), the histopathological diagnosis of the resected specimen is recorded from the routine clinical pathology report and used as a secondary reference standard. Diagnoses are categorized per the WHO Classification of Lung Tumors as: atypical adenomatous hyperplasia (AAH), adenocarcinoma in situ (AIS), minimally invasive adenocarcinoma (MIA), invasive adenocarcinoma (IAC), or other benign / non-adenocarcinoma diagnoses. Concordance between AI-predicted trajectory class and final histopathology is reported.
Measured: At the time of clinical surgical resection (varies by participant; up to 60 months from baseline)
Timeline
From the start of the study to its completion; the mark is today. Estimated dates are the sponsor’s plan.
- First posted15 Jun 2026
- Study start1 Jun 2026 (estimated)
- Primary completion1 Jun 2027 (estimated)
- Study completion1 Jun 2031 (estimated)
Resources
- Official record on ClinicalTrials.govThe registry entry this page is built from, with its full change history.
- Other trials for Pulmonary NodulesStudies of the same condition, open and under way.
- What the trial phases meanHow a treatment moves from first tests in people to approval.
More details
For doctors and researchers: how the study is designed, who runs it, and its registry IDs.
Study design
- Study type
- Observational
- Observational model
- Cohort
- Time perspective
- Other
- Enrolment
- 4,750 participants (estimated)
- Target duration
- 5 Years
Sponsor and investigators
- Lead sponsor
- Peking University People's Hospital
- Sponsor type
- University, hospital or other
- Responsible party
- Principal investigator, HaoLi, Peking University People's Hospital
- Investigators
- Hao Li, Principal investigator, Peking University People's Hospital
IDs, dates and publications
- ClinicalTrials.gov ID
- NCT07647692
- Sponsor's protocol ID
- PKUPH-GGN-TRAJ-2026
- Other IDs
- L252064, 2025PHB380
- Acronym
- GGN-Trajectory
- Status last verified
- Jun 2026
- First submitted
- 10 Jun 2026
- Last updated
- 15 Jun 2026
- Results posted
- No
- Data monitoring committee
- No
- FDA-regulated drug
- No
- FDA-regulated device
- No
- Individual data sharing
- No: De-identified individual participant data are not planned to be shared publicly, consistent with the data-management and confidentiality requirements of the sponsoring institution described in the study protocol. All patient data are stored on the institution's internal research server, with access restricted to the research team and the institutional ethics committee. Aggregated model-performance metrics and summary results will be reported in the primary publication. Requests from qualified researchers for collaborative re-analysis may be considered on a case-by-case basis by the Principal Investigator, subject to institutional review and a formal data-use agreement.
Study at a glance
From the registry record, last updated by the sponsor on 15 Jun 2026. Recruitment status is as the sponsor reported it: confirm with the study team.
- Official title
- Development and Multi-Cohort Validation of a Deep Learning Spatiotemporal Model for Predicting Long-Term Progression of Pulmonary Ground-Glass Nodules Using Serial Thoracic CT
- ClinicalTrials.gov ID
- NCT07647692
- Acronym / sponsor ID
- GGN-Trajectory / PKUPH-GGN-TRAJ-2026
- Conditions
- Pulmonary Nodules, Lung Neoplasms, Adenocarcinoma of Lung
- Keywords
- Ground Glass Opacity, Ground-Glass Nodule, Longitudinal CT, Time-Series Analysis, Growth Trajectory, Volume Doubling Time, Deep Learning, Radiomics
- Study type
- Observational
- Recruitment status
- Not yet recruiting
- Enrolment
- 4,750 participants (estimated)
- Lead sponsor
- Peking University People's HospitalUniversity, hospital or other
- Study start
- 1 Jun 2026 (estimated)
- Primary completion
- 1 Jun 2027 (estimated)
- Study completion
- 1 Jun 2031 (estimated)
- First posted
- 15 Jun 2026 (actual)
- Results
- Not posted in the source record
Clinical summary
The research question as the sponsor registered it. This describes what the study plans to test, not what it found.
