3D to 2D Anatomical Data Mapping for Surgical Planning

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Current medical imaging technologies struggle to accurately map three-dimensional anatomical data from imaging technologies like CT or MRI to two-dimensional images, particularly for patients in different positional states, such as from a horizontal to a vertical position, which limits the effectiveness of surgical planning and implant design.

Innovation Solution

A system that uses image processing and machine learning algorithms to map 3D anatomical data from CT or MRI scans to corresponding 2D images, allowing for the alignment of vertebrae and other anatomical features in both loaded and unloaded states, enabling the generation of high-resolution 3D models for surgical planning and implant design.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Measurement precision

If 3D anatomical data is mapped to 2D images using conventional imaging technologies, then the mapping accuracy deteriorates due to patient positional differences, but the use of advanced image processing and machine learning algorithms increases system complexity

Engineering Contradiction:
Improvemapping accuracyVSAvoidsystem complexity
Core Design Contradiction:
Measurement precisionVSDevice complexity

Solution Approach 1:

The patent introduces an image processing module as an intermediary component that receives both 3D anatomical data and 2D image data, processes them through machine learning algorithms, and generates mapped 2D images with improved accuracy. This intermediary handles the complex computational tasks separately, allowing the core imaging system to remain relatively simple while achieving high mapping precision through the specialized processing layer.

Inventive Principle:
Principle #24Intermediary (Mediator)

Solution Approach 2:

The system performs preliminary processing of 3D anatomical data to extract key features and characteristics before mapping to 2D images. By pre-processing the 3D data to identify anatomical landmarks, bone structures, and spatial relationships in advance, the mapping process becomes more accurate and efficient, reducing the complexity of the actual mapping operation.

Inventive Principle:
Principle #10Preliminary action

2Manufacturing precision

If high-resolution 3D models are generated through advanced image processing, then the surgical planning precision improves, but the processing time and computational resources increase

Engineering Contradiction:
Improvesurgical planning precisionVSAvoidprocessing time
Core Design Contradiction:
Manufacturing precisionVSLoss of time

Solution Approach 1:

The image processing module segments the 3D anatomical data into distinct components such as vertebrae, intervertebral discs, and surrounding soft tissues. By dividing the complex 3D model into manageable segments, the system can process each segment independently and efficiently, generating high-resolution detailed models where needed while reducing overall processing time through parallel computation of separate anatomical structures.

Inventive Principle:
Principle #1Segmentation

Solution Approach 2:

The system applies high-resolution processing selectively to critical anatomical regions that require precise surgical planning, such as the vertebral bodies and disc spaces, while using lower resolution for less critical areas. This partial application of high-resolution processing maintains surgical planning precision for essential structures while significantly reducing the total computational burden and processing time.

Inventive Principle:
Principle #16Partial or excessive action

Data Source

PatentUS20240252248A1Techniques to map three-dimensional human anatomy data to two-dimensional human anatomy data
Publication Date: 2024.08.01 CARLSMED INC
  • US20240252248A1 patent drawing
  • US20240252248A1 patent drawing
  • US20240252248A1 patent drawing

AI summary

Systems and methods for designing and implementing patient-specific surgical procedures and/or medical devices are disclosed. An example method includes obtaining a first multi-dimensional image data of an anatomical region of a patient in a first loading state; determining, from the first multi-dimensional image data, regions corresponding to anatomical elements of a spine; identifying, in each region, a first set of landmarks; obtaining a second multi-dimensional image data of the anatomical region comprising the spine of the patient in a second loading state; identifying a second set of landmarks from the second multi-dimensional image data that map to the first set of landmarks; obtaining an aligned multi-dimensional image data of the patient's spine; generating a design for a medical implant based on spinopelvic parameters measured from the aligned multi-dimensional image data; and causing a medical implant to be manufactured by sending the design for the medical implant to a manufacturing device.