WO2022175062A1

WO2022175062A1 - Method for estimating radiation exposure in a 3d environment

Info

Publication number: WO2022175062A1
Application number: PCT/EP2022/052064
Authority: WO
Inventors: Vaitheeswaran Ranganathan; Saravanan KARUNANITHI
Original assignee: Koninklijke Philips N.V.
Priority date: 2021-02-22
Filing date: 2022-01-28
Publication date: 2022-08-25

Abstract

A method for estimating radiation exposure within a 3D environment, the 3D environment containing a radiopharmaceutical located inside the body of a patient. The method is based on modelling distribution and attenuation of the pharmaceutical within the body of the patient and using this to estimate the resulting radiation exposure as a function of location within the 3D environment.

Description

METHOD FOR ESTIMATING RADIATION EXPOSURE IN A 3D ENVIRONMENT

FIELD OF THE INVENTION

The present invention relates to a method for estimating radiation exposure in a 3D environment, in particular a radiation exposure caused by a radiopharmaceutical.

BACKGROUND OF THE INVENTION

Nuclear medicine involves handling of radioactive materials that can give rise to external and internal exposure of staff. The magnitude of exposure to an individual depends upon the radionuclide concerned, its activity and the type of work within a department which the individual is involved in.

A relatively newer imaging modality involves use of positron-emitting radionuclides for PET scanning. This has led to increased radioactive exposure of staff. Furthermore, within the field of therapeutic nuclear medicine, new therapeutic agents with beta emitters of higher therapeutic effectiveness have been used, resulting in significantly increased exposure of medical staff to radiation.

Thermoluminescent Dosimetry (TLD) badges are a common approach to monitoring radiation exposure. However, these are not able to provide any real-time information about exposure, and thus are of limited use for helping avoid over-exposure before it occurs. They instead only allow a cumulative exposure level (e.g. per month) to be determined after the event. In addition, TLD measurements are less helpful when medical staff are actively engaged in a medical procedure.

An improved approach to estimating radiation exposure of individuals caused by radiopharmaceuticals would be of value.

SUMMARY OF THE INVENTION

The invention is defined by the claims.

According to examples in accordance with an aspect of the invention, there is provided a computer-implemented method for estimating a radiation exposure within a 3D environment, the 3D environment containing a radiopharmaceutical located inside the body of a patient. The method comprises: obtaining an indication of the radiopharmaceutical, and retrieving a model of radiation emission from the body. The model of radiation emission is configured to model at least: a radiation distribution within the body of the patient as a function of time for the radiopharmaceutical, and a radiation attenuation by the body. The method further comprises estimating radiation emission from the body based on the model of radiation emission, generating a representation of estimated radiation exposure in the 3D environment based on the estimated radiation emission from the body; and generating a data output indicative of the generated representation.

Embodiments of the invention are based on simulating radiation exposure in a 3D space based on a model of radiation emission from a patient body, where the patient body has been provided with a radiopharmaceutical. The radiation emission from the body will vary over time due to the biokinetic behavior of radiopharmaceuticals within the body. By modelling the biokinetic behavior of the radiation source, including its spatial distribution as a function of time, and its attenuation, the time-varying radiation exposure caused by the body can be modelled. A model-based approach allows an expected radiation exposure as a function of time and as a function of location in the 3D space to be estimated in advance and/or estimated in real time. This allows, in accordance with certain embodiments, for a real-time exposure of an individual in the 3D environment to be determined (e.g. based on location information in some examples), allowing them to modify their behavior so as to minimize exposure. It also allows them to potentially plan in advance how to minimize exposure.

A radiopharmaceutical means a substance which is introduced to the body of a patient, for example through injection or ingestion, and which contains a radioactive agent or ingredient. Examples include for example radioactive contrast agents.

In accordance with one or more embodiments, the estimated radiation emission for the body may comprise estimated radiation emission as a function of location on the body. This provides for more accurate modelling of radiation exposure as a function of position in the 3D environment. For example, biological modelling of distribution (e.g. concentration) of the radiopharmaceutical in the body as a function of time allows modelling of the relative quantities of radioactive material at different locations of the body at a given time.

In some embodiments, the model of radiation emission includes one or more model parameters related to structural properties of the patient body. These may be included as part of the modelling of the radiation attenuation for example. For example, the structural properties may relate to dimensions of the different parts of the patient body, body composition, such as thickness of tissue layers, e.g. muscle, fat, skin, attenuation coefficients of the different tissue layers etc.

The modelling of radiation distribution within the body may be based at least in part on modelling concentration of the radiopharmaceutical in a discrete set of anatomical structures, regions or locations in the body of the patient as a function of time. For example, the model of radiation emission may be a compartmentalized model. In a compartmentalized model, radiopharmaceutical concentration in a plurality of different anatomical structures, components, systems or regions may each be modelled as a function of time, e.g. each with an associated concentration equation as a function of time. Transfer of radiopharmaceutical between different compartments may be modelled. Each of the anatomical regions may be assigned or associated with a particular spatial location or volume or area within the 3D environment. This allows the body to be modelled as a composite radioactivity source in the 3D environment, comprised of multiple source points, areas or volumes, each with a modelled time-dependent concentration of the radiopharmaceutical.

