Endoscopic OCT Guiding Percutaneous Nephrostomy

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Current imaging modalities for percutaneous nephrostomy (PCN) needle placement in urological procedures suffer from inadequate spatial resolution, leading to high failure rates and complications such as bleeding and renal injury due to difficulty in accurately locating the needle tip position within the kidney, especially in non-dilated systems or complex stone diseases.

Innovation Solution

An endoscopic Optical Coherence Tomography (OCT) system integrated with neural networks is used to distinguish renal tissue types and blood vessels, providing real-time 3D imaging and automatic classification of renal cortex, medulla, and calyx, guiding precise needle placement and reducing the risk of vascular injury.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Measurement precision

If conventional imaging modalities (ultrasound, fluoroscopy, CT) are used for PCN needle placement guidance, then the procedure can be performed with standard equipment, but the spatial resolution is inadequate for accurately locating the needle tip position

Engineering Contradiction:
Improveneedle tip position accuracyVSAvoidimaging system complexity
Core Design Contradiction:
Measurement precisionVSDevice complexity

Solution Approach 1:

The endoscope is inserted inside the PCN needle, creating a nested configuration where the imaging device resides within the needle structure. This allows the imaging system to travel with the needle to the target location, providing high-resolution imaging exactly where needed without requiring separate complex imaging equipment.

Inventive Principle:
Principle #7Nested doll (Nesting)

Solution Approach 2:

The patent replaces conventional mechanical imaging systems (ultrasound transducers, fluoroscopy equipment, CT scanners) with an optical imaging system based on Optical Coherence Tomography. OCT uses light interference principles to achieve micrometer-scale resolution, substituting mechanical scanning and large equipment with optical field-based imaging.

Inventive Principle:
Principle #28Mechanics substitution (Replace mechanical system)

2Reliability

If multiple needle insertion attempts are performed to achieve correct PCN placement, then the likelihood of renal injury increases and operational time lengthens

Engineering Contradiction:
Improvefirst-attempt success rateVSAvoidoperational time
Core Design Contradiction:
ReliabilityVSLoss of time

Solution Approach 1:

The endoscopic OCT system performs preliminary imaging of the renal tissue ahead of the needle tip before the needle actually contacts or penetrates the target structure. This allows the operator to identify the optimal insertion path and confirm correct positioning in advance, ensuring first-attempt success and avoiding repeated insertions that would increase operational time and injury risk.

Inventive Principle:
Principle #10Preliminary action

Solution Approach 2:

The real-time OCT imaging provides continuous visual feedback during needle insertion, allowing the operator to monitor needle position relative to renal structures and adjust the insertion path accordingly. This feedback loop enables precise positioning on the first attempt by showing the operator exactly where the needle tip is relative to blood vessels and collecting system structures.

Inventive Principle:
Principle #23Feedback

3Object-affected harmful factors

If fluoroscopy is used for PCN guidance, then the procedure can be performed with standard equipment, but soft tissue contrast is insufficient to differentiate critical tissues such as blood vessels

Engineering Contradiction:
Improvevascular injury riskVSAvoidtissue differentiation capability
Core Design Contradiction:
Object-affected harmful factorsVSMeasurement precision

Solution Approach 1:

The patent replaces fluoroscopy's X-ray-based imaging with Optical Coherence Tomography, which uses near-infrared light to image tissue. OCT provides inherent soft tissue contrast based on optical scattering properties, allowing differentiation of blood vessels, renal parenchyma, and collecting system structures without requiring contrast agents or relying on density differences that limit fluoroscopy.

Inventive Principle:
Principle #28Mechanics substitution (Replace mechanical system)

Solution Approach 2:

The endoscope acts as an intermediary carrier that delivers the OCT imaging system directly to the needle tip location. This intermediary device enables high-resolution optical imaging within the confined space of the needle, providing detailed visualization of blood vessels and tissue structures that would be invisible to both fluoroscopy and external ultrasound.

Inventive Principle:
Principle #24Intermediary (Mediator)

Applied Scientific Principles

This section explains which scientific principles are used to turn an abstract innovation direction into a practical engineering solution.

Function Achieved in This Case

The OCT system achieves an average classification accuracy of 82.6% for renal tissue types, significantly reducing the risk of complications by enabling precise needle placement and real-time detection of blood vessels, thereby improving the safety and efficiency of PCN procedures.

Implementation Method 1

OCT is a well-established, non-invasive biomedical imaging modality which can image subsurface tissue with the penetration depth of several millimeters. By obtaining and processing the coherent infrared light backscattered from the reference arm and sample arm, OCT can provide 2D cross-sectional images with high axial resolution ( ̃10 μm)

Methodology Applied
Scientific EffectOptical Coherence Tomography: Interference

Implementation Method 2

a neural network classifier to distinguish types of renal tissue and other components. The types of renal tissue include the cortex, medulla, and calyx. Other components include blood vessels and diseased renal tissues

Methodology Applied
Scientific EffectNeural Network Classification: Image Processing

Data Source

PatentUS20220151708A1Endoscopic Guidance Using Neural Networks
Publication Date: 2022.05.19 THE BOARD OF RGT UNIV OF OKLAHOMA
  • US20220151708A1 patent drawing
  • US20220151708A1 patent drawing
  • US20220151708A1 patent drawing

AI summary

A method comprises obtaining an endoscope; obtaining a needle; inserting the endoscope into the needle to obtain a system; inserting the system into an animal body; and distinguishing components of the animal body using the endoscope and while the system remains in the animal body. A system comprises a needle; and an endoscope inserted into the needle and configured to: store a convolutional neural network (CNN); distinguish among a cortex of a kidney of an animal body, a medulla of the kidney, and a calyx of the kidney using the CNN; and distinguish between vascular tissue and non-vascular tissue in the animal body using the CNN.