Skip to content

. Use of artificial intelligence to detect nasal structure changes (deviated nasal septum and concha bullosa) on CT scan.

Harnessing artificial intelligence in revolutionizing nasal anatomy: automated detection of concha bullosa and deviated nasal septum by AI using 128 slice CT.

Status
Active, not recruiting
Phases
Unknown
Study type
Interventional
Source
CTRI
Registry ID
CTRI/2026/05/109942
Enrollment
500
Registered
2026-05-04
Start date
Unknown
Completion date
Unknown
Last updated
2026-06-01

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

Conditions

Health Condition 1: J010- Acute maxillary sinusitis Health Condition 2: J988- Other specified respiratory disorders

Interventions

Intervention1: Nil: Nil Intervention2: Nil: Nil Intervention3: Nil: Nil Intervention4: Intervention: Artificial intelligence based image analysis of CT paranasal sinuses: Comparator: Radiologist asses

Sponsors

Saveetha Institute of Medical and Technical Sciences
Lead Sponsor

Eligibility

Inclusion criteria

Inclusion criteria: Adult patients aged 18 years and above undergoing CT paranasal sinus imaging for sinonasal symptoms or preoperative evaluation. Patients with complete CT datasets acquired on 128 slice CT scanner and who provide informed consent will be included.

Exclusion criteria

Exclusion criteria: Patients with prior nasal or sinus surgery. Patients with sinonasal tumors. Patients with congenital craniofacial anomalies. CT studies with poor image quality or motion artifacts. Patients who do not provide consent.

Design outcomes

Primary

MeasureTime frame
Diagnostic accuracy of the artificial intelligence model for detection of deviated nasal septum and concha bullosa on CT paranasal sinus imaging measured by sensitivity specificity and area under the receiver operating characteristic curve compared with expert radiologist reference standardTimepoint: At the time of CT image acquisition and analysis for each participant during the study period

Secondary

MeasureTime frame
Specificity positive predictive value negative predictive value and overall accuracy of the artificial intelligence modelTimepoint: At time of CT image analysis during study period

Countries

India

Contacts

Public ContactKarunakaram Sriram

Saveetha Medical College and Hospital, SIMATS

sriram.1797@gmail.com6301546735

Outcome results

None listed

Source: CTRI (via WHO ICTRP) · Data processed: Jun 11, 2026