Deep Learning Signature for Predicting Aggressive Histological Pattern in Resected Non-small Cell Lung Cancer

Positron Emission Tomography/ Computed Tomography (PET/CT) Based Deep Learning Signature for Predicting Aggressive Histological Pattern in Resected Non-small Cell Lung Cancer

Status

UNKNOWN

Phases

Unknown

Study type

Observational

Source

ClinicalTrials.gov

Registry ID

NCT05925738

Enrollment

1500

Registered

2023-06-29

Start date

2023-05-01

Completion date

2023-10-31

Last updated

2023-06-29

For informational purposes only — not medical advice. Sourced from public registries and may not reflect the latest updates. Terms

Conditions

Lymphovascular Invasion, Non-small Cell Lung Cancer, Spread Through Air Space, Visceral Pleural Invasion

Brief summary

The purpose of this study is to evaluate the performance of a PET/ CT-based deep learning signature for predicting aggressive histological pattern in resected non-small cell lung cancer based on a multicenter prospective cohort.

Interventions

DIAGNOSTIC_TESTPET/CT-based Deep Learning Signature

Deep Learning Signature Based on PET-CT for Predicting the Aggressive Histological Pattern in Resected Non-small Cell Lung Cancer

Study design

Observational model

COHORT

Time perspective

PROSPECTIVE

Eligibility

Sex/Gender

ALL

Age

20 Years to 75 Years

Healthy volunteers

Yes

Inclusion criteria

(1) Participants scheduled for surgery for radiological finding of pulmonary lesions from the preoperative thin-section CT scans; (2) Pathological confirmation of primary NSCLC; (3) Age ranging from 20-75 years; (4) Obtained written informed consent.

Exclusion criteria

(1) Multiple lung lesions; (2) Poor quality of PET-CT images; (3) Participants with incomplete clinical information; (4) Participants who have received neoadjuvant therapy.

Design outcomes

Primary

Measure	Time frame	Description
Area under the receiver operating characteristic curve	2023.5.1-2023.10.31	The area under the receiver operating characteristic curve (ROC) of the deep learning model in predicting the presence or absence of the aggressive histological pattern. The aggressive histological pattern includes spread through air space (STAS), visceral pleural invasion (VPI), and lymphovascular invasion (LVI). And the model will output all predictive values (presence or absence) of the three kinds of aggressive histological patterns.

Secondary

Measure	Time frame	Description
Sensitivity	2023.5.1-2023.10.31	The sensitivity of the deep learning model in predicting the presence or absence of the aggressive histological pattern. The aggressive histological pattern includes spread through air space (STAS), visceral pleural invasion (VPI), and lymphovascular invasion (LVI). And the model will output all predictive values (presence or absence) of the three kinds of aggressive histological patterns.

Other

Measure	Time frame	Description
Specificity	2023.5.1-2023.10.31	The specificity of the deep learning model in predicting the presence or absence of the aggressive histological pattern. The aggressive histological pattern includes spread through air space (STAS), visceral pleural invasion (VPI), and lymphovascular invasion (LVI). And the model will output all predictive values (presence or absence) of the three kinds of aggressive histological patterns.
Positive predictive value	2023.5.1-2023.10.31	The positive predictive value of the deep learning model in predicting the presence or absence of the aggressive histological pattern. The aggressive histological pattern includes spread through air space (STAS), visceral pleural invasion (VPI), and lymphovascular invasion (LVI). And the model will output all predictive values (presence or absence) of the three kinds of aggressive histological patterns.
Negative predictive value	2023.5.1-2023.10.31	The negative predictive value of the deep learning model in predicting the presence or absence of the aggressive histological pattern. The aggressive histological pattern includes spread through air space (STAS), visceral pleural invasion (VPI), and lymphovascular invasion (LVI). And the model will output all predictive values (presence or absence) of the three kinds of aggressive histological patterns.
Accuracy	2023.5.1-2023.10.31	The accuracy of the deep learning model in predicting the presence or absence of the aggressive histological pattern. The aggressive histological pattern includes spread through air space (STAS), visceral pleural invasion (VPI), and lymphovascular invasion (LVI). And the model will output all predictive values (presence or absence) of the three kinds of aggressive histological patterns.

Countries

China

Outcome results

None listed

Source: ClinicalTrials.gov · Data processed: Feb 4, 2026