Pulmonary ground-glass nodules (GGNs) are commonly found on chest CT scans. Some stay stable for years, while others slowly or rapidly turn into lung cancer. Doctors currently follow these nodules with repeated CT scans, but it is difficult to tell ahead of time which nodules will progress, how fast they will progress, and which ones can be safely monitored rather than immediately treated.
This observational study aims to develop and validate an artificial intelligence (AI) model that uses each patient's series of CT scans over time to predict the long-term growth behavior of a GGN. The research team will collect three retrospective single-center cohorts from Peking University People's Hospital (a development cohort and two internal test cohorts, one from surgically resected patients and one from non-operated patients followed by serial CT) as well as a prospective multi-center validation cohort enrolled after the AI model is locked.
For every patient, each GGN is automatically segmented in three dimensions on every CT scan. A deep learning model extracts imaging features at each timepoint and feeds the sequence of features, together with the actual times between scans, into a time-aware sequence model. The model is trained to predict (i) whether the nodule will show radiological progression at 1, 3, and 5 years after baseline, and (ii) which of four long-term growth patterns the nodule will follow: stable, slow progression, slow-then-rapid progression, or rapid progression. In patients who were ultimately resected, the histopathological diagnosis serves as a secondary reference standard.
This is an observational study. No experimental treatment is given. All CT scans and clinical visits are part of routine clinical care.
Detailed description
Pulmonary ground-glass nodules (GGNs), including pure ground-glass nodules (pGGN) and mixed ground-glass nodules (mGGN), span a biological spectrum from atypical adenomatous hyperplasia and adenocarcinoma in situ to invasive lung adenocarcinoma. Current management guidelines (Fleischner Society, BTS, NCCN) rely primarily on cross-sectional CT features (diameter, density, consolidation-to-tumor ratio); these features do not capture the non-linear long-term behavior of GGNs. Long-term cohorts show that a meaningful fraction of GGNs remain indolent for years and then accelerate, demonstrating the limits of single-timepoint assessment.
Existing GGN management algorithms emphasize cross-sectional features measured on a single CT scan. Cross-sectional features alone are known to lose discriminative performance at longer (3-5 year) prediction horizons, where the relevant signal is increasingly carried by how the nodule changes over time rather than how it looks at any single moment. The present study is designed around this observation. It shifts the modeling target from static single-CT classification to a long-term spatiotemporal deep-learning framework that explicitly encodes the full trajectory of the nodule across the entire available serial-CT record.
This study uses a mixed retrospective-prospective design and is reported under TRIPOD guidance. Four cohorts are pre-specified:
- Development Cohort (Cohort 1): n ≈ 2,700. Surgically resected patients at Peking University People's Hospital from January 2007 to June 2025, with ≥ 2 pre-operative thin-slice chest CT scans available for the resected GGN.
- Internal Test Cohort A (Cohort 2): n ≈ 350. Surgically resected patients at Peking University People's Hospital from July 2025 to January 2026, with ≥ 2 pre-operative thin-slice chest CT scans available for the resected GGN.
- Internal Test Cohort B (Cohort 3): n ≈ 1,200. Non-operated patients at Peking University People's Hospital from January 2020 to December 2025, with ≥ 3 thin-slice chest CT scans of the target GGN.
- Prospective External Validation Cohort (Cohort 4): n ≈ 500. Patients (operated or non-operated) prospectively enrolled at Peking University People's Hospital and additional co-sites after the AI model is locked, with serial thin-slice chest CT performed as part of routine surveillance. This cohort serves as independent external (in-time and multi-center) validation and is not used for any model training or hyperparameter tuning.
After resampling to 1 × 1 × 1 mm and lung-window normalization, serial CTs are spatiotemporally registered (rigid + deformable) to baseline. For each timepoint, two regions of interest (ROIs) are derived for every target GGN: (i) the intratumoral ROI, defined as the full 3D extent of the nodule itself, automatically segmented using a pre-trained 3D U-Net with expert review; and (ii) the peritumoral ROI, defined as the shell of lung parenchyma extending 5 mm outward from the segmented nodule boundary, with intervening vessels, airways, and pleural surfaces masked out, to capture the perinodular lung microenvironment around the nodule. Radiomic features (per the Image Biomarker Standardization Initiative, IBSI) are extracted separately from each ROI, and deep features are extracted by a 3D convolutional neural network (e.g., 3D ResNet) applied independently to the intratumoral and peritumoral volumes. The two feature streams are concatenated at each timepoint to capture both intra-lesional heterogeneity and the perilesional microenvironment, which prior work from our team has shown to be informative.
