Systems and methods for identifying surgical workflow outliers

Through density-based clustering algorithms and visualization technology, outliers of the surgical workflow are identified, which solves the problem of review difficulties caused by the large amount of surgical video data, and automatically recognizes key cases and improves data quality.

CN118985030APending Publication Date: 2024-11-19DIGITAL SURGERY LTD
View PDF 0 Cites 0 Cited by

Patent Information

Application Number
CN202380032263.8
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Priority Date
2023-04-13
Filing Date
2023-04-14
Publication Date
2024-11-19

AI Technical Summary

Technical Problem

The data of surgical videos is large, and manual review of key cases consumes a lot of manpower, making it difficult to identify the most critical cases.

Method used

The distance between surgical workflows is determined by density-based clustering algorithms, outliers are identified, and visualized using uniform manifold approximation and projection techniques, providing a surgical dashboard interface to display and analyze outliers.

Benefits of technology

Automatically identify cases of clinical concern, reduce the burden of manual review, improve data quality and annotation quality, and highlight the cases that surgeons are most concerned about.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure HDA0005069078750000011
    Figure HDA0005069078750000011
  • Figure HDA0005069078750000012
    Figure HDA0005069078750000012
  • Figure HDA0005069078750000021
    Figure HDA0005069078750000021
Patent Text Reader

Abstract

Aspects include systems, methods, and computer-implemented methods that provide identification of surgical workflow outliers, where the identification of outliers includes determining distances between workflows using a density-based clustering algorithm.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] Aspects relate generally to computing techniques and, more particularly, to computing techniques for identifying surgical workflow outliers. Background Art

[0002] Through video management and analysis platforms, surgeons have access to a large amount of their surgical case records. For example, this may include hundreds to thousands of cases for a surgeon, as well as videos shared by colleagues. Manually reviewing this data is labor-intensive. Given such a large number of potential cases, it can be challenging to identify the most critical cases.

[0003] Surgeons typically follow a standard workflow when performing surgery; deviations from this workflow may indicate intricacies, complications, and variations caused by patient factors. Surgical videos can be annotated with key surgical phases for a given surgical procedure. The sequence of surgical phases in a video recording is called a workflow. Summary of the invention

[0004] Illustrative aspects that overcome the above-referenced and other deficiencies are provided, including systems, methods, and computer-implemented methods that provide surgical workflow outlier identification, including identifying outliers by determining distances between workflows using a density-based clustering algorithm.

[0005] In an exemplary aspect, a system for identifying surgical workflow outliers includes: a non-volatile memory storing a plurality of surgical workflows; and a processor configured to access the plurality of surgical workflows and analyze the workflows to identify one or more surgical workflows as outliers for review, wherein the identified one or more surgical workflows are further identified as including events of interest or low-quality data, wherein the identification of outliers includes determining distances between workflows using a density-based clustering algorithm.

[0006] In a further exemplary aspect, the system provides visualization of the workflow and outliers on a display, for example, using uniform manifold approximation and projection techniques.

[0007] In additional exemplary aspects, the display or interface identifies surgical workflow details or annotations for each workflow, wherein each surgical workflow is shown as a linear sequence of the identified details.

[0008] In a further exemplary aspect, the surgical dashboard interface displays the plurality of surgical workflows with surgical workflow details or annotations and provides accessible tools for identifying outliers, for example, wherein the surgical workflow details and identified outliers are color coded to identify details within each workflow.

[0009] Other exemplary aspects provide a method for identifying surgical workflow outliers, the method comprising analyzing a plurality of surgical workflows to identify one or more surgical workflows as outliers for review, wherein the one or more surgical workflows so identified are further identified as including events of interest, wherein the identifying of the outliers comprises determining distances between the workflows using a density-based clustering algorithm.

[0010] A further exemplary aspect provides a computer-implemented method for identifying surgical workflow outliers, the computer-implemented method comprising providing a processor configured to analyze a plurality of surgical workflows to identify one or more surgical workflows for review as outliers, wherein identifying the outliers comprises determining distances between the workflows using a density-based clustering algorithm.