The modelling of radiation distribution within the body may be based at least in part on modelling transport or diffusion of the radiopharmaceutical through the body of the patient as a function of time, and as a function of location within the patient body. Where the model is compartmentalized, this may comprise modelling transfer of the radiopharmaceutical between different anatomical compartments.

The representation of the estimated radiation exposure may comprise a 3D map of radiation exposure as a function of 3D co-ordinate position in the 3D environment. This thereby provides an indication of a spatial exposure distribution in the 3D environment.

In accordance with one or more embodiments, the method may comprise generating an augmented reality visual representation of the radiation exposure, based on overlaying at least a portion of the generated 3D map of radiation exposure atop an image of a region of the 3D environment.

This may involve a step of registering the 3D map spatially with the acquired image, so that the portion of the 3D map which is overlaid the image spatially corresponds to the spatial region depicted by the image.

The augmented reality visual representation may be generated in real time with image acquisition. The method may comprise generating a real-time augmented reality image stream, wherein new, updated images are recurrently received and the 3D map is registered to each new image, and overlaid atop the new image based on the registration. According to one or more embodiments, the method may further comprise generating an estimate of a received radiation dose of a user located within the 3D environment, based on position information for the user within the 3D environment as a function of time, and based on the representation of estimated radiation exposure in the 3D environment. The position of the user may be tracked and represented in terms of the co-ordinate system of the 3D environment. The position of the user may be tracked in real time.

In some embodiments, the estimate of received radiation dose of the user may be based on application of a further sub-model, and wherein the sub-model comprises one or more machine learning algorithms.

In accordance with one or more embodiments, the method may further comprise generating guidance for communication to a user, the guidance related to the radiation exposure dose.

Examples in accordance with a further aspect of the invention provide a computer program product comprising computer program code, the computer program code configured, when executed on a processor, to cause the processor to perform a method in accordance with any example or embodiment outlined above or described below, or in accordance with any claim of this application.

Examples in accordance with a further aspect of the invention provide a processing arrangement for use in estimating a radiation exposure within a 3D environment, the 3D environment containing a radiopharmaceutical located inside the body of a patient. The processing arrangement is adapted to: obtain an indication of the radiopharmaceutical, and retrieve a model of radiation emission from the body. The model of radiation emission is configured to model at least: a radiation distribution within the body of the patient as a function of time for the radiopharmaceutical, and a radiation attenuation by the body.

The processing arrangement is further adapted to estimate radiation emission from the body based on the model of radiation emission; generate a representation of estimated radiation exposure in the 3D environment based on the estimated radiation emission from the body; and generate a data output indicative of the generated representation.

Examples in accordance with a further aspect of the invention may provide a mobile computing device comprising a processing arrangement in accordance with any example or embodiment outlined above or described below, or in accordance with any claim of this application. In accordance with one or more embodiments, the mobile computing device may comprise a camera and a display device.

The representation of the estimated radiation exposure may comprise a 3D map of radiation exposure as a function of 3D co-ordinate position in the 3D environment.

The processing arrangement may be adapted to: acquire image data of a 3D region of the 3D environment using the camera; generate an augmented reality visual representation of the radiation exposure, based on overlaying the generated 3D map of radiation exposure atop the acquired image of the region of the 3D environment; and display the augmented reality visual representation on the display device.

These and other aspects of the invention will be apparent from and elucidated with reference to the embodiment(s) described hereinafter.

BRIEF DESCRIPTION OF THE DRAWINGS

For a better understanding of the invention, and to show more clearly how it may be carried into effect, reference will now be made, by way of example only, to the accompanying drawings, in which:

Fig. 1 shows a block diagram of an example method in accordance with one or more embodiments;

Fig. 2 schematically illustrates a representation of a body of patient as a compartmentalized source of radioactivity; and

Fig. 3 schematically illustrates a 3D environment containing a body of a patient which includes a radiopharmaceutical, and further including a user exposed to the radioactivity emitted from the patient body.

DETAILED DESCRIPTION OF THE EMBODIMENTS

The invention will be described with reference to the Figures.

It should be understood that the detailed description and specific examples, while indicating exemplary embodiments of the apparatus, systems and methods, are intended for purposes of illustration only and are not intended to limit the scope of the invention. These and other features, aspects, and advantages of the apparatus, systems and methods of the present invention will become better understood from the following description, appended claims, and accompanying drawings. It should be understood that the Figures are merely schematic and are not drawn to scale. It should also be understood that the same reference numerals are used throughout the Figures to indicate the same or similar parts.

