Intellectual tissue classifier for bone and soft tissue

Abstract

To provide an intellectual tissue classifier for bone and soft tissue.SOLUTION: A method for an intraoperative state analysis and classification of a joint tissue includes: a step for sensing data of the joint tissue via a plurality of sensors installed in proximity to the joint tissue so as to detect a response to a stimulus; a step for determining a state analysis and classification information through collation means; a step for processing the sensed data in a format adapted so as to be assessed against a comparator; a step for using a history data set of the processed information and generating means that predicts the state analysis and classification; and a step for using the generated means to perform the state analysis and classification on the basis of processing of a stimulus response acquired during the operation.SELECTED DRAWING: None

Description

[Technical field]

[0001] The present invention relates generally to the analysis of bone and soft tissues, and more particularly to the biological status analysis and classification of said tissues within an intraoperative environment.

[0002] The present invention has been developed primarily for use in methods and systems for orthopaedic surgery, in particular systems and methods for biological status analysis and classification of bone and soft tissue in orthopaedic applications, including post-operative treatment and evaluation of orthopaedic surgical procedures, and will be described hereinafter with reference to this application, however, it will be understood that the invention is not limited to this particular field of use. [Background technology]

[0003] Any discussion of background art throughout the specification should not be regarded in any way as an admission that such background art is prior art or that such background art is widely known or forms part of the common general knowledge in the field in Australia or throughout the world.

[0004] All references cited herein, including any patents or patent applications, are incorporated herein by reference. No admission is made that any reference constitutes prior art. The discussion of a reference states what its author asserts, and the applicant reserves the right to challenge the accuracy and pertinence of the cited documents. Although several prior art publications are referenced herein, it should be clearly understood that this reference does not constitute an admission that any of these documents form part of the common general knowledge in the art in Australia or any other country.

[0005] Understanding the tissue status and classification allows various modifications and precautions to be taken during surgery, which can increase patient success and recovery rates.

[0006] This is especially evident in surgery involving the musculoskeletal system, where poor tissue condition can have physical implications for bodily movement and range, and is likely to be accompanied by some degree of pain. Articular tissues such as cartilage, muscle, and bone make up the joints within this system that enable it to function, and their performance inevitably deteriorates as they function.

[0007] Total knee arthroplasty is a prominent form of orthopedic surgery in which a predefined amount of hard tissue must be removed from the bones involved in the knee joint using osteotomy. A prosthetic implant is then fixed to the remaining bone to replace what was removed. This surgery is typically required when the cartilage surrounding the femur, tibia, and patella begins to dissipate. This causes them to grind against each other during normal movement, enduring increased levels of stress that would normally be absorbed by cartilage. By inserting prosthetic implants into these bones that are designed to absorb stress instead of them, these effects can be significantly reduced.

[0008] A prosthetic implant can be fixed to the articular hard tissue using one of two different methods. The first method is by attaching it directly to the hard tissue and relying on osseointegration, which refers to the natural growth of the hard tissue into the prosthetic implant and stabilizing it. This is a more natural method and generally tends to result in a stronger connection interface. The second method is through bone cement, a fixative that forms a strong bond between the prosthetic implant and the hard tissue. This method relies on the strength and tenacity of the cement, which is not as reliable as natural bone and can potentially be toxic depending on its production. It also leads to increased difficulty when positioning the osteotomy tool and inserting the prosthetic implant, since the size of the applied cement and its distribution before and after pressure is applied must be considered. The implant fixation method is generally selected based on the health of the underlying tissue. If so, direct implantation is considered a possibility, otherwise bone cement must be relied upon.

[0009] According to the National Center for Health Statistics, over 700,000 total knee arthroplasty procedures are performed annually in the United States alone, and this is expected to rise to 3,480,000 by 2030. The majority of these procedures are initially successful with patients (whose average age is 66.2 years) reporting significant pain reduction and increased mobility. However, after a period of postoperative persistence, it is possible that problems may arise, requiring additional revision surgeries. This represents approximately 8% of all knee replacement procedures, and the number is also on track to increase by 601% by 2030.

[0010] These problems are related to the quality of the interface between the prosthetic implant and the hard tissue. They are generally caused by an incomplete implantation action, but sustained or sudden trauma can also result in or at least exacerbate them. They include aseptic loosening, infection, polyethylene wear, instability, pain, osteolysis, and malposition, which are responsible for 23.1%, 18.4%, 18.1%, 17.7%, 9.3%, 4.5%, and 2.9% of all revisions, respectively. Each is generally interdependent, with the occurrence of one potentially being triggered or influenced by the onset of another.

[0011] Aseptic loosening is the largest cause of revision surgery and refers to the breakdown of fixation at the implant and articular tissue interface, leading to increased levels of pain and instability for patients. The etiology of aseptic loosening includes four main causes. The first is a biological response to wear particles from the prosthetic implant. It is possible that small particles within a critical range of 0.3-10 micrometers can break off from the implant, assuming sufficient stress is applied. Depending on the health and genetics of the patient's articular tissue, this can then give rise to a phagocyte-based inflammatory response, leading to osteolysis.

[0012] The second cause is the build-up of intra-articular fluid pressure, which is the result of overproduction of synovial fluid due to exposed hard tissue or wear particles surrounding the joint. This excess synovial fluid creates additional pressure that can result in abnormal bone perfusion or ischemia, leading to necrosis and osteolysis.

[0013] A third cause is the physical design of the implant; the surface pattern and contour affect the rate and potential for osseointegration. If this effect is negative, the amount of ingrowth may not be sufficient to stabilize and fixate the prosthesis.

[0014] A fourth cause may be the biological idiosyncrasies of the patient, including their unique characteristics such as their age and habits, any pre-existing infections or diseases that may affect the joints, and their genes. If the patient participates in regular physical exercise such as running, or has naturally weak joints, the risk may be increased.

[0015] This causation may be attributable, at least in part, to the condition or alternatively health of the underlying joint tissues and the corresponding patient. Although various procedures exist that can analyze tissue condition and structure, no final conclusions can be made until the tissue condition is established intraoperatively.

[0016] Common methods of intraoperative tissue status analysis and classification generally rely on the visual analysis of the surgeon performing the procedure. This means that any adjustments or changes based on tissue status, independent of preoperative knowledge, typically rely on the surgeon's experience. This dependency leads to discrepancies in patient satisfaction and surgical longevity, with 20% of all knee arthroplasty patients reported to be dissatisfied with their results. By gaining increased knowledge of the target tissues intraoperatively, the quality of the surgery and the surgeon's ability to react to unknown situations can be increased.

[0017] Preoperative approaches to achieving some knowledge of the surrounding tissue condition and classification are typically based on invasive procedures that require sections of tissue or cells to be removed for subsequent analysis. Depending on the analysis technique, information such as composition, topology, mineralogy, and water content about any particular tissue sample can be determined.

[0018] The preparation required for these collected tissue samples can be lengthy and involves numerous preservation and fixation techniques in an attempt to maintain the original natural state of the tissue against apparent deterioration. Despite this, the composition of the tissue will generally differ from its original composition to varying degrees depending on the preparation process. This difference must be appropriately taken into account in any subsequent analysis to ensure that the results are portable and comparable.

[0019] Although patients are usually under the influence of anesthesia during these invasive procedures, some patients will still feel pain depending on the ease with which the tissue surrounding the extraction point can be numbed. Recovery time will also be required depending on the procedure, which will likely mean mild discomfort for the patient. For the body, this will mean regeneration of the extracted tissue, resulting in temporary vulnerability, including the risk of infection. These incidences, not to mention the consequences, limit the potential for tissue salvage, as only small amounts can be harvested for fear of patient pain.

[0020] The small amount of tissue or cells removed will therefore be held accountable for being representative of the surrounding population, but this will not necessarily be the case in all cases. If this were not the case, incorrect conclusions could be observed, which would lead to greater problems than potential retesting.

[0021] Approaches exist that do not require invasive procedures or direct removal of tissue, but focus on structural analysis of the tissue as opposed to its composition. This can aid classification, as location is useful in defining the type of joint tissue, but has little comparable capability for determining condition.

[0022] Non-invasive procedures generally work by sending a form of energy into the subject and monitoring that energy as it is either reflected back or passed through. This is typically considered safe, but the more common procedures tend to focus on the use of X-rays, a form of radiation. The risks associated with this are reduced through close control of the machinery involved in the output, but still exist nonetheless.

[0023] In these pre-operative approaches, the analysis is primarily performed by humans, which means that the accuracy of the results and conclusions cannot be conclusively proven, as the skill of the individual depends primarily on their experience and education, which means that additional opinions are sometimes necessary.

[0024] With advances in artificial intelligence and data science, it is now possible to process large amounts of data into meaningful information that would otherwise be difficult to discern. This enables new techniques, such as optical and acoustic analysis, that provide additional information related to tissue condition and classification, but lack many of the shortcomings suffered by current techniques.

[0025] The invention disclosed herein provides a method for performing joint tissue condition analysis and classification within an intraoperative environment. Summary of the Invention [Means for solving the problem]

[0026] The present invention provides systems and methods for joint tissue condition analysis and classification that can be performed intraoperatively. In particular, the present invention provides methods for the collection of data from different sensors, the processing of that data, and its inclusion in the preparation and execution phases of machine learning, data science, and mathematical algorithms and techniques.

[0027] In one aspect, the present invention provides a system for collecting different types of data that can describe various attributes associated with joint tissues based on the method of data generation. A preferred system includes multiple different sensors and possible acquisition tools within a typical surgical environment where the sensors collectively operate in an automated manner to transparently assist the surgeon.

[0028] The sensor selection may comprise at least one sensor, which may exist independently or as part of a sensor system or set of sensors. Each sensor may be capable of monitoring, sensing, and collecting data based on various attributes, characteristics, occurrences, or measurements from different angles, positions, proximity, placement, or arrangements present in, or directed at, its subject, which may be the joint tissue, the surrounding environment, the result of an action or interaction, an individual system or device or collection thereof, and any other advantageous source or set of sources associated therewith. The sensor may be completely self-contained or may require additional devices, services, platforms, or conditions to interface, configure, or operate properly.

[0029] Selected sensors may include those based on Raman spectroscopy, spectral imaging, hyperspectral imaging, optical imaging, thermal imaging, fluorescence spectroscopy, microscopy, acoustics, 3D metrology, optical coherence tomography, movement, balance, laser power, and any other single, combination, or sequence of sensing modalities that may contribute data during surgery.

[0030] The sensed attributes may include tissue composition, hydration, density, necrosis, discoloration, reflectance, thermal consistency, and any other single, combination, or sequence of attributes that can be used to describe a condition or class.

[0031] In one embodiment, sensing may occur transparently during surgery as the surgeon performs at least one act of the task. The sensing process may pause, omit, or otherwise ignore sensed data in scenarios where any obstruction occurs that results in a change to viable sensing conditions, which may include obscuration of the sensor by personnel, excessive light or noise, undesirable movement of the subject, and any other single, combination, or sequence of adverse sensing conditions.

[0032] In another embodiment, sensing may interrupt the natural progression of the surgical procedure for a predetermined or intraoperatively calculated duration to provide an environment beneficial to the sensing procedure. This interruption may include changes to the surgical environment, which may include temporary removal of personnel, lighting modifications or dimming, surrounding alterations, repositioning of the subject, and any other single, combination, or sequence of environmental changes.

[0033] In one embodiment, sensed data may be interpreted based on the individual sensor that provided it, without regard to other sensors that may surround it or operate in conjunction with it.

[0034] In another embodiment, the sensed data may be interpreted based on a set or sets of systems or sensors whose inclusion may be coincident or defined by any other single, combination, or sequence of attributes, similarities, conditions, states, and grouping factors.

[0035] In another embodiment, sensed data interpreted based on a collection of sensors may be compiled to provide increasingly accurate information, used as a fault tolerance measure to determine operational efficiency, or any other single, combination, or sequence of methods may be performed where coordination of the sensors involved may be beneficial.

[0036] In further embodiments, interpretation of sensed data from a single, system, set, or multiple sets of sensors may occur regardless of or in relation to environmental or internal conditions and physical sensor arrangements, which may include temperature, humidity, pressure, variable amounts of illumination and its orientation, different positions, angles, proximity or placement, and any other single, combination, or sequence of contributing factors.

[0037] In another aspect, the present invention provides a method for pre-processing the sensed data into at least one different sequential form that can increase its usability. A preferred method includes cleaning the data to remove noise and redundancy, changing the format or arrangement of the data, and sampling the data to isolate portions or areas that can be considered useful.