[0011] Other advantages, novel features and further scope of applicability of the present invention will be described in the following illustration and description. BRIEF DESCRIPTION OF THE DRAWINGS

[0012] To illustrate the invention and its advantages, a detailed description and accompanying drawings of exemplary aspects described herein are provided. In the description of the method, steps occurring sequentially may also occur simultaneously, in parallel, or may be repeated multiple times before the next step occurs (e.g., to obtain an estimate of the measurement by calculating a statistic such as an average). It should be understood that the invention is not intended to be limited to the precise arrangements and instruments shown, in the accompanying drawings:

[0013] Figure 1 An exemplary flow chart for evaluating a workflow and determining outliers according to one or more aspects is presented;

[0014] Figure 2 A flow chart for reviewing outliers according to one or more aspects is presented;

[0015] Figure 3 A graph illustrating identifying short duration outliers and long duration outliers according to one or more aspects is presented;

[0016] Figure 4 A graph illustrating identifying short duration outliers and long duration outliers by defining durations according to one or more aspects is presented;

[0017] Figure 5 A visualization showing a clustering method for determining outliers according to one or more aspects;

[0018] Figure 6A flow chart of an autoencoder method according to one or more aspects is presented, the method comprising training an autoencoder neural network to compute an abstracted and compressed version of a sequence of stages;

[0019] Figure 7 A flowchart showing a workflow converted into a tensor for input into an autoencoder neural network according to one or more aspects;

[0020] Figure 8 showing a comparison of the workflows according to one or more aspects with a calculated average workflow for determining the deviation of each workflow from the average;

[0021] Fig. 9 a graph showing a workflow aligned according to one or more aspects using multiple alignment based on an average workflow and determining the number of times each phase occurs at each point in the surgery;

[0022] Fig.10 A graph showing the likelihood of transitions in a workflow based on the number of occurrences of usage phase transitions (one phase occurring after another phase) for one or more aspects; and

[0023] Fig.11 A computer system according to one or more aspects is described. DETAILED DESCRIPTION

[0024] According to one or more aspects, the present disclosure recognizes how a set of workflows can be analyzed to identify outliers as surgical cases of interest. One or more of a variety of algorithms can be used to pinpoint these important cases.

[0025] In one example, workflow data for two robotic surgeries (partial nephrectomy, e.g., about 250 cases; radical prostatectomy, e.g., about 800 cases) were considered with respect to cases from multiple sites and surgeons. This data was analyzed using multiple types of outlier detection algorithms: duration-based, density-based, deep learning (autoencoder)-based, and likelihood-based. Found outliers were evaluated by domain experts.

[0026] Preliminary results showed that each outlier detection method was able to detect cases of interest. For example, outliers in robotic prostatectomies performed by a single surgeon included cases where an alternative approach was used (which was associated with postoperative outcomes) and also included multiple incomplete videos.

[0027] Cases of concern can be discovered through different outlier algorithms. Outliers can be roughly divided into issues related to annotation during the surgical phase and outliers of clinical significance. The first category of cases can be reviewed by the annotation team to improve the quality of the annotation, or marked as low-quality videos. The latter group contains cases that may be of concern to the surgeon performing the operation. Each outlier detection method has advantages and disadvantages, which can be weighed when choosing which one or more techniques to use. For example, when presenting clinical outliers to the surgeon, an explanation can be given as to why a given case was marked as an outlier. For real-time applications, such as highlighting when creating annotation issues, it may be preferable to pre-train the model for speed. In addition, internal reporting of outliers can be utilized to improve annotation quality and user trial attention of surgeons to clinical outliers.

[0028] Figure 1 An exemplary flow chart for evaluating workflows and determining outliers is generally shown at 100. At step 110, distances between workflows are calculated to calculate outliers, wherein each point 112 in a scatter plot (generally shown at 114) is a workflow. Outliers 116 are identified, for example, by using a density-based clustering algorithm (DBSCAN), wherein uniform manifold approximation and projection (UMAP) is used for visualization. A color key 118 is shown, which shows surgical case / workflow details or annotations for each surgical case (surgical cases are presented with different annotations, wherein each row represents a surgical case, such as at 120).

