Method for selecting a type of implantable medical device for treating an aneurysm

Abstract

The present disclosure relates to a method for selecting a type of implantable medical device, IMD, from among a set of IMD types, the IMD being intended to be positioned in a vascular structure comprising an area of interest, the method comprising the steps of: - obtaining an image of a vascular structure comprising an area of interest; - extracting a plurality of features of the vascular structure from the obtained image; - processing, by means of a supervised learning model, the extracted features in order to obtain, for each type of IMD, a probability of compatibility quantifying a compatibility of the type of IMD with respect to the area of interest of the vascular structure; and - selecting, from among the extracted features, and according to each probability of compatibility, at least one essential feature affecting the probability of compatibility associated with each type of IMD.

Description

[0001] DESCRIPTION

[0002] TITLE: Method for choosing a type of implantable medical device to treat an aneurysm

[0003] TECHNICAL FIELD

[0004] This presentation concerns the field of treatment of a vascular structure, such as an artery, undergoing a local pathology such as an aneurysm, by implantation of an implantable medical device (or IMD).

[0005] More specifically, the presentation concerns the choice of the right type of DMI to implant in the vascular structure for which a three-dimensional image is available.

[0006] STATE OF THE ART

[0007] Many strokes are linked to the presence of an aneurysm in the walls of a blood vessel. Furthermore, the risk of stroke increases with the size of the aneurysm.

[0008] It is therefore necessary to prevent the expansion and rupture of the aneurysm, as well as to prevent clots formed in the aneurysm from migrating into the vascular structure and locally blocking an artery.

[0009] It is common to use an implantable medical device (IMD) to treat an artery affected by an aneurysm. Several types of IMDs exist for this purpose, such as a stent, an intrasaccular cage, a flow diverter, or endovascular embolization using microcoils. Each type of IMD is available in several sizes.

[0010] Before selecting the size of the implantable median device (IMD), a clinician must choose from the different types of IMDs available. Each type is more or less well-suited to each aneurysm.

[0011] The clinician currently has no other aid in choosing the type of implantable medical device (IMD) to treat the specific aneurysm they are facing than their own experience or the experience of colleagues physically present to advise them. GENERAL PRESENTATION

[0012] One aim of the presentation is to improve the treatment of aneurysms by advising the clinician on the choice of the type of DMI to use based on the particular characteristics of the aneurysm.

[0013] To this end, a computer-implemented method is proposed, according to one aspect of this presentation, for selecting a type of implantable medical device (IMD) from a set of IMD types, the IMD being intended to be positioned in a vascular structure containing a region of interest. The method comprises the following steps: obtaining an image of a vascular structure containing a region of interest; extracting a plurality of features of the vascular structure from the image obtained; processing the extracted features by a supervised learning model to obtain, for each IMD type, a compatibility probability quantifying the compatibility of the IMD type with the region of interest of the vascular structure; and selecting, from among the extracted features, and according to each compatibility probability, at least one essential feature influencing the compatibility probability associated with each IMD type.

[0014] This selection process improves the treatment of aneurysms by making the choice of the type of MDI to use safer and faster.

[0015] This process increases the clinician's confidence in the choice of the type of medical device (MD) suggested by the method. Indeed, the method allows the clinician to understand the reasons for choosing one type of MD over another.

[0016] The process allows for the automation of the choice of the type of DMI to use by taking into account previously trained databases.

[0017] Advantageously, but optionally, the described process includes at least one of the following features, taken alone or in any combination:

[0018] - the selection classifies each type of DMI as an appropriate type, if the probability of compatibility of the type of DMI is greater than a previously set threshold, or as an inappropriate type, if the probability of compatibility of the type of DMI is less than the threshold;

[0019] - the selection is implemented based on a database of appropriate patterns and a database of inappropriate patterns, the database of appropriate patterns and the database of inappropriate patterns each comprising at least one explainability pattern for each type of DMI, each explainability pattern comprising at least one influential characteristic and an impact level associated with the influential characteristic, the influential characteristic being a characteristic having a non-zero associated impact level, the impact level qualifying the impact of each characteristic in the calculation of the probability of compatibility of the type of DMI considered, the explainability pattern of the database of appropriate patterns being common to at least one reference vascular structure for which the type of DMI considered is an appropriate type,and the explainability pattern of the inappropriate pattern database being common to at least one reference vascular structure for which the type of DMI considered is an inappropriate type;

[0020] - The selection process determines the essential characteristic for each type of DMI:

[0021] - by comparing the characteristics of the vascular structure to the explainability patterns in the appropriate pattern database if the type of MDI considered is an appropriate type, or to the explainability patterns in the inappropriate pattern database if the type of MDI considered is an inappropriate type; and

[0022] - by retaining as essential characteristic(s) the influential characteristic(s) common to the characteristics of the vascular structure, the influential characteristic(s) being included in one or more patterns of explainability having the most influential characteristics common to the characteristics of the vascular structure;

[0023] - a generation of the model from a feature database including features of each of the images of a plurality of reference vascular structures from a training image database;

[0024] - the compatibility probabilities of each type of DMI for the reference vascular structures are calculated by the model from the database of characteristics;

[0025] - an initial training session on a database of appropriate transactions and a database of inappropriate transactions,

[0026] - the database of appropriate transactions including, for each type of DMI, a transaction comprising the influential characteristics of a reference vascular structure for which the DMI type is considered appropriate, and

[0027] - the inappropriate transaction database including for each type of DMI a transaction including the influential characteristics of a reference vascular structure for which the type of DMI is considered an inappropriate type;

[0028] - each transaction is calculated based on the probability of compatibility of the type of MDI considered for each reference vascular structure and an explainability table including for each reference vascular structure the level of impact of each characteristic for the probability of compatibility of the type of MDI considered, each transaction including the influential characteristics of a reference vascular structure and the level of impact associated with each of the influential characteristics;

