AI Needle Path Planning With 3D Organ Segmentation

Resolve Bottlenecks,
Find Innovative SolutionsGenerate Solutions

Solution Overview

Problem

Existing surgical planning systems for needle insertion paths, particularly in tumor punctures, are time-consuming, highly dependent on doctor expertise, and prone to subjective opinions, with risks of damaging blood vessels due to inadequate three-dimensional visualization and cross-plane path planning.

Innovation Solution

An assisted surgical planning system utilizing a discriminative AI module for organ segmentation and a generative AI module to generate and adjust needle insertion paths, integrated with a user navigation interface for doctor interaction, reducing reliance on two-dimensional imaging and enhancing path planning accuracy.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Ease of operation

If doctors perform needle insertion path planning in axial view of CT images, then the path planning is more convenient and easier to imagine, but cross-plane needle insertion path planning becomes difficult and time-consuming

Engineering Contradiction:

Improveconvenience of path planningVSAvoidtime for adjusting needle insertion paths

Core Design Contradiction:

Ease of operationVSLoss of time

Solution Approach 1:

The system transforms two-dimensional axial CT images into three-dimensional reconstructed images, enabling doctors to visualize and plan needle insertion paths from multiple angles simultaneously. This dimensional transition allows cross-plane path planning without requiring repeated axial slice adjustments, thereby reducing time consumption while maintaining ease of operation.

Inventive Principle:

Principle #17Another dimension (Dimensionality change)

2Productivity

If doctors rely on their expertise and experience for path planning, then the planning process is faster, but the results are highly subjective and prone to errors

Engineering Contradiction:

Improvespeed of path planningVSAvoidaccuracy of path planning

Core Design Contradiction:

ProductivityVSReliability

Solution Approach 1:

The system introduces an AI-based intermediary module that automatically analyzes CT images, identifies anatomical structures, and generates preliminary needle insertion paths. This intermediary assists doctors by providing objective, data-driven path suggestions that reduce subjectivity and improve reliability, while still allowing doctor expertise to guide final decisions.

Inventive Principle:

Principle #24Intermediary (Mediator)

Solution Approach 2:

The system replaces the purely mechanical reliance on doctor expertise with an automated AI system that processes imaging data algorithmically. The AI module automatically segments organs, identifies vessels and nerves, and calculates safe paths, substituting human cognitive processing with computational algorithms that provide consistent and reliable results.

Inventive Principle:

Principle #28Mechanics substitution (Replace mechanical system)

3Measurement precision

If doctors perform multiple CT scans during surgery to verify needle insertion paths, then the path accuracy is improved, but the surgical time and complexity increase

Engineering Contradiction:

Improveaccuracy of needle insertion pathVSAvoidcomplexity of surgical process

Core Design Contradiction:

Measurement precisionVSDevice complexity

Solution Approach 1:

The system performs all necessary path planning, verification, and optimization actions before surgery begins. By pre-calculating multiple candidate paths and verifying them against anatomical structures in advance, the system eliminates the need for intraoperative CT scans, thereby maintaining high accuracy while reducing surgical complexity and time.

Inventive Principle:

Principle #10Preliminary action

4Difficulty of detecting and measuring

If doctors use contrast-enhanced computed tomography (CECT) method to identify vessels, then the visibility of blood vessels is improved, but the examination time and radiation exposure increase

Engineering Contradiction:

Improvevisibility of blood vesselsVSAvoidexamination time

Core Design Contradiction:

Difficulty of detecting and measuringVSLoss of time

Solution Approach 1:

The system creates a digital three-dimensional copy of the patient's anatomy from standard CT images, allowing virtual exploration of vascular structures without requiring additional contrast-enhanced scans. This virtual model enables doctors to visualize and measure vessel locations accurately while avoiding the time and radiation costs of repeated imaging procedures.

Inventive Principle:

Principle #26Copying

Data Source

PatentEP4699560A1Assisted surgical planning system and operation method thereof

Publication Date: 2026.02.25 NAT TAIWAN UNIV

Figure 1~2
Figure 3~4
Figure 5~6

AI summary

An assisted surgical planning system includes a host computer, a discriminative Al module, a user navigation interface, and a generative Al module. The discriminative Al module is electrically connected to the host computer, and is configured to form plural organ segmentation images based on plural CT images. The user navigation interface is electrically connected to the host computer, and is configured to display the organ segmentation images, an initial needle insertion path, plural suggested needle insertion paths, and a final needle insertion path. The generative Al module is electrically connected to the host computer, such that the host computer connects the user navigation interface to the generative Al module. The generative Al module is configured to generate the suggested needle insertion paths based on the organ segmentation images and the initial needle insertion path, and display the suggested needle insertion paths in the user navigation interface.