[0029] To verify the correctly identified outlier 116, an outlier workflow may be selected and explained by a domain expert at step 122. In the example shown, outlier 124 is shorter in duration than some workflows, but also has many alternating stages. Outliers 126 and 128 appear to be incomplete.

[0030] The collection of all cases for a surgeon may show too much variability to be easily understood. The aspects described herein can identify which outliers are clinically interesting cases to review. Rather than the surgeon having to manually review a large volume of workflow, the aspects can automatically highlight clinically important cases.

[0031] A set of surgical cases can be presented to a user for review. The various aspects described herein reduce the burden of manually reviewing cases and increase the possibility of gaining insights from the data. The cases presented for user review can include low-quality data (e.g., unfinished surgeries) or events of interest (e.g., complex cases or new surgical methods). Various aspects can be used to improve the data cleaning process, the annotation process, the data quality, and / or to provide clinically interesting cases for surgeons to review.

[0032] The aspects described herein can be used to provide surgeons with more targeted workflow insights, highlighting the cases they are most interested in. Additionally, these methods can be used to identify incomplete surgeries or surgeries with low data quality, which can then be excluded from the analysis, thereby improving the quality of the output.

[0033] Aspects of example methods of outlier analysis are summarized below. Each of these methods can be used alone or in combination with one or more other outlier analysis methods.

[0034] Identify cases for review:

[0035] As surgeons upload large numbers of cases to computer platforms, the expectation is that outlier cases will be highlighted as well as cases that may need review. Reasons why outlier cases may warrant attention may include M&M review, self-reflection, training, and peer review.

[0036] In addition, outlier cases can be used to iterate annotation guidelines based on edge cases. Outlier cases can also be used to guide quality review checks in annotation pipelines and investigations into machine learning quality.

[0037] Types of outliers:

[0038] refer to Figure 2 , which generally illustrates a flow chart for reviewing outliers at 200. Outliers 210 may be arranged for review by a surgeon (e.g., at 212), where such outliers include one or more events of interest (at 214). Separately, outliers having low quality data (at 216) may alternatively be flagged for quality review (at 218).

[0039] Events of interest may include unusual phase sequences that indicate a novel workflow or a complex case with a repeating phase pattern. Cases or phase durations outside of expected ranges may also be of interest.

[0040] Low data quality can include ineffective workflows that are missing stages necessary for a complete case or clinically incorrect stage sequences. Stage sequences that indicate multiple cases contained in a single video can also be considered low-quality data.

[0041] Method: Duration Outlier Calculation:

[0042] Figure 3 A method for identifying short duration outliers and long duration outliers that is robust to skewed distributions is generally shown at 300 . Figure 3The calculation of outliers for a data set containing, for example, five or more cases is shown, with long outliers identified and displayed at 310 and short outliers identified and displayed at 312 .

[0043] refer to Figure 4 , case duration outliers can be shown by highlighting the duration, for example, short outliers at 412 and long outliers at 410. These outliers can also be graphically displayed using different colors or patterns, for example, short outliers are represented by green and long outliers are represented by orange. For example, stage duration outliers can be shown by displaying up and down arrows on a colored stage sequence of a workflow.

[0044] Method: Clustering method used to identify workflow outliers:

[0045] Figure 5 A clustering method is generally shown at 500 in FIG. 5 , which determines clusters 510 of similar workflows and outliers 512 outside of these main clusters. The method can account for the structure of the data (e.g., the presence of groupings of similar workflows when detecting outliers). An example of a density-based clustering algorithm is DBSCAN, which has established techniques for making good parameter choices. Different distance metrics can be used to identify different types of outliers. The display of this clustering can also be provided to be rotatable or otherwise viewable in 3D space to better view the clusters and outliers (note the play icon 514).

[0046] Method: Autoencoder Outliers:

[0047] Figure 6 The autoencoder method is generally shown at 600, and includes training an autoencoder neural network to compute an abstract and compressed version 610 of a sequence of stages via an encoder 612 and a decoder 613. After the neural network training is complete, the reconstruction error can be used to obtain an indication of whether the sequence is typical or atypical. Alternatively, the encoded sequence can be used as a low-dimensional representation; and algorithms such as DBSCAN can be used to detect outliers in the embedding space.

