# US 11,896,312 B2 · Image-guided lung tumor planning and ablation system

> Agents: this data is available as JSON from the patentgrep API and MCP server — see https://patentgrep.com/llms.txt

- Number: US 11,896,312 B2
- Document ID: US11896312B2
- Status: Granted
- Kind: B2
- Application number: 16/963,745
- Filed: 2019-02-04
- Published: 2021-12-30
- Granted: 2024-02-13
- Earliest claimed: 2018-02-05
- Assignees: Broncus Medical Inc.
- Applicants: Broncus Medical Inc.
- Inventors: Yixun Liu; Ronnarit Cheirsilp; Kun-Chang Yu; Henky Wibowo
- Web page: https://patentgrep.com/patent/US11896312B2

## CPC

- A61B 34/10: Computer-aided planning, simulation or modelling of surgical operations
- A61B 18/082: {Probes or electrodes therefor}
- A61B 18/1492: {having a flexible, catheter-like structure, e.g. for heart ablation (A61B18/1477 takes precedence)}
- A61B 34/25: {User interfaces for surgical systems}
- A61B 2018/00541: {Lung or bronchi}
- A61B 2018/00577: {Ablation}
- A61B 2034/104: {Modelling the effect of the tool, e.g. the effect of an implanted prosthesis or for predicting the effect of ablation or burring}
- A61B 2034/105: {Modelling of the patient, e.g. for ligaments or bones}
- A61B 2034/107: {Visualisation of planned trajectories or target regions}
- A61B 2090/376: {using X-rays, e.g. fluoroscopy}
- A61B: DIAGNOSIS; SURGERY; IDENTIFICATION (usefulness limited to only animals A61D)

## Abstract

A lung tumor ablation planning system includes a processor operable to compute a target ablation zone and a set of optimum ablation parameters to create the target lesion with the ablation catheter. A predictive algorithm is employed to model the ablation zone based on training data. Various ablation plans are displayed to the physician corresponding to various metrics including without limitation maximizing tumor ablation coverage, shortest travel, obstacle avoidance, and shortest ablation time. Related methods are described.

## Claims

### Claim 1

A bronchoscopic-based system for planning to ablate a target tissue in a lung of a patient with an ablation applicator comprising:
a storage for receiving image data of the lung of the patient including the target tissue to be ablated; and
a processor programmed and operable to:
compute, based on the image data of the lung, at least one candidate path for the ablation applicator to be advanced through the airway of the patient to a candidate point of entry (POE), and from the POE to the target tissue;
select a learned ablation model from a plurality of candidate models based on a set of candidate ablation parameters and at least one characteristic of the target tissue, wherein the plurality of candidate models are based on past experimental data, and wherein the past experimental data includes measurements from ablation testing on sample tissue; and
compute an ablation zone based on said learned ablation model to maximize ablation coverage of the target tissue for each said candidate path.

### Claim 2 (depends on 1)

The system of claim 1, wherein the set of candidate ablation parameters are selected from the group consisting of power, frequency, and treatment time.

### Claim 3 (depends on 2)

The system of claim 2, further comprising computing the plurality of candidate ablation treatment parameters for each said candidate path to the target tissue.

### Claim 4 (depends on 1)

The system of claim 1, further comprising a bronchoscope, the bronchoscope comprising a working lumen through which the ablation applicator may be advanced.

### Claim 5 (depends on 1)

The system of claim 1, further comprising the ablation applicator.

### Claim 6 (depends on 5)

The system of claim 5, wherein the ablation applicator is adapted to raise a temperature of the target tissue to a lethal temperature.

### Claim 7 (depends on 6)

The system of claim 6, wherein the ablation applicator is a radio-frequency energy catheter.

### Claim 8 (depends on 1)

The system of claim 1, wherein the target tissue is a tumor, and the processor is operable to compute the set of candidate ablation parameters which maximize ablation coverage of the tumor.