[0038] The sensed data is provided by a selection of sensors, the form of which depends on those sensors, and may include wavelengths, signals, arbitrary numbers, equations, coordinates, models, or any other single, combination, or sequence of directly or indirectly interpretable data forms.

[0039] Pre-processing of the sensed data may involve a variety of different, similar, or identical methods, in the same or alternating order, to produce a single or multiple sequential forms that lead to the final form. Some algorithms or methods may not be available for every form of data or sensor type, but this may vary, subject to appropriate modifications. Each individual form may produce advantages, and the intent of the sequential transformation is not necessarily only to result in the final form.

[0040] In one embodiment, large sections or sets of data may be removed whose added value may not significantly affect the conclusions drawn from the remaining data, or which are incorrect or erroneous. This may include data where the event of interest or an aspect that may support it does not occur, consists of anomalous values, or is any other single one, combination, or sequence of conditions where extracting utility is impractical or negligible. For example, audio samples may be trimmed to remove sections that are silent.

[0041] In another embodiment, sets or series of data corresponding to identical, similar, or different events with structural similarity may be averaged or otherwise combined to outline portions or areas where variation may exist, including noise or erroneous data, which can then be removed from either the single or combined set or series of data.

[0042] In further embodiments, similar data that may have little value individually may be collated or combined into single or multiple representative sets of data to reduce the sheer volume of data without significantly affecting any conclusions drawn.

[0043] In one embodiment, the format, form, or structure of the data may be rearranged, altered, or changed through a process that may include steps of flattening the data and changing the locations or relationships between specific or ordered values ​​to generate additional or alternative utilities.

[0044] In one embodiment, the data may be sampled to extract areas or portions deemed more advantageous, or to create a series or set of data samples that can be processed or manipulated separately for purposes such as cross-validation and testing.

[0045] In another aspect, the present invention provides a method for manipulating the preprocessed data into at least one different sequential form that can increase its assessability. A preferred method includes the steps of normalizing the preprocessed data and restricting it to a comparable range, decomposing the data and defining its constituent elements, performing fractional abundance estimation of these elements, and aggregating them into entities of significant utility.

[0046] Manipulation of the pre-processed data may involve a variety of different, similar, or identical methods, in the same or alternating order, to produce a single or multiple sequential forms that lead to the final form. Some algorithms or methods may not be available for every form of data or sensor type, but this may vary, subject to appropriate modifications. Each individual form may produce advantages, and the intent of the sequential transformation is not necessarily only to result in the final form.

[0047] Component elements represent individual or grouped components present in the original data. The number and type of component elements generated depends on the data format, any previously performed processing methods, the situation or environment in which the sensing occurred, and any other single, combination, or sequence of conditions that may result in multiple components being present in the data. Component elements of articular tissues would typically include cancellous bone, cortical bone, cartilage, fat, ligament, muscle, or meniscus. Additional component elements may exist as differentiations of these, which may include composition, hydration, density, necrosis, reflectance, temperature, and any other single, combination, or sequence of elements that may potentially describe the condition of articular tissues.

[0048] Fractional abundance represents the presence of a particular single or combination of constituent elements in the data. This abundance or relative amount is dependent on the method, circumstances, environment, and any other single, combination, or sequence of conditions that lead to or influence the extraction of the associated constituent element.

[0049] In one embodiment, the data may be normalized through algorithms and methods such as constant shifting, smoothing, scaling, standard normal variate, baseline correction, continuum removal, or any other single, combination, or sequence of algorithms and methods capable of improving data consistency.

[0050] In one embodiment, the data may be decomposed or deconvolved into its component elements or features, which may be accomplished through algorithms and methods including an automatic target generation process, pixel purity index, N-FINDR, matched filtering, independent component analysis, nonlinear least squares, fuzzy k-means, and any other single, combination, or sequence of algorithms and methods capable of decomposition. Some of these methods or algorithms may not be possible without potential modification, depending on the form of the data provided and its purpose.

[0051] In another embodiment, constituent elements may be identified prior to initiating the extraction to determine content that may be present in the data and any directives that may aid in its extraction.

[0052] In another embodiment, the constituent elements of a series or set may be averaged or combined in a beneficial manner, provided they share or do not share any similar patterns or other elements that may be used as a means of grouping. This may occur when the number of constituent elements exceeds the expected number.

[0053] In further embodiments, the decomposition may include data dimension reduction to reduce complexity and computational burden, which may be performed through algorithms and methods including decision trees, random forests, highly correlated filters, backward feature elimination, factor analysis, principal component analysis, linear discriminant analysis, generalized discriminant analysis, and any other single, combination, or sequence of algorithms and methods capable of removing dimension or otherwise assisting in the process.

[0054] In one embodiment, fractional abundance estimates may be calculated through algorithms and methods such as unconstrained least squares, non-negative constrained least squares, fully constrained least squares, fuzzy k-means, and any other single, combination, or sequence of algorithms or methods capable of estimating fractional abundances or otherwise assisting in the process.

[0055] In another embodiment, portions or areas of fractional abundance estimation that are advantageous, beneficial, or provide alternative utility may be isolated.

[0056] In further embodiments, the separation may be focused on areas where the series or sets of fractional abundances differ by a large or meaningful degree, which may provide advantages or additional utility to subsequent machine learning, data science, and mathematical algorithms or methods.

[0057] In one embodiment, representative, component, or otherwise single set of data, elements, or features may be aggregated together into a single entity or fewer entities that may be more easily processed while maintaining similar or increased usefulness.

[0058] In another aspect, the present invention provides a method for the preparation and execution phase of machine learning, data science, and mathematical algorithms and methods. A preferred method includes using the collated processed data to train, in a supervised manner, a plurality of machine learning, data science, and mathematical algorithms or methods, which can then be provided with the raw processed data and generate corresponding outputs based on this training.

[0059] The data used may be processed to ensure that it is in a form that is conducive to increased usefulness when used in conjunction with a machine learning, data science, or mathematical algorithm or method. The form may depend on the initial state of the sensed data, the algorithm or method tailored, and the intent behind its use. This may be defined as data that has been normalized and cleaned to contain only processed or representative portions of the original dataset that will be beneficial to a particular machine learning, data science, or mathematical algorithm or method as defined in the previous aspect.

[0060] Some processed data may be collated such that its intended output according to a machine learning, data science, or mathematical algorithm or method has already been determined and confirmed through external means.

[0061] The machine learning, data science, and mathematical algorithms or methods may be based on supervised approaches. These algorithms or methods may include linear and polynomial regression, logistic regression, naive Bayes networks, Bayes networks, support vector machines, decision trees, random forests, k-nearest neighbor classifiers, neural networks, and any other single, combination, or sequence of supervised approaches.

[0062] In one embodiment, the collated processed data pool is split into at least two splits of different purpose, the split not necessarily being uniform or proportional.

[0063] In another embodiment, the split collated processed data single or set may be provided to single or multiple machine learning, data science, or mathematical algorithms or methods in a sequential, simultaneous, or cyclical manner.

[0064] In one embodiment, a single one or set of all or a portion of the remaining split collated processed data may be provided to a previously trained machine learning, data science, or mathematical algorithm or method to measure the accuracy of its corresponding output against externally confirmed outputs.

[0065] In another embodiment, the accuracy of a particular trained machine learning, data science, or mathematical algorithm or method may be deemed sufficient depending on its statistical significance, which may be determined or influenced by the application of its prediction or inference.

[0066] In further embodiments, if accuracy does not prove sufficient, the selected collated data, its input procedures, single or multiple machine learning, data science or mathematical algorithms or methods, or any other single, combination, or sequence of causal relationships may be modified, removed, rearranged, or added, potentially resulting in increased accuracy.

[0067] In one embodiment, the raw, processed data may be provided to a single or set of trained machine learning, data science, or mathematical algorithms or methods to generate a corresponding output.

[0068] In another embodiment, corresponding outputs from at least two machine learning, data science, or mathematical algorithms or methods may be averaged, combined, or compared, potentially to arrive at an increasingly conclusive conclusion.

[0069] According to an aspect of the invention, there is provided a method for intraoperative status analysis and classification of joint tissue, comprising the steps of: Sensing data of the joint tissue via a plurality of sensors mounted proximate to the joint tissue; determining status analysis and classification information through a matching means; processing the sensed data into a form adapted to be evaluated against a comparator; Utilizing a historical data set of processed information to generate a predictive condition analysis and classification means; and using the generated means to perform a condition analysis and classification based on the processed stimuli provided intraoperatively. A method is provided that includes:

[0070] A sensor may comprise at least one sensor, which may exist independently or as part of a sensor system or set of sensors. A sensor may be completely self-contained or may require additional devices, services, conditions, platforms, or any other single, combination, or sequence of requirements to be appropriately interfaced, configured, or operated. An individual sensor may be capable of monitoring, sensing, and collecting data based on any other single, combination, or sequence of various properties, characteristics, occurrences, measurements, or features. This may be done from any other single, combination, or sequence of different angles, positions, proximity, nearness, movement, speed, placement, arrangement, or settings with, in, or oriented by its subject.

[0071] The object may be an articular tissue, a surrounding environment, a result of an action or interaction, an individual system or device or a collection thereof, and any other advantageous source or series of sources associated therewith. The object may be treated through any possible method to affect its original, initial, or current state for the purpose of preservation, identification, unification, fixation, or any other single, combination, or sequence of status alteration. The object may be modified structurally, chemically, or through any other single, combination, or sequence of approaches that may change its form as part of, or independently of, any intraoperative procedure, surgical procedure, or any other single, combination, or sequence of medical procedures.

[0072] The sensors may operate to provide data based on each individual sensor or sensor type, a group of sensors or sensor types, a positioning of the sensors or sensor types, an angle of the sensors or sensor types, a proximity of the sensors or sensor types, or any other single, combination, or sequence of configurations or arrangements that may provide an advantageous combination of data that may be analyzed independently or collectively. The sensors may be run in an automated manner, through a manual trigger, or through any combination or sequence of the two. Each sensor does not necessarily have the same control scheme, and any number of control schemes are applicable to any number of sensors.

[0073] A manual trigger involves any form of non-automated trigger, which may include a button, a voice command, a gesture control, any form of physical actuation, and any other single, combination, or sequence of manual control.

[0074] The sensors may engage in sensing indefinitely, periodically, once, or in any other single, combination, or sequence of sensing approaches that can be influenced by conditions, environment, user control, sensor configuration, and any other single, combination, or sequence of variables that can have a direct or indirect effect.

[0075] Sensing may operate in real time, near real time, through some form of delayed processing, or in any other single, combination, or sequence of processing approaches that can be influenced by conditions, environment, user control, sensor configuration, and any other single, combination, or sequence of variables that can have a direct or indirect effect.

[0076] A sensor may require external intervention to operate correctly, which may include changes to its position, angle, proximity, proximity, configuration, illumination, timing, or any other single, combination, or sequence of sensor, situation, or environmental changes.

[0077] The data or other information may be provided by a collated person, database, system, or any other single, combination, or sequence of internal or external sources that may have been collated and verified.

[0078] Condition analysis refers to the state of the joint tissue, including composition, hydration, density, necrosis, discoloration, reflectance, thermal consistency, and any other properties or characteristics that can be used to describe the condition.

[0079] The classification refers to the type of joint tissue, which may include cancellous bone, cortical bone, cartilage, fat, ligaments, muscles, menisci, and any other joint tissue type, among other possible types.

[0080] Matching means may include expert surgical pronouncements, single or multiple post-operative matching techniques, and any other single, combination, or sequence of forms of matching deemed to have an appropriate level of accuracy. Matching may be supported by medical records and medical history, ancestry, genetic factors, the subject's typical lifestyle and environment, and any other single, combination, or sequence of factors for which conclusions may not be directly derivable but may be used to support their applicability.

[0081] The level of accuracy appropriate for any particular match may depend on the technique used, the subject on which it is used, the personnel applying the technique, the environment or circumstances in which the technique occurs, the information derived from the technique, the amount of time the technique is repeated, the amount of information or data supporting the technique, the amount of similar or different techniques used in concert, and any other single, combination, or sequence of contributing factors.

[0082] Processing the sensed data involves at least one act of operation related to transforming the sensed data into an evaluable form. Transforming data may include at least one act of operation involving a single, multiple, combination, or sequence of pre-processing steps.