[0029] - a second training of the database of appropriate patterns and the database of inappropriate patterns, each including for each type of DMI at least one explainability pattern, such as:

[0030] - the explainability pattern of the appropriate pattern database includes an influential characteristic of the type of DMI considered and the level of impact associated with the influential characteristic, the influential characteristic and the level of impact being common to at least one transaction of the type of DMI considered in the appropriate transaction database, and

[0031] - the explainability pattern of the inappropriate pattern database includes an influential characteristic of the type of DMI considered and the level of impact associated with the influential characteristic, the influential characteristic and the level of impact being common to at least one transaction of the type of DMI considered in the inappropriate transaction database;

[0032] - the set of DMI types includes DMI types such as "stent", "intrasaccular cage", "flow diverter" or endovascular embolization by microcoils;

[0033] - a display of the probability of compatibility of each type of DMI and essential characteristics of the vascular structure for each probability of compatibility.

[0034] According to another aspect, a computer program product is proposed comprising code instructions for the execution of a process as previously described, when said program is executed on a computer.

[0035] DESCRIPTION OF THE FIGURES

[0036] Other features, purposes and advantages will become apparent from the following description, which is purely illustrative and not limiting, and which should be read in conjunction with the accompanying drawings on which: Figure 1 illustrates a schematic view of a DMI positioned in a vascular structure comprising an area of ​​interest, according to one embodiment of the present presentation.

[0037] Figure 2 schematically illustrates the steps of an initialization of the process of choosing a type of DMI, according to a particular implementation of this presentation.

[0038] Figure 3 schematically illustrates the steps in the classification process for choosing a type of DMI, according to a particular implementation of this presentation.

[0039] Across all figures, similar elements bear identical references.

[0040] DETAILED DESCRIPTION

[0041] Aneurysm and DMI

[0042] Figure 1 schematically illustrates a vascular structure 1. Vascular structure 1 includes a region of interest 2. Region of interest 2 is an area of ​​the wall of vascular structure 1 that exhibits a defect. Region of interest 2 may be an aneurysm or any other pathology related to vascular structure 1. The aneurysm illustrated in Figure 1 comprises a sac called an aneurysmal sac, but this discussion concerns any other type of aneurysm. For simplicity, we will refer to any type of region of interest 2 as an aneurysm 2.

[0043] To treat an aneurysm, a clinician must choose an implantable medical device (IMD). Choosing an IMD may involve selecting a specific type and size. Here, we will focus on the choice of IMD type, or model. The different types of IMDs available to clinicians are generally stent-type, intrasaccular cage-type, flow diverter (as illustrated in Figure 1), or endovascular microcoil embolization (EMB) type. Each of these IMD types also comes in different sizes, from which the clinician will subsequently need to select a specific size.

[0044] The DMI 3 is configured to be inserted and then positioned in vascular structure 1. Positioning the DMI 3 in vascular structure 1 helps to prevent expansion or rupture of aneurysm 2 or any other problem related to the presence of aneurysm 2 in vascular structure 1, such as the creation of a dried blood clot in aneurysm 2 or migration of a blood clot created in aneurysm 2 to vascular structure 1.

[0045] The type of DMI 3 must therefore be chosen according to the vascular structure 1 as well as according to the aneurysm 2. In other words, the vascular structure 1, and therefore the aneurysm 2, have their own characteristics 4 which must be taken into account in the process of choosing the type of DMI 3 in order to treat the aneurysm 2. Indeed, each type of DMI 3 is more or less suited to the treatment of each aneurysm 2.

[0046] The characteristics of vascular structure 1 (character 4) are physical and morphological features that influence the choice of the type of implantable medical device (IMD) 3. Each characteristic 4 includes degrees that qualify the characteristic. Indeed, each vascular structure 1 exhibits a particular degree of each characteristic 4. For example, the characteristics 4 and their degrees may be, but are not limited to:

[0047] Of course, there are other characteristics 4 that allow us to characterize the vascular structure 1.

[0048] Hereafter, we will refer to characteristic 4 of a vascular structure 1 to refer to the characteristic and degree of characteristic 4 for the vascular structure 1 under consideration. For example, for vascular structures 1 A and B and a characteristic 4 f1 comprising three degrees 1, 2 and 3; if the degree of A for f1 is 1 and the degree of B for f1 is 3, we will refer to f1 = 2 for characteristic 4 of A and f1 = 3 for characteristic 4 of B.

[0049] Method for choosing a type of DMI

[0050] A method for selecting the type of DMI 3 to be positioned in vascular structure 1 to treat aneurysm 2 is presented below. The method is configured to rank the type(s) of DMI 3 best suited for treating aneurysm 2 based on an image of vascular structure 1 including the aneurysm 2. Advantageously, the method provides, for each type of DMI 3, a score quantifying its suitability for treating aneurysm 2. Furthermore, the method advantageously presents an explanation of the score, that is, the characteristics of vascular structure 1 that led to this score and not another score.

[0051] The selection process includes an initialization E1 and a classification E2. The initialization E1 is implemented prior to the implementation of the classification E2 in order to allow the implementation of the classification E2.

[0052] Initialization E1 includes generation E11 of a supervised learning model 7 and creation E14 of one or more pattern database(s) 151, 152.

[0053] The E2 classification is carried out by implementing the trained supervised learning model 7 and by using the pattern database(s) 151, 152.

