Systems and methods for detecting tissue contact by an ultrasound probe

Abstract

A contact detection system (300) includes a memory (302) that stores instructions (306) and a processor (304) that is communicatively coupled to the memory and configured to execute the instructions to: classify each pixel in an ultrasound image captured by an ultrasound probe located within a patient as display tissue or display non-tissue, and determine a contact state of the ultrasound probe based on the classification, the contact state indicating whether the ultrasound probe is in surgical physical contact with the patient's tissue. Based on the determined contact state, the contact detection system can, for example, control the display of the ultrasound image within a visual image displayed by a display device, set parameters of an ultrasound machine connected to the ultrasound probe, and / or generate a control signal that is configured to be used by a computer-assisted surgery system to control the positioning of the ultrasound probe.

Description

[0001] Related Inventions

[0002] This application claims priority to U.S. Provisional Patent Application No. 62 / 855,881, filed May 31, 2019, entitled "SYSTEMS AND METHODS FOR DETECTING TISSUE CONTACT BY AN ULTRASOUND PROBE", the content of which is incorporated herein by reference in its entirety. Background Art

[0003] During a surgical procedure, an endoscope can be positioned within a patient to capture endoscopic images of a surgical region within the patient. The endoscopic images can be presented to a surgeon via a display device such that the surgeon can visualize the internal anatomy and the outer surfaces of other types of tissue within the patient while performing the surgical procedure.

[0004] In some scenarios, an ultrasound probe can also be positioned within the patient to capture ultrasound images within the patient during a surgical procedure. The ultrasound images can be presented to the surgeon simultaneously with the endoscopic images (e.g., via the same display device that presents the endoscopic images). In this manner, the surgeon can visualize both the outer surfaces of the tissues included in the surgical region (using the endoscopic images) and the internal structures of the tissues within the surgical region (using the ultrasound images) while performing the surgical procedure.

[0005] To capture useful ultrasound images, the ultrasound probe must make good physical contact with the tissue. Poor contact between the ultrasound probe and the tissue will result in ultrasound images that are dominated by noise (e.g., noise generated by electronic components and / or signal artifacts that appear near the transducer surface of the ultrasound probe). If the ultrasound probe does not make good contact with the tissue, presenting the ultrasound images to the surgeon during the surgical procedure may be distracting and / or useless. Summary of the Invention

[0006] An exemplary system includes a memory storing instructions; and a processor communicatively coupled to the memory and configured to execute the instructions to: classify each pixel among a plurality of pixels included in an ultrasound image captured by an ultrasound probe positioned within a patient as displaying tissue or displaying non-tissue; and determine a contact state of the ultrasound probe based on the classification of each pixel among the plurality of pixels as displaying tissue or displaying non-tissue, the contact state indicating whether the ultrasound probe is in operative physical contact with the tissue of the patient.

[0007] Another exemplary system includes a memory storing instructions and a processor communicatively coupled to the memory and configured to execute the instructions to: determine a contact state of an ultrasound probe based on an ultrasound image captured by an ultrasound probe located within a patient, the contact state indicating whether the ultrasound probe is in surgical physical contact with the patient's tissue; and control the display of the ultrasound image within a visual image displayed on a display device based on the contact state of the ultrasound probe.

[0008] An exemplary method includes classifying each pixel among a plurality of pixels included in an ultrasound image captured by an ultrasound probe located within a patient as display tissue or display non-tissue by a contact detection system; and determining, by the contact detection system, a contact state of the ultrasound probe based on classifying each pixel among the plurality of pixels as display tissue or display non-tissue, the contact state indicating whether the ultrasound probe is in surgical physical contact with the patient's tissue. BRIEF DESCRIPTION OF THE DRAWINGS

[0009] The drawings illustrate various embodiments and are a part of this specification. The illustrated embodiments are merely examples and do not limit the scope of the disclosure. Throughout the drawings, the same or similar reference numerals represent the same or similar elements.

[0010] Figure 1 Shows various components of an exemplary ultrasound imaging system in accordance with the principles described herein.

[0011] Figures 2A to 2C Shows different possible physical states of an ultrasound probe relative to tissue in accordance with the principles described herein.

[0012] Figure 3 Shows an exemplary contact detection system in accordance with the principles described herein.

[0013] Figure 4A Shows a detailed view of an ultrasound image in accordance with the principles described herein.

[0014] Figure 4B Shows in accordance with the principles described herein Figure 4A an exemplary region of interest within the ultrasound image.

[0015] Figures 5A to 5B Shows an exemplary visual image displayed on a display device in accordance with the principles described herein.

[0016] Figures 6A to 6B Shows an exemplary visual image displayed on a display device in accordance with the principles described herein.