[0083] Pre-processing steps may include cleaning the data, including removing or repairing any noisy, erroneous, or redundant data, and any other single, combination, or sequence of processes that may remove unnecessary data or increase the overall usefulness of the remaining data. Pre-processing steps may include formatting the data, including rearranging the data into a more appropriate structure or form, flattening the data or extracting it from its current storage, and any other single, combination, or sequence of formatting that may increase the usability of the data. Pre-processing steps may include sampling the data, including selecting or partitioning a portion of the data, or any other single, combination, or sequence of processes that may result in more representative or advantageous data.

[0084] Transforming data may include at least one act of manipulation involving a single, multiple, combination, or sequence of raw or preprocessed data manipulations. Manipulation of raw or preprocessed data may include normalization, scaling, or alignment of the data so that it is within a comparable range or may achieve some additional level of intercomparability. Manipulation of raw or preprocessed data may include decomposition or deconvolution of the data so that representative or otherwise specific features or portions of the data may be split into constituent elements or elements that individually provide more utility. Manipulation of the raw or preprocessed data may include estimation of fractional abundance based on constituent elements identified in the deconvoluted data. Manipulation of the raw or preprocessed data may include aggregation of the data so that individual features, constituent elements, segments, or portions of the data may be combined into a single entity.

[0085] Transformation of data may include at least one act of operation associated with any other single, combination, or sequence of any other functions, techniques, or approaches that may better prepare the data for processing, manipulation, generation, modification, or use.

[0086] Processing of the sensed data may not be required or may be partially performed if additional entities, such as a sensor controller or bridge device, perform this processing individually or independently.

[0087] The order or presence of the data pre-processing and manipulation processes may not be reflective of the order herein.

[0088] A comparator is a set of data, in a similar or otherwise comparable form, pertaining to a single, combination, or sequence of joint tissues.

[0089] The generation of a means for performing tissue condition analysis and classification may include at least one act of operation involving the training or construction of machine learning, data science, mathematical or computational entities, concepts, models, equations, or any other single, combination, or sequence of embodiments.

[0090] Training refers to the provision of data to a machine learning, data science, mathematical or computational entity, concept, model, equation, or any other single, combination, or sequence of embodiments in which the data is created, captured, transformed, extended, calculated, or otherwise involved in any preliminary or preparatory phase required to establish the functionality of the embodiment.

[0091] The historical dataset of processed data may include data that has been previously processed at any prior point in time by any single one, combination, or sequence of measures that are compatible with the predictive measures and may be used during their occurrence.

[0092] The data present in the historical dataset may come from a single, multiple, collection, or sequence of sensors used, may be provided externally through collatable specialty personnel, prior medical records and medical history, ancestry, the patient's lifestyle, and the intended environment, or may be retrieved from accurate and well-tested data sources, previously discovered relationships, and any other single, combination, or sequence of sources from any period of time that may provide usable or supporting data.

[0093] Construct refers to at least one act of work that involves predicting, generating, calculating, verifying, verifying, or developing a simulation or other entity that may be used in any other single, combination, or sequence of use related to machine learning, data science, mathematical or computational entities, concepts, models, equations, or any other single, combination, or sequence of embodiments.

[0094] Any other single, combination, or sequence of trained machine learning, data science, mathematical or computational entities, concepts, models, equations, or embodiments may predict tissue state, tissue classification, or both, to varying degrees of accuracy, either independently, in collaboration with other embodiments, as part of a set, or through any other form of collective or collaborative setting.

[0095] Methods for intraoperative joint tissue condition analysis and classification include spectral or hyperspectral analysis.

[0096] A spectral or hyperspectral sensor may include any single or combination of potentially available bands within the entire electromagnetic spectrum.

[0097] Additional light sources may be involved to extend or refine the spectral or hyperspectral analysis, which may include UV, visible, infrared, and any other single, combination, or sequence of light sources.

[0098] Pre-processing steps may include removal of any noisy, redundant, or erroneous data, rearrangement or formatting of the data into a more appropriate structure or form, conditioning or normalization of the data, sampling of the data to extract more representative or useful portions or segments, and any other single, combination, or sequence of steps that may provide useful or alternative utility.

[0099] The manipulation of the raw or pre-processed spectral data may include at least one act of an operation relating to the decomposition of the spectral data.

[0100] Decomposition of the spectral data may include dimensionality reduction, which may involve techniques such as principal component analysis, linear discriminant analysis, quadratic discriminant analysis, and any other single, combination, or sequence of techniques that may reduce dimensionality.

[0101] Decomposition of spectral data may include at least one act of operation related to deconvolution, endmember determination, or disaggregation of various spectra within the spectral data into several spectral signatures or other forms of identifiable data belonging to individual or groups of endmembers that make up the original spectral data.

[0102] Decomposition of the spectral data may include at least one act of operations related to deconvoluting spectral signatures and inversion of their original spectra to estimate the fractional abundance of each endmember in the spectrum or spectral data.

[0103] Manipulation of raw or preprocessed spectral data may include at least one act of operation relating to outlining sections, areas, or portions of the spectral data or derivatives where various wavelengths, measurements, or other information differ from one another to a degree that is deemed useful.

[0104] The method for intraoperative joint tissue condition analysis and classification includes acoustic analysis. The acoustic sensor may have any possible sampling rate, including human perceptible, ultrasonic, and any other single, combination, or sequence in range. The acoustic signal may be generated by any object or actuator capable of making sound, independently, through contact with another entity, or through any other single, combination, or sequence of actions or functions.

[0105] Pre-processing steps may include removal of any noisy, redundant, or erroneous data, rearrangement or formatting of the data into a more appropriate structure or form, conditioning or normalization of the data, sampling of the data to extract more representative or useful portions or segments, and any other single, combination, or sequence of steps that may provide useful or alternative utility.

[0106] The manipulation of the raw or pre-processed acoustic data may include at least one act of an operation relating to the decomposition of the acoustic data.

[0107] Decomposition of the acoustic data may include dimensionality reduction, which may involve techniques such as principal component analysis, linear discriminant analysis, quadratic discriminant analysis, and any other single, combination, or sequence of techniques that may reduce dimensionality.

[0108] Decomposition of acoustic data may include at least one act of operation related to deconvolution, endmember determination, or disaggregation of the acoustic signal or data into some set of frequencies, amplitudes, or any other single, combination, or sequence of identifiable aspects belonging to individuals or groups of sources that make up the original acoustic data.

[0109] Decomposition of acoustic data may include at least one act of operation related to the decomposed acoustic signal and the inversion of its original signal to estimate the fractional abundance of each endmember within the acoustic signal or data.

[0110] Manipulation of raw or preprocessed acoustic data may include at least one act of operation relating to outlining sections, areas, or portions of the acoustic data or derivatives in which various frequencies, amplitudes, measurements, or other information differ from one another to an extent that is deemed useful.

[0111] The step of performing the condition analysis and classification may involve the execution of a previously generated or constructed measure of prediction and may involve at least one act of work related to its preparation or initialization.

[0112] The previously generated means may include any other single, combination, or sequence of machine learning, data science, mathematical or computational entities, concepts, models, equations, or embodiments.

[0113] The step of performing the condition analysis and classification may involve the performance of at least one act of operation involving the use of at least one simulation or other entity that may be used in conjunction with, or as an adjunct to, machine learning, data science, mathematical or computational entities, concepts, models, equations, or any other single, combination, or sequence of embodiments.

[0114] Any other single, combination, or sequence of sensed, raw, preprocessed, manipulated, interpreted, processed, usable, evaluable, or generated, derived, or received data may be electronically stored, which may be done offline, online, or through some combination of the two, for later retrieval, processing, or use in any other form.

[0115] Any processing or storage required may occur internally within a custom or general-purpose system, externally on a centralized, decentralized, or otherwise online entity, or in any other single, combination, or sequence of computational approaches.