[0054] To generate the supervised learning model 7, various algorithms can be used, such as a random forest or even a neural network. The supervised learning model 7 is first trained and then configured to calculate, for each type of DMI 3 in the set of DMI 3 types, when implemented during classification E2, for example, a probability called the compatibility probability 6. The compatibility probability 6 quantifies the compatibility of a DMI 3 with the aneurysm 2 of vascular structure 1. In other words, the compatibility probability 6 provides a score quantifying the suitability of the considered DMI 3 type to treat the aneurysm 2.

[0055] Furthermore, the pattern database(s) 151, 152 are created following the generation E11 of the supervised learning model 7 to offer a library of explainability patterns 14 providing an explanation of the compatibility probability 6 of each type of DMI 3. In other words, the pattern database(s) 151, 152 allow the selection of the characteristics 4 of the vascular structure 1 that were decisive in the calculation of the compatibility probability 6 of each type of DMI 3.

[0056] The process can be implemented on a server. Advantageously, the initialization E1 can be implemented by a first server and the classification E2 can be implemented by a second server, separate and independent from the first server. Advantageously, the first and second servers each comprise a processing unit. The processing unit of the first and second servers is, for example, a processor configured to implement the steps of the process that will be explained below.

[0057] The first and second servers can each include a communication interface enabling communication between them. Such communication can be implemented, for example, via a wired or wireless connection over any type of communication network, such as the Internet. The first and second servers can, however, operate independently. Once the E1 initialization is performed by the first server and its results transmitted to the second server, the E2 classification can be implemented by the second server without requiring communication between them. This is because the results of the E1 initialization can be stored in a remote and decentralized storage service (or cloud storage, as it is commonly known).

[0058] Advantageously, the first and second servers can each include a storage unit, such as a hard drive. Typically, the first server can store one or more databases of data used in the selection process on this storage unit, or have access to these databases. The architecture can be advantageously complemented by random access memory (RAM) to store intermediate calculations during the E1 initialization.

[0059] A person skilled in the art will easily understand that other architectures for implementing the process are possible, the first server and the second server being able to be merged into a single server.

[0060] Figure 2 schematically illustrates steps in a particular implementation of the initialization E1, that is, the generation steps E11 of the supervised learning model 7 and the creation E14 of the pattern database(s) 151, 152.

[0061] Model learning

[0062] The process includes the generation E11 of the supervised learning model 7, hereafter referred to as the model for simplicity. The generation E11 of model 7 allows the model 7, once trained, to calculate, for each type of DMI 3 in the set of DMI 3 types, the probability of compatibility 6 of the DMI 3 with the vascular structure 1, or, in other words, with the area of ​​interest 2 of the vascular structure 1.

[0063] The E11 generation includes an E12 extraction of 4 features and an E13 training of the model 7 from the extracted 4 features.

[0064] The extraction of features 4 (E12) is performed on reference vascular structures 1a derived from reference images previously recorded and stored in a reference database (not shown). The previously recorded reference images can be simple images of the reference vascular structures 1a or 3D surface meshes extracted from the images of the reference vascular structures 1a. Advantageously, each reference vascular structure 1a includes at least one pathology, such as an aneurysm 2. The reference vascular structures 1a and the aneurysms 2 of the reference vascular structures 1a each contain numerous unique features 4. The reference database includes, for each vascular structure 1a, several features 4 of each reference vascular structure 1a, as well as a type of DMI 3 adapted to the pathology.

[0065] Once extracted, the features 4 populate a feature database 5. The feature database 5 includes, for each image of reference vascular structures 1a, the features 4 specific to the reference vascular structure 1 considered, as well as a mention of the type of DMI 3 associated with the treatment of the reference vascular structure 1a.

[0066] The E13 training of model 7 is implemented using the characteristic database 5. The presence in the characteristic database 5 of the characteristics 4 specific to a reference vascular structure 1a and of the type of DMI 3 used to treat the considered reference vascular structure 1a allows for the training of model 7. Indeed, model 7 calculates, using the algorithm, the links between the presence of one or more characteristics 4 and the choice of a particular type of DMI 3. Since the characteristics 4 of each extracted reference vascular structure 1a are linked in the characteristic database 5 to a type of DMI 3, model 7 can perform calculations on all these relationships in order to deduce compatibility probabilities 6 of each type of DMI 3 with a vascular structure based on the characteristics 4 of the considered vascular structure 1.In other words, the E13 training of model 7 allows model 7 to establish links between one or more characteristics 4 and a compatibility of each type of DMI 3 to a vascular structure 1 exhibiting this characteristic 4.

[0067] Model 7 is trained (step E13) from the feature database 5. Once trained, model 7 is configured to calculate (step E15), based on the specific features 4 of a vascular structure 1, a compatibility probability 6 of each type of DMI 3 with the vascular structure 1 under consideration.

[0068] Creation of the pattern database(s) The process also includes the creation E14 of a pattern database 151,152. Preferably, the process includes the creation E14 of two pattern databases 151,152. The creation E14 of the pattern databases 151,152 subsequently allows the selection, for the compatibility probability 6 of each type of DMI 3 for a vascular structure 1 to be treated, of the characteristics 4 of the vascular structure 1 considered having been decisive in the calculation of the compatibility probability 6.

[0069] The characteristics 4 of the vascular structure 1 having been decisive in the calculation of the probability of compatibility 6 are the characteristics 4 selected (step E24) by the implementation of the pattern databases 151,152, once the creation E14 has been carried out and are said to be essential characteristics 40.

[0070] The creation E14 of the pattern databases 151,152 includes a calculation E15 of compatibility probability 6 and an explainability table 9, a first training E16 of one or more transaction database(s) 11,12, an extraction E17 of explainability patterns 14 and a second training E18 of the pattern databases 151,152.