[0017] Figure 7 Shows an exemplary computer-assisted surgical system in accordance with the principles described herein.

[0018] Figures 8 to 12 An exemplary method in accordance with the principles described herein is shown.

[0019] Figure 13 An exemplary computing device in accordance with the principles described herein is shown. DETAILED DESCRIPTION

[0020] Systems and methods for detecting tissue contact by an ultrasound probe are described herein. For example, a contact detection system can be configured to classify each of a plurality of pixels included in an ultrasound image captured by an ultrasound probe located within a patient as displaying tissue or displaying non - tissue, and determine a contact state of the ultrasound probe based on the classification of each of the plurality of pixels as displaying tissue or displaying non - tissue. The contact state indicates whether the ultrasound probe is in surgical physical contact with the patient's tissue.

[0021] In some examples, the contact detection system can determine local descriptor values of a plurality of pixels included in an ultrasound image captured by an ultrasound probe located within a patient and use the local descriptor values to perform the classification. As described herein, the local descriptor values can characterize the intensity distribution and / or spatial autocorrelation of each of the plurality of pixels.

[0022] As used herein, surgical physical contact means that when the ultrasound probe makes sufficient tissue contact to capture a useful ultrasound image (i.e., an ultrasound image that includes at least a threshold amount of useful information instead of or in addition to noise, where the threshold amount can be determined in any of the ways described herein). Thus, the ultrasound probe can be in surgical physical contact with the tissue by full physical contact with the tissue or partial physical contact with the tissue, as long as the partial physical contact is sufficient to present a useful ultrasound image. When the ultrasound probe does not make sufficient tissue contact to capture a useful ultrasound image, the ultrasound probe is not in surgical physical contact with the tissue.

[0023] Based on the determined contact state of the ultrasound probe, the contact detection system can perform one or more operations. For example, based on the contact state of the ultrasound probe, the contact detection system can control the display of the ultrasound image within a visual image displayed on a display device, set parameters of an ultrasound machine connected to the ultrasound probe, and / or generate control signals configured to be used by a computer - assisted surgery system to control the positioning of the ultrasound probe. These and other operations that can be performed by the contact detection system based on the determined contact state of the ultrasound probe are described herein.

[0024] The systems and methods described herein can provide various advantages and benefits. For example, when an ultrasound image does not include useful information, the systems and methods described herein can intelligently prevent the ultrasound image from being included in the visual image presented to a user (e.g., a surgeon), thereby providing an improved visual experience for the user during a surgical procedure. Additionally or alternatively, the systems and methods described herein can automatically optimize one or more settings of an ultrasound machine used during a surgical procedure, thereby improving the quality of the ultrasound images generated by the ultrasound machine. Additionally or alternatively, the systems and methods described herein can facilitate the optimal positioning of an ultrasound probe within a patient. Each of these operations can improve the efficiency and effectiveness of a surgical procedure.

[0025] The systems and methods described herein advantageously determine whether an ultrasound probe is in surgical physical contact with tissue based only on the content of an ultrasound image (also referred to as a B-mode image). In particular, the systems and methods described herein can be configured to distinguish speckle (content in an ultrasound image generated by the constructive and destructive coherence of sound waves reflected from structures within tissue) from unwanted noise included in the ultrasound image. Although speckle may visually resemble noise, the intensity distribution and spatial autocorrelation of speckle within an ultrasound image are different from those of noise. The system and method utilize this difference to determine whether the ultrasound probe is in surgical physical contact with tissue. This can advantageously result in a substantially real-time determination of the contact state of the ultrasound probe.

[0026] These and other advantages and benefits of the systems and methods described herein will be apparent herein.

[0027] Figure 1 Various components of an exemplary ultrasound imaging system 100 are illustrated. As shown, the ultrasound imaging system 100 can include an ultrasound machine 102, an ultrasound probe 104, and a display device 106. The ultrasound machine 102 is communicatively coupled to the ultrasound probe 104 via a communication link 108 and is communicatively coupled to the display device 106 via a communication link 110. The communication links 108 and 110 can be implemented via any suitable wired and / or wireless components. For example, the communication link 108 can be implemented as a cable, shaft, or other structure that carries one or more wires that communicatively interconnect the ultrasound machine 102 and the ultrasound probe 104.

[0028] The ultrasound machine 102 may include computing components configured to facilitate the generation of ultrasound images. For example, the ultrasound machine 102 may include a controller configured to control the operation of the ultrasound probe 104 by guiding the ultrasound probe 104 to emit and detect sound waves. In some examples, the controller and / or any other components of the ultrasound machine 102 are configured to operate according to one or more definable (e.g., adjustable) parameters. For example, the ultrasound machine 102 may be configured to guide the ultrasound probe 104 to emit sound waves having a definable frequency and / or receive sound waves at a particular gain. As another example, the ultrasound machine 102 may also be configured to specify the sector depth of the ultrasound image 114.