[0048] exist Figure 6 As can be seen in , the neural network will capture many key features of the original data 614, but not an exact copy 616.

[0049] Figure 7 The workflow 710 is shown which is converted into a tensor 714 (mathematical representation) in step 712. Figure 6 As in , the autoencoder 716 learns a representation 718 of the workflow.

[0050] Then, at 720, outlier analysis may be applied to the compressed data in the abstract representation.

[0051] The advantage of this approach is that there is no need to choose a specific distance metric or focus on one type of difference (e.g., number of transformations or edits).

[0052] Method: Deviation Cost:

[0053] The method can detect outliers and also explain why the workflow was identified as an outlier.

[0054] Figure 8 A method of using a calculated average workflow (or standard workflow) 810 and finding deviations from the average for each workflow 812 is generally shown at 800. Each deviation has an associated cost, for example, stage insertion = 1, stage deletion = 1, stage replacement = 2.

[0055] The method creates a deviation cost 814 for each workflow based on its similarity to the average.

[0056] Outlier workflows are workflows with high outlier deviation costs, identified using the box plot method or cumulative distribution function. The cause of each outlier score can be traced back (i.e., to one or more specific stages in the workflow).

[0057] Method: Stage Possibility:

[0058] The method can detect outliers and also explain why the workflow was identified as an outlier.

[0059] Fig. 9 A method of aligning workflows using a multiple alignment based on an average workflow and determining the number of times each phase occurs at each point in the procedure is generally shown at 900. This is used to calculate the phase likelihood for each workflow.

[0060] The likelihood of each workflow stage was calculated based on the sum product of the frequency of each stage occurring at the same point in other aligned sequences in the set.

[0061] For example, for workflow 4 on the left (at 910), stage probability = 1 / 2*1 / 4*1 / 1*1 / 4*1 / 4*1 / 3*1 / 5*1 / 5*1 / 2

[0062] Outlier workflows are workflows with high outlier stage likelihood scores, identified using the box plot method or cumulative distribution function. The cause of each outlier score can be traced back (i.e., to one or more specific stages in the workflow).

[0063] Method: Conversion Possibility:

[0064] The method can detect outliers and also explain why the workflow was identified as an outlier.

[0065] Fig.10 A method for determining a transition probability of a workflow using the occurrence rate of phase transitions (one phase occurring after another phase) is generally shown at 1000. The transition probability is the sum product of the occurrence rates of the phase transitions across the entire data set.

[0066] The transition likelihood of each workflow is calculated as the sum product of the frequencies at which each stage transition occurs in the set.

[0067] The transition likelihood is then normalized by the length of the workflow relative to the longest workflow in the collection.

[0068] For example, for workflow 3 on the left (at 1010), transition probability = 1 / 4*1 / 2*1 / 1*1 / 3*1 / 8*1 / 5

[0069] Normalization Possibility =

[0070] Conversion probability^(longest workflow - workflow length + 1)

[0071] Outlier workflows are workflows with high outlier transition likelihood scores, identified using the box plot method or cumulative distribution function. The cause of each outlier score can be traced back (i.e., to one or more specific transitions in the workflow).

[0072] In further exemplary aspects, any user interface or dashboard (e.g., a surgical dashboard) can be used in parallel with outlier identification and / or to facilitate display of identified outliers. Such an interface or dashboard can include stage annotations, video case labels, instrument annotations, anatomical structure annotations, user added annotations, and / or any other medical instrument data or patent data, other metadata, etc.

[0073] Now go to Fig.11, according to one aspect, a computer system 1100 is generally shown. As described herein, the computer system 1100 may be an electronic computer framework including and / or employing any number of computing devices and networks utilizing various communication technologies and combinations thereof. The computer system 1100 may be easily expanded, extended, and modularized, and may have the ability to change to different services or reconfigure some features independently of other features. The computer system 1100 may be, for example, a server, a desktop computer, a laptop computer, a tablet computer, or a smart phone. In some examples, the computer system 1100 may be a cloud computing node. The computer system 1100 may be described in the general context of computer executable instructions (such as program modules) executed by a computer system. Typically, a program module may include routines, programs, objects, components, logic, data structures, etc. that perform specific tasks or implement specific abstract data types. The computer system 1100 may be practiced in a distributed cloud computing environment where tasks are performed by remote processing devices linked through a communication network. In a distributed cloud computing environment, program modules may be located in local and remote computer system storage media including memory storage devices.