[0071] Calculation E15 of the compatibility probability 6 of each type of DMI 3 to the reference vascular structures 1a uses the characteristic database 5. Model 7 then gives, for each reference vascular structure 1a in the characteristic database 5, a compatibility probability 6 of each type of DMI 3. For each reference vascular structure 1a, the compatibility probability 6 of each type of DMI 3 is between 0 and 1, and the sum of the compatibility probabilities 6 of the types of DMI 3 for each of the reference vascular structures 1a is equal to 1.

[0072] The explainability table 9 is calculated by applying an explainability method to the characteristic data base 5 and the compatibility probabilities 6. This explainability method is configured to quantify, for each reference vascular structure 1a, an impact level 13 of each characteristic 4 in the calculation of the compatibility probability 6 of each type of DMI 3. Therefore, the explainability table 9 includes, for each reference vascular structure 1a, the impact level 13 of each characteristic 4 in the calculation of the compatibility probability 6 of each type of DMI 3. The impact level 13 reflects the weight of characteristic 4 in the result of the calculation of the compatibility probability 6 of each type of DMI 3 for the reference vascular structure 1a under consideration.

[0073] Advantageously, the explainability method is an interpretability method such as, for example, a LIME algorithm (or "Local Interpretable Model-agnostic Explanations", according to Anglo-Saxon terminology) or a method for estimating Shapley values, called the SHAP algorithm.

[0074] The explainability method associates, for each reference vascular structure 1a, with each characteristic 4 (in other words, each degree of characteristic) an impact level 13. The impact level 13 can range from -3 to +3, with -3 representing a significant negative impact level 13, +3 representing a significant positive impact level 13, and 0 representing no impact level 13. In other words, for each reference vascular structure 1a, the explainability method indicates for each characteristic 4 whether that characteristic 4 (in other words, whether the degree of that characteristic) has tended to increase or decrease the probability of compatibility 6 for each type of DMI 3. Furthermore, the explainability method indicates for each characteristic 4 how that characteristic 4 has tended to increase or decrease the probability of compatibility 6 for each type of DMI 3, for example, whether the impact is low or high.

[0075] Advantageously, impact level 13 can be discretized into a predetermined number of values ​​to facilitate understanding of the explainability table 9. For example, impact level 13 can be discretized into 7 values, ranging from -3 (strong negative impact) to +3 (strong positive impact), passing through 0 (neutral impact). The value of impact level 13 can thus reflect a very strong / strong / weak positive / negative impact and a neutral impact.

[0076] The creation of pattern databases E14 151 and 152 also includes, for each reference vascular structure 1a, a classification of each type of DMI 3. Each type of DMI 3 is classified as either appropriate or inappropriate for the given reference vascular structure 1a. The classification is based on the probability of compatibility 6 of the DMI 3 type with the given reference vascular structure 1a.

[0077] Thus, for each reference vascular structure 1a, each type of DMI 3 is classified as: appropriate if the probability of compatibility 6 of the type of DMI 3 is greater than a previously fixed threshold, and inappropriate if the probability of compatibility 6 of the type of DMI 3 is less than the threshold.

[0078] Appropriate DMI 3 types are those most suitable for appropriately treating aneurysm 2 of the considered reference vascular structure 1a. The threshold used to classify DMI 3 types as appropriate or inappropriate can be set based on equiprobability. In other words, if the number of DMI 3 types in the set of DMI 3s is four, the threshold will be 14, or 0.25. Thus, any DMI 3 type with a compatibility probability 6 with a reference vascular structure 1a greater than 0.25 is appropriate for the considered reference vascular structure 1, and conversely, any DMI 3 type with a compatibility probability 6 with a reference vascular structure 1a less than 0.25 is not.

[0079] The creation E14 of the pattern databases 151, 152 includes the first formation E16 of one or more transaction database(s) 121, 122. Each transaction database 121, 122 includes, for each type of DMI 3, one or more transactions 12. Each transaction 12 of the transaction database 121, 122, is specific to a type of DMI 3. The transaction 12 of a type of DMI 3 includes influential features 4a of a reference vascular structure 1a for the type of DMI 3 considered.

[0080] The influential characteristics 4a are the characteristics 4 of the reference vascular structure 1a considered whose impact level 13 is not equal to zero for the type of DMI 3 considered.

[0081] Preferably, a first transaction database 121, 122, called the appropriate transaction database 121, and a second transaction database 121, 122, called the inappropriate transaction database 122, are formed (step E16) during the creation E14 of the pattern databases 151, 152.

[0082] The appropriate transaction database 121 includes, for each type of DMI 3, the 12 transactions of the reference vascular structures 1a for each of which the DMI 3 type is classified as appropriate. The inappropriate transaction database 122 includes, for each type of DMI 3, the 12 transactions of the reference vascular structures 1a for each of which the DMI 3 type is classified as inappropriate.

[0083] The appropriate transaction database 121 therefore includes for each type of DMI 3 one or more transactions 12. Each transaction 12 of the appropriate transaction database 121 includes the influential characteristics 4a, and the associated impact levels 13, of the reference vascular structures 1a for which the type of DMI 3 considered is classified as an appropriate type.

[0084] The inappropriate transaction database 122 therefore includes for each type of DMI 3 one or more transactions 12. Each transaction 12 of the inappropriate transaction database 122 includes the influential characteristics 4a, and the associated impact levels 13, of the reference vascular structures 1a for which the type of DMI 3 considered is classified as an inappropriate type.

[0085] The creation E14 of the pattern databases 151, 152 then includes an extraction E17 of the explainability patterns 14. The explainability patterns 14 are extracted from the transaction databases 121, 122. Advantageously, in the case where a database of appropriate transactions 121 and a database of inappropriate transactions 122 have been created, the explainability patterns 14 are extracted from the database of appropriate transactions 121 and the database of inappropriate transactions 122.