[0029] The ultrasound machine 102 may additionally or alternatively include one or more image processing components configured to generate ultrasound image data 112 based on the sound waves detected by the ultrasound probe 104. As shown, the ultrasound machine 102 may transmit the ultrasound image data 112 to the display device 106 via the communication link 110. The display device 106 may use the ultrasound image data 112 to generate and display an ultrasound image 114.

[0030] In some examples, the ultrasound machine 102 is connected to, integrated into, or implemented by a surgical system. For example, the ultrasound machine 102 may be connected to, integrated into, or implemented by a computer-assisted surgical system that utilizes robotic and / or teleoperation technologies to perform surgical procedures (e.g., minimally invasive surgical procedures). Exemplary computer-assisted surgical systems are described herein.

[0031] The ultrasound probe 104 (also referred to as a transducer) is configured to capture an ultrasound image by emitting sound waves and detecting the sound waves after they are reflected from structures inside the body (e.g., internal structures of an organ or other tissue within a patient). The ultrasound probe 104 may have any suitable shape and / or size to serve a particular implementation. In some examples, the ultrasound probe 104 may have a shape and size that allows the ultrasound probe 104 to be inserted into a patient through a port in the patient's body wall. In these examples, the positioning of the ultrasound probe 104 within the patient may be manually controlled (e.g., by manually manipulating the shaft to which the ultrasound probe 104 is attached). Additionally or alternatively, the positioning of the ultrasound probe 104 may be controlled in a computer-assisted manner (e.g., by a computer-assisted surgical system utilizing robotic and / or teleoperation technologies).

[0032] The display device 106 can be implemented by any suitable device configured to render or display an ultrasound image 114 based on the ultrasound image data 112. As described herein, the display device 106 can also be configured to display additional or alternative images and / or information. For example, in some scenarios, the display device 106 can display a visual image including the ultrasound image 114 and an endoscopic image obtained by an endoscope, and / or a preoperative model (e.g., a 3D model) of the patient's anatomy registered with the endoscopic image.

[0033] As described above, the ultrasound probe 104 must be in surgical physical contact with the patient's tissue to capture useful ultrasound images. For illustration, Figures 2A to 2C illustrates different possible contact states of the ultrasound probe 104 relative to the tissue 202. The tissue 202 can represent any organ or anatomical feature of the patient.

[0034] Figure 2A illustrates a first contact state in which the ultrasound probe 104 is in surgical physical contact with the tissue 202. As shown, the entire bottom surface 204 of the ultrasound probe 104 (which is convex in the examples provided herein) is in physical contact with the tissue 202. In this contact state, there is sufficient acoustic coupling between the ultrasound probe 104 and the tissue 202 to capture useful ultrasound images.

[0035] Figure 2B illustrates a second contact state in which the ultrasound probe 104 is not in surgical physical contact with the tissue 202. As shown, there is a separation gap 206 between the bottom surface 204 of the ultrasound probe 104 and the tissue 202. In this contact state, since there is no physical contact between the ultrasound probe 104 and the tissue 202, the ultrasound images captured by the ultrasound probe 104 will be dominated by noise and thus useless to the user.

[0036] Figure 2C illustrates another example of the second contact state in which the ultrasound probe 104 is not in surgical physical contact with the tissue 202. In Figure 2C only a small portion of the bottom surface 204 of the ultrasound probe 104 is in physical contact with the tissue 202. Thus, if the amount of useful information included in the ultrasound images generated by the ultrasound probe 104 is below a specific threshold, it can be determined that the ultrasound probe 104 is not in surgical physical contact with the tissue 202. Therefore, as Figure 2C shown, even if the ultrasound probe 104 is at least partially in contact with the tissue 202, the ultrasound probe 104 may sometimes not be in surgical physical contact with the tissue 202.

[0037] Figure 3An exemplary contact detection system 300 (“system 300”) is shown, which can be configured to detect tissue contact through an ultrasound probe (e.g., ultrasound probe 104). System 300 can be included in, implemented by, or connected to any surgical system, ultrasound machine, or other computing system described herein. For example, system 300 can be implemented by a computer-assisted surgical system and / or an ultrasound machine 102. As another example, the contact detection system 300 can be implemented by an independent computing system communicatively coupled to a computer-assisted surgical system and / or an ultrasound machine 102.

[0038] As shown, system 300 can include, but is not limited to, a storage facility 302 and a processing facility 304 that are selectively and communicatively coupled to each other. Facilities 302 and 304 can each include hardware and / or software components (e.g., processors, memories, communication interfaces, instructions stored in the memory for execution by the processor, etc.) or be implemented by them. For example, facilities 302 and 304 can be implemented by any component in a computer-assisted surgical system. In some examples, facilities 302 and 304 can be distributed among multiple devices and / or multiple locations to serve a particular implementation.