### Claim 9 (depends on 1)

The system of claim 1, wherein the processor is operable to compute a maximum tumor ablation coverage by maximizing a ratio (COV) defined as a product of ATT and ATAR where ATT is ablated tumor size to tumor size and an ATAR is the ablated tumor size to ablated region size.

### Claim 10 (depends on 1)

The system of claim 1, wherein the plurality of candidate models is based on a plurality of different types of tissue.

### Claim 11 (depends on 1)

The system of claim 1, wherein the learned ablation model is a predictive model.

### Claim 12 (depends on 11)

The system of claim 11, wherein the predictive model is a deep learning, neural network, or machine learning model.

### Claim 13 (depends on 11)

The system of claim 11, wherein the predictive model is a non-linear regression algorithm.

### Claim 14 (depends on 1)

The system of claim 1, wherein the processor is operable to execute a feasibility test for determining whether each said candidate path can allow a bronchoscope to reach the candidate POE based on a predefined path criteria selected from the group consisting of airway diameter, bronchoscope tip diameter, and bronchoscope bending angle.

### Claim 15 (depends on 14)

The system of claim 14, wherein the processor is operable to execute a feasibility test for determining whether each said candidate path can access the target tissue from the airway without crossing vessels or other critical structures.

### Claim 16 (depends on 1)

The system of claim 1, wherein the processor is programmed and operable to output an optimal ablation zone to maximize coverage of the target tissue, an optimal path to the target tissue, and generator parameters to provide said optimal ablation zone.

### Claim 17

A bronchoscopic-based system for predicting an ablation zone for ablating a target tissue in a lung of a patient with an ablation applicator comprising:
a storage for receiving image data of the lung of the patient including the target tissue to be ablated, and a first experimental data, wherein the first experimental data was generated by:
ablating a first tissue according to a first set of ablation parameters,
taking measurements of the first tissue subsequent to the ablating to obtain the first experimental data; and
a processor programmed and operable to:
compute a plurality of candidate models based on the first experimental data;
compute, based on the image data of the lung, at least one candidate path for the ablation applicator to be advanced through the airway of the patient, to a candidate point of entry (POE), and through the airway wall to the target tissue; and
determine a first learned ablation model based on the plurality of candidate models, wherein the first learned ablation model predicts ablation zone size for each said candidate path.

### Claim 18 (depends on 17)

The system of claim 17, wherein the processor is further operable to compute a second learned ablation model based on a second experimental data, wherein the second experimental data was generated by ablating the first tissue or a second tissue according to a second set of ablation parameters; and to store the second learned ablation model.

### Claim 19 (depends on 18)

The system of claim 18, wherein the processor is further operable to predict the ablation zone for ablating the target tissue in the patient based on applying at least one of the first learned ablation model and the second learned ablation model and at least one characteristic of the target tissue.

### Claim 20 (depends on 17)

The system of claim 17 wherein the image data includes an annotated tumor.

### Claim 21 (depends on 17)

The system of claim 17, wherein the processor is further operable to determine the first learned ablation model based on minimizing error between a predicted ablation zone and a measured ablation zone.

### Claim 22 (depends on 17)

The system of claim 17, wherein the processor is further operable to determine the first learned ablation model based on cross validation, and wherein the cross validation is performed by (a) training using a plurality of subsets of the first experimental data as training data and (b) validating on a remaining part of the first experimental data.

### Claim 23 (depends on 17)

The system of claim 17, wherein the ablation applicator is an electrosurgical device operable to deliver radio-frequency energy.

### Claim 24

A bronchoscopic-based system for planning to ablate a target tissue in a lung of a patient with an ablation applicator comprising:
a storage for receiving image data of the lung of the patient including the target tissue to be ablated; and
a processor programmed and operable to:
compute, based on the image data of the lung, at least one candidate path for the ablation applicator to be advanced through the airway of the patient to a candidate point of entry (POE), and from the POE to the target tissue;
create a learned ablation model based on past experimental data, and wherein the past experimental data includes measurements from ablation testing on sample tissue; and
compute an ablation zone and ablation treatment parameters based on said learned ablation model to maximize ablation coverage of the target tissue for each said candidate path.