[0116] At least one act of the operation may occur within an intraoperative environment. At least one act of the operation may occur in the same, different, or alternating sequences and may produce the same, similar, or different end results. At least one act of the operation may occur in real-time, near real-time, through some form of delayed processing, or in any other single, combination, or sequence of processing approaches. The present invention provides, for example, the following: (Item 1) 1. A method for intraoperative status analysis and classification of joint tissue, comprising: sensing data about the articular tissue via a plurality of sensors mounted proximate to the articular tissue; determining status analysis and classification information through a matching means; processing the sensed data into a form adapted to be evaluated against a comparator; utilizing a historical data set of the processed information to generate a predictive condition analysis and classification; performing condition analysis and classification using said generated means based on the processed stimuli provided intraoperatively; A method comprising: (Item 2) Item 10. The method of item 1, wherein the sensor comprises at least one sensor that exists independently or as part of a sensor system or set of sensors. (Item 3) 3. The method of any of claims 1 or 2, wherein the sensor is fully self-contained or requires additional devices, services, conditions, or platforms. (Item 4) The method of any of items 2 or 3, wherein the individual sensors are configured to monitor, sense, and collect data based on various properties, characteristics, occurrences, measurements, or combinations thereof. (Item 5) 5. The method of claim 4, wherein the monitoring, sensing, and collecting of data is performed from different angles, positions, proximity, nearness, movement, speed, placement, arrangement, or combinations thereof with, within, or directed by an object. (Item 6) The method of claim 4, wherein the subject comprises a joint tissue, a surrounding environment, a result of an action or interaction, an individual system or device, or a collection thereof. (Item 7) 7. The method according to item 6, wherein the subject is treated through a predetermined surgical procedure for preserving, identifying, unifying, fixing, or a combination thereof, adapted to affect its original, initial, or current condition. (Item 8) The method of claim 6, wherein the object is adapted to be structurally, chemically modified or configured to change its morphology as part of, or independently of, an intraoperative procedure, surgical procedure, or medical procedure combination or sequence. (Item 9) 9. The method of any one of claims 2-8, wherein the plurality of sensors are configured to provide data based on each individual sensor or sensor type, a group of sensors or sensor types, a positioning of the sensors or sensor types, an angle of the sensors or sensor types, a proximity of the sensors or sensor types, or a combination thereof, and to operate independently or collectively to provide an advantageous combination of data to be analyzed. (Item 10) 9. The method of claim 8, wherein each of the plurality of sensors is configured to operate in an automated manner, through a manual trigger, or through a combination or sequence of the two. (Item 11) Item 11. The method of item 10, wherein each of the plurality of sensors is provided with a control scheme, and a selected control scheme is applicable to a selected sensor. (Item 12) Item 12. The method of item 11, wherein the manual trigger comprises a non-automated trigger, the trigger comprising a button, a voice command, a gesture control, or a combination or sequence of manual control. (Item 13) Item 11. The method of item 10, wherein the plurality of sensors are configured to sense indefinitely, periodically, once, or a combination thereof, and the sensing is adapted to a situation, an environment, a user control, a combination of sensor configurations, or a sequence of variables that can have a direct or indirect effect. (Item 14) Item 14. The method of item 13, wherein the sensing is configured for sensing in real time, near real time, through some form of delayed processing, or in other combinations or sequences of processing approaches adapted to the situation, environment, user control, sensor configuration, and any other single one, combination, or sequence of variables that can have a direct or indirect effect. (Item 15) 10. The method of claim 9, wherein the plurality of sensors are configured to receive external intervention for correct operation including changes to their position, angle, proximity, proximity, configuration, illumination, timing, or any single, combination, or sequence of sensor, situation, or environmental changes. (Item 16) The method of any one of the preceding claims, wherein the data or other information is provided by a collated person, database, system, or another single, combination, or sequence of internal or external sources that have been collated and verified. (Item 17) Item 11. The method of any one of the preceding items, wherein the condition analysis includes the condition of the joint tissue including composition, degree of hydration, density, necrosis, discoloration, reflectance, thermal consistency, and any other property or characteristic adapted to be used to describe the condition. (Item 18) Said classification includes, among other possible types: cancellous bone, cortical bone, cartilage, fat, ligament, muscle, Meniscus, or Other joint tissue types The method of any one of the preceding claims, comprising a joint tissue type comprising one or more of: (Item 19) The collation is Expert surgical representation, Single or multiple postoperative matching techniques, or A single, combination, or sequence of forms of matching that is deemed to have an appropriate level of accuracy The method of any one of the preceding items, comprising one or more of the following: (Item 20) 20. The method of claim 19, wherein the matching is adapted to be supported by medical records and medical history, ancestry, genetic factors, the subject's typical lifestyle and environment, and a combination or sequence of factors where a conclusion is not directly derivable but is adapted to support a directly derivable conclusion. (Item 21) 20. The method of claim 19, wherein the level of accuracy appropriate for any particular match depends on one or more of the technique used, the subject on which the technique is used, the personnel applying the technique, the environment or situation in which the technique occurs, the information derived from the technique, the amount of time the technique is repeated, the amount of information or data supporting the technique, the amount of similar or different techniques used in concert, and / or another single, combination, or sequence of triggering factors. (Item 22) 2. The method of any one of the preceding claims, wherein processing the sensed data includes at least one act of an operation related to converting the sensed data into an evaluable form. (Item 23) 23. The method of claim 22, wherein the transformation of the data comprises at least one act of performing an operation involving a single, a plurality, a combination, or a sequence of pre-processing steps. (Item 24) 24. The method of claim 23, wherein the pre-processing step includes cleaning the data including removing or repairing noisy, erroneous or redundant data, and another single, combination or sequence of processes that removes unnecessary data or increases the overall usefulness of the remaining data. (Item 25) 24. The method of claim 23, wherein the pre-processing step includes formatting the data including rearranging the data into a more appropriate structure or form, flattening the data or extracting it from its current storage device, and any other single, combination, or sequence of formatting to increase the usability of the data. (Item 26) 24. The method of claim 23, wherein the pre-processing step comprises sampling the data including selecting or partitioning a portion of the data, or any other single, combination, or sequence of processes that results in more representative or advantageous data. (Item 27) 23. The method of claim 22, wherein the transformation of the data comprises at least one act of performing an operation involving a single, a plurality, a combination, or a sequence of raw or pre-processed data manipulations. (Item 28) 24. The method of claim 23, wherein the manipulation of the raw or preprocessed data includes normalizing, scaling, or aligning the data to place the data within a comparable range or level of additive intercomparability. (Item 29) 28. The method of claim 27, wherein the manipulation of the raw or preprocessed data includes decomposing or deconvolving the data such that representative or otherwise specific features or portions of the data are adapted to be split into component elements or elements that individually provide increased usefulness. (Item 30) 30. The method of claims 27 and 29, wherein the manipulation of the raw or preprocessed data includes estimating fractional abundances based on components identified in the deconvoluted data. (Item 31) 26. The method of claim 25, wherein the manipulation of the raw or pre-processed data includes aggregating the data such that individual features, components, segments, or portions of the data are adapted to be combined into a single entity. (Item 32) 23. The method of claim 22, wherein the transformation of the data includes at least one act of processing, manipulation, generation, modification, or operation involving a combination or sequence of other functions, techniques, or approaches adapted to prepare the data for use. (Item 33) 23. The method according to claim 22, wherein the processing of the sensed data is not required or is performed in part if an additional entity, such as a sensor controller or a bridge device, performs this processing individually or independently. (Item 34) 34. The method according to any one of items 22-33, wherein the order or presence of the data pre-processing and manipulation processes does not reflect the order herein. (Item 35) 2. The method of any one of the preceding claims, wherein the comparator comprises sets of data in similar or otherwise comparable form belonging to single ones, combinations or sequences of joint tissues. (Item 36) 2. The method of any one of the preceding claims, wherein the generation of the means for performing the tissue condition analysis and classification comprises at least one act of machine learning, data science, operations involving the training or construction of mathematical or computational entities, concepts, models, equations, or combinations or sequences thereof. (Item 37) 38. The method of claim 36, wherein the training includes providing data to a machine learning, data science, mathematical or computational entity, concept, model, equation, or another single, combination, or sequence of embodiments in which the data is created, captured, transformed, augmented, calculated, or otherwise adapted to participate in a preliminary or preparatory phase. 2. The method of claim 1, wherein the historical dataset of processed data comprises data that has been previously processed by a single, combination or sequence of measures that are compatible with and adapted to the occurrence of the predictive measures. (Item 39) The data present in the historical data set includes: the single, multiple, set or sequence of sensors used; provided externally through collatable specialist personnel, previous medical records and medical history, pedigree, the patient's lifestyle and intended environment; Accurate and well-tested data sources, derived from previously discovered relationships, Another single, combination, or sequence of sources from a period that is adapted to provide usable or supporting data 39. The method according to claim 38, wherein the compound is derived from at least one of the following: (Item 40) 37. The method of claim 36, wherein the constructing includes at least one act of predicting, generating, calculating, verifying, verifying, or working with machine learning, data science, mathematical or computational entities, concepts, models, equations, or simulations or other entities used in another single, combination, or sequence of uses related to another single, combination, or sequence of embodiments. (Item 41) 37. The method of claim 36, wherein the trained machine learning, data science, mathematical or computational entities, concepts, models, equations, or other single, combination, or sequence of embodiments is configured to predict tissue state, tissue classification, or both, to varying degrees of accuracy, either independently, in cooperation with other embodiments, as part of a set, or through some form of a collective or collaborative setting. (Item 42) 42. The method according to any one of items 22-41, wherein the method for intraoperative joint tissue status analysis and classification comprises spectral or hyperspectral analysis. (Item 43) 43. The method of claim 42, wherein the spectral or hyperspectral sensor comprises one or a combination of the possible bands available within the electromagnetic spectrum. (Item 44) 41. The method of claim 40, further comprising providing an additional light source for extending or adjusting the spectral or hyperspectral analysis, the light source comprising at least one or more of UV, visible, infrared, or a combination or sequence thereof. (Item 45) The pre-processing step is Removal of noisy, redundant or erroneous data; rearrange or format the data into a more appropriate structure or form; Adjustment or normalization of data; Sampling of data to extract a more representative or useful portion or segment; and Another single entity, combination, or sequence of steps that is adapted to provide a beneficial or alternative utility The method according to any one of the preceding items, comprising at least one of the following: (Item 46) 2. The method of claim 1, wherein the manipulation of the raw or pre-processed spectral data comprises at least one operation relating to decomposition of the spectral data. (Item 47) The decomposition of the spectral data may include principal component analysis, Linear discriminant analysis, Quadratic discriminant analysis, or Another single, combination, or sequence of techniques adapted for data dimensionality reduction Item 47. The method of item 46, comprising dimensionality reduction comprising techniques selected from one or more of: (Item 48) 48. The method of claim 46 or 47, wherein the decomposition of the spectral data comprises at least one operation related to deconvolution of various spectra within the spectral data, endmember determination, or other form of identifiable data belonging to individual or groups of endmembers constituting the original spectral data. (Item 49) 49. The method of any of claims 46 or 48, wherein the decomposition of the spectral data comprises at least one operation involving deconvoluting a spectral signature and inverting its original spectrum to estimate the fractional abundance of each endmember in the spectrum or spectral data. (Item 50) The method according to any one of the preceding claims, wherein the manipulation of the raw or pre-processed spectral data comprises at least one act of operation relating to outlining sections, areas or portions of the spectral data or derivatives in which various wavelengths, measurements or other information differ from one another by a predetermined degree. (Item 51) 2. The method of any one of the preceding claims, wherein the method for intraoperative joint tissue status analysis and classification comprises acoustic analysis. (Item 52) Item 52. The method of item 51, wherein the acoustic sensor includes a sampling rate. (Item 53) 52. The method of claim 51, wherein the acoustic signal is generated by an object or actuator capable of producing sound, independently or through contact with another entity. (Item 54) The pre-processing step is Removal of noisy, redundant or erroneous data; Re-arrangement or formatting of data into a more appropriate structure or form; Adjustment or normalization of the data; Sampling of data to extract more representative or useful portions or segments The method according to any one of the preceding items, comprising: (Item 55) 2. The method of claim 1, wherein the manipulation of the raw or pre-processed acoustic data comprises at least one operation relating to decomposition of the acoustic data. (Item 56) The decomposition of the acoustic data includes: principal component analysis, Linear discriminant analysis, or Quadratic discriminant analysis 56. The method of claim 55, comprising dimensionality reduction comprising one or more techniques including: (Item 57) 57. The method of claim 55 or 56, wherein the decomposition of the acoustic data comprises at least one operation related to deconvolution, endmember determination, or disaggregation of the acoustic signal or data into a set of frequencies, amplitudes, or combinations or sequences of identifiable aspects belonging to individual or groups of sound sources constituting the original acoustic data. (Item 58) 58. The method of any one of claims 55-57, wherein the decomposition of the acoustic data comprises at least one operation relating to the inversion of the decomposed acoustic signal and its original signal to estimate the fractional abundance of each endmember in the acoustic signal or data. (Item 59) A method according to any one of the preceding claims, wherein the manipulation of the raw or pre-processed acoustic data includes at least one act of operation relating to outlining sections, areas or portions of the acoustic data or derivatives in which various frequencies, amplitudes, measurements or other information differ from one another by a predetermined degree. (Item 60) 2. The method according to claim 1, wherein the step of performing the condition analysis and classification includes the execution of a previously generated or constructed means of prediction and includes at least one action of work related to its preparation or initialization. (Item 61) 61. The method of claim 60, wherein the previously generated means comprises another single, combination, or sequence of machine learning, data science, mathematical or computational entities, concepts, models, equations, or embodiments. (Item 62) The method of any one of the preceding items, wherein the step of performing the condition analysis and classification comprises performing at least one act of prediction, generation, calculation, verification, validation, or use of at least one simulation or other entity adapted for use in conjunction with or as an adjunct to another single, combination, or sequence of machine learning, data science, mathematical or computational entities, concepts, models, equations, or combinations thereof. (Item 63) The method of any one of the preceding items, wherein the sensed, raw, pre-processed, manipulated, interpreted, processed, usable, evaluable, or another single, combination, or sequence of generated, derived, or received data is adapted to be electronically stored, the electronic storage being either offline, online, or a combination thereof, for later retrieval, processing, or use of the sequence in any form. (Item 64) The method of any one of the preceding items, wherein the required processing or storage is configured to occur internally within a custom or general-purpose system, externally on a centralized, decentralized, or otherwise online entity, or in a combination thereof in a sequence of computational approaches. (Item 65) 2. The method of any one of the preceding claims, comprising at least one effect of an operation occurring within an intraoperative environment. (Item 66) 2. The method of any one of the preceding claims, comprising at least one action of operations occurring in the same, different or alternating sequence and adapted to produce the same, similar or different end result. (Item 67) 13. The method of any one of the preceding claims, comprising at least one act of operation occurring through real-time, near real-time, delayed processing, or in a combination or sequence of processing approaches. [Brief description of the drawings]

[0117] Notwithstanding any other forms which may fall within the scope of the present invention, preferred embodiments of the present invention will now be described, by way of example only, with reference to the accompanying drawings, in which: [Figure 1] FIG. 1 is an abstract schematic flow diagram depicting the intraoperative tissue type and composition analysis process, including the steps required for the complete implementation of a preferred embodiment. [Diagram 2]FIG. 2 is a detailed schematic flow diagram depicting the data sources and associated procedures involved in the collection and accessibility of data as introduced in the exemplary data collection steps in FIG. [Diagram 3] FIG. 3 is a detailed schematic flow diagram depicting the pre-processing and manipulations required to transform the data into a more assessable form for further use within predictive algorithms and methods as introduced in the exemplary data processing steps in FIG. [Figure 4] FIG. 4 is a detailed schematic flow diagram depicting a type of predictive algorithm or method that is capable of generating information and properties related to tissue type and composition based on existing processed data as introduced in the exemplary data interpretation step in FIG. [Diagram 5] FIG. 5 generally illustrates a basic sensing system and a sample intraoperative environment in which it may be used. [Figure 5A] FIG. 5A generally illustrates a hyperspectral sensing system of the system in FIG. 5 that collects object-based spectral data. [Figure 5B] FIG. 5B generally illustrates an acoustic sensing system of the system in FIG. 5 that collects object-based acoustic data. [Figure 6] FIG. 6 illustrates a computing device upon which various embodiments described herein may be implemented, in accordance with an embodiment of the present invention.

[0118] definition The following definitions are provided as general definitions and should not in any way limit the scope of the present invention to only those terms, but are set forth for a better understanding of the following description.

[0119] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by those skilled in the art to which this invention belongs. It is further understood that terms used herein should be interpreted to have a meaning consistent with their meaning in the context of this specification and related art, and will not be interpreted in an idealized or overly formal sense unless expressly so defined herein. For the purposes of this invention, additional terms are defined below. Furthermore, all definitions as defined and used herein should be understood to take precedence over dictionary definitions, definitions in documents incorporated by reference, and / or ordinary meanings of the defined terms, unless there is a doubt as to the meaning of a particular term (in which case the general dictionary definition and / or common usage of the term shall take precedence).

[0120] For purposes of the present invention, the following terms are defined below.

[0121] The articles "a" and "an" are used herein to refer to one or to more than one (i.e., to at least one) of the grammatical object of the article. As an example, "an element" refers to one element or to more than one element.