The invention provides a method for estimating radiation exposure within a 3D environment, the 3D environment containing a radiopharmaceutical located inside the body of a patient. The method is based on modelling distribution and attenuation of the pharmaceutical within the body of the patient and using this to estimate the resulting radiation exposure as a function of location within the 3D environment.

Fig. 1 outlines, in block diagram form, steps of an example method 10 according to one or more embodiments. The method is for estimating a radiation exposure within a 3D environment, where the 3D environment contains a radiopharmaceutical located inside the body of a patient. The method 10 comprises obtaining 12 an indication of the radiopharmaceutical. This information may for example be obtained or received from an external processor or computer, from a local memory, or from a user interface.

The method 10 further comprises retrieving 14 a model of radiation emission from the body. The model of radiation emission is configured to model at least: radiation distribution within the body of the patient as a function of time for the radiopharmaceutical, and a radiation attenuation by the body. The model may be retrieved for example from a local or remote datastore.

The method 10 further comprises estimating 16 radiation emission from the body based on the model of radiation emission. The model may be run or executed or processed based on one or more model inputs. The model inputs may for example be received from a local or remote processor or computer or from a user interface.

The method 10 further comprises generating 18 a representation of estimated radiation exposure in the 3D environment based on the estimated radiation emission from the body. This means the expected radiation exposure level for an individual positioned within the 3D environment. The estimated radiation exposure may comprise estimated radiation exposure as a function of (3D co-ordinate) position within the 3D environment.

The method 10 further comprises generating 20 a data output indicative of the generated representation of estimated radiation exposure in the 3D environment.

The model of radiation emissions from the body may be a biokinetic model, or may include a biokinetic sub-model, by which is meant a model which represents biological transport or diffusion or transmission through the body as a function of time. The model may comprise one or more model equations representative of concentration of the radiopharmaceutical in one or more locations of the body of the patient, which may be evolved over time to determine the concentration of the radiopharmaceutical.

The estimated radiation emission for the body preferably comprises estimated radiation emission as a function of location on the body. The model may include functionality for modelling a concentration of the radiopharmaceutical as a function of location within the body and as a function of time. In one set of examples, the body may be treated as a spatial volume within the 3D environment, and wherein different point locations in the body volume each have an associated co-ordinate position within the 3D environment. The one or more model equations may therefore model concentration of the radiopharmaceutical as a function of co-ordinate position in the body and as a function of time. Concentration means for example mass per unit volume.

Based on modelling of the concentration of the radiopharmaceutical as a function of position and time in the body, a corresponding modelled radioactivity as a function of position in the body and as a function of time may be determined, based on knowledge of the base radioactivity of the radiopharmaceutical.

Once concentration of the radiopharmaceutical as a function of time and position in the body is known, a radioactive exposure as a function of 3D co-ordinate position in the 3D environment can be modelled based on the known base radioactivity of the radiopharmaceutical, and based on the modelled concentration as a function of time and position in the body, and based on modelling of radiation absorption, attenuation and/or scattering by the body as a function of body location.

This can be done by using a pre-determined model of radiation absorption, attenuation and/or scattering as a function of body location. By this is meant the absorption, attenuation and/or scattering by the body as a result of the radiation passing from inside the body to outside the body (where the outside corresponds to the 3D environment).

A radiation exposure as a function of co-ordinate location in the 3D environment may then be determined based on the known radiopharmaceutical radioactivity, the known radiopharmaceutical concentration as a function of position in the body, the known radioactive attenuation, absorption and/or scattering by the body as a function of positon, and based on a calculated distance between each point in the body and the relevant location in the 3D environment for which an exposure is to be determined. An inverse square law can be applied to the distance to determine the distance-related radioactive attenuation.

One example approach to modelling distribution of the radiopharmaceutical as a function of position in the body will now be outlined in more detail. In accordance with one or more embodiments, the concentration of the radiopharmaceutical as a function of position in the body and as a function of time can be modelled using a compartmentalized model. A compartmentalized model represents the body as a plurality of discrete anatomical structures, systems, or components, each with an associated location, area or volume within the co-ordinate system of the 3D environment. For example, each of a plurality of organs belonging to the patient may form the discrete anatomical structures, and a concentration of the radiopharmaceutical with each of these organs as a function of time may be modelled. Additionally or alternatively, the different anatomical structures, systems or components may comprise different bodily systems such as the circulatory system and/or a portion of the digestive system.

The compartmentalized model may incorporate modelled transfer of the radiopharmaceutical between compartments.

The compartmentalized model may be based on representing the concentration of the radiopharmaceutical in each compartment with a time-dependent equation. The concentration at a certain time in a certain compartment can be determined by evolving the equation in time.

The use of compartmentalized models for representing radiopharmaceutical distribution in a human body as function of time has been studied and explored for many years.