The ordered sequence of per-timepoint feature vectors, together with the actual inter-scan time intervals, is fed into a time-aware sequence model (LSTM, GRU, or continuous-time Transformer) to model growth dynamics. Clinical covariates (age, sex, smoking history, family history of malignancy, emphysema score) are fused into a multimodal network. Temporal-attention maps and Shapley values are used for interpretability, with separate attribution reported for the intratumoral and peritumoral feature streams.
Model performance is reported with AUC and 95% CI for binary 1-, 3-, and 5-year progression endpoints, with DeLong testing against a single-baseline-CT radiomics benchmark; multi-class performance for the four-pattern trajectory task is reported with weighted / macro / micro F1 plus per-class precision and recall. Class imbalance, in particular the slow-then-rapid subgroup, is addressed with ADASYN oversampling and focal loss. For the subset of patients ultimately resected (Cohorts 1, 2, and the operated subset of Cohort 4), histopathological diagnosis serves as a secondary reference standard against which the imaging endpoints and the AI-predicted trajectory are compared.
Study design
- Observational model
- Cohort
- Time perspective
- Other
- Target follow-up
- 5 Years
- Number of arms
- 4
| Arm | Type | Receives |
|---|---|---|
| Retrospective Surgical Development Cohort (Training) | – | Diagnostic Test: Serial Thin-Slice Chest CTAnticipated n: 2,700. Enrollment period: January 2007 - June 2025. Adults aged 18 years or older who underwent surgical resection for a pulmonary ground-glass nodule (pGGN or mGGN, 5-30 mm) at Peking University People's Hospital between January 2007 and 30 June 2025, with at least two pre-operative thin-slice chest CT scans (slice thickness ≤ 1.5 mm) of the resected nodule available. Imaging and clinical data from this cohort are used exclusively for model development (training and hyperparameter tuning). Surgical histopathology is collected and used as the secondary reference standard. |
| Retrospective Surgical Internal Test Cohort | – | Diagnostic Test: Serial Thin-Slice Chest CTAnticipated n: 350. Enrollment period: July 2025 - January 2026. Adults aged 18 years or older who underwent surgical resection for a pulmonary ground-glass nodule at Peking University People's Hospital between 1 July 2025 and 31 January 2026, with at least two pre-operative thin-slice chest CT scans of the resected nodule available. This cohort is held out from model development and used exclusively for internal testing on operated patients. Surgical histopathology is available as the secondary reference standard. |
| Retrospective Non-Surgical Internal Test Cohort | – | Diagnostic Test: Serial Thin-Slice Chest CTAnticipated n: 1,200. Enrollment period: January 2020 - December 2025. Adults aged 18 years or older with a persistent pulmonary ground-glass nodule at Peking University People's Hospital between 1 January 2020 and 31 December 2025 who were managed non-operatively with serial CT surveillance, with at least three thin-slice chest CT scans of the target GGN available. This cohort is held out from model development and used exclusively for internal testing in the non-operated population. Histopathology is not available; the primary imaging endpoints are used as the reference standard. |
| Prospective Multi-Center External Validation Cohort | – | Diagnostic Test: Serial Thin-Slice Chest CTAnticipated n: 500. Enrollment period: June 2026 onward. Adults aged 18 years or older newly identified with a persistent pulmonary ground-glass nodule (5-30 mm) at participating centers, prospectively enrolled after the AI model is locked. Both operated and non-operated patients are eligible; a baseline thin-slice chest CT is required, and at least two additional thin-slice follow-up CTs are obtained as part of routine clinical care. Imaging and clinical data from this cohort are used exclusively for external (in-time and multi-center) validation of the locked model and are not used for any model training or hyperparameter tuning. Histopathology, where available from clinical resection, is used as the secondary reference standard. |
Who may qualify
- Ages
- 18 years and older
- Sex
- All
- Healthy volunteers
- Not accepted
- Age groups
- Adult, Older adult
- Study population
- Adult patients (≥ 18 years) with a persistent pulmonary ground-glass nodule who underwent routine chest CT surveillance at the participating centers. Three retrospective cohorts (surgical development, surgical internal test, non-surgical internal test) are identified from the institutional PACS and clinical records of Peking University People's Hospital; one prospective multi-center cohort is enrolled consecutively after the AI model is locked.