[0086] The explainability patterns 14 are specific to each type of DMI 3. Indeed, each explainability pattern 14 is extracted from a transaction 12, which is itself specific to a type of DMI 3. The explainability pattern 14 is a pair, from a transaction 12, comprising an influential characteristic 4a and an impact level 13 associated with the influential characteristic 4a, the impact level 13 of the influential characteristic 4a being non-zero and the pair being common to one or more other transactions 12 of the type of DMI 3 considered.

[0087] Advantageously, the explainability pattern 14 can include several pairs extracted from the same transaction 12 under consideration if several influential features 4a of the transaction 12 under consideration are common to one or more other transactions 12 of the same type of DMI 3.

[0088] Advantageously, a method for extracting explainability patterns 14 can be implemented. The extraction method is based on a frequent pattern extraction algorithm (or "frequent itemset extraction algorithm") such as an Apriori algorithm or an FPGrowth algorithm. A pair comprising an influential feature 4a and an impact level 13, associated with the influential feature 4a, of a transaction 12, is considered an explainability pattern 14 if it is common to at least K transactions 12, K being a parameter set by a user of the selection process.

[0089] The extraction method may further include a means of selecting a so-called maximal explainability pattern 14. An explainability pattern 14 is maximal if it is the most frequent explainability pattern 14 for the type of DMI in question 3.

[0090] The explainability pattern 14 of a type of DMI 3 is: an appropriate pattern 141 if the explainability pattern 14 arises from a transaction 12 for reference vascular structures 1a for which the type of DMI 3 considered is an appropriate type and is common to one or more transactions 12 for reference vascular structures 1a for which the type of DMI 3 considered is an appropriate type; and an inappropriate pattern 142 if the explainability pattern 14 arises from a transaction 12 for reference vascular structures 1a for which the type of DMI 3 considered is an inappropriate type and is common to one or more transactions 12 for reference vascular structures 1a for which the type of DMI 3 considered is an inappropriate type.

[0091] In the case where a database of appropriate transactions 121 and a database of inappropriate transactions 122 have been created, the explainability pattern 14 of a type of DMI 3 is: an appropriate pattern 141 if the explainability pattern 14 is extracted from a transaction 12 of the database of appropriate transactions 121, or an inappropriate pattern 142 if the explainability pattern 14 is extracted from a transaction 12 of the database of inappropriate transactions 122.

[0092] The creation E14 of the pattern databases 151, 152 then includes the second training E18 during which the extracted explainability patterns 14 are recorded in a pattern database 151, 152. Advantageously, the second training E18 includes the creation of a database of appropriate patterns 151 and the creation of a database of inappropriate patterns 152. The appropriate patterns 141 are recorded in the appropriate pattern database 151 and the inappropriate patterns 142 are recorded in the inappropriate pattern database 152.

[0093] Preferably, the appropriate pattern database 151 consists, for each type of DMI 3, of one or more explainability patterns 14, each extracted from a transaction 12 of the appropriate transaction database 121. And, the inappropriate pattern database 152 consists, for each type of DMI 3, of one or more explainability patterns 14, each extracted from a transaction 12 of the inappropriate transaction database 122.

[0094] Advantageously, the explainability patterns 14 of the appropriate pattern database 151 and the inappropriate pattern database 152 can each include the influential features 4a that affected the calculation of the compatibility probability 6 of a given type of MDI 3, either increasing or decreasing the compatibility probability 6 of the MDI 3 under consideration. The appropriate pattern database 151 and the inappropriate pattern database 152 link the explainability patterns 14 comprising influential features 4a, and their associated impact level 13. The appropriate pattern database

[0095] 151 and the database of inappropriate patterns 152 therefore allow for the selection, for each new vascular structure 1 for which compatibility probabilities 6 of each type of DMI 3 have been calculated, of one or more of the characteristics 4 of the vascular structure 1 called essential characteristic 40, with their level of impact 13. The obtaining of the essential characteristics 40 is detailed below.

[0096] Optionally, the appropriate transaction database 121 and the inappropriate transaction database 122 can be formed into a single global database, and the appropriate pattern database 151 and the inappropriate pattern database 152 can also be formed into a single global database.

[0097] Classification

[0098] The process includes the implementation of classification E2. Classification E2 includes the implementation of model 7, previously trained by initialization E1, and the use of the database of appropriate patterns 151 and the database of inappropriate patterns.

[0099] 152 created during initialization E1.

[0100] Advantageously, classification E2 is implemented independently of initialization E1; in other words, classification E2 can be performed without initialization E1 necessarily being performed as well. It is only necessary that initialization E1 has been implemented once in order to train model 7 and to create the database of appropriate patterns 151 and the database of inappropriate patterns 152. The selection process can therefore be implemented simply by performing classification E2 once initialization E1 has been previously implemented.

[0101] The E2 classification includes several steps to choose the most suitable type of DMI 3 for the treatment of an aneurysm 2 present in a vascular structure 1 to be treated, indicating the reasons for this choice.

[0102] Classification E2 includes obtaining an image (E21) of vascular structure 1, which includes aneurysm 2. The image of vascular structure 1 can be obtained in various ways and is transmitted to the processing unit of the second server. From now on, vascular structure 1 will be understood to mean the vascular structure 1 containing the aneurysm 2 to be treated. This vascular structure 1 is distinct from the reference vascular structures 1a.

[0103] The image of vascular structure 1 can be a two-dimensional image, 2D, or a three-dimensional image, 3D.

[0104] The E2 classification then implements an E22 extraction of features 4 from vascular structure 1. The E22 extraction can be carried out in the same way as the E12 extraction of features 4 from reference vascular structures 1a. The extracted features 4 are then processed by the trained model 7.