[0074] like Fig.11 As shown, the computer system 1100 has one or more central processing units (CPUs) 1101a, 1101b, 1101c, etc. (collectively or generally referred to as (multiple) processors 1101). The processor 1101 can be a single-core processor, a multi-core processor, a computing cluster, or any number of other configurations. The processor 1101 is also referred to as a processing circuit, which is coupled to a system memory 1103 and various other components via a system bus 1102. The system memory 1103 may include one or more memory devices, such as a read-only memory (ROM) 1104 and a random access memory (RAM) 1105. The ROM 1104 is coupled to the system bus 1102 and may include a basic input / output system (BIOS) that controls certain basic functions of the computer system 1100. The RAM is a read-write memory coupled to the system bus 1102 for use by the processor 1101. The system memory 1103 provides temporary storage space for the operation of the instructions during operation. The system memory 1103 may include a random access memory (RAM), a read-only memory, a flash memory, or any other suitable memory system.

[0075] Computer system 1100 includes an input / output (I / O) adapter 1106 and a communication adapter 1107 coupled to system bus 1102. I / O adapter 1106 may be a small computer system interface (SCSI) adapter that communicates with hard disk 1108 and / or any other similar components. I / O adapter 1106 and hard disk 1108 are collectively referred to herein as mass storage device 1110.

[0076] Software 1111 for execution on computer system 1100 may be stored in mass storage device 1110. Mass storage device 1110 is an example of a tangible storage medium readable by processor 1101, wherein software 1111 is stored as instructions executed by processor 1101 to cause computer system 1100 to operate as described below with reference to the various figures. Examples of computer program products and execution of such instructions are discussed in greater detail herein. Communications adapter 1107 interconnects system bus 1102 with network 1112, which may be an external network that enables computer system 1100 to communicate with other such systems. In one aspect, a portion of system memory 1103 and mass storage device 1110 together store an operating system, which may be a coordinating Fig.11 The various components shown function as any suitable operating system.

[0077] Additional input / output devices are shown connected to the system bus 1102 via a display adapter 1115 and an interface adapter 1116. In one aspect, adapters 1106, 1107, 1115, and 1116 may be connected to one or more I / O buses that are connected to the system bus 1102 via an intermediate bus bridge (not shown). A display 1119 (e.g., a screen or display monitor) is connected to the system bus 1102 by a display adapter 1115, which may include a graphics controller for improving the performance of graphics-intensive applications, as well as a video controller. A keyboard, mouse, touch screen, one or more buttons, speakers, etc. may be interconnected to the system bus 1102 via an interface adapter 1116, which may include, for example, a super I / O chip that integrates multiple device adapters into a single integrated circuit. Suitable I / O buses for connecting peripheral devices such as hard disk controllers, network adapters, and graphics adapters typically include common protocols such as the Peripheral Component Interconnect (PCI). Thus, as shown in FIG. Fig.11 As configured, the computer system 1100 includes processing capabilities in the form of a processor 1101, as well as storage capabilities including a system memory 1103 and a mass storage device 1110, input devices such as buttons and a touch screen, and output capabilities including a speaker 1123 and a display 1119.

[0078] In some aspects, the communication adapter 1107 can use any suitable interface or protocol (such as Internet Small Computer System Interface, etc.) to transmit data. The network 1112 can be a cellular network, a radio network, a wide area network (WAN), a local area network (LAN), or the Internet, etc. An external computing device can be connected to the computer system 1100 through the network 1112. In some examples, the external computing device can be an external network server or a cloud computing node.

