Smart Robotic Biopsy Needle Path Planning for Lung Biopsy
Project Reference :
Principal Investigator :
Dr Lee Hwee Kuan, Bioinformatics Institute (BII)
Technology Readiness :
3 (Experimental proof of concept)
Technology Categories :
Remote-controlled robotic devices for percutaneous image-guided biopsy are still heavily dependent on operator skills in needle positioning and are error-prone and time consuming. Existing AI-based automated medical image segmentation techniques still need operator interaction for error correction. There is currently no comprehensive solution that can combine AI-driven segmentation techniques with AI-enhanced robotics targeting accuracy.
An AI model based on the latest R-CNN and U-Net model for lung nodule detection and vessel segmentation using CT images.
A robotic system can be coupled with image fusion that uses the AI-driven vessel segmentation and lesion diagnosis technique to enhance lesion targeting accuracy and achieve high sensitivity on nodule malignancy and position estimation.
- Nodules can be located more precisely on CT images for biopsy operations which can further improve the surgery yield and reduce false negative diagnosis
- Vessel segmentation function helps the radiologist visualize the biopsy trajectory for the radiologist to avoid small but vital veins in the lung, thereby reducing the risk of complications to patients
- Entire biopsy process can be automated by the robotic-assisted intervention system, enabling larger number of cases to be handled with the same accuracy and faster speed
Medical image analysis and automated robotic-guided biopsy by healthcare and medical industry.
We welcome interest from the industry for collaboration/ co-development / customisation of the technology into a new product or service. If you have any enquiries or are keen to collaborate, please contact us.