Development of Three-dimensional Deep Learning for Automatic Design of Skull Implants

• Sponsor: Chang Gung Memorial Hospital (Other)
• Overall Status: Not yet recruiting
• CT.gov ID: NCT05603949
• Collaborator: Ministry of Science and Technology, Taiwan (Other)
• Enrollment: 6
• Anticipated Duration (Months): 7.4

Study Details

Study Description

Brief Summary

This project aims to develop an effective deep learning system to generate numerical implant geometry based on 3D defective skull models from CT scans. This technique is beneficial for the design of implants to repair skull defects above the Frankfort horizontal plane.

Condition or Disease	Intervention/Treatment	Phase
Skull Defect	Device: 3D deep learning neural network system

Detailed Description

Designing a personalized implant to restore the protective and aesthetic functions of the patient's skull is challenging. The skull defects may be caused by trauma, congenital malformation, infection, and iatrogenic treatments such as decompressive craniectomy, plastic surgery, and tumor resection. The project aims to develop a deep learning system with 3D shape reconstruction capabilities. The system will meet the requirement of designing high-resolution 3D implant numerical models efficiently.

A collection of skull images were used for training the deep learning system. Defective models in the datasets were created by numerically masking areas of intact 3D skull models. The final implant design should be verified by neurosurgeons using 3D printed models.

Study Design

• Study Type: Observational
• Anticipated Enrollment: 6 participants
• Observational Model: Case-Only
• Time Perspective: Retrospective
• Official Title: Development of Three-dimensional Deep Learning for Automatic Design of Skull Implants
• Anticipated Study Start Date: Dec 1, 2022
• Anticipated Primary Completion Date: Jul 15, 2023
• Anticipated Study Completion Date: Jul 15, 2023

Arms and Interventions

Arm	Intervention/Treatment
experimental group	Device: 3D deep learning neural network system; With the consent of the patient, we will assist in the production of images of 3D defect blocks for free (3D deep learning neural network system (3D DNN) system process planning), complete the repair and reconstruction under the clinical routine surgery, and track the repair results after surgery. meet medical needs.

Outcome Measures

Primary Outcome Measures

1. Number of patients where there is no need to adapt the Patient Specific Implant (PSI) edges [6 weeks after surgery by standardised questionnaire]

   Number of patients where there is no need to adapt the Patient Specific Implant (PSI) edges

2. Number of patients where there is no need to augment/fill clefts between the Patient Specific Implant (PSI) and patient´s bone [6 weeks after surgery by standardised questionnaire]

   Number of patients where there is no need to augment/fill clefts between the Patient Specific Implant (PSI) and patient´s bone

Eligibility Criteria

Criteria

• Ages Eligible for Study: 15 Years to 80 Years
• Sexes Eligible for Study: All
• Accepts Healthy Volunteers: No

Inclusion Criteria:

1. Scheduled for cranioplasty

2. Informed consent

Exclusion Criteria:

(1)No informed consent

Contacts and Locations

Locations

No locations specified.

Sponsors and Collaborators

• Chang Gung Memorial Hospital
• Ministry of Science and Technology, Taiwan

Investigators

None specified.

Study Documents (Full-Text)

None provided.

More Information

Publications

None provided.

• Responsible Party: Yau-Zen Chang, Professor, Chang Gung Memorial Hospital
• ClinicalTrials.gov Identifier: NCT05603949
• Other Study ID Numbers: 202201082B0
• First Posted: Nov 3, 2022
• Last Update Posted: Nov 3, 2022
• Last Verified: Nov 1, 2022

• Studies a U.S. FDA-regulated Drug Product: No
• Studies a U.S. FDA-regulated Device Product: No
• Keywords provided by Yau-Zen Chang, Professor, Chang Gung Memorial Hospital: Deep Neural Networks;3D Shape Inpainting

Study Results

No Results Posted as of Nov 3, 2022