[0079] It should be understood that Fig.11 The block diagram is not intended to indicate that the computer system 1100 will include Fig.11 Instead, the computer system 1100 may include Fig.11 1100 (e.g., additional memory components, embedded controllers, modules, additional network interfaces, etc.). Further, the aspects described herein with respect to computer system 1100 may be implemented with any appropriate logic, wherein, in various aspects, the logic as mentioned herein may include any appropriate hardware (e.g., a processor, an embedded controller, or an application specific integrated circuit, etc.), software (e.g., an application, etc.), firmware, or any appropriate combination of hardware, software, and firmware.

[0080] Exemplary aspects of the technical solutions described herein relate to, among other things, devices, systems, methods, computer-readable media, techniques, and methodologies for identifying surgical outliers and generating related visualizations using machine learning and computer vision.

[0081] Computer readable storage medium can be a tangible device that can retain and store instructions for use by instruction execution devices. Computer readable storage medium can be, for example, but not limited to, electronic storage devices, magnetic storage devices, optical storage devices, electromagnetic storage devices, semiconductor storage devices, or any suitable combination of the above. A non-exhaustive list of more specific examples of computer readable storage medium includes the following: portable computer disk, hard disk, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), static random access memory (SRAM), portable compact disc read-only memory (CD-ROM), digital versatile disk (DVD), memory stick, floppy disk, mechanical encoding device (such as punch card or the convex structure in the groove with instructions recorded thereon) and any suitable combination of the above. Computer readable storage medium used herein should not be interpreted as instantaneous signal itself, such as radio waves or other free propagating electromagnetic waves, electromagnetic waves propagated by waveguides or other transmission media (for example, light pulses transmitted by fiber optic cables), or electrical signals transmitted by wires.

[0082] The computer-readable program instructions described herein can be downloaded from a computer-readable storage medium to a corresponding computing / processing device via a network (e.g., the Internet, a local area network, a wide area network, and / or a wireless network), or downloaded to an external computer or external storage device. The network can include copper transmission cables, optical transmission fibers, wireless transmissions, routers, firewalls, switches, gateway computers, and / or edge servers. The network adapter card or network interface in each computing / processing device receives the computer-readable program instructions from the network and forwards the computer-readable program instructions to be stored in a computer-readable storage medium in the corresponding computing / processing device.

[0083] The computer-readable program instructions for performing the operation of the present invention may be assembly instructions, instruction set architecture (ISA) instructions, machine instructions, machine-related instructions, microcode, firmware instructions, state setting data, configuration data of an integrated circuit, or source code or object code written in any combination of one or more programming languages, including object-oriented programming languages ​​such as Smalltalk, C++, and procedural programming languages ​​such as "C" programming language or similar programming languages. The computer-readable program instructions may be executed completely on a user's computer, partially on a user's computer, executed as an independent software package, partially on a user's computer, and partially on a remote computer, or completely on a remote computer or server. In the latter scenario, a remote computer may be connected to a user's computer via any type of network (including a local area network (LAN) or a wide area network (WAN)), or may be connected to an external computer (e.g., via the Internet, using an Internet service provider). In some respects, an electronic circuit including, for example, a programmable logic circuit, a field programmable gate array (FPGA), or a programmable logic array (PLA) may be personalized electronic circuits to execute computer-readable program instructions using the state information of the computer-readable program instructions, so as to perform various aspects of the present invention.

[0084] Various aspects of the present invention are described herein with reference to flowchart illustrations and / or block diagrams of methods, devices (systems) and computer program products according to various aspects of the present invention. It will be understood that each frame of the flowchart illustration and / or block diagram and the combination of frames in the flowchart illustration and / or block diagram can be implemented by computer-readable program instructions.

[0085] These computer-readable program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, or other programmable data processing device to produce a machine, so that the instructions executed by the processor of the computer or other programmable data processing device create a way to implement the functions / actions specified in one or more boxes of the flowchart and / or block diagram. These computer-readable program instructions can also be stored in a computer-readable storage medium, which can instruct a computer, a programmable data processing device, and / or other equipment to operate in a specific manner, so that the computer-readable storage medium in which the instructions are stored includes an article of manufacture, which includes instructions for implementing various aspects of the functions / actions specified in one or more boxes of the flowchart and / or block diagram.