A useful explanation of the use of compartmentalized models in the context of tracking concentration of radionuclides in the body can be found in the publication: Andersson, M. (2017). “Radiation dose to patients in diagnostic nuclear medicine. Implementation of improved anatomical and biokinetic models for assessment of organ absorbed dose and effective dose”. Lund University: Faculty of Medicine. Reference is made in particular to Chapter 2 (“Biokinetic modelling”) and even more particularly to pages 26-34 (“descriptive modelling”).

The International Commission on Radiological Protection (ICRP) has generated a number of standard compartmental models for modelling concentration and transport of radionuclides within the human body. By way of example, ICRP publication 100 (ICRP, 2006. Human Alimentary Tract Model for Radiological Protection. ICRP Publication 100. Ann. ICRP 36 (1-2)) outlines an example biokinetic model for the alimentary tract.

ICRP publication 128 also provides details of a number of different biokinetic models for different organ systems or sets of organs, and for different radionuclides. Reference is also made to Chapter 6 (“Tracer Kinetic Modelling in PET”) of the book: Richard E Carson, “Positron emission tomography”, pp.127-159. This outlines in detail the mathematics of a compartmental model of radionuclides within the body. This chapter refers in particular to radioactive tracers but the same principles can be applied for any radiopharmaceutical substance.

By way of one example, with reference to Andersson, M. (2017) cited above, one form of biokinetic modelling is Descriptive Modelling. This is outlined between pages 26-34 of Andersson, M. (2017) cited above. Descriptive modelling is based on least squares criteria and is the type of modeling most frequently used in the ICRP standard models for radiopharmaceuticals. The body is modelled as comprising a plurality of pools corresponding to different biological regions or systems in the body (e.g. organs), and each pool comprising one or more compartments. Concentration or quantity of the radiopharmaceutical in different pools can be modelled, and transfer between pools modelled. For example, organs may be assumed to have instantaneous uptake, with excretion occurring to urine and feces.

Fractional uptake, F_s, in a pool S can be modelled according to the equation:

where As(t)/Ao is the fraction of the injected radiopharmaceutical activity at time t in pool 5, a is the fraction of F_s uptake j or elimination i with corresponding the biological half-time 7j,

T.

Within ICRP publications 53, 80, 106 and 128, a special case of the above equation is assumed for most of the models presented therein, wherein an immediate uptake by each pool S is assumed:

Further details can be found between pages between pages 26-34 of Andersson, M. (2017) cited above.

Fig. 2 schematically illustrates a patient body 30 modelled with a plurality of compartments 32, each corresponding to a particular organ of the body. Each organ- associated compartment has a designated location or volume occupancy within the body, and thus within the co-ordinate system of the 3D environment that the body is located within. By thus modelling the radiopharmaceutical concentration in each organ-associated compartment as a function of time, a representation of the radioactivity at each of the compartment locations or volumes as a function of time can be derived. This may be represented in the form of a single unitary model in which all compartments have been combined, and a radiopharmaceutical concentration as a function of position in the body and time is provided. Alternatively, it may be represented in a distributed compartmental model, wherein the whole body source is represented as the sum of each of the model concentration equations for each of the different anatomical compartments.

The modelling of radiation distribution within the body may further include modelling of an effective decay of radiation activity of the radiopharmaceutical within the body. The effective decay may include intrinsic decay of activity of the radiopharmaceutical, and/or biologically-induced decay. Biologically induced decay may include for example physiological processes which lead to excision or excretion of the radioactive content of the radiopharmaceutical. In further examples however, the decay may be assumed to be negligible, at least for the period of the medical procedure in question, and thus may not be factored into the model.

As mentioned above, once the radiopharmaceutical concentration as function of time and location in the body is derived, a radiation exposure as function of position in the 3D environment can be derived. This can be derived using a further sub-model or can be derived as a further part of a same model of radiation emission from the body as is used to determine the radiopharmaceutical concentration as a function of time and position.

Modelling the radiation exposure as a function of position in the 3D environment, is based on the following input information:

- modelled radiopharmaceutical concentration as a function of location within the patient body as a function of time

- corresponding co-ordinate location of each body location in the 3D environment (optionally as a function of time, if the patient is moving), and comprises modelling the following factors:

- radiation attenuation, absorption and/or scattering (by the body) as function of position in the body; and

- radiation attenuation as a function of distance.