[0105] Model 7 performs an E23 processing of the features 4 of vascular structure 1 previously extracted from the image of vascular structure 1. The E23 processing allows the calculation of the compatibility probability 6 of each type of DMI 3 for the vascular structure 1 to be processed. Advantageously, the compatibility probabilities 6 of each type of DMI 3 are between 0 and 1. The sum of the compatibility probabilities 6 of each of the types of DMI 3 is equal to 1.

[0106] The E2 classification then allows a selection E24 of at least one essential characteristic 40 that has influenced the probability of compatibility 6 associated with each type of MID 3 through the use of the database of appropriate patterns 151 and the database of inappropriate patterns 152.

[0107] The E24 selection first classifies each type of DMI 3 according to the probability of compatibility 6 of the type of DMI 3 with the vascular structure 1. Each type of DMI 3 is therefore classified as a suitable type or an unsuitable type for the vascular structure 1. The type of DMI 3 is: a suitable type if the probability of compatibility 6 of the type of DMI 3 is greater than a previously set threshold, or an unsuitable type if the probability of compatibility 6 of the type of DMI 3 is less than the threshold.

[0108] The threshold can be the same as the threshold set during the implementation of the E1 initialization, or it can be recalculated using the same method or a different method.

[0109] The E24 selection is then configured to select for each type of DMI 3 one or more essential characteristic(s) 40 of the vascular structure 1.

[0110] Selection E24 determines the essential characteristics 40 of the vascular structure 1 for each type of DMI 3 using the database of appropriate patterns 151 and the database of inappropriate patterns 152. The essential characteristics 40 are selected by comparing the characteristics 4 of the vascular structure 1 to the explainability patterns 14 associated with the types of DMI 3 considered, recorded in the database of appropriate patterns 151 or the database of inappropriate patterns 152. In other words, the essential characteristics 40 are selected by comparing the characteristics 4 of the vascular structure 1: to the appropriate patterns 141 of the type of DMI 3 considered if the type of DMI 3 is an appropriate type for the vascular structure 1, or to the inappropriate patterns 142 of the type of DMI 3 if the type of DMI 3 is an inappropriate type for the vascular structure 1.

[0111] For each type of DMI 3, selection E24 compares the characteristics 4 of the vascular structure 1 to the influential characteristics 4a of the explainability patterns 14 associated with the type of DMI 3 considered. Furthermore, selection E24 retains the explainability pattern(s) 14 with the most influential characteristics 4a common to the characteristics 4 of the vascular structure 1 to be treated, among the explainability patterns 14 of the type of DMI 3 considered. Finally, selection E24 retains as essential characteristics 40 of the vascular structure 1 all the influential characteristics 4a of the retained explainability patterns 14 common to the characteristics 4 of the vascular structure 1 to be treated.

[0112] Advantageously, selection E24 also retains the level of impact 13 associated with influential characteristics 4a selected as essential characteristics 40 of the vascular structure 1.

[0113] Thus, the essential characteristics 40 of a vascular structure 1 for a type of MDI 3 are the characteristic(s) of this vascular structure 1 selected as having influenced the probability of compatibility 6 of the type of MDI 3. The essential characteristics 40 can be characteristics 4 of the vascular structure 1 that favored the choice of the type of MDI 3 considered, if the type of MDI 3 is proposed as appropriate to treat the vascular structure 1, and favored a rejection of the type of MDI 3 considered, if the type of MDI 3 is proposed as inappropriate to treat the vascular structure 1. This allows a user to know the reasons for the choice of a type of MDI based on the vascular structure 1 considered.However, the essential characteristics 40 can also be characteristics 4 of the vascular structure 1 which have tended to: disfavor the choice of the type of MID 3 considered, in the case of a type of MID 3 proposed as appropriate to treat the vascular structure 1, or disfavor a refusal of the type of MID 3 considered, in the case of a type of MID 3 proposed as inappropriate to treat the vascular structure 1. This allows a user to know the elements of the vascular structure 1 considered which could call into question the choice of a type of MID in function.

[0114] Finally, after processing E23 and selection E24, the process may advantageously include a display step E25 of the DMI 3 type having the highest probability of compatibility 6 with vascular structure 1, or of the DMI 3 type(s) classified as suitable. Optionally, display E25 may include the compatibility probabilities 6 of all DMI 3 types for vascular structure 1.

[0115] Advantageously, the E25 display can also cover the essential characteristics 40 of the vascular structure 1 for the types of MDI 3 for which the probability of compatibility 6 is displayed. The impact level 13 can further be associated with the E25 display of each essential characteristic 40 shown.

[0116] Example of implementing the steps in the selection process

[0117] Subsequently, an example of the implementation of the process for choosing a type of DMI 3 is explained.

[0118] In this example, the procedure implements an initialization from images of four reference vascular structures 1a, labeled C1 to C4. The vascular structures 1 comprise three features 4, labeled f1, f2, f3, each comprising three degrees (1, 2, 3). The set of DMI types 3 includes three different DMI types A, B, and C.

[0119] The following table presents the results of the E22 extraction by the probabilistic module of the features 4 f 1 , f2 , f3 , of each reference vascular structure 1a C1 , C2 , C3 and C4 . These features 4 as well as the mention of the type of DMI 3 used for the processing of each reference vascular structure 1a form the feature database 5 which allows the training E13 of the model 7 .

[0120] The processing by model 7 of each reference vascular structure 1a of the characteristic database 5 gives the probability of compatibility 6 for each reference vascular structure 1a of each type of MID 3 A, B and C, noted P (A) for type MID A, P(B) for type MID B and P(C) for type MID C. Thus, for the vascular structure C1 having a characteristic f1 of degree 1, a characteristic f2 of degree 1 and a characteristic f3 of degree 3, the probability of compatibility 6 of type DMI A, denoted P(A) is 60%, that of type B is 30% and that of type C is 10%.