[0086] Computer-readable program instructions may also be loaded onto a computer, other programmable data processing apparatus, or other device to cause a series of operating steps to be performed on the computer, other programmable apparatus, or other device, thereby producing a computer-implemented process, so that the instructions executed on the computer, other programmable apparatus, or other device implement the functions / actions specified in one or more boxes of the flowchart and / or block diagram.

[0087] The flowcharts and block diagrams in the accompanying drawings show the architecture, functions and operations of possible implementations of systems, methods and computer program products according to various aspects of the present invention. In this regard, each box in the flowchart or block diagram can represent a module, fragment or part of an instruction, which includes one or more executable instructions for implementing (multiple) specific logical functions. In some alternative embodiments, the functions marked in the box may not occur in the order marked in the accompanying drawings. For example, depending on the functions involved, the two boxes shown in succession can actually be executed substantially simultaneously, or these boxes can sometimes be executed in reverse order. It will also be noted that each box of the block diagram and / or flowchart illustration and the combination of boxes in the block diagram and / or flowchart illustration can be implemented by a dedicated hardware-based system that performs a combination of a specified function or action or performs dedicated hardware and computer instructions.

[0088] The description of various aspects of the present invention is presented for the purpose of illustration, but is not intended to be exhaustive or limited to the disclosed aspects. Various modifications and variations will be apparent to those skilled in the art without departing from the scope and spirit of the described aspects. The terms used herein are selected to best explain the principles of various aspects, practical applications or technical improvements over existing technologies on the market, or to enable those of ordinary skill in the art to understand the various aspects described herein.

[0089] Various aspects of the present invention are described herein with reference to the accompanying drawings. Without departing from the scope of the present invention, alternative aspects of the present invention can be designed. Various connections and positional relationships (e.g., above, below, adjacent, etc.) between elements are set forth in the following description and the accompanying drawings. Unless otherwise indicated, these connections and / or positional relationships may be direct or indirect, and the present invention is not intended to be limited in this respect. Accordingly, the coupling of entities may refer to direct or indirect coupling, and the positional relationship between entities may be direct or indirect positional relationships. In addition, the various tasks and process steps described herein may be incorporated into a more comprehensive program or process with additional steps or functions not described in detail herein.

[0090] The following definitions and abbreviations are used to interpret the claims and specification. As used herein, the terms "comprises / comprising / includes / including", "has / having", or "contains / containing" or any other variation thereof are intended to cover a non-exclusive inclusion. For example, a composition, mixture, process, method, article, or apparatus that includes a list of elements is not necessarily limited to only those elements but may include other elements not expressly listed or inherent to such composition, mixture, process, method, article, or apparatus.

[0091] Additionally, the term "exemplary" is used herein to mean "serving as an example, instance, or illustration." Any aspect or design described herein as "exemplary" is not necessarily to be construed as preferred or advantageous over other aspects or designs. The terms "at least one" and "one or more" may be understood to include any integer greater than or equal to one, i.e., one, two, three, four, etc. The term "plurality" may be understood to include any integer greater than or equal to two, i.e., two, three, four, five, etc. The term "connected" may include both indirect "connections" and direct "connections."

[0092] The terms "about," "substantially," "approximately," and variations thereof are intended to include the degree of error associated with measuring a particular quantity based on the equipment available at the time the application was filed. For example, "about" may include a range of ±8% or 5% or 2% of a given value.

[0093] For the sake of brevity, conventional techniques related to making and using various aspects of the present invention may or may not be described in detail herein. In particular, various aspects of computing systems and specific computer programs for implementing the various technical features described herein are well known. Accordingly, for the sake of brevity, many conventional implementation details are only briefly mentioned herein or omitted entirely, without providing well-known system and / or process details.

[0094] It should be understood that the various aspects disclosed herein may be combined in combinations different from those specifically presented in the specification and drawings. It should also be understood that, according to examples, certain actions or events of any process or method described herein may be performed in a different order, may be added, combined, or omitted entirely (e.g., all described actions or events may not be necessary to implement these techniques). In addition, although for clarity, certain aspects of the present disclosure are described as being performed by a single module or unit, it should be understood that the technology of the present disclosure may be performed by a combination of units or modules associated with, for example, a surgical system.

