US-20260123839-A1 - PREDICTING VESSEL COMPLIANCE RESPONSIVE TO MULTIPLE POTENTIAL TREATMENTS

Abstract

The present disclosure provides apparatus and methods to both infer stent expansion (vessel expansion or compliance) and probability of procedural success (vessel patency) from pretreatment diagnostic imaging at the point-of-care and also train an inference model to generate such an inference, thus allowing a physician to choose with greater certainty an optimal treatment tool and treatment protocol for treating a vessel of a patient.

Inventors

• DANIEL FRANK MASSIMINI
• Andrew David Bicek
• Wenguang Li

Assignees

• BOSTON SCIENTIFIC SCIMED, INC.

Dates

Publication Date

20260507

Application Date

20251219

Claims (20)

1. 1 . A computing apparatus for an intravascular imaging system, comprising: a processor; and a memory storing instructions that, when executed by the processor, cause the apparatus to: generate, using an inference model, a predicted vessel expansion for a treatment protocol; and generate an uncertainty metric associated with the predicted vessel expansion, wherein the uncertainty metric is based on variability in model outputs, variability in image-derived features, or both.
2. 2 . The computing apparatus of claim 1 , wherein the inference model comprises a machine learning model trained using intravascular image data associated with vessel expansion outcomes.
3. 3 . The computing apparatus of claim 2 , wherein the machine learning model comprises a convolutional neural network.
4. 4 . The computing apparatus of claim 1 , wherein the uncertainty metric is based on variability in predicted vessel expansion generated from multiple executions of the inference model.
5. 5 . The computing apparatus of claim 4 , wherein the multiple executions comprise at least one of stochastic sampling, dropout variation, or ensemble model execution.
6. 6 . The computing apparatus of claim 1 , wherein the uncertainty metric is based on variability in one or more image-derived features extracted from intravascular image data.
7. 7 . The computing apparatus of claim 6 , wherein the image-derived features comprise at least one of calcium arc, calcium thickness, lesion length, lumen geometry, plaque composition, or combinations thereof.
8. 8 . The computing apparatus of claim 1 , wherein the uncertainty metric comprises a confidence interval, variance value, probability distribution width, or confidence score.
9. 9 . The computing apparatus of claim 1 , wherein the instructions further cause the apparatus to generate a graphical representation of the predicted vessel expansion and the associated uncertainty metric.
10. 10 . The computing apparatus of claim 9 , wherein the graphical representation includes a visual indicator of confidence associated with the predicted vessel expansion.
11. 11 . A method for an intravascular imaging system, comprising: generating, by a computing device using an inference model, a predicted vessel expansion for a treatment protocol; and generating, by the computing device, an uncertainty metric associated with the predicted vessel expansion, wherein the uncertainty metric is based on variability in model outputs, variability in image-derived features, or both.
12. 12 . The method of claim 11 , further comprising executing the inference model multiple times to determine variability in the predicted vessel expansion.
13. 13 . The method of claim 11 , further comprising extracting image-derived features from intravascular images and determining variability in the extracted features.
14. 14 . The method of claim 11 , wherein generating the uncertainty metric comprises computing a statistical measure representing dispersion of predicted vessel expansion values.
15. 15 . The method of claim 11 , further comprising displaying the predicted vessel expansion and the uncertainty metric at a point-of-care interface.
16. 16 . A non-transitory computer-readable storage medium storing instructions that, when executed by a computing device, cause the computing device to: generate, using an inference model, a predicted vessel expansion for a treatment protocol; and generate an uncertainty metric associated with the predicted vessel expansion, wherein the uncertainty metric is based on variability in model outputs, variability in image-derived features, or both.
17. 17 . The non-transitory computer-readable storage medium of claim 16 , wherein the instructions further cause the computing device to generate the uncertainty metric based on multiple inference model executions.
18. 18 . The non-transitory computer-readable storage medium of claim 16 , wherein the uncertainty metric is generated based on variability in extracted vessel morphology features.
19. 19 . The non-transitory computer-readable storage medium of claim 16 , wherein the instructions further cause the computing device to generate a visual indication of confidence associated with the predicted vessel expansion.
20. 20 . The non-transitory computer-readable storage medium of claim 16 , wherein the predicted vessel expansion and the uncertainty metric are used to assist selection of a treatment protocol for a vascular lesion.