For modelling the radiation attenuation, absorption and/or scattering by the body as a function of position in the body (to thereby derive radiation emission from the body as a function of surface location on the body), a wide variety of different example models have been developed in the field. For example such modelling is frequently used in the domain of positron emission tomography (PET) to enable accurate PET imaging to be performed based on detected radiation from the body of a patient who has been injected with PET tracer. By way of example, any of the following papers provide details as to how attenuation by the body can be modelled:

Torrado et al (2020), “Importance of attenuation correction in PET/MR image quantification: Methods and applications”;

Kinahan et al (1998), “Attenuation correction for a combined 3D PET/CT scanner”;

Koepfli et al (2006), “CT attenuation correction for myocardial perfusion quantification using a PET/CT hybrid scanner”;

Dong et al (2020), “Deep learning-based attenuation correction in the absence of structural information for whole-body positron emission tomography imaging”;

Siegal et al (1992), “Implementation and evaluation of a calculated attenuation correction for PET”;

Yang et al (2016), “Sinogram -based attenuation correction in PET/CT”;

Wang et al (2020), “Attenuation correction for PET/MRI using MRI-based pseudo CT”.

Various Monte-Carlo based simulation packages also exist in the field for performing this modelling, and more details in this regard may be found in the paper: Zaidi, Habib. "Relevance of accurate Monte Carlo modeling in nuclear medical imaging." Medical physics 26.4 (1999): 574-608.

Modelling of the radiation attenuation by the body means the radiation attenuation caused by the material of the body as the radiation penetrates from inside the body to outside the body. Where the biokinetic model of distribution of the radiopharmaceutical in the body is done with a compartmentalized model, optionally the modelling of the radiation attenuation by the body may be done in a compartmentalized way, with the attenuation at each compartment of the model (corresponding to a particular anatomical structure or location) having a pre-determined value or spatial distribution.

In some examples, the model of radiation emission includes one or more model parameters related to structural properties of the patient body. These may be included as part of the modelling of the radiation attenuation. For example, the structural properties may relate to dimensions of the different parts of the patient body, body composition, such as thickness of tissue layers, e.g. muscle, fat, skin, attenuation coefficients of the different tissue layers etc.

Using the modelled radiation attenuation in combination with the modelled radiopharmaceutical concentration in the body as a function of position, the result is effectively a representation of the patient body as a dynamical 3D source of radioactivity, where the radioactivity varies as a function of position on the patient body surface, and as a function of time.

For modelling the radiation attenuation as a function of distance from a given body surface location, a simple inverse square law can be applied, as is well known in the art.

Combining all of the above factors together, a representation of radiation exposure as a function of position in the 3D environment and as a function of time can be obtained.

The representation of the estimated radiation exposure in the 3D environment may comprise a 3D map of radiation exposure as a function of 3D co-ordinate position in the 3D environment. The 3D map may simply be represented by radiation exposure function, with dependency upon a 3D vector position in the 3D environment. The 3D map may additionally or alternatively comprise a visual representation of the radiation exposure as a function of time and 3D position. This may be displayed on a display device.

According to one or more embodiments, the method may further comprise generating an estimate of a received radiation dose of a user located within the 3D environment, based on position information for the user within the 3D environment as a function of time, and based on the representation of estimated radiation exposure in the 3D environment. The position of the user may be tracked and represented in terms of the co-ordinate system of the 3D environment. The position of the user may be tracked in real time. This may be done in different ways, for example with a position tracking device which the user holds on their person, e.g. a wearable device, or a pocket device. Tracking could be implemented using native hardware functionality of a mobile computing device carried by the user, e.g. a smartphone. The tracking may employ electromagnetic emissions, e.g. Bluetooth tracking or radio-wave based tracking. GPS tracking could be used if position resolution is high enough. In further examples, position tracking could be done using hardware installed in the 3D environment, e.g. optical or image-based tracking.

A radiation dose received by the user at any given time can be determined based on the position of the user in the 3D environment, and the generated representation of the radiation exposure in the 3D environment. The conversion from radiation exposure to radiation dose could be done in a number of different ways. In some examples, a dedicated sub-model may be used which is pre-configured to provide the conversion. This may include one or more assumptions regarding the volume occupied by the user within the 3D environment and/or the surface area of the user available for the absorption of radiation, and its spatial positioning within the 3D space. As will be known, absorbed dose is the measure of energy per unit mass deposited by ionizing radiation.

In some examples, the body of the user may be modelled as a plurality of point locations, each with an associated mass, and an associated location in the 3D environment, and an absorbed dose determined for each point. An absorbed dose representative of the whole body may be calculated by taking a mass-weighted average of the absorbed doses at each point, i.e.

_ _ f_B D(x,y,z)p(x,y,z)dV f_B p(x,y,z)dV where D is the mass-averaged absorbed dose for the entire body of the user, B is the body of the user, D ( x , y, z) is the absorbed dose as a function of location in the body, p(x, y, z) is the density as a function of location, and V is volume of the body.

In addition to or instead of absorbed dose, a measure of Equivalent Dose and/or Effective Dose may be calculated for the user. These are well-known terms of the art and means for their calculation will be known by the skilled reader. Thus reference in this disclosure to determining absorbed dose should be understood as replaceable without loss of technical effect with determining Equivalent Dose or Effective Dose.