[0122] The term "about" is used herein to refer to a quantity that varies by about 30%, preferably about 20%, and more preferably about 10% of the reference quantity. The use of the term "about" to modify a number is merely an explicit indication that the number should not be interpreted as an exact value.

[0123] Throughout this specification, unless the context requires otherwise, the words "comprise", "comprises" and "comprising" will be understood to imply the inclusion of a stated step or element or group of steps or elements but not to exclude any other step or element or group of steps or elements.

[0124] As used herein, the terms "including" or "which" Any one of "includes" or "that includes" is also an open-ended term and means the inclusion of at least the element / feature that follows the term but does not exclude others. Thus, "including" is synonymous with and means the same as "comprising."

[0125] In the claims and in the summary above and description below, all transitional phrases such as "comprising," "including," "carrying," "having," "containing," "involving," "holding," "composed of," and the like, are to be understood to be open-ended, i.e., to mean "including but not limited to." Only the transitional phrases "consisting of" and "consisting essentially of" shall be closed or semi-closed transitional phrases, respectively.

[0126] The term "real-time," e.g., "displaying real-time data," refers to the display of data without intentional delay, subject to the processing limitations of the system and the time required to accurately measure the data.

[0127] The term "near-real-time", e.g., "obtaining real-time or near-real-time data", refers to data that is acquired and recorded or transmitted without any intentional delay, whether intentional or not, within the constraints and processing limits of the system for acquiring and recording or transmitting the data ("real-time" or Refers to the acquisition of data either in as close to real time as practical (i.e., with slight, but minimal, delay).

[0128] Although any methods and materials similar or comparable to those described herein can be used in the practice or testing of the present invention, the preferred methods and materials are described. It should be understood that the methods, devices, and systems described herein may be implemented in a variety of ways and for a variety of purposes. The description herein is by way of example only.

[0129] As used herein, the term "exemplary" is used in the sense of providing an example, as opposed to indicating a quality. That is, an "exemplary embodiment" is necessarily an embodiment of exemplary quality. These are embodiments that are provided as examples, as opposed to serving as preferred models or representing the best of their kind.

[0130] The various methods or processes outlined herein may be coded as software executable on one or more processors employing any one of a variety of operating systems or platforms. In addition, such software may be written using any of a number of suitable programming languages ​​and / or programming or scripting tools, and may be compiled as executable machine language code or intermediate code that runs on a framework or virtual machine.

[0131] In this regard, the various concepts of the present invention may be embodied as a single or multiple computer-readable media, which may comprise computer memory, one or more floppy disks, compact disks, optical disks, magnetic tapes, flash memory, circuitry in field programmable gate arrays or other semiconductor devices, or any other non-transitory or tangible computer storage media. These media may be encoded with one or more programs that, when executed on one or more computers or other processors, perform methods that implement the various embodiments of the present invention as discussed above. The computer-readable medium or media may be transportable, such that the program or programs stored thereon may be loaded onto one or more different computers or other processors to implement the various aspects of the present invention as discussed above.

[0132] The term "program" or "software" is used herein in a generic sense to refer to any type of computer code or set of computer-executable instructions that may be employed to program a computer or other processor to implement various aspects of the embodiments as discussed above. In addition, it should be understood that, according to one aspect, one or more computer programs that, when executed, perform the methods of the present invention need not reside on a single computer or processor, but may be distributed in a modular manner among several different computers or processors to implement various aspects of the present invention.

[0133] Computer-executable instructions may exist in various forms, such as program modules, which may be executed by one or more computers or other devices, which may have differing levels of cooperation. Program modules generally include routines, programs, objects, components, data structures, and any other one or more combinations or sequences of components, structures, or executable entities that perform particular tasks, implement specific abstract data types, or coordinate different processes. The functionality of the program modules may typically be combined or distributed as desired in various embodiments.

[0134] The data structure may be stored in a computer-readable medium in any suitable form. For convenience of illustration, the data structure may be shown as having fields that are related through locations within the data structure. Such relationships may in turn be achieved by assigning locations within the computer-readable medium to storage devices for the fields, which convey the relationships between the fields. However, any suitable mechanism may be used to establish relationships between information within fields of the data structure, including through the use of pointers, tags, or other mechanisms that establish relationships between data elements.

[0135] Various concepts of the invention may be embodied as one or more methods, examples of which are provided. The acts performed as part of a method may be ordered in any suitable manner. Thus, embodiments may be constructed such that the acts are performed in an order different from that shown, which may include performing some acts simultaneously even when shown as sequential acts in the illustrative embodiments.

[0136] The phrase "and / or," as used herein in the specification and claims, should be understood to mean "either or both" of elements conjoined such that the elements may be conjunctively present in some cases and disjunctively present in other cases. Multiple elements listed with "and / or" should be construed in the same manner, i.e., as "one or more" of the elements so conjoined. Other elements than those specifically identified by the "and / or" clause may optionally be present, whether or not related to those elements specifically identified. Thus, as a non-limiting example, a reference to "A and / or B," when used in conjunction with open-ended language such as "comprising," may refer in one embodiment to only A (optionally including elements other than B), in another embodiment to only B (optionally including elements other than A), in yet another embodiment to both A and B (optionally including other elements), and in any other embodiment to include unions, intersections, or otherwise other combinations of the associated elements.

[0137] As used herein in the specification and claims, "or" should be understood to have the same meaning as "and / or," as defined above. For example, when separating items in a list, "or" or "and / or" should be construed to be inclusive, i.e., including not only the inclusion of at least one, but also more than one of some element or list of elements, and optionally, additional unlisted items. "Only "one of" or "exactly one of" or "consisting" when used in the claims Only terms clearly indicated to the contrary, such as "consisting of," will refer to the inclusion of exactly one element of several elements or lists of elements. In general, the term "or," as used herein, shall be construed to indicate exclusive alternatives (i.e., "one or the other but not both") only when preceded by exclusive terminology, such as "either," "one of," "only one of," or "exactly one of." "Consisting essentially of," when used in the claims, shall have its ordinary meaning as used in the field of patent law.

[0138] As used herein in the specification and claims, the phrase "at least one" in reference to a list of one or more elements should be understood to mean at least one element selected from any one or more of the elements in the list of elements, including, but not necessarily, at least one of every element specifically recited in the list of elements, and not excluding any combination of elements in the list of elements. This definition also allows that there may, optionally, be elements other than the elements specifically identified in the list of elements to which the phrase "at least one" refers, whether or not related to those elements specifically identified. Thus, as a non-limiting example, "at "at least one of A and B" (or, equivalently, "at least one of A or B") or, equivalently, "at least one of A and / or "B (at least one of A and / or B)" can refer in one embodiment to at least one A (optionally including more than one) in the absence of B, in another embodiment to at least one B (optionally including more than one) in the absence of A, in yet another embodiment to at least one A, including more than one, and optionally to at least one B (optionally including other elements), etc., and in any other embodiment can include different combinations of inclusion and exclusion of A, B, and any other associated elements.

[0139] For purposes of this specification, when method steps are described in a sequence, the sequence does not necessarily mean that the steps should be performed in chronological order in the sequence. Steps may be performed in entirely alternative orders, which may mean that some may occur simultaneously or be omitted entirely.

[0140] In addition, where features or aspects of the invention are described in terms of a Markush group, those skilled in the art will recognize that the invention is also thereby described in terms of any individual components or subgroups of components of the Markush group. DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS

[0141] The following detailed description is illustrative of the invention and should not be limited in scope by the depicted embodiments, nor should it be understood in any way as a limitation on the broad description of the invention as set forth hereinabove. These embodiments are described in sufficient detail to enable one skilled in the art to practice or implement the invention. The precise shape, size, and appearance of the components described or shown are not expected or required by the invention, unless otherwise stated. It is understood that any utilization, combination, or structural, logical, electrical, and mechanical changes, modifications, enhancements, or modifications of any of the embodiments described or otherwise related may be made without departing from the scope of the invention. Similarly, any functionally equivalent products, compositions, and methods will also remain within the scope, along with all single, combined, and sequence steps, features, structures, sequences, processes, combinations, and compounds referenced or shown in this description, either singly or collectively.

[0142] The entire disclosure of all documents cited herein, including patents, patent applications, journal articles, laboratory manuals, books, charts, repositories, and any other form of documentation or resource otherwise referenced, is not in any way an admission of prior art, prior or common knowledge claimed by one of ordinary skill in the art, or any other connection or assumption to the present invention, unless otherwise stated.

[0143] Throughout this description, unless otherwise stated, the words "comprise", "include", and any variations that may consist of "comprising", "comprises", "including", or "includes" will be understood to imply the inclusion of a stated integer or group of integers, but not the exclusion of any other integer or group of integers. Relative terms such as "about" or "approximately" will be understood to apply a variability of 10% in the positive and negative directions of their subject matter, unless otherwise stated or specified. Other definitions for selected terms may be found herein and will apply to the remainder of this section unless otherwise redefined. All other definitions will reflect the general understanding of one of ordinary skill in the art of the invention or as declared by the subject field.

[0144] Features presented throughout the figures are referenced using the numerical order of the step of the invention to which they belong, along with their logical order within the figure itself, except for the first figure, which serves as an initial overview.

[0145] Similar or identical reference numbers may be used to indicate the same or similar features.

[0146] The present invention will be described in terms of embodiments directed to analyzing specific portions of joint tissue during orthopaedic surgical procedures to determine the condition and classification of that tissue, however, the invention has applicability more generally in the field of intraoperative tissue analysis.

[0147] Based on the discussion from the background of this specification, it is apparent that the current methods used to analyze tissue states and classes are suboptimal and only usable in limited scenarios. The present embodiments aim to improve on this by providing an alternative that allows the analysis to occur within an intraoperative environment, increasing the accuracy of the information derived from this analysis and providing assistance to the personnel involved during the associated procedure.

[0148] This is accomplished by utilizing an alternative approach that focuses on the use of various sensors in conjunction with data that is retrieved and stored across multiple object analyses. Different types of sensors generate data based on a single or combination of objects that can be processed and interpreted to extract information that cannot be obtained manually. This is aided by algorithms and methods trained from historically generated data and associated information that can predict state and class information surrounding an object when given the same inputs associated with them.

[0149] It should be understood that the present invention is not limited to orthopedic surgery, nor is it limited to any form or type of tissue.

[0150] Biological tissues are heterogeneous structures that can absorb, reflect, scatter, and re-emit light. Light reflected from tissues can be detected and measured through a process called diffuse reflectance spectroscopy. Emitted autofluorescent light can be detected and measured through a process called fluorescence excitation spectroscopy. Most tissues, including articular tissues, exhibit unique spectral characteristics in the ultraviolet, visible, and near-visible ranges due to their biochemical and morphological state. By sensing and processing these unique spectra, it is possible to classify and determine the state of the tissue.

[0151] This process typically involves a light source and a capture method. The light source, the type of which depends on the form of light being captured, must illuminate the tissue. The capture method, such as a reflectance probe and a spectrometer, will capture the results from the tissue based on this light exposure. It can be used on tissue samples preoperatively and on the patient intraoperatively without causing any changes to the state of the tissue. Depending on the light source used, it may be possible to reach under the skin to some extent, so it is mechanically non-invasive, but the results received from this are unlikely to be comparable to the exposed equivalent.

[0152] Biological tissues mechanically vibrate differently depending on their composition and type. When a tissue acts as an acoustic source through this vibration, the medium surrounding the tissue, such as air and other tissues, will begin to vibrate as a result. This will continue as the sound waves propagate away from the source. These sound waves can be detected and captured through acoustic sensors, such as microphones. By listening for distinct sounds, it is possible to distinguish between different tissue types and determine various aspects of their composition, such as water content or density.

[0153] The process requires an initial impact to trigger vibrations in the tissue or source. For example, this could be generated by a tightly controlled impact from an actuator, a laser pulse, or an air jet. This creates a sound wave that can be captured using an acoustic sensor, which must be within the range of occurrence and have a high enough sampling rate to bring out sufficient detail. The process can be used pre- and intra-operatively, but care must be taken to ensure that the initial triggering impact does not cause damage to the underlying tissue. It may be possible to provide information based on the sound generated in response to the impact trigger, taking into account the epithelial tissue that reaches below the skin to some extent and acts as a buffer. This would limit the amount of information that could be obtained, but properties such as bone density would still be readily available.

[0154] The data read from these different types of sensors typically needs to be analyzed, processed, and transformed before it can be used in various machine learning, data science, and mathematical techniques. This can involve multiple steps depending on the sensors involved and the intended technique. We start by processing the data, which is generally split into two different parts: pre-processing and manipulation. Pre-processing consists of cleaning, reorganizing, formatting, and sampling the data to achieve a more usable form. Manipulation consists of scaling or aligning the pre-processed data, breaking it down into its components or representative elements, and then aggregating the results, if necessary.