Key inclusion criteria (10 listed)
- Age ≥ 18 years.
- Persistent pulmonary ground-glass nodule (pGGN or mGGN, 5-30 mm) on thin-slice chest CT (slice thickness ≤ 1.5 mm).
- Baseline and follow-up thin-slice chest CTs of sufficient quality for 3D segmentation and registration.
- Minimum interval between any two consecutive CTs > 1 month.
- Complete baseline clinical data available (age, sex, smoking history, family history of malignancy, relevant comorbidities).
Key exclusion criteria (5 listed)
- Coexisting severe pulmonary disease that obscures evaluation of the target GGN (e.g., active pulmonary tuberculosis, severe interstitial lung disease).
- Prior history of any other thoracic malignancy, or active extrathoracic malignancy under treatment within 5 years, that would confound interpretation of the target GGN.
- CT image quality insufficient for registration and feature extraction (severe motion artifact, slice thickness > 1.5 mm at any required timepoint, or extensive metallic artifact projecting over the target GGN).
- Pure solid nodule with no ground-glass component.
- Target GGN already received treatment (resection, ablation, or radiotherapy) prior to the baseline CT used in this study.
Eligibility is decided by the study team after screening; this overview does not establish that a patient qualifies. Full inclusion and exclusion criteria.
Interventions
| Intervention | Type | Arms |
|---|---|---|
| Serial Thin-Slice Chest CTRoutine-care thin-slice non-contrast chest CT (slice thickness ≤ 1.5 mm, lung-window reconstruction) acquired at baseline and at subsequent clinical follow-up timepoints (minimum inter-scan interval > 1 month). Images are resampled to 1 × 1 × 1 mm and intensity-normalized before analysis. No additional imaging, radiation exposure, or procedures are performed for this study; all imaging is part of routine clinical care. | Diagnostic test | Prospective Multi-Center External Validation Cohort, Retrospective Non-Surgical Internal Test Cohort, Retrospective Surgical Development Cohort (Training), Retrospective Surgical Internal Test Cohort |
Primary outcome
Radiological Progression of the Target Ground-Glass Nodule at 1 Year
Time frame: 12 months from baseline CT (± 3-month window)
Radiological progression is defined as meeting either of the following on a follow-up thin-slice CT compared with the baseline CT, based on 3D automated segmentation with expert adjudication: (a) increase of the overall maximum diameter of the nodule by ≥ 2 mm; OR (b) the appearance of a new solid component, or the increase in maximum diameter of an existing solid component, by ≥ 2 mm. The solid component is defined as regions with an attenuation value greater than -300 HU. Each participant is classified as a progression event at the 1-year timepoint if either criterion is met on a CT performed within the ± 3-month window around 12 months after baseline. Applies to all four cohorts.
Radiological Progression of the Target Ground-Glass Nodule at 3 Years
Time frame: 36 months from baseline CT (± 6-month window)
Same progression definition as Primary Outcome 1, assessed on a CT performed within the ± 6-month window around 36 months after baseline. Ascertained where the available follow-up duration permits. Applies to all four cohorts.
Radiological Progression of the Target Ground-Glass Nodule at 5 Years
Time frame: 60 months from baseline CT (± 6-month window)
Same progression definition as Primary Outcome 1, assessed on a CT performed within the ± 6-month window around 60 months after baseline. Ascertained where the available follow-up duration permits. Applies to all four cohorts.
Long-Term Growth Trajectory Classification of the Target GGN
Time frame: Assessed across the full serial CT record, up to 60 months from baseline
Each participant's target GGN is assigned, based on the full serial CT record, to exactly one of four mutually exclusive trajectory classes: (1) Stable - no progression event during follow-up; (2) Slow progression - continuous, approximately constant slow growth or slow increase of the solid component; (3) Slow-then-rapid progression - stable or minimally changing for an early period (e.g., 1-3 years) followed by abrupt acceleration (e.g., marked shortening of volume doubling time or new prominent solid component); (4) Rapid progression - aggressive growth evident early in follow-up. Classification is performed by two senior chest radiologists reading independently on the 3D automated outputs, with a third senior radiologist adjudicating disagreements.