Fig. 3 schematically illustrates an example 3D environment 40 which contains a patient 30 who has been administered with a radiopharmaceutical. The 3D environment has an associated 3D co-ordinate system 42. The 3D environment further includes a user 44 (e.g. a clinician) who is shown at a distance, Ad , from the patient body 30. The distance, Ad , may vary as a function of time. The user further has an associated co-ordinate position in the 3D space, X (x, y, z).

The determination of the absorbed dose by the user may be performed by an analytical sub-model. The sub-model may include one or more model equations for modelling an absorbed dose as a function of user position, X, and as a function of the determined radiation exposure in the 3D environment as a function of time. The user may be modelled as having a certain surface area following a particular 3D geometry in the 3D environment, and may estimate an absorbed dose at each point comprised by the user body surface at each point in time.

In further examples, the determination of the absorbed dose may be performed using a sub-model which employs one or more machine learning algorithms. This may be termed a machine learning model. The one or more machine learning algorithms may be trained to receive as an input geometric information pertaining to the position and possibly 3D extension within the 3D environment of the user (whose dose is to be estimated), and input information regarding the radiation exposure as a function of position (and optionally time). Alternatively, the machine learning algorithm may be configured to implicitly determine the radiation exposure itself, based on input information relating to the patient body position and/or geometry and the radioactivity as a function of position on the patient body (as determined from the biokinetic model discussed above). The output of the machine learning model is the absorbed dose (or effective or equivalent dose) by the user, preferably as a function of time. Preferably the machine learning model is capable of determining the dose in real-time, so that the user can be advised in real-time of the radioactive dose they are receiving.

By way of further explanation, a machine-learning algorithm is any self training algorithm that processes input data in order to produce or predict output data. In the present context, in some examples, the input data may comprise position and geometry information relating to the user (whose radioactive dose is to be determined) and may comprise position and geometry information relating to the patient (whose body comprises the radiopharmaceutical), as well as information relating to the radioactive emission of the patient body. The output information is the absorbed dose (or effective or equivalent dose) by the user. In a further example, the input information may comprise user position and/or geometry information, in combination with a measure of radioactive emission as a function of position on the patient body, or a measure of radioactive exposure as a function of position in the room (determined using models as discussed in more detail above).

Suitable machine-learning algorithms for being employed in the present invention will be apparent to the skilled person. Examples of suitable machine-learning algorithms include decision tree algorithms and artificial neural networks. Other machine learning algorithms such as logistic regression, support vector machines or Naive Bayesian models are suitable alternatives. The structure of an artificial neural network (or, simply, neural network) is inspired by the human brain. Neural networks are comprised of layers, each layer comprising a plurality of neurons. Each neuron comprises a mathematical operation. In particular, each neuron may comprise a different weighted combination of a single type of transformation (e.g. the same type of transformation, sigmoid etc. but with different weightings). In the process of processing input data, the mathematical operation of each neuron is performed on the input data to produce a numerical output, and the outputs of each layer in the neural network are fed into the next layer sequentially. The final layer provides the output.

Methods of training a machine-learning algorithm are well known. Typically, such methods comprise obtaining a training dataset, comprising training input data entries and corresponding training output data entries. An initialized machine-learning algorithm is applied to each input data entry to generate predicted output data entries. An error between the predicted output data entries and corresponding training output data entries is used to modify the machine-learning algorithm. This process can be repeated until the error converges, and the predicted output data entries are sufficiently similar (e.g. ±1%) to the training output data entries. This is commonly known as a supervised learning technique.

For example, where the machine-learning algorithm is formed from a neural network, (weightings of) the mathematical operation of each neuron may be modified until the error converges. Known methods of modifying a neural network include gradient descent, backpropagation algorithms and so on.

During the training phase of the machine learning model, the model may be trained with training data which comprises known staff and patient position and/or geometry information, and this being tagged with corresponding measured radiation exposure and staff dosage information for a particular 3D environment, e.g. measured using traditional dosimeter technology. The machine learning algorithm is configured to learn from this input training data, such that, after training, the algorithm is capable of determining absorbed dose information for a given user, based on position and/or geometry information for the user and for the patient whose body contains the radionuclide.

By way of non-limiting example, the input geometric information may include one or more of: user and patient positions relative to one another (or simply their positions within the common 3D co-ordinate system of the 3D environment); user and patient movements as a function of time, either relative to one another or within the common co-ordinate system (e.g. approach velocity, movement of specific body parts of patient and user); effective (3D) shape and size (e.g. volumetric extent) of patient and user (optionally in different body poses, e.g. sitting, standing, sleeping).

The learning of the model is embodied in algorithms forming the model which may take the form of a mathematical cost function involving factors of time, accuracy and number of scenarios, and wherein the model is configured to minimize the cost function.

By way of one illustrative example, the machine learning model may be configured to minimize the cost function:

where Wi, W2— WN are weightings (each with a value between 0 and 1) for different possible scenarios. The different scenarios may correspond for example to different types or classes of geometric arrangement between the patient and the user, for example, the user and patient being static relative to one another, the user and patient moving relative to one another, patient sitting and user standing, patient standing and user standing, and any of a plurality of others, and combinations thereof.

