System and method of improving surgical devices using captured images for efficient surgical plan development
AssigneeMaterialise N.V.
InventorsBenjamin Geebelen, Roel Wirix-Speetjens
Life of this patent
Estimating the term…
Abstract
A two-step approach for image segmentation during the treatment planning process is disclosed. In a first step, an automatic segmentation method can be used to generate a first, provisional segmentation. The first, provisional segmentation may be generated using fast, but less accurate segmentation methods. The first provisional segmentation may be used to generate a default treatment plan for approval. Once the default treatment plan is approved, a more robust, second image segmentation may be performed. The second segmentation may be used to design patient-specific devices that can be used to deliver the patient-specific medical treatment.
Claims18
A method of delivering a patient-specific medical treatment to a patient, the method comprising:
- acquiring image data of a patient anatomy;
- uploading the image data to an automated segmentation portal;
- receiving a default treatment plan from the automated segmentation portal, wherein the default treatment plan is generated based on a first 3D model of the patient anatomy that is generated based on a first segmentation of the image data performed by the automated segmentation portal;
- approving the generated treatment plan;
- transmitting the approved treatment plan to a service provider;
- receiving a medical device from the service provider, wherein the medical device comprises at least one of a patient-matched medical device selected from a device library or a manufactured patient-specific medical device, wherein the medical device is based on the approved treatment plan and a second 3D model of the patient anatomy that is generated based on a second segmentation of the image data, the second segmentation of the image data being more accurate than the first segmentation of the image data, and the second 3D model being more accurate than the first 3D model, wherein the first 3D model of the patient anatomy and the first segmentation are not accurate enough to design the medical device as a patient-specific device, and wherein the second 3D model of the patient anatomy and the second segmentation are accurate enough to design the medical device as a patient-specific device;
- and
- delivering the patient-specific treatment to the patient using the received medical device.
A method of delivering a patient-specific medical treatment to a patient, the method comprising:
- acquiring image data of a patient anatomy;
- uploading the image data to an automated segmentation portal;
- receiving a default treatment plan from the automated segmentation portal, wherein the default treatment plan is generated based on a first 3D model of the patient anatomy that is generated based on a first segmentation of the image data performed by the automated segmentation portal;
- approving the generated treatment plan;
- transmitting the approved treatment plan to a service provider;
- receiving a medical device from the service provider, wherein the medical device comprises at least one of a patient-matched medical device selected from a device library or a manufactured patient-specific medical device, wherein the medical device is based on the approved treatment plan and a second 3D model of the patient anatomy that is generated based on a second segmentation of the image data, the second segmentation of the image data being more accurate than the first segmentation of the image data, and the second 3D model being more accurate than the first 3D model, wherein the first 3D model of the patient anatomy and the first segmentation are not accurate enough to design the medical device as a patient-specific device, and wherein the second 3D model of the patient anatomy and the second segmentation are accurate enough to design the medical device as a patient-specific device;
- and
- delivering the patient-specific treatment to the patient using the received medical device.
Dependencies are inferred from the claim text.