Skip to content

CT image features and artificial intelligence for predicting EGFR types in non-small cell lung cancer patients: a multicenter syudy

CT image features and artificial intelligence for predicting EGFR types in non-small cell lung cancer patients

Status
Active, not recruiting
Phases
Unknown
Study type
Observational
Source
ChiCTR
Registry ID
ChiCTR2400083082
Enrollment
Unknown
Registered
2024-04-15
Start date
2022-12-22
Completion date
Unknown
Last updated
2024-04-22

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

Conditions

non-small cell lung cancer

Interventions

Gold Standard:Molecular pathology results.
Index test:Method: CT features and radiomics or deep learning features. CT features are the most common descriptions of lesions by radiologists, such as "longest diameter"
radiomics or deep learning features are generated by networks. CT scanning equipment: Somatom Definition AS+, Siemens Healthcare, German
GE Optima 670, GE Medical Systems, USA.

Sponsors

Anhui Chest Hospital
Lead Sponsor

Eligibility

Sex/Gender
All
Age
20 Years to 85 Years

Inclusion criteria

Inclusion criteria: 1. Histologically confirmed diagnosis of non-small cell lung cancer; 2. Tumor specimen determined EGFR genotype; 3. CT image slice thickness =3 mm; 4. Age 20-85 years; 5. Obtained written informed consent.

Exclusion criteria

Exclusion criteria: 1. Multiple pulmonary diseases; 2. Poor quality of CT images; 3. Incomplete clinical information; 4. The patient received antitumor treatment before the CT scan.

Design outcomes

Primary

MeasureTime frame
Area Under the Receiver Operating Characteristic ;

Secondary

MeasureTime frame
Sensitivity;Specificity;Positive Predictive Value;Negative Predictive Value;Accuracy;

Countries

China

Contacts

Public ContactXuhong Min

Anhui Chest Hospital

ahch_minxuhong@163.com+86 138 5517 9548

Outcome results

None listed

Source: ChiCTR (via WHO ICTRP) · Data processed: Jul 22, 2026