Description

CROSS-REFERENCE TO RELATED APPLICATIONS This application is a continuation of U.S. application Ser. No. 18/143,481, filed May 4, 2023, which claims the benefit of priority under 35 U.S.C. § 119 of U.S. Provisional Application No. 63/339,258, filed May 6, 2022, the entire disclosure of which is hereby incorporated by reference. TECHNICAL FIELD The present disclosure pertains to medical devices and/or medical device systems. More particularly, the present disclosure pertains to medical device systems for predicting vessel compliance to a treatment. BACKGROUND A wide variety of intracorporeal medical devices have been developed for medical use, for example, intravascular use. Some of these devices include guidewires, catheters, and the like. These devices are manufactured by any one of a variety of different manufacturing methods and may be used according to any one of a variety of methods. Of the known medical devices and methods, each has certain advantages and disadvantages. There is an ongoing need to determine whether treatments using such devices or methods will be successful. For example, in the context of intravascular use, there is a need to predict or even improve the compliance of the vessel to increase the effectiveness or improve the outcome of treatment. BRIEF SUMMARY An intravascular imaging system arranged to capture diagnostic images of a patient's vessel and to infer, at the point-of-care, from the diagnostic images based on an inference model, a probability of vessel expansion for a number of treatment protocols is provided. It is to be appreciated that point-of-care vessel compliance is difficult to predict a priori, yet it is essential to improve vessel compliance. This is particularly true when the vessel includes high calcium lesions. In one embodiment, a method for predicting vessel compliance includes: receiving, at a computing device from an intravascular imaging device, a plurality of images associated with a vessel of a patient, the plurality of images including multidimensional and multivariate images; identifying, by the computing device, a probability of expansion of the vessel for each of a plurality of treatment protocols based on an inference model and the plurality of images; generating, by the computing device, a graphical information element that includes an indication of the plurality of treatment protocols and the identified probabilities of expansion; and causing, by the computing device, the graphical information element to be displayed on a display coupled to the computing device. With some embodiments, identifying the probability of expansion of the vessel for each of the plurality of treatment protocols includes providing the plurality of images as inputs to the inference model, and executing the inference model to generate the probability of expansion of the vessel for each of the plurality of treatment protocols. With some embodiments, the plurality of treatment protocols includes a first treatment protocol and a second treatment protocol and the inference model includes a first inference model. In such embodiments, the method includes providing the plurality of images as inputs to the first inference model, executing the first inference model to generate the probability of expansion of the vessel for the first treatment protocol, providing the plurality of images as inputs to a second inference model, and executing the second inference model to generate the probability of expansion of the vessel for the second treatment protocol. With some embodiments, the inference model is a convoluted neural network (CNN). With some embodiments, the graphical information element includes a table that includes an indication of each of the treatment protocols and the identified probability of expansion. With some embodiments, identifying, by the computing device, the probability of expansion of the vessel for each of the plurality of treatment protocols based on the inference model and the plurality of images includes identifying the probability of expansion relative to a treatment parameter. With some embodiments, the intravascular imaging device is an intravascular ultrasound (IVUS) device, optical coherence tomography (OCT) device, an optical coherence elastography (OCE) device, or a spectroscopy device. With some embodiments, the vessel of the patient includes a lesion. With some embodiments, the vessel of the patient includes a calcified lesion. In another embodiment, an apparatus includes: a processor arranged to be coupled to an intravascular imaging device and a memory device storing instructions and an inference model, where the processor is arranged to execute the instructions to implement the method of any one of the above examples. With another embodiment, a computing apparatus, includes a processor. The computing apparatus also includes a memory device storing instructions that, when executed by the processor, configure the apparatus to: receive, from an intravascula