[0121] The implementation of the explainability method on the basis of characteristics 5 as a function of the compatibility probabilities 6 of each type of DMI 3 obtained for each reference vascular structure 1 makes it possible to quantify an impact level 13 (very strong / strong / weak positive / negative impact and a neutral impact) of each characteristic 4 in the calculation E15 of the compatibility probability 6 of each type of DMI 3.

[0122] Thus, for vascular structure C1, the characteristic f1, due to its degree of 1, strongly positively influenced the probability of compatibility 6 of type DM A, and the characteristic f3, due to its degree of 3, very strongly positively influenced the probability of compatibility 6 of type DM A; while the characteristic f2, due to its degree of 1, weakly positively influenced the probability of compatibility 6 of type DM A. In other words, the presence of a characteristic f1 = 1 favors the use of type DM A for vascular structure C1, the presence of a characteristic f3 = 3 favors it very strongly, while the presence of a characteristic f2 = 1 tends to disfavor the use, and therefore lower the probability of compatibility 6, of type DM A for vascular structure C1.

[0123] The appropriate transaction database 121 created includes for each type of DMI 3 the transactions 12 including the influential characteristics 4a of the reference vascular structures 1a for which the type of DMI 3 considered is an appropriate type.

[0124] Transactions for solution A, solution B, solution C: (f1=1, strong pos.), (f2=1, weak (f1=3, very strong pos.), (f2=2, (f2=3, very strong pos.) neg.), (f3=1, very strong pos.), (f3=1, weak (f3=1, weak pos.) neg.), (f1=1, f1 pos.), (f3=3, very (f1=3, very strong pos.), (f2=2, (f1=3, weak pos.) (f2=2, strong pos.), (f3=3, very strong neg.), (f3=1, neg.) weak pos.)

[0125] The inappropriate transaction database 122 created includes for each type of DMI 3 the transactions 12 including the influential characteristics 4a of the reference vascular structures 1a for which the type of DMI 3 considered is an inappropriate type.

[0126] Transactions for the Transactions for the Transactions for solution A solution B solution C

[0127] (f1=3, strong negative), (f2=2, weak positive) (f1=1, very strong negative) (f1=1, strong negative) f2=1, negative), (f3=1, weak positive) strong positive) (f3=3, very strong negative)

[0128] (f1=3, strong negs..),(f2=2, (f1=1, very strong neg.),(f3=1 , (f1=3, strong positive) (f3=3, weak neg.) weak neg.) very strong neg.)

[0129] Thus, DM1 type A is appropriate for treating vascular structure 1 if vascular structure 1 includes feature f1=1 (that is, whose f1 features are of degree 1), feature f2=1, and feature f3=3, or if the vascular structure includes feature f1=1 and feature f3=3. And, for example, DM1 type B is inappropriate for treating vascular structure 1 if vascular structure 1 includes feature f1=1, or if vascular structure 1 includes feature f1=1 and feature f3=1.

[0130] Following the extraction E17 of appropriate patterns 141 from the appropriate transaction database 121, the appropriate pattern database 151 includes the influential characteristics 4a of each type of DMI 3, and their associated level of impact 13, common to several transactions 12 of the considered type of DMI 3 from the appropriate transaction database 121.

[0131] Suitable patterns for A Suitable patterns for B Suitable patterns for C

[0132] (f1=1, strong positive) (f1=3, very strong positive), (f2=2, (f3=1, weak positive) very strong positive)

[0133] Following the extraction E17 of inappropriate patterns 142 from the inappropriate transaction database 122, the inappropriate pattern database 152 includes the influential characteristics 4a of each type of DMI 3, and their associated impact level 13, common to several transactions 12 of the considered type of DMI 3 from the inappropriate transaction database 122.

[0134] Inappropriate patterns for A Inappropriate patterns for B Inappropriate patterns for C (f1=3, strong neg.), (f2=2, (f1=1, very strong neg.) (f3=3, very strong neg.) weak neg.)

[0135] Thus, and to summarize, DM type A is an appropriate type to treat vascular structure 1 if vascular structure 1 includes the feature f1 =1 (in other words, whose features f1 are of degree 1) and DM type B is an inappropriate type to treat vascular structure 1 if vascular structure 1 includes the feature f1 =1.

[0136] The database of appropriate patterns 151 and the database of inappropriate patterns 152 are thus formed (step E18).

[0137] The process then includes the implementation of the obtaining steps E21, extraction E22, processing E23 and selection E24 by algorithm 7 and the use of the database of appropriate patterns 151 and the database of inappropriate patterns 152.

[0138] For a vascular structure 1 C5 to be treated, extraction E22 provides the characteristics 4 of vascular structure 1 as shown below. Processing E23 using algorithm 7 provides the compatibility probabilities 6 for each type of DMI 3 A, B, and C for vascular structure 1 C5.

[0139] Selection E24 allows for the classification of DMI type 3A as appropriate and types 3B and 3C as inappropriate. DMI type 3A is classified as appropriate because its compatibility probability (6) for vascular structure 1C5 is greater than 1 / 3, or 0.33, given that there are three types of DMI 3. Similarly, types 3B and 3C are classified as inappropriate for vascular structure 1C5 because their compatibility probability (6) is less than 1 / 3. Selection E24 also allows for the selection of essential characteristics (40) of vascular structure 1C5 for each type of DMI 3, as well as the impact level associated with these essential characteristics (40), using the appropriate pattern database (151) and the inappropriate pattern database (152).

[0140] Finally, display E25 allows the following table to be presented.

