Under construction – not a live service
Sign in
Not yet taking people in ChinaNo phase

AI Predicts Long-Term Growth of Lung Ground-Glass Nodules From CT Scans

Tests an AI model on repeated chest CT scans to predict growth of lung nodules.

Key facts

Who runs it
Peking University People's Hospital
Where
Beijing, ChinaSee the site
Trial code
Registry title
Deep Learning Time-Series Prediction of Long-Term Growth Patterns of Pulmonary Ground-Glass Nodules Using Serial CT
Status
Not yet recruiting
People taking part
4,750 people, planned
Started
1 Jun 2026
Expected to end
1 Jun 2031
Type of study
Observational, 4 groups
Treatments tested
  • Serial Thin-Slice Chest CT
Record updated
15 June 2026

Who can take part

AI summary

From the trial's eligibility criteria. Machine-read from the registry text on this page, so it can be wrong. The registry text below and the trial team decide who can take part.

The trial is looking for adults with a lasting ground-glass nodule in the lung that has been followed on several thin-slice chest CT scans. It tests an AI model that predicts how the nodule will grow.

Age
18 years or older
Sex
All sexes can join
Disease stage
A lasting ground-glass nodule (pure or mixed), 5-30 mm, on thin-slice chest CT (slices 1.5 mm or thinner)
Earlier treatment
The nodule must not have been treated (resection, ablation or radiotherapy) before the baseline CT used in the study

Main reasons for not taking part

  • Severe lung disease that hides the nodule, such as active tuberculosis or severe interstitial lung disease
  • Another chest cancer in the past, or another cancer outside the chest under treatment within 5 years
  • CT images of too poor quality for the analysis
  • A pure solid nodule with no ground-glass part

The registry criteria, word for word

Show all 14 criteriaShow less

Who can take part

  • 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
  • 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 take part

  • Prior history of any other thoracic malignancy, or active extrathoracic malignancy under treatment within 5 years, that would confound interpretation of the target GGN
  • Target GGN already received treatment (resection, ablation, or radiotherapy) prior to the baseline CT used in this study
  • Coexisting severe pulmonary disease that obscures evaluation of the target GGN (e.g., active pulmonary tuberculosis, severe interstitial lung disease)
  • 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

Where in China

  • Peking University People's HospitalBeijing, ChinaContact: Hao LiNo longer taking part

About the trial

What the trial wants to find out

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.

Read full original descriptionShow less

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.

The 4 groups in the trial

  • 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.

    Treatment: 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.

    Treatment: 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.

    Treatment: 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.

    Treatment: Serial Thin-Slice Chest CT

Questions to ask the study team

  1. How often do I need to come in, and for how long each time?
  2. Are travel costs paid?
  3. Can I keep my own doctor?
  4. What happens if I want to stop?

Contact the study team: see the registry record → Contacts and Locations

Print a page for my doctor

Data and sources

Registry record
Listed on ClinicalTrials.gov.
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
Plain-language title
AI Predicts Long-Term Growth of Lung Ground-Glass Nodules From CT ScansGenerated from the registry record. The registry title is the official one.
AI summary
From the trial's eligibility criteria. Read by machine on 12 November 2026.
Record updated
15 June 2026