Skip to content

Using artificial intelligence (AI) (Deep Learning) to create an AI Model for automating assessment Of vertebral pathologies by quantifying the signal drop on in and out-phase component of Chemical Shift Imaging (CSI) sequence on MRI spine

Using Deep Learning Model to Create a Model for Automating Chemical Shift Imaging (CSI) Assessment Of Vertebral Lesions on MRI Spine - A prospective, observational study

Status
Active, not recruiting
Phases
Unknown
Study type
Observational
Source
CTRI
Registry ID
CTRI/2022/07/044330
Enrollment
1250
Registered
2022-07-26
Start date
Unknown
Completion date
Unknown
Last updated
2022-08-02

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

Conditions

Health Condition 1: M959- Acquired deformity of musculoskeletal system, unspecified

Interventions

None listed

Sponsors

Dr DY Patil Hospital College and Research Center Pune
Lead Sponsor
DeepTek Inc
Collaborator
International Skeletal Society
Collaborator

Eligibility

Inclusion criteria

Inclusion criteria: All patients presenting for an MRI spine who may have any benign pathology- hemangioma, schmorls nodule, degenerative changes. Any patient presenting with a malignant etiology- spinal metastasis, spinal vertebral tumor.

Exclusion criteria

Exclusion criteria: Post-operative spinal column changes.

Design outcomes

Primary

MeasureTime frame
A deep learning based artificial intelligence algorithm which can perform at par with radiologists in picking up a spinal vertebral body lesion on VIBE-DIXON sequence and use it to classify a lesion as benign or malignant. Calculate sensitivity, specificity, precision, accuracy and area under the curve.Timepoint: Single timepoint (Baseline only and no follow-up)- the study is only performed once on a patient and after which processing of the data happens. We will not be reacquiring mri spine scans again for the same patient.

Secondary

MeasureTime frame
Inferences from the data will allow creation of normative data for inphase-outphase chemical shift imaging of MR spine scans on our SIEMNES scannersTimepoint: Immediately after data is analysed.

Countries

India

Contacts

Public ContactPranav Ajmera

Dr DY Patil Medical College, Hospital and Research Center, DPU, Pune

pranavajmera@gmail.com918802100420

Outcome results

None listed

Source: CTRI (via WHO ICTRP) · Data processed: Feb 4, 2026