Bone Point Cloud Prediction for Surgical Alignment Planning

Resolve Bottlenecks,
Find Innovative SolutionsGenerate Solutions

Solution Overview

Problem

Orthopedic surgeries face challenges in accurately planning implant alignment due to incomplete or poor-quality image content of bone portions, particularly in pre-operative scans, which can lead to increased surgical complications.

Innovation Solution

A computing system utilizes point cloud neural networks (PCNNs) to generate a second point cloud representing missing bone portions or directly determine an axis along the bone, based on a first point cloud, enabling precise surgical planning without reconstructing unavailable bone sections.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Loss of information

If pre-operative scans are performed to obtain image content of bone portions, then surgical planning information can be generated, but image content of certain bone portions may not be available due to scanning limitations or patient anatomy

Engineering Contradiction:

Improveavailability of bone image contentVSAvoidaccuracy of surgical planning

Core Design Contradiction:

Loss of informationVSReliability

Solution Approach 1:

The patent uses a point cloud neural network to generate a virtual copy (second point cloud) of the missing bone portion based on the available first point cloud. This synthetic copy allows surgical planning to proceed even when direct image content of the bone portion is unavailable, effectively replacing the missing information with an AI-generated approximation.

Inventive Principle:

Principle #26Copying

Solution Approach 2:

The system performs preliminary generation of the second point cloud representing the missing bone portion before actual surgical planning occurs. This advance reconstruction allows surgeons to have complete bone models available for pre-operative planning, eliminating the need to proceed with incomplete information.

Inventive Principle:

Principle #10Preliminary action

2Measurement precision

If complete bone image content is obtained through scanning, then accurate surgical planning is enabled, but scanning time and patient exposure increase

Engineering Contradiction:

Improvecompleteness of bone representationVSAvoidscanning time

Core Design Contradiction:

Measurement precisionVSLoss of time

Solution Approach 1:

The patent applies partial scanning to obtain the first point cloud of available bone portions, then uses the point cloud neural network to generate the remaining portions. This approach performs only the necessary minimum scanning required, avoiding excessive scanning time while still achieving complete bone representation through AI completion.

Inventive Principle:

Principle #16Partial or excessive action

3Reliability

If traditional methods are used to handle missing bone portions, then surgical complications may occur, but advanced imaging increases cost and complexity

Engineering Contradiction:

Improvesurgical outcome accuracyVSAvoidimaging system complexity

Core Design Contradiction:

ReliabilityVSDevice complexity

Solution Approach 1:

The patent replaces complex physical imaging systems with a computational approach using point cloud neural networks. Instead of using additional sophisticated scanning hardware to capture missing bone portions, the system uses AI algorithms to generate the missing data computationally, reducing hardware complexity while maintaining surgical planning accuracy.

Inventive Principle:

Principle #28Mechanics substitution (Replace mechanical system)

Data Source

PatentUS20250359935A1Prediction of bone based on point cloud

Publication Date: 2025.11.27 HOWMEDICA OSTEONICS CORP

AI summary

A method for surgical planning includes obtaining, by a. computing system, a. first point cloud representing a first portion of a bone or a first cloud representing at least a portion of a bone, applying, by the computing system, a point cloud neural network to generate a second point cloud based on the first point cloud, the second point cloud comprising at least one of points representing at least a second portion of the bone or points representing an axis along the bone, and generating, by the computing system, surgical planning information based on the second point cloud.