US-12620493-B2 - Thrombus treatment metric

US12620493B2US 12620493 B2US12620493 B2US 12620493B2US-12620493-B2

Abstract

A computer-implemented method of predicting a success metric, achieved by performing a treatment procedure on a thrombus, is provided. The method includes: receiving angiographic image data, including one or more angiographic images comprising the thrombus; inputting the angiographic image data into a model, comprising a neural network, configured to output a prediction related to the treatment procedure; and calculating the success metric based on the output of the model.

Inventors

Ayushi Sinha
Javad Fotouhi
Vipul Shrihari Pai Raikar
Leili Salehi
Ramon Quido Erkamp
Sean Kyne

Assignees

KONINKLIJKE PHILIPS N.V.

Dates

Publication Date: 20260505
Application Date: 20221205
Priority Date: 20220214

Claims (14)

1 . A system for predicting a success metric for a treatment procedure performable on a thrombus, the system comprising: a deployment catheter configured to be positioned relative to the thrombus; an imaging system configured to generate current angiographic image data including one or more angiographic images comprising the thrombus, while the deployment catheter is positioned relative to the thrombus; a display configured to output the success metric for the treatment procedure; and a controller configured to: receive, from the imaging system, the current angiographic image data that includes an angiographic image comprising the thrombus; input the angiographic image into a model configured to output a prediction, related to performance of the treatment procedure, based on the angiographic image, wherein the model is trained to determine the prediction based on a position of a deployment catheter relative to the thrombus in the angiographic image; calculate the success metric for the treatment procedure based on the output of the model; and output, via the display, the success metric for the treatment procedure.
2 . The system according to claim 1 , wherein the model comprises a neural network.
3 . The system according to claim 1 , wherein the controller is further configured to: train the model, to output the prediction related to the treatment procedure, based on training data comprising angiographic training images representing the treatment procedure and corresponding ground truth outcome data of the represented treatment procedure.
4 . The system according to claim 3 , wherein the controller is further configured to: receive latent space representations for the angiographic training images; generate, for the inputted angiographic image, a latent space representation based on the model; analyze ground truth output data corresponding to each of the angiographic training images having latent space representations within a predetermined distance of the latent space representation of the inputted angiographic image; and calculate the success metric for the treatment procedure based on the analyzed ground truth outcome data.
5 . The system according to claim 1 , wherein the controller is further configured to: classify the inputted angiographic image with an expected outcome of the treatment procedure based on the model; and calculate the success metric for the treatment procedure based on the classified expected outcome of the treatment procedure.
6 . The system according to claim 1 , wherein the success metric is a metric of success for deploying the mechanical thrombectomy device from the deployment catheter to perform the treatment procedure.
7 . The system according to claim 1 , wherein: the received angiographic image data includes a plurality of angiographic images including the thrombus and the deployment catheter for deploying a mechanical thrombectomy device to treat the thrombus, the success metric is a success metric for deploying the mechanical thrombectomy device from the deployment catheter during the treatment procedure, and the controller is configured to: input the plurality of angiographic images into the model; generate, based on the model, latent space representations representing the inputted plurality of angiographic images; and predict, from the generated latent space representations, future angiographic images including predicted future positions of the deployment catheter.
8 . The system according to claim 3 , wherein the controller is further configured to: train the model further based on at least one of: training device data corresponding to the angiographic training images or training patient data corresponding to the angiographic training images; receive at least one of device data for a mechanical thrombectomy device to be used in the treatment procedure and patient data relating to the thrombus; and input at least one of the device data or the patient data into the model to output the prediction related to the performance of the treatment procedure.
9 . The system according to claim 1 , wherein the controller is further configured to: calculate a confidence value for the inputted angiographic image; and output the confidence value.
10 . The system according to claim 4 , wherein the controller is further configured to: receive user input indicative of an extent of the predetermined distance; and output at least one of: a graphical representation of the latent space representation of the inputted angiographic image, a graphical representation of the latent space representations of at least one of the angiographic training images, and an indication of the predetermined distance.
11 . The system according to claim 3 , wherein at least one of: the success metric represents a probability of success of the treatment procedure, the ground truth procedure outcome data represents a binary classification of success or failure of the treatment procedure, and the ground truth procedure outcome data comprises one or more of: a speed of the treatment procedure, a measure of completeness of re-perfusion achieved by the treatment procedure, a mortality rate subsequent to the treatment procedure, and whether the treatment procedure needed to be repeated.
12 . The system according to claim 3 , wherein the controller is further configured to: receive angiographic training data including a plurality of angiographic training images that each include a thrombus; input the angiographic training images into the model; and for each inputted angiographic training image: generate a latent space representation of the inputted angiographic training image based on the model; reconstruct the inputted angiographic training image from the latent space representation based on the model; and adjust parameters of the model based on a difference between the inputted angiographic training image and the reconstructed inputted angiographic training image.
13 . The system according to claim 3 , wherein the controller is further configured to: receive the angiographic training data including a plurality of angiographic training images that each comprise a thrombus; receive the ground truth procedure outcome data corresponding to the angiographic training data, wherein, for each angiographic training image, the ground truth procedure outcome data represents a success or a failure achieved when performing an instance of the treatment procedure corresponding to the angiographic training image; input the angiographic training images into the model; and for each inputted angiographic training image: predict a procedure outcome for performance of the treatment procedure based on the model; and adjust parameters of the model based on a difference between the predicted procedure outcome and the ground truth procedure outcome data for the inputted angiographic training image.
14 . The system according to claim 4 , wherein the controller is further configured to: receive angiographic training data including a temporal sequences of angiographic training images, each temporal sequence of training images comprising the thrombus and the deployment catheter; input the angiographic training images into the model; and for each inputted angiographic training image of the temporal sequence: generate a latent space representation of the inputted angiographic training image based on the model; predict, from the generated latent space representation, a future angiographic image with respect to the inputted angiographic image, the future angiographic image including a predicted future position of the deployment catheter; and adjust parameters of the model based on a difference between the predicted future angiographic image to the inputted angiographic image, and a future angiographic image corresponding to the predicted future angiographic image to the inputted training angiographic image.