[0155] Now the training phase begins, which allows a specific machine learning, data science, or mathematical technique to be built and identify its target. Training consists of matching a set of processed data against the tissue state or classification ground truth, and determining which of the values ​​or combinations of values ​​result in which truth. Once the right amount of data has been sent through the training phase, the technique can be executed.

[0156] Utilizing a specific machine learning, data science, or mathematical technique once trained typically involves passing it processed data that does not have a matching tissue state or classification ground truth. The values ​​it contains are fed through the technique and matched against an existing ground truth obtained through previous training. This existing truth would be the predicted matching tissue state or classification of tissue that belongs to the data. This process can be repeated using data that does have a matching ground truth, and depending on how closely a given truth matches its actual one, the accuracy of the technique is determined.

[0157] FIG. 1 is a schematic flow diagram depicting an intraoperative tissue status and class analysis method 10, compartmentalized into the individual steps that compose it. The flow of information between these steps and the individual processes that they may contain is outlined. Data collection 100 utilizes a series of different sensors, possibly in an interleaved arrangement, to generate varying amounts and types of data based on the subject, which may be tissue. Data processing 200 preprocesses and manipulates this data to create a form with increased usability and assessability. Data interpretation 300 passes this processed data through various models and algorithms capable of predicting status and classification information. These models and algorithms are initially trained based on the mapping between historical analysis information and actual corresponding results, and may comprise an artificial neural network (ANN) or equivalent, as will be understood by those skilled in the art. Once captured, new processed data can be passed through and the identified indicators will be mapped to corresponding values ​​and will predict status and classification information.

[0158] Figure 2 is a detailed schematic diagram depicting an exemplary data collection and readout step 100 of the type depicted in Figure 1. Data may be collected through a series of sensors, which may vary in terms of type, quantity, and arrangement, or may be read out through an external source associated with the subject or a procedure surrounding the subject across a number of possible embodiments.

[0159] Sensors may act independently or in concert as part of a system or collection of sensors that will cooperate in some manner to increase the quality or quantity of the data sensed, respectively. Each sensor may be completely self-contained or may require additional devices or systems to handle all or part of the required processing.

[0160] The physical arrangement of the sensors should be such that they surround the object (e.g., a patient's joint, e.g., knee, elbow, hip, shoulder, etc., on which an orthopedic surgical procedure is being or has previously been performed) in a manner that maximizes the sensing potential of the multiple sensors while introducing a minimal amount of disturbance to the surrounding environment. If the sensors are present as part of a system in a collaborative setting, the arrangement should reflect this, e.g., sensing the object from different angles and later stitching the different perspectives together.

[0161] The sensors may be automated, manually triggered, or controlled through some combination of the two, depending on the embodiment. In situations where an appropriate sensing environment must be created, it will be more convenient to manually control the sensors when this environment is presented. Manual control can be achieved through approaches that may include voice control, gesture control, and different forms of physical actuation (the latter of which is present in the preferred embodiment due to its precise control). Otherwise, it will be more advantageous to have them operate autonomously and provide information without involvement. Variations of these approaches may also exist, such as sensors that are automatically triggered once they perceive the required conditions.

[0162] A sensor will typically sense in a periodic manner since a perceived change may be unlikely to occur at any one time and its sensing rate may be limited. In some embodiments, sensing may only need to occur once, or may be continuous to provide a feed of information as close to real-time as possible. In situations where a snapshot or specific condition is sensed, providing sensed data in the form of a delayed time may be implemented since some conditions may be required to produce useful data.

[0163] The choice of sensor and its configuration will depend on what is to be sensed. Sensing tissue will typically include at least one 2D scanner, a 3D scanner, and a hyperspectral or spectral sensor. These should be positioned to surround the tissue with a particular focus on the area of ​​interest that is likely to be relevant to the procedure being performed.

[0164] Some of these sensors operate in real time, sensing periodically. Other sensors may be removed from direct operation until a point is reached where personnel prepare the operating room environment for ideal sensing conditions prior to returning the environment after sensing has occurred. In both cases, in addition to its autonomous operation, it will be advantageous for trusted personnel to manually trigger the sensor. The manual trigger should comprise a physical button or touch screen to allow for efficient binary interaction.

[0165] Turning now to FIG. 2, the data collection and readout step 100 of FIG. 1 is described in more detail. The surrounding environment and relevant personnel should be prepared for any sensing procedure that may occur depending on the sensors in use (101). This may involve implicit preparation of the environment to ensure or increase the probability that optimal conditions occur, or temporary explicit modification of the environment if the sensors involved are unable to sense effectively during typical conditions. These modifications may include personnel moving any interfering equipment and adjusting any environmental conditions such as lighting. A preferred embodiment will require implicit preparation as well as some elements of explicit preparation. Since orthopedic surgery is generally time-constrained, both from a financial and medical standpoint, reliance on periodic sensor bypass operations is more reasonable than one that requires constant changes in settings, although setting configuration changes that occur several times during the procedure may be acceptable.

[0166] The configuration of the sensors should be prepared for any sensing procedure to occur assuming the environment is in a way that makes this possible or at least efficient (102). This may involve changing the position, alignment, and orientation of the sensors, both independently and in relation to one another. Additional equipment, such as a stand or platform, may be required for these changes. In a preferred embodiment, the sensors will already have the required configuration as part of a pre-built system or platform. When the opportunity arises, the system as a whole can be moved into position within a relatively small time frame, reducing impact and disruption to the environment. After preparations 101 and 102 are complete, the sensing procedure 103 can begin.

[0167] Sensing will occur based on a set duration, which determines the number of possible iterations based on the particular type and quantity of sensors present in a particular set arrangement. In embodiments that require the environment and sensor configuration to be adjusted for sensing, these parameters are likely to be constrained by the setting. During orthopedic surgery, this duration is likely to be only a few minutes long, as time is critical to the success of the surgical procedure, and the number of sensing iterations is consequently similarly limited. In embodiments that allow for passive sensors, the duration may depend on the total lifespan of the object being sensed or the actions performed in relation thereto, allowing a relatively higher number of iterations for the capabilities of the sensors involved. After sensing occurs, the previously implemented preliminary measurements 101, 102 may be reinstated, if necessary.

[0168] Data may also be collected directly, through collated personnel or through provision from systems 104, which may include documents, records, and databases. In certain embodiments, this would comprise any resource that may provide additional information about the patient or the procedure they are undergoing, such as patient records, medical records, and historical procedure or surgical data.

[0169] All sensed and provided data will be collected and presented in an easily accessible format 105, on demand, by the necessary processing steps 200 depicted in detail in FIG. 3. Collection may involve extraction of the data, the format of which is generally that deemed most usable, determined by the sensor from which it originates. The sensed data may first appear in a raw form, which must be converted into data whose meaning can be extracted, typically by an external control unit. Similarly, provided data may appear in a form that is not easily accessible, such as paper, which requires input into a digital system for remediation. In certain embodiments, all data will be stored in the same way so that they can be accessed in the same way. This method of storage would ideally be random access memory (RAM) of the central system, although solid state drives or hard disks may alternatively be used, depending on the raw amount of data and the processing speed required for traversal. In other embodiments, a database may be used to store and access this data. This may use strict storage and access guidelines such as those imposed by SQL, or may be more flexible and scalable using technologies such as NoSQL.

[0170] Figure 3 is a detailed schematic diagram depicting an exemplary data pre-processing and manipulation step 200 of the type depicted in Figure 1. Data will generally be processed to transform it into a form of greater utility, both in terms of its usability and evaluability.

[0171] The data source 201 comprises the collected data of interest, which comprises at least raw sensed data either generated from multiple sensors located around the object and / or provided externally and / or data provided by trusted personnel or systems. This data should contain sufficient information to determine the state and class of its associated tissue.

[0172] The intent behind processing the data is to best prepare it for training and execution within predictive algorithms and methods, including, for example, machine learning or artificial neural network systems, as will be understood by those skilled in the art. This may involve different types of pre-processing and manipulation to transform the data into a form that provides the most advantage for this use.

[0173] Preprocessing the data involves converting it into a usable form in preparation for subsequent data manipulation and to generate the most utility therefrom (202). This data may initially be in a somewhat raw form that may contain noise, errors, or redundancies. If data containing these defects is used during normal processing, redundant calculations, inconsistencies, or incorrect results may result. These must therefore be repaired or removed depending on their type and severity (203).

[0174] Noisy data may be defined as data that is partially correct but contains other parts that are corrupted or erroneous. The ratio between correct and erroneous data is an indicator of the type of action that may be taken in response. If only a small amount is erroneous, it may be possible to correct this amount based on the correct data, or the remaining data may be removed, provided that it provides sufficient benefit in its reduced form. However, if the amount of incorrect data is large, removing the data in its entirety is likely to be the only option.

[0175] Erroneous data may be defined as data that contains a value that is incorrect and possibly cannot exist either through the medium that created it or in relation to the surrounding data. Erroneous data cannot be corrected in most scenarios because it typically does not bear a relationship to the value it should have had, and therefore is usually removed.

[0176] Redundant data may be defined as data that is free of error, but that does not add any added value or benefit to the data set as a whole, but serves only to increase its volume and introduce inconsistencies. Redundant data cannot be corrected because it is technically correct, and therefore is typically removed or ignored instead.

[0177] Removal or modification of data depends heavily on the origin and format of the data and the criticality of the portion. Removal may be relatively straightforward, depending on the format, but will leave the remaining data in a reduced state. In some cases, the data will remain valid, while others may require additional modification to achieve this. This may involve combining the remaining data with another set of reduced data to create a complete set, or replacing the data with dummy data that would not affect the final result. In comparison, modification of data is more difficult and requires knowledge of the expected structure in order to determine the missing or erroneous content so that it can be corrected. Techniques to achieve this depend heavily on the data itself and may not even be possible. In a preferred embodiment, all redundancies and errors will be directly removed, while any noise will be corrected if an additional benefit can be discerned.

[0178] The collected data (201) will typically need to be rearranged and formatted to increase access efficiency and make its storage more logical from a processing standpoint (204), since its initial form will likely be based on the order and format of its origin, such as a specific sensor, system, or collection of personnel, that is suboptimal for the operation.

[0179] In a preferred embodiment, specifically for the intended prediction approach, rearrangement would consist of grouping data together that may have established similarities or other relationships. This would make access or searching for related data or data that clearly represents a particular aspect or set of aspects easier and more efficient. Formatting would consist of structuring these different groupings to allow different sets of data to be simultaneously and subsequently manipulated and analyzed. This would make traversal from one set of data to another related set of data relatively simple and computationally inexpensive. Other embodiments would have different approaches to formatting and arranging depending on the type of manipulation and subsequent prediction approach intended for the data.

[0180] The collected data 201 may, as part of pre-processing, be sampled to create distinct portions that may provide additional utility as opposed to operating on the data as a whole (205). Sampling consists of reducing the data pool to one more favorable towards a specific type of use, such as the data as a whole reduced to only a portion that may be considered representative.

[0181] In a preferred embodiment, specifically for the intended predictive approach, data will first be sampled to create a single data pool that is more representative than the data as a whole. This means that the utility provided by this representative data pool should be equal to or better than the original one. This representative pool will then be split into three different partitions. The first and largest partition, known as the training set, will be used to train predictive algorithms and methods. The second smaller partition, known as the test set, will be used to test the trained predictive approach. The third smaller partition, known as the validation set, will be used to verify the results of the trained predictive approach that is producing a favorable accuracy against the test set that is generated.

[0182] Other embodiments will likely use a similarity sampling approach that is consistent with the predictive approach, although additional customization may be performed depending on the specifics.

[0183] Manipulating the data (208) involves converting it into a form of good evaluability in preparation for, and from which the most utility will be derived, a subsequent predictive algorithm or method. The data may initially be in a form in which values ​​exist based on how they are originally represented. Because the representations will likely differ across the data, achieving an adequate level of comparability between different sets may be infeasible or may be done to a suboptimal degree. By scaling or aligning these values ​​to a common point (209), comparability between different sets is increased.

[0184] In a preferred embodiment, specifically, all values ​​present in the dataset that can be considered comparable and have a directly or similarly equivalent initial expression for the intended predictive approach should be scaled. This is because some types of predictive analytics generally work better when all data is within some known range. It also makes it easier to handle and differentiate the data when presenting it, especially if the need arises. Other embodiments will likely use similar scaling techniques, which will again be based on the intended predictive algorithm or method.