In one set of embodiments, the method comprises generating an augmented reality visual representation of the determined radiation exposure in the 3D environment.

This may be based on first generating a 3D map of radiation exposure as function of position in the 3D environment (as discussed above). At least a portion of the generated 3D map may then be overlaid atop an image of a region of the 3D environment.

The image may be captured for example by a mobile computing device, e.g. a smartphone, and may project the derived map of radiation exposure onto the image. The overlaid map of radiation exposure may comprise a partially transparent (translucent) overlay with different colors, shades, or transparencies corresponding to different levels of the radiation exposure at different locations in the 3D space.

The augmented reality visual representation may be generated in real time with image acquisition. The method may comprise generating a real-time augmented reality image stream, wherein new, updated images are recurrently received and the 3D map is registered to each new image, and overlaid atop the new image based on the registration. By way of example, the augmented reality visual representation may be presented on a display of a mobile computing device, such as a smartphone.

The augmented reality representation could additionally or alternatively overlay a map of expected relative radiation dose for the user for different locations in the room (relative to other locations). In this way, the user can seek to minimize radiation dose.

In accordance with one or more embodiments, the method may further comprise generating guidance for communication to a user, the guidance related to the radiation exposure or dose. For example, this may be a message indicative of an absorbed radiation dose for a particular operation session or a particular time period. The operation session may correspond to a particular medical procedure or scan. The guidance may further include an estimated total radiation exposure, if a current sessions extends to a certain time duration. This allows a user to see if they need to take action to reduce their exposure, in order not to exceed a certain maximum dose before the end of the session.

Examples in accordance with a further aspect of the invention provide a processing arrangement for use in estimating a radiation exposure within a 3D environment, the 3D environment containing a radiopharmaceutical located inside the body of a patient.

The processing arrangement is adapted to perform a computed implemented method in accordance with any example or embodiment outlined above or described below, or in accordance with any claim of this application.

In particular, the processing arrangement is adapted to: obtain an indication of the radiopharmaceutical; retrieve a model of radiation emission from the body, wherein the model of radiation emission is configured to model at least a radiation distribution within the body of the patient as a function of time for the radiopharmaceutical, and a radiation attenuation by the body; estimate radiation emission from the body based on the model of radiation emission; generate a representation of estimated radiation exposure in the 3D environment based on the estimated radiation emission from the body; and generate a data output indicative of the generated representation. Implementation options and details for each of the above steps may be understood and interpreted in accordance with the explanations and descriptions provided above for the computer implemented method aspect of the present invention.

Any of the examples, options or embodiment features or details described above in respect of the apparatus aspect of this invention (in respect of the computer implemented method) may be applied or combined or incorporated into the present processing arrangement aspect of the invention.

A further aspect of the invention also provides a mobile computing device comprising a processing arrangement as described above. The mobile computing device may be a smartphone or tablet for example. The processing arrangement may be facilitated by native processing component(s) of the mobile computing device.

The mobile computing device may comprise a camera and a display device, e.g. a touchscreen display.

In some embodiments, the representation of the estimated radiation exposure may comprise a 3D map of radiation exposure as a function of 3D co-ordinate position in the 3D environment. Here, the processing arrangement may be adapted to: acquire image data of a 3D region of the 3D environment using the camera; generate an augmented reality visual representation of the radiation exposure, based on overlaying at least a portion of the generated 3D map of radiation exposure atop the acquired image of the region of the 3D environment; and display the augmented reality visual representation on the display device. Embodiments of the invention described above employ a processing arrangement. The processing arrangement may in general comprise a single processor or a plurality of processors. It may be located in a single containing device, structure or unit, or it may be distributed between a plurality of different devices, structures or units. Reference therefore to the processing arrangement being adapted or configured to perform a particular step or task may correspond to that step or task being performed by any one or more of a plurality of processing components, either alone or in combination. The skilled person will understand how such a distributed processing arrangement can be implemented. The processing arrangement may include a communication module or input/output for receiving data and outputting data to further components. The one or more processors of the processing arrangement can be implemented in numerous ways, with software and/or hardware, to perform the various functions required. A processor typically employs one or more microprocessors that may be programmed using software (e.g., microcode) to perform the required functions. The processor may be implemented as a combination of dedicated hardware to perform some functions and one or more programmed microprocessors and associated circuitry to perform other functions.

Examples of circuitry that may be employed in various embodiments of the present disclosure include, but are not limited to, conventional microprocessors, application specific integrated circuits (ASICs), and field-programmable gate arrays (FPGAs).