[0141] Thus, for the C5 vascular structure, type A DM is the most suitable for treating the aneurysm, as its P(A) compatibility probability is the highest. Furthermore, this choice is explained by the presence of the characteristic f1 = 1 in the C5 vascular structure. This characteristic f1 = 1 is therefore an essential characteristic of the C5 vascular structure, and its impact on the choice of type A DM is strongly positive; in other words, the characteristic f1 = 1 strongly influenced the choice of type A DM for treating the C5 vascular structure.

Claims

DEMANDS 1. A computer-implemented method for selecting a type of implantable medical device (3), IMD (3), from a set of IMD types (3), the IMD (3) being intended to be positioned in a vascular structure (1) comprising a zone of interest (2), the method comprising the following steps: obtaining (E21) an image of a vascular structure (1) comprising a zone of interest (2); extracting (E22) a plurality of features (4) of the vascular structure (1) from the image obtained; processing (E23) by a supervised learning model (7) of the extracted features (4) to obtain, for each type of IMD (3), a compatibility probability (6) quantifying the compatibility of the type of IMD (3) with the zone of interest (2) of the vascular structure (1);and selection (E24) from among the extracted features (4), and according to each compatibility probability (6), of at least one essential feature (40) influencing the compatibility probability (6) associated with each type of DMI (3).; 2. A method according to claim 1, wherein the selection (E24) classifies each type of DMI (3) as an appropriate type, if the probability of compatibility (6) of the type of DMI (3) is greater than a previously fixed threshold, or as an inappropriate type, if the probability of compatibility (6) of the type of DMI (3) is less than the threshold.

3. A method according to claim 2, wherein the selection (E24) is implemented based on a database of suitable patterns (151) and a database of unsuitable patterns (152), the database of suitable patterns (151) and the database of unsuitable patterns (152) each comprising at least one explainability pattern (14) of each type of DMI (3), each explainability pattern (14) comprising at least one influencing feature (4a) and an impact level (13) associated with the influencing feature (4a), the influencing feature (4a) being a feature (4) having a non-zero associated impact level (13), the impact level (13) qualifying the impact of each feature (4) in the calculation of the compatibility probability (6) of the type of DMI (3) considered;the explainability pattern (14) of the appropriate pattern database (151) being common to at least one reference vascular structure (1a) for which the type of DMI (3) considered is an appropriate type; and; the explainability pattern (14) of the inappropriate pattern database (152) being common to at least one reference vascular structure (1a) for which the type of DMI (3) considered is an inappropriate type.

4. A method according to claim 3, wherein the selection (E24) determines for each type of DMI (3) the essential characteristic (40): by comparing the characteristics (4) of the vascular structure (1) to the explainability patterns (14) of the database of appropriate patterns (151) if the type of DMI (3) considered is an appropriate type or to the explainability patterns (14) of the database of inappropriate patterns (152) if the type of DMI (3) considered is an inappropriate type; and retaining as essential characteristic(s) (40) the influential characteristic(s) (4a) common to the characteristics (4) of the vascular structure (1), the influential characteristic(s) (4a) being included in one or more explainability patterns (14) having the most influential characteristics (4a) common to the characteristics (4) of the vascular structure (1).

5. A method according to any one of claims 1 to 4, comprising a generation (E11) of the model (7) from a feature database (5) comprising features (4) of each of the images of a plurality of reference vascular structures (1a) from a training image database.

6. Method according to claim 5, wherein the compatibility probabilities (6) of each type of DMI (3) for the reference vascular structures (1a) are calculated (E15) by the model (7) from the characteristic database (5).

7. A method according to any one of claims 3 to 6, comprising a first formation (E16) of a database of appropriate transactions (121) and a database of inappropriate transactions (122); the database of appropriate transactions (121) comprising for each type of DMI (3) a transaction (12) comprising the influential characteristics (4a) of a reference vascular structure (1a) for which the type of DMI (3) is considered to be an appropriate type; and the database of inappropriate transactions (122) comprising for each type of DMI (3) a transaction (12) comprising the influential characteristics (4a) of a reference vascular structure (1a) for which the type of DMI (3) is considered to be an inappropriate type.

8. A method according to claim 7, wherein each transaction (12) is calculated as a function of the compatibility probability (6) of the type of MDI (3) considered for each reference vascular structure (1a) and an explainability table (9) comprising for each reference vascular structure (1a) the impact level (13) of each characteristic (4) for the compatibility probability (6) of the type of MDI (3) considered, each transaction (12) comprising the influential characteristics (4a) of a reference vascular structure (1a) and the impact level (13) associated with each of the influential characteristics (4a).

9. A method according to any one of claims 7 to 8, comprising a second formation (E18) of the appropriate motive database (151) and the inappropriate motive database (152), each comprising for each type of DMI (3) at least one explainability motive (14), such that: the explainability motive (14) of the appropriate motive database (151) comprises an influential feature (4a) of the type of DMI (3) considered and the impact level (13) associated with the influential feature (4a), the influential feature (4a) and the impact level (13) being common to at least one transaction (12) of the type of DMI (3) considered of the appropriate transaction database (121);and the explainability pattern (14) of the inappropriate pattern database (152) includes an influential feature (4a) of the considered DMI type (3) and the impact level (13) associated with the influential feature (4a), the influential feature (4a) and the impact level (13) being common to at least one transaction (12) of the considered DMI type (3) in the inappropriate transaction database (122).

10. Method according to any one of claims 1 to 9, wherein the set of DMI types (3) comprises the DMI types (3) of "stent", "intrasaccular cage", "flow diverter" or endovascular microcoil embolization.

11. Method according to any one of claims 1 to 10, comprising a display (E25) of the compatibility probability (6) of each type of MDI (3) and of essential characteristics (40) of the vascular structure (1) for each compatibility probability (6).

12. Product computer program comprising code instructions for the execution of a process according to any one of claims 1 to 11, when said program is executed on a computer.

Images