[0185] The collected data (201) may be reduced, split, or decomposed into its component elements (210) as part of the data manipulation. These individual elements can be used to identify existing features that make up the data and may be more useful or representative compared to others. This is important for predictive analytics because these types of features are generally good indicators, which can greatly increase their usefulness.

[0186] In a preferred embodiment, specifically for the intended predictive approach, the data will be decomposed into constituent elements where individual elements or otherwise features are found to make a significant contribution in determining an overall explanation of the data as a whole.

[0187] Collected data 201 and the constituent elements derived therefrom may be aggregated together into a single entity 211 as part of data manipulation. The aggregated entity should provide more utility as compared to the individual elements or data used to create it, but this may not be the case when decisions are made from a storage or computational perspective.

[0188] The aggregation approach depends primarily on the application, the type and representation of the data, and the form of processing in which the results will be used. A simple approach may involve averaging together the data involved, while a more complex one may involve performing procedures that provide weights to each individual element, process them, and combine them based on these weights. As the amount of information related to the data and the context of the application increases, the complexity and usefulness provided by these aggregation approaches may increase as well.

[0189] In the preferred embodiment, specifically, for the intended predictive approach, elements should be aggregated together if additional utility would be generated. This means that if the aggregated entity exhibits properties of a better set of data as compared to the individual elements, the aggregation should be maintained. Although it may be performed with respect to all sources of data, it will likely be limited to data of similar origin, since different aggregation algorithms may require a certain amount of similarity to be generated. Other embodiments will likely aggregate data as well, with dependencies determining how and to what extent this will occur.

[0190] Final processed data 214 will be generated after the collected data 201 is pre-processed and manipulated. Other pre-processing approaches 206 and manipulation approaches 212 may also exist in addition to those mentioned above, as would be readily understood by one of ordinary skill in the art. The order and existence of these pre-processing approaches 207 and manipulation approaches 213 do not necessarily reflect the order and existence of the approaches herein.

[0191] Figure 4 is a detailed schematic diagram depicting an exemplary data interpretation and information generation step 300 of the type depicted in Figure 1. This involves using two different data sources within a series of different predictive approaches to generate information and value that may provide insight into the state and classification of a particular tissue.

[0192] The first data source 214 is data that has been recently processed to generate additional utility during predictive analysis as detailed in Figure 3 (see Figure 3). The second data source is identical except that it contains historical processed data 301 that has been previously generated and retrieved (104). These sources will be used as derivable data on which indicators and other mapping mechanisms may be found.

[0193] The third data source 302, which contains a set of concrete values ​​corresponding to each value in the second data source, is historical data of actual tissue condition and classification information, which can be used as ground truth and what can be predicted.

[0194] Predictions may be generated 303 based on the first data source 214 by training and running different forms of machine learning, data science, and mathematical algorithms or methods. In preferred embodiments, this will primarily consist of different supervised approaches. These types of approaches generally operate in two distinct phases, comprising a training phase and an execution phase.

[0195] Turning now to FIG. 4, the data interpretation and information generation step 300 of FIG. 1 is described in more detail. The process 300 involves the training of an algorithm for data interpretation and output in a machine learning or ANN framework. The training phase involves a second and a third data source, including processed data 214 generated by a number of sensors located around the subject, and retrieved historical data 104, where each set of data in the second data source 301 is mapped to a set of concrete values ​​in the third data source 302. This consists of identifying the indicators in each set of data that are involved in this mapping, either in part or in large part, such that if another set of data contains these same indicators, it will likely have the same or similar corresponding values ​​as well. This will continue until a mapping structure is developed that will map the analyzed indicators to the values ​​to which they most commonly refer.

[0196] The training phase is often performed using different partitions of the data as opposed to the data as a whole, which may include training, test, and validation partitions, for which the data and corresponding values ​​are known for each. This would begin by first generating a mapping structure corresponding to only the training partition. The data in the test partition is then run through this structure and the values ​​it returns are compared to the actual known values ​​of the partition. This would provide a measure of accuracy depending on the closeness of the returned values ​​to the actual ones. If the accuracy is satisfactory (somewhere between 95-100% based on the preferred embodiment), it is again tested using the validation partition. This is to simulate its performance on real-world data, since it has previously experienced the training and test partitions, but the validation partition will remain unknown to it. This ensures that the mapping structure will perform well on all the data as opposed to only the test partition, a phenomenon known as overfitting.

[0197] The execution phase involves only the first data source 214, which does not have known corresponding values. It consists of first identifying identical indicators found in each set of data in this source during the training phase. These indicators are then applied to the previously created mapping structure to identify the values ​​to which they correspond.

[0198] Supervised algorithms or methods vary widely in their complexity and their predictive power, and using different types of them in parallel can provide useful results in addition to comparison points. These algorithms or methods may include linear and polynomial regression, logistic regression, naive Bayes networks, Bayes networks, support vector machines, decision trees, random forests, k-nearest neighbor classifiers, and neural networks.

[0199] Other embodiments may use different predictive approaches, including unsupervised, semi-supervised, and reinforcement approaches. Unsupervised and semi-supervised algorithms or methods are provided with a dataset and attempt to extract meaning from it with little or no direction as to what they are looking for. This allows unknown information or connections present in the data to be found, which may provide additional utility depending on its content and its consistency in other datasets.

[0200] Reinforcement algorithms or methods may attempt to launch a series of calculations with the goal of resulting in a particular value. They are provided with a positive or negative stimulus depending on the accuracy of this value compared to what they should have had. When provided with a positive stimulus, they may continue performing the same calculations they were doing and perform additional ones similar to these. When provided with a negative stimulus, they may stop performing their current calculations and try one that is different to a variable degree. A certain amount of randomness is typically added to these algorithms to give them a starting point, which means that they may require more execution cycles to reach a satisfactory result compared to previous predictive analytics approaches.

[0201] Predictions may be generated based on the processed data 214 by invoking simulations 304 with different types of scenarios and conditions that may affect the state of the tissue. These types of cases will likely be mathematically simulated and probabilistic measures will be added to account for situations that are currently not deterministic.

[0202] In a preferred embodiment, the simulation will be designed for different procedures or techniques that may occur during surgery and their associated effects on tissue. This will provide two primary sources of data.

[0203] The first source will be the processed data 214, which contains a variety of information related to tissue states and classes. This will be used as a base platform from which the simulation will begin its processing.

[0204] The second source 301 would be information similar to the first source, but occurring after a particular event or procedure where any associated variables are known. This information would indicate the effects that these variables may have been involved in producing.

[0205] Although currently simulation refers to a single thing, this may not be the case where additional benefits may be found by having multiple different simulations, or by splitting a single simulation into multiple individual simulations, each with its own purpose or predictive goal. Given the complexities typically involved, splitting may be advantageous, at least from a development and production standpoint.

[0206] Other embodiments may utilize different simulations depending on their context and application, which will likely depend on the subject and desired outcome of the simulation.

[0207] The generated predictions will be used to provide insight into the state and classification related information of the tissue. (307) These two sets of discriminatory information have different properties and characteristics that give rise to their value as a whole. They can be used individually or together to determine and inform the outcome of various procedures or events surrounding the specific tissue.

[0208] Tissue state comprises a set of descriptors that provide information related to tissue health. These descriptors generally focus on specific aspects of the tissue and can change over time or after significant events. Composition is one such descriptor that describes the types of minerals that may compose the tissue. Different minerals and their abundances are generally reliable indicators of the health and age of a specific tissue, and it is important to note that they are different when there is variation in these properties. This is particularly useful when measuring tissue density, which is defined by the tightness of these minerals or at least the specific minerals relative to each other. Thermal consistency is another such descriptor, which describes the temperature of the tissue and its distribution across it. Measuring thermal consistency is often a good way to monitor the extent to which tissue is affected when performing a surgery such as an osteotomy. Other condition descriptors may include hydration, which may describe the water content present in the tissue, which may be useful in measuring the effects of any previous osteotomy, necrosis, which describes the death of tissue cells that may have been caused via osteotomy or internal issues within the body, reflectance, which describes the specific color and discoloration the tissue exhibits, and the amount and color the tissue may actively reflect, any variations of which typically cannot be discerned without advanced visual sensors. Tissue condition information or descriptors may be used individually or collectively within a select set to determine or predict the outcome of a particular procedure or set of variables on a tissue.

[0209] Tissue classification involves defining a particular tissue type and any differentiation that may be derived in addition. This may include bone, cartilage, fat, ligament, muscle, and meniscus. Either individually or as part of a selected area or region, may be used to define the tissue type and may reinforce or further inform conclusions made in conjunction with status information.

[0210] Other predictive approaches and resulting information may exist outside of those explicitly outlined herein (305). Predictive approaches are not necessarily performed only once; they may also be performed in parallel and serially when there is a reason to do so (306).

[0211] 5 generally illustrates a basic embodiment for tissue condition and class analysis and the intraoperative environment in which it is used. It includes multiple sensors 502 arranged around a patient's target joint 501 (in the illustrated case, the patient's left knee). The multiple sensors 502 may comprise different types and models and may not necessarily be uniform. The number and arrangement 503 of these sensors may vary depending on the specificity of the target 501 and the application in analyzing a particular target.

[0212] Some sensors may not operate independently and instead require additional sensors or assistant devices 504, such as light sources. These devices may be of different types and models and may vary in number and arrangement 505 according to requirements.

[0213] The sensors 502 may not generate data directly, but instead rely on separate capture devices 506 that handle or assist this generation process to various degrees. These capture devices 506 may comprise different types and models, and may vary in number and arrangement 507 according to requirements, the specifics of which will likely depend on their associated sensors 502.

[0214] In a particular embodiment, the target of these sensors and any additional instruments will be articular tissue from the knee 501 during an orthopaedic surgical procedure, for example, different joints of the patient (hip, elbow, shoulder, etc.) on which the orthopaedic surgical procedure is being performed. However, it may be any other form of tissue present in any other form of surgical procedure. The illustrated arrangement provides an example of how the sensors and associated instruments may be positioned relative to the target 501 in this embodiment. It may be assumed that by positioning the sensors around the target 501 through many different angles, a high level of visibility may be achieved.

[0215] During an associated medical procedure or surgical operation, temporary or permanent adjustments or modifications to the intra-operative environment may be necessary to achieve proper sensing conditions or to increase sensing accuracy. This may include adjustments to the immediate environmental conditions such as illumination 513, changes to the position or arrangement of objects (e.g., by moving a surgical bed / table 514 relative to the sensor 502), and removal or repositioning of personnel 515 within the environment.

[0216] Similar adjustments or modifications may need to be made to the sensor 502 and its associated equipment, e.g., computer 509 and monitor 510, controller 508, etc. Depending on the type of medical procedure or surgery, the associated equipment may need to be completely outside of the operating environment and reintroduced at specific time intervals once deemed necessary or safe for the patient. In certain embodiments, the associated equipment will be safely positioned around the subject so as not to obstruct or impede the vision of associated surgical or support personnel. Once a point within the surgery is reached or its involvement is deemed necessary, the associated equipment may be moved to a closer or more convenient location prior to being returned. Other embodiments may not require any repositioning, with the sensors remaining exactly as passive devices, or they may be prioritized such that personnel will be moved to a fixed location at the point where the sensors would otherwise be given priority, as determined by the system.

[0217] All data and information provided by the sensors 502 is advantageously received by a peripheral controller 508. This controller 508 may perform any amount of processing required to compile the data into a form that can be delivered to and interpreted by the rest of the system 509.

[0218] The collected data will be processed in a system 509 that is responsible for performing an analytical process. As defined through the process depicted in Figures 1-4, this processing will include steps of pre-processing and manipulating the data, generating predictive analytical measures based on this data, and executing the analysis to derive meaningful results.

[0219] All generated information will be displayed through some form of communication medium that is interpretable by intended personnel. In the preferred embodiment, this will be an LCD screen such as that provided by computer monitor 510. In other embodiments, this may comprise an audio recording, representative illumination, or printed material.

[0220] Based on the actions provided by the user, interaction with the selected communication medium may be possible. In a preferred embodiment, this would include a keyboard and mouse 511, which would allow the LCD screen 510 to be interacted with in a natural and familiar way. This may also allow the possible forms of interaction to be more complex with a larger range of options. In other embodiments, this may include voice commands, gesture commands, and a touch screen interface.