[0095] In one or more examples, the described techniques can be implemented in hardware, software, firmware, or any combination thereof. If implemented in software, the functions can be stored as one or more instructions or codes on a computer-readable medium and executed by a hardware-based processing unit. The computer-readable medium may include a non-transitory computer-readable medium, which corresponds to a tangible medium such as a data storage medium (e.g., RAM, ROM, EEPROM, flash memory, or any other medium that can be used to store the desired program code in the form of instructions or data structures and can be accessed by a computer).

[0096] Instructions may be executed by one or more processors, such as one or more digital signal processors (DSPs), general-purpose microprocessors, application-specific integrated circuits (ASICs), field programmable logic arrays (FPGAs), or other equivalent integrated or discrete logic circuits. Accordingly, the term "processor" as used herein may refer to any of the above structures or any other physical structures suitable for implementing the described techniques. In addition, these techniques may be fully implemented in one or more circuits or logic elements.

Claims

1. A system for identifying surgical workflow outliers, comprising: a non-transitory memory storing a plurality of surgical workflows; as well as a processor configured to access the plurality of surgical workflows and analyze the workflows to identify one or more surgical workflows as outliers for review, wherein the one or more surgical workflows so identified are further identified as including events of interest or low quality data, Among them, the identification of outliers involves using a density-based clustering algorithm to determine the distances between workflows.

2. The system according to claim 1, wherein: The processor is further configured to provide a visualization of the workflow and outliers on the display.

3. The system according to claim 2, wherein: Visualization using uniform manifold approximation and projection techniques.

4. A system according to claim 1 or claim 2, wherein: The display or interface identifies surgical workflow details or annotations for each workflow.

5. The system according to claim 4, wherein: Each surgical workflow is shown as a linear sequence of identified details.

6. The system according to claim 5, wherein: The surgical dashboard interface utilizes these surgical workflow details or annotations to display the multiple surgical workflows and provide accessible tools for identifying outliers.

7. The system according to claim 6, wherein: Surgical workflow details and identified outliers are color-coded to identify details within each workflow.

8. A method for identifying surgical workflow outliers, comprising: analyzing, by a processor, a plurality of surgical workflows to identify one or more surgical workflows as outliers for review, wherein the one or more surgical workflows so identified are further identified as including events of interest, Among them, the identification of outliers involves using a density-based clustering algorithm to determine the distances between workflows.

9. The method of claim 8, further comprising providing a visualization of the workflow and outliers as output on a display.

10. The method according to claim 9, wherein: Visualization using uniform manifold approximation and projection techniques.

11. The method of any one of claims 8 to 10, further comprising displaying surgical workflow details or annotations for each workflow.

12. The method according to claim 11, wherein: Each surgical workflow is shown as a linear sequence of identified details.

13. The method according to claim 12, wherein: The displaying includes providing a surgical dashboard interface that displays the plurality of surgical workflows with the surgical workflow details or annotations and provides accessible tools for identifying outliers.

14. The method according to claim 13, wherein: Surgical workflow details and identified outliers are color-coded to identify details within each workflow.

15. A computer-implemented method for identifying surgical workflow outliers, comprising: analyzing, by a processor, the plurality of surgical workflows to identify one or more surgical workflows that are outliers for review, Among them, the identification of outliers involves using a density-based clustering algorithm to determine the distances between workflows.

16. The computer-implemented method of claim 15, further comprising providing a visualization of the workflow and outliers as output on a display.

17. The computer-implemented method of claim 16, wherein: Visualization using uniform manifold approximation and projection techniques.

18. The computer-implemented method of any one of claims 15 to 17, further comprising displaying surgical workflow details or annotations for each workflow.

19. The computer-implemented method of claim 18, wherein: Each surgical workflow is shown as a linear sequence of identified details.

20. The computer-implemented method of claim 19, wherein: The display includes providing a surgical dashboard interface that displays the plurality of surgical workflows using the surgical workflow details or annotations and provides accessible tools for identifying outliers, and wherein the surgical workflow details and identified outliers are color coded to identify details within each workflow.