In various implementations, the processor may be associated with one or more storage media such as volatile and non-volatile computer memory such as RAM, PROM, EPROM, and EEPROM. The storage media may be encoded with one or more programs that, when executed on one or more processors and/or controllers, perform the required functions. Various storage media may be fixed within a processor or controller or may be transportable, such that the one or more programs stored thereon can be loaded into a processor.

Variations to the disclosed embodiments can be understood and effected by those skilled in the art in practicing the claimed invention, from a study of the drawings, the disclosure and the appended claims. In the claims, the word "comprising" does not exclude other elements or steps, and the indefinite article "a" or "an" does not exclude a plurality.

A single processor or other unit may fulfill the functions of several items recited in the claims.

The mere fact that certain measures are recited in mutually different dependent claims does not indicate that a combination of these measures cannot be used to advantage.

A computer program may be stored/distributed on a suitable medium, such as an optical storage medium or a solid-state medium supplied together with or as part of other hardware, but may also be distributed in other forms, such as via the Internet or other wired or wireless telecommunication systems.

If the term "adapted to" is used in the claims or description, it is noted the term "adapted to" is intended to be equivalent to the term "configured to".

Any reference signs in the claims should not be construed as limiting the scope.

Claims

CLAIMS:

1. A computer-implemented method (10) for estimating a radiation exposure within a 3D environment, the 3D environment containing a radiopharmaceutical located inside the body of a patient, the method comprising: obtaining (12) an indication of the radiopharmaceutical; retrieving (14) a model of radiation emission from the body, wherein the model of radiation emission is configured to model at least a radiation distribution within the body of the patient as a function of time for the radiopharmaceutical, and a radiation attenuation by the body; estimating radiation emission (16) from the body based on the model of radiation emission; generating (18) a representation of estimated radiation exposure in the 3D environment based on the estimated radiation emission from the body; and generating (20) a data output indicative of the generated representation.

2. The method as claimed in claim 1, wherein the estimated radiation emission for the body comprises estimated radiation emission as a function of location on the body.

3. The method as claimed in claim 1 or 2, wherein the model of radiation emission includes one or more model parameters related to structural properties of the patient body.

4. The method as claimed in any of claims 1-3, wherein the modelling of radiation distribution within the body is based at least in part on modelling concentration of the radiopharmaceutical in a discrete set of anatomical locations in the body of the patient as a function of time.

5. The method as claimed in any of claims 1-4, wherein the representation of the estimated radiation exposure comprises a 3D map of radiation exposure as a function of 3D co-ordinate position in the 3D environment.

6. The method as claimed in claim 5, wherein the method comprises generating an augmented reality visual representation of the radiation exposure, based on overlaying at least a portion of the generated 3D map of radiation exposure atop an image of a region of the 3D environment.

7. The method as claimed in claim 6, wherein the augmented reality visual representation is generated in real time with image acquisition.

8. The method as claimed in any of claims 1-7, wherein the method further comprises generating an estimate of received radiation dose of a user located within the 3D environment, based on position information for the user as a function of time, and based on the representation of estimated radiation exposure in the 3D environment.

9. The method as claimed in claim 8, wherein the estimate of received radiation dose of the user is based on application of a further sub-model, and wherein the sub-model comprises one or more machine learning algorithms.

10. The method as claimed in any of claims 1-9, wherein the method further comprises generating guidance for communication to a user, the guidance related to the radiation exposure dose.

11. A computer program product comprising computer program code, the computer program code configured, when executed on a processor, to cause the processor to perform a method as claimed in any of claims 1-10.

12. A processing arrangement for use in estimating a radiation exposure within a 3D environment, the 3D environment containing a radiopharmaceutical located inside the body of a patient, the processing arrangement adapted to: obtain an indication of the radiopharmaceutical; retrieve a model of radiation emission from the body, wherein the model of radiation emission is configured to model at least a radiation distribution within the body of the patient as a function of time for the radiopharmaceutical, and a radiation attenuation by the body; estimate radiation emission from the body based on the model of radiation emission; generate a representation of estimated radiation exposure in the 3D environment based on the estimated radiation emission from the body; and generate a data output indicative of the generated representation.

13. The processing arrangement as clamed in claim 12, the processing arrangement further adapted to generate an estimate of received radiation dose of a user located within the 3D environment, based on position information for the user as a function of time, and based on the representation of estimated radiation exposure in the 3D environment.

14. A mobile computing device comprising the processing arrangement of claim 12 or 13.

15. The mobile computing device as claimed in claim 13 or 14, wherein the mobile computing device comprises a camera and a display device, wherein the representation of the estimated radiation exposure comprises a 3D map of radiation exposure as a function of 3D co-ordinate position in the 3D environment, and wherein the processing arrangement is adapted to: acquire image data of a 3D region of the 3D environment using the camera; generate an augmented reality visual representation of the radiation exposure, based on overlaying at least a portion of the generated 3D map of radiation exposure atop the acquired image of the region of the 3D environment; and display the augmented reality visual representation on the display device.