1 secondary outcome
Histopathological Diagnosis at Surgical Resection
Time frame: At the time of clinical surgical resection (varies by participant; up to 60 months from baseline)
Results and safety
This study is still under way. Results are not available in the source record yet.
Research links
- Official record on ClinicalTrials.govLast updated by the sponsor 15 Jun 2026.
- Individual participant dataSharing planned: No. De-identified individual participant data are not planned to be shared publicly, consistent with the data-management and confidentiality requirements of the sponsoring institution described in the study protocol. All patient data are stored on the institution's internal research server, with access restricted to the research team and the institutional ethics committee. Aggregated model-performance metrics and summary results will be reported in the primary publication. Requests from qualified researchers for collaborative re-analysis may be considered on a case-by-case basis by the Principal Investigator, subject to institutional review and a formal data-use agreement.
Related trials for Pulmonary Nodules
Recruiting
Longitudinal AI-Assisted Management of Indeterminate Pulmonary Nodules
Pulmonary Nodules, Lung Neoplasms
Active, not recruitingObservational study
Clinical Application of Artificial Intelligence Methods in Diagnostic Imaging of Pulmonary Nodules
Pulmonary Nodules, Lung Neoplasms
RecruitingObservational study
Study of Collection and Analysis of Clinical, Anamnestic, Functional, Biological Data Through the Support of Artificial Intelligence to Evaluate the Possibility of Defining a Digital Twin of the Lung (LUCE)
Thoracic Neoplasm, Pulmonary Nodules
RecruitingObservational study
Lung Cancer Detection in Never Smokers Using Urine Volatile Organic Compound (VOCs)
Lung Cancer
Not yet recruitingPhase 4
Preoperative Pneumococcal and Influenza Vaccination to Prevent Postoperative Pulmonary Infection in Patients Undergoing Lung Resection for Pulmonary Nodules or Lung Cancer
Pneumococcal Polysaccharide Vaccine, Influenza Vaccines
Referral and contact
AzTrials does not enrol participants or take referrals. Contact the study team or a site listed below; they decide who can take part.
Hao Li principal investigator
Peking University People's Hospital
1 site in 1 country: see every site and its status.
Questions about this trial
What is this clinical trial studying?
An observational study of Pulmonary Nodules and Lung Neoplasms, run by Peking University People's Hospital at 1 site in China.
The full registered description is in the About this study section and the official record.
Who may be eligible to take part?
The sponsor lists 10 inclusion and 5 exclusion criteria. Eligibility is decided by the study team after screening, so read the full criteria and contact a listed site.
Is this clinical trial currently recruiting?
The record says: opening soon, as of the sponsor's last update on 15 Jun 2026. Status can change between updates, so confirm with the study contact before making plans.
Where is the study taking place?
The record lists 1 site in China. Whether a site is taking part right now should be confirmed with that site. See every site.
What are the possible benefits and risks?
They depend on the study and the treatment, and no study can promise a benefit. The study team explains the known risks during informed consent, before anyone joins; the record itself does not list them.
Are results available for this study?
This study is still under way. Results are not available in the source record yet.
How can a doctor refer a patient or contact the research team?
Contact Hao Li (13051713494, haolipkuph@pku.edu.cn), or a site near the patient. AzTrials does not enrol participants or take referrals.
What does the primary outcome measure?
Radiological Progression of the Target Ground-Glass Nodule at 1 Year (time frame: 12 months from baseline CT (± 3-month window)). The study lists 4 primary outcomes in all. It is what the study was designed to measure, not a finding.
Where can I read the original study information?
Does a listing mean the treatment is approved or proven to work?
No. A listing means the study is registered. It does not show that the treatment is safe, works, or is approved by a regulator.
How often is this information updated?
AzTrials copies changed records from ClinicalTrials.gov every night and reloads the whole registry every week. The sponsor last updated this record on 15 Jun 2026.