Skip to content

AI-based detection and classification of kidney tumours using CT scans

Development and Validation of a Renal Explainable AI Network (RenalXNet) for Detection and Differential Diagnosis of Renal Tumour using CT Radiomic Features - NIL

Status
Active, not recruiting
Phases
Unknown
Study type
Observational
Source
CTRI
Registry ID
CTRI/2026/01/100361
Enrollment
390
Registered
2026-01-05
Start date
Unknown
Completion date
Unknown
Last updated
2026-02-02

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

Conditions

Health Condition 1: C649- Malignant neoplasm of unspecifiedkidney, except renal pelvis

Interventions

Intervention1: Nil: Nil

Sponsors

Ms. Meera Radhakrishnan
Lead Sponsor

Eligibility

Inclusion criteria

Inclusion criteria: For Case Group: Archived CECT abdominal scans with radiologically confirmed renal tumors. Availability of corresponding histopathological reports confirming renal tumors. Lesions measuring greater than equal to 5 mm in diameter on axial CT images. For Control Group: Archived CECT abdominal scans showing no evidence of renal tumors or pathology. CT images of good quality with normal renal tissue available for radiomic analysis.

Exclusion criteria

Exclusion criteria: Common for Both Groups: CT images with significant motion artifacts. History of renal surgery. History of chemotherapy or radiation therapy for renal conditions.

Design outcomes

Primary

MeasureTime frame
Diagnostic performance of the RenalXNet model for detection and differential diagnosis of renal tumors using CT radiomic features measured by accuracy sensitivity specificity and area under the ROC curve with histopathology as the reference standardTimepoint: At the time of CT image acquisition and analysis and at the time of availability of histopathology results

Secondary

MeasureTime frame
Identification of significant CT radiomic features associated with benign and malignant renal tumorsTimepoint: During retrospective phase data analysis;Comparative performance of RenalXNet with traditional machine learning models for renal tumor classificationTimepoint: After model development and testing on retrospective dataset ;Prospective validation performance of RenalXNet for detection and differential diagnosis of renal tumorsTimepoint: At completion of prospective validation phase;Subgroup analysis performance of RenalXNet across renal tumor subtypesTimepoint: During final data analysis

Countries

India

Contacts

Public ContactMs Meera Radhakrishnan

Manipal College of Health Professions

r.meera@manipal.edu8689844096

Outcome results

None listed

Source: CTRI (via WHO ICTRP) · Data processed: Feb 7, 2026