Description

CROSS REFERENCE TO RELATED APPLICATIONS This application claims the benefit of U.S. Provisional Patent Application No. 63/287,165 filed Dec. 8, 2021 and European Patent Application Number 22156482.6 filed Feb. 14, 2022. These applications are hereby incorporated by reference herein. TECHNICAL FIELD The present disclosure relates to predicting a success metric that will be achieved by performing a treatment procedure on a thrombus. A computer-implemented method, a computer program product, and a system, are disclosed. BACKGROUND A thrombus, or clot, is a blockage in a blood vessel. A thrombus may occur in a vein or in an artery. In the former case, i.e. a venous thrombus, blood becomes congested, leading to swelling and fluid congestion. In the latter case, i.e. an arterial thrombus, the supply of blood is restricted, leading to a condition known as ischemia, which risks damage to tissue supplied by the artery. In both cases, a portion of the thrombus can also break-away as an embolus. The embolus can become lodged elsewhere in the body and form an embolism that likewise blocks a blood vessel. Thromboses may occur in various parts of the body, including in the heart and the brain, where their effects can be severe unless treated quickly. In the brain, for example, a thrombus, or an embolism, can lead to conditions such as (ischemic) stroke. Various treatments are available for treating thromboses. These include pharmacological treatments in which thrombolytic drugs such as Alteplase are administered in order to break-up a thrombus by means of thrombolysis. Various treatment procedures are also available for treating thromboses. Such treatment procedures include the use of treatment devices such as mechanical thrombectomy devices, and which are used in so-called mechanical thrombectomy procedures. At present, there are two main groups of mechanical thrombectomy devices: aspiration catheters, and stent retrievers. Aspiration catheters typically include a delivery catheter that is used to deliver an irrigation fluid to the thrombus, and an extraction catheter that is used to extract the irrigation fluid, together with broken-up pieces of the thrombus. In-use, an aspiration catheter is positioned close to the clot, and at which position the aspiration takes place, resulting in the broken pieces of the clot being extracted from the body. Stent retrievers typically include an expandable wire mesh tube that is designed to remove the clot in one piece. In-use, a stent retriever is positioned close to the thrombus using a delivery catheter. After positioning the delivery catheter, the wire mesh tube is extended out of the delivery catheter, where it expands and captures the clot. The stent retriever is then withdrawn into the delivery catheter and the stent retriever, together with the clot, is removed from the body. In some studies, mechanical thrombectomy devices have been shown to have a higher clinical efficacy in achieving re-perfusion of blood vessels than thrombolytic drugs. The success of mechanical thrombectomy procedures in reducing long-term functional dependency and mortality has been found to be highly correlated with the “technical success” of the procedure. Technical success is assessed based on several criteria, including the speed of the procedure and completeness of re-perfusion. That is, if complete re-perfusion is achieved but only after a lengthy procedure, or if the procedure is fast but complete re-perfusion is not achieved, then a patient is likely to have poor long-term outcome. Achieving complete re-perfusion in the first pass has been shown to have a strong correlation with positive long-term outcome in patients. However, a physician typically takes several attempts to successfully remove a thrombus. Recent publications have shown that the location of the thrombus with respect to the anatomy can affect the success of different types of mechanical thrombectomy procedures. This is described in a document by Alverne, F., et al., entitled “Unfavorable Vascular Anatomy during Endovascular Treatment of Stroke: Challenges and Bailout Strategies”, Journal of stroke 22(2): 185-202 (2020), and in another document by Bernava, G., et al., entitled “Direct thromboaspiration efficacy for mechanical thrombectomy is related to the angle of interaction between the aspiration catheter and the clot”, Journal of NeuroInterventional Surgery 12(4): 396-400 (2020). As mentioned in these two documents, the tortuosity of a vessel in the vicinity of the thrombus can indicate the likely success of a mechanical thrombectomy procedure. When unfavorable vascular anatomy, such as tortuosity, is combined with sub-optimal device selection and/or placement, this can result in a poor long-term outcome for a patient. The location of a thrombus within tortuous intracerebral arteries can for example affect the success of both stent retriever and aspiration catheter based treatments, as described in the aforementioned document b