[0221] The system components may be arranged together in a single system or container 512 such that all interactions with an individual component will constitute interactions with the container. In a preferred embodiment, a structure will be developed to house all of these components such that they may be moved, adjusted, and associated with one another in a clear and simple manner. In other embodiments, they may be positioned and arranged such that each exists individually and independently and may be adjusted without necessarily affecting the state of the remaining components.

[0222] FIG. 5A generally illustrates an implementation of the base embodiment of FIG. 5, which utilizes spectral or hyperspectral sensors for intraoperative tissue condition and class analysis. It includes an array of spectral or hyperspectral sensors 531, which may comprise different types and models and not necessarily uniform. They may have any single or combination of bands available in the electromagnetic spectrum, which will likely be determined by the band that elicits the maximum response from the subject. The number and arrangement of these spectral sensors may vary depending on the subject and application 532. In a preferred embodiment, each subject will have a single corresponding spectral sensor unless there is an advantage to having multiple, such as a scenario where multiple bands are required but cannot be contained within a single sensor.

[0223] Spectral or hyperspectral sensors generally require a specific type or level of light to generate useful information. This light may be achieved from natural illumination or from that introduced by the surgical environment, but specialized sources that can be controlled or that exhibit specific forms of light may be required. These light sources 533 typically consist of a generator 536, a transmission medium, usually of fiber type, and an emitter device such as an LED or some other form of director. They may comprise UV, visible, and infrared light of variable brightness and intensity, and may differ in type, model, number, and arrangement 534. They may exist independently or be combined into other hardware such as a spectral or hyperspectral sensor. In a preferred embodiment, each spectral or hyperspectral sensor will have as many light sources as necessary to illuminate its target and increase its accuracy.

[0224] Temporary adjustments to the environment may be necessary to allow the spectral or hyperspectral sensors to perform as intended. Because they operate based on light, this typically includes adjustments to illuminance, which may involve dimming external light, increasing the effectiveness of special lights, removing any obstructions that are within their field of view or that may cause shadows, and decreasing the distance between them and the object to encourage light transmission.

[0225] Light sensed by a spectral or hyperspectral sensor may need to be passed through a spectrometer 535 before it can be utilized. This is a device that takes light and splits it into an array of distinct colors determined by the possible available bands. Each spectrometer is matched with at least one spectral or hyperspectral sensor, and the nature of this correspondence will depend on the types and models of all components involved.

[0226] The light sources and spectrometers will be controlled by and in communication with one or more peripheral controllers 508, depending on the application and sensor arrangement. This controller will likely perform some form of pre-processing to convert the received data into a more usable form before passing it through to the rest of the system 509.

[0227] A preferred embodiment would likely possess some form of spectral or hyperspectral sensing to distinguish between different types of tissue, as each may reflect and absorb different amounts and frequencies of light. These amounts may also be affected by condition-related variables such as hydration and necrosis, which may also be determined through these sensors.

[0228] FIG. 5B generally illustrates an implementation of the base embodiment of FIG. 5 utilizing acoustic sensors for intraoperative tissue condition and class analysis. It includes an array of acoustic sensors 564, which may comprise different types and models and not necessarily uniform. They may have any possible sampling rate, which is likely determined by the sounds derived from physically impacting the object. The number and arrangement 565 of these acoustic sensors may vary depending on the object and application. In a preferred embodiment, each object will be surrounded by multiple acoustic sensors, sampling sounds generated from many different angles.

[0229] The acoustic sensor can only perceive sound from static tissue when it is affected by something 563. The actuator of this effect 561 must therefore generate it in a constant and measured manner, since if the amount of force or any other variable is different, a different sound will be generated. While the signature of the real sound will likely be the same, it would be advantageous to have actuators that would reduce any inconsistencies. The number and arrangement of these actuators 562 may vary depending on the application, since it may be beneficial to create sound from multiple different angles, assuming the actuators are properly synchronized. In a preferred embodiment, as shown, the actuator will comprise a single laser system that will emit a measured and consistent single pulse of light into the tissue and generate the sound. By using a highly controlled actuator, the resulting sound frequency will be more consistent. This is important when dealing with subjects whose potentially different states may generate subtly similar sounds, so much so that even relatively small actuator differences can affect the end result.

[0230] Temporary adjustments to the environment may be necessary to allow acoustic sensors to perform as intended. Because they operate based on sound, moving the sensor closer to the source of the sound will typically render its specific audio frequency more prevalent compared to other sounds generated in the environment. However, this also means that the data returned from these sensors will likely vary based on their placement, but will still maintain the same or similar signature. This makes it likely that large movements of the sensors will offer little advantage compared to placing them statically. In a preferred embodiment, the sensors will be statically placed at the start of a medical procedure or surgery and will remain there until they are no longer needed. The development will therefore likely focus on identifying signatures instead of raw acoustic signals.

[0231] The actuator 561 or actuators used will require a single or multiple devices to control its power and triggering. The laser system shown requires two different devices, the configuration and selection of which will depend on the strength and type of laser. The first of these is the laser current source 566, which will generate the required current internally prior to sending it to the laser. The second is the laser chiller 567, which will cool the laser between pulses, ensuring that it does not overheat and damage itself or its surroundings. The preferred embodiment will require both of these components.

[0232] The acoustic signals monitored by the sensors will need to be received and converted into a form that can be interpreted, typically handled by an audio interface or receiver 568. The configuration of the different sensors, including their rates and sensitivities, can be controlled throughout the system. A preferred embodiment would use a single receiver with all involved acoustic sensors attached to it so that their signals can be interpreted as a whole, instead of individually, as they would likely perceive the same object, but from different angles and positions.

[0233] All components may be attached to a single or multiple peripheral controllers 508 depending on the application and sensor arrangement. This controller will likely perform some form of pre-processing to convert the received data into a more usable form before passing it to the rest of the system 509.

[0234] A preferred embodiment would likely incorporate some form of acoustic sensing to determine specific types of tissue condition information such as density and hydration. The tissue type can then be derived from this or used as an enhancement for conclusions developed through other sensing methods.

[0235] The features presented herein may be implemented electronically through any possible system or machine that can complete them within any limitations imposed by the particular application, which may be implemented in an online, offline, or in a capacity relying on some combination of the two.

[0236] Data extracted or generated as a result of the features presented herein may be stored electronically, which can be done offline, online, or through some combination of the two. It may be accessed immediately or within a delayed time frame for retrieval, processing, and any other form of use. All types of data may be stored and maintained once, intermittently, routinely, or through any other timing paradigm.

[0237] The method 10 of biological condition analysis and classification of bone and soft tissue in orthopedic applications depicted in FIG. 1 and associated sub-methods (e.g., methods 100, 200, and 300 depicted in FIGS. 2-4) may be implemented using a computing device / computer system 600 such as that shown in FIG. 6, and the processes of FIGS. 1-4 may be implemented as software, such as one or more application programs executable within the computing device 600. In particular, the steps of the methods 10, 100, 200, and 300 depicted in FIGS. 1-4 are effected by instructions in the software performed within the computer system 600. The instructions may be formed as one or more code modules, each for performing one or more specific tasks. The software may also be divided into two separate parts, a first part and corresponding code modules implementing the described method, and a second part and corresponding code modules managing the user interface between the first part and the user. The software may be stored in a computer-readable medium, including a storage device, described below, for example. The software is loaded from the computer readable medium into the computer system 600 and then executed by the computer system 600. The computer readable medium having such software or computer program recorded thereon is a computer program product. Use of the computer program product in the computer system 600 preferably results in an advantageous apparatus for biological condition analysis and classification of bone and soft tissue in orthopaedic surgical applications, including post-operative treatment and evaluation of orthopaedic surgical procedures.

[0238] 6, an exemplary computing device 600 is illustrated. The exemplary computing device 600 may include one or more central processing units (CPUs) 601, including, but not limited to, one or more processors 602, a system memory 603, and a system bus 604 that couples various system components including the system memory 603 to the processing unit 601. The system bus 604 may be any of several types of bus structures including a memory bus or memory controller, a peripheral bus, and a local bus using any of a variety of bus architectures.

[0239] Computing device 600 also typically includes computer-readable media, which may include any available media that may be accessed by computing device 600 and may include both volatile and nonvolatile media and removable and non-removable media. By way of example, and not limitation, computer-readable media may comprise computer storage media and communication media. Computer storage media includes media implemented in any method or technology for storage of information, such as computer-readable instructions, data structures, program modules, or other data. Computer storage media includes, but is not limited to, RAM, ROM, EEPROM, flash memory or other memory technology, CD-ROM, digital versatile disks (DVD) or other optical disk storage, magnetic cassettes, magnetic tape, magnetic disk storage or other magnetic storage devices, or any other medium that may be used to store the desired information and that may be accessed by computing device 600. Communication media typically embodies computer-readable instructions, data structures, program modules, or other data in a modulated data signal, such as a carrier wave or other transport mechanism, and includes any information delivery media. By way of example, and not limitation, communication media includes wired media such as a wired network or direct-wired connection, and wireless media such as acoustic, RF, infrared and other wireless media. Combinations of any of the above should also be included within the scope of computer-readable media.

[0240] The system memory 603 includes computer storage media in the form of volatile and / or nonvolatile memory such as read only memory (ROM) 605 and random access memory (RAM) 606. A basic input / output system 607 (BIOS), containing the basic routines that help to transfer information between elements within the computing device 600, such as during start-up, is typically stored in ROM 605. RAM 606 typically contains data and / or program modules that are immediately accessible to and / or presently being operated on by the processing unit 601. By way of example, and not limitation, FIG. 6 illustrates an operating system 608, other program modules 609, and program data 610.

[0241] Computing device 600 may also include other removable / non-removable volatile / non-volatile computer storage media. By way of example only, FIG. 6 illustrates a hard disk drive 611 that reads from and writes to a non-removable non-volatile magnetic medium. Other removable / non-removable volatile / non-volatile computer storage media that may be used with the exemplary computing device include, but are not limited to, magnetic tape cassettes, flash memory cards, digital versatile disks, digital video tape, solid state RAM, solid state ROM, and the like. Hard disk drive 611 is typically connected to system bus 604 through a non-removable memory interface such as interface 612.

[0242] The drives and their associated computer storage media, discussed above and illustrated in Figure 6, provide storage of computer-readable instructions, data structures, program modules, and other data for computing device 600. In Figure 6, for example, hard disk drive 611 is illustrated as storing operating system 613, other program modules 614, and program data 615. Note that these components can be either the same as or different from operating system 608, other program modules 609, and program data 610. Operating system 613, other program modules 614, and program data 615, which are given different numbers thereto, illustrate that, at a minimum, they are different copies.

[0243] The computing device also includes one or more input / output (I / O) interfaces 630 connected to the system bus 604, including an audio-video interface that is coupled to output devices, including one or more of a video display 634 and a loudspeaker 635. The input / output interface 630 is also coupled to one or more input devices, including, for example, a mouse 631, a keyboard 632, or a touch-sensitive device 633, such as, for example, a smartphone or tablet device.

[0244] In connection with the following description, the computing device 600 may operate in a networked environment using logical connections to one or more remote computers. For convenience of illustration, the computing device 600 is shown in FIG. 6 as connected to a network 620, which is not limited to any particular network or networking protocol, but may include, for example, Ethernet, Bluetooth, or IEEE 802.X wireless protocol. The logical connection depicted in FIG. 6 is a general network connection 621, which may be a local area network (LAN), a wide area network (WAN), or other network, such as the Internet. The computing device 600 is connected to the general network connection 621 through a network interface or adapter 622, which is in turn connected to the system bus 604. In a networked environment, program modules depicted with respect to the computing device 600 or portions or peripherals thereof may be stored in memory of one or more other computing devices communicatively coupled to the computing device 600 through the general network connection 621. It should be understood that the network connections shown are exemplary and other means of establishing a communication link between computing devices may be used.

[0245] It is to be understood that the features presented herein and the different processes they contain do not necessarily have to be performed in the order described, nor do they require any particular environment or circumstances, whose order, nature, preparation, and execution may depend on a number of circumstances that are typically applicable to medically applicable inventions or methods.

[0246] It will be understood by those skilled in the art that variations and modifications of the invention described herein will become apparent without departing from the spirit and scope thereof. Such variations and modifications that become apparent to those skilled in the art are deemed to fall within the broad scope and sphere of the invention as described herein.

[0247] Future patent applications may be filed in Australia or overseas based on or claiming priority from this application. It should be understood that the following provisional claims are provided by way of example only and are not intended to limit the scope of what may be claimed in any such future applications. Features may be added to, or omitted from, the provisional claims at a later date so as to further define or redefine the invention or inventions.

Claims

[Claim 1] An apparatus, system, method, etc.

Images