[0039] The storage facility 302 can maintain (e.g., store) executable data used by the processing facility 304 to perform any of the operations described herein. For example, the storage facility 302 can store instructions 306 executable by the processing facility 304 to perform any of the operations described herein. Instructions 306 can be implemented by any suitable application, software, code, and / or other executable data instance. The storage facility 302 can also maintain any data received, generated, managed, used, and / or transmitted by the processing facility 304.

[0040] The processing facility 304 can be configured to perform (e.g., execute instructions 306 stored in the storage facility 302 to perform) various operations associated with detecting tissue contact through an ultrasound probe. For example, the processing facility 304 can be configured to classify each of a plurality of pixels included in an ultrasound image captured by an ultrasound probe located within a patient as showing tissue or showing non-tissue. The processing facility 304 can further be configured to determine the contact state of the ultrasound probe based on the classification of each of the plurality of pixels as showing tissue or showing non-tissue. These and other operations that can be performed by the processing facility 304 are described herein. In the following description, any reference to an operation performed by system 300 can be understood to be performed by the processing facility 304 of system 300.

[0041] Figure 4AIllustrates a detailed view of the ultrasound image 114. As shown, the ultrasound image 114 includes a plurality of pixels (e.g., pixel 402). Each pixel has an intensity value defined by the ultrasound image data 112. The term "pixel" is used herein to refer to any suitable sized and / or shaped region of the ultrasound image 114 to serve a particular implementation.

[0042] In some examples, the system 300 can limit the processing of its pixels to the pixels within a particular region of interest for the purpose of determining the contact state of the ultrasound probe 104. For example, Figure 4B An exemplary region of interest 404 within the ultrasound image 114 is shown. In this case, the system 300 can determine only the local descriptor values of the pixels within the region of interest 404 rather than a set of pixels outside the region of interest 404. This can limit the effects of artifacts near the surface of the ultrasound probe ( Figure 4B region A in) and deeper signal loss in the ultrasound image 114 ( Figure 4B region B in), as both regions can confound the results of the system 300 processing the local descriptor values. As shown, the left and right boundary regions of the ultrasound image 114 ( Figure 4B region C in) can also be excluded from the region of interest 404. Alternatively, boundary processing heuristics can be used to include boundary region pixels in the processing. The region of interest 404 can include any suitable number of pixels to serve a particular implementation. In some examples, the region of interest 404 includes all the pixels included in the ultrasound image 114. In other examples, multiple regions of interest can be included in the ultrasound image 114.

[0043] The system 300 can determine one or more local descriptor values for each pixel included in the region of interest 404 in any suitable manner. The local descriptor values characterize the intensity distribution of each pixel in the region of interest 404 and / or the spatial autocorrelation of each pixel in the region of interest 404. Exemplary local descriptor values characterizing pixel intensity distribution include moments of the pixel intensity distribution (e.g., local variance and / or mean) and / or any other metric representing the pixel intensity distribution. Exemplary local descriptor values characterizing spatial autocorrelation include autocorrelation values (e.g., one or more terms of the autocovariance function) and / or any other metric representing the spatial autocorrelation of the pixel.

[0044] In some examples, the autocorrelation value determined by the system 300 is a spatial autocorrelation value (e.g., a lag-1 autocorrelation value in the vertical (y) or horizontal (x) direction). Additionally or alternatively, the autocorrelation value can be temporal. In the examples provided herein, it will be assumed that the autocorrelation value is spatial.

[0045] In some examples, system 300 can determine multiple local descriptor values for each pixel in region of interest 404. For example, system 300 can determine a local variance value and an autocorrelation value for each pixel included in region of interest 404. In some alternative examples, system 300 can determine only a single local descriptor value for each pixel. For example, system 300 can merely determine the local variance value for each pixel included in region of interest 404. Examples of determining local descriptor values for pixels are described herein.

[0046] System 300 can classify pixels as display tissue or display non - tissue in any suitable manner based on the local descriptor values. System 300 can alternatively classify pixels as display tissue or display non - tissue in any other suitable manner. For example, one or more image processing techniques, machine learning techniques, etc. can be used to classify pixels as display tissue or display non - tissue. However, for illustrative purposes, the classification examples herein are based on local descriptor values.

[0047] For example, system 300 can compare the local descriptor values with one or more thresholds. For illustration, system 300 can classify pixels with local descriptor values higher than the local descriptor threshold as display tissue and pixels with local descriptor values lower than the local descriptor threshold as display non - tissue.

[0048] As an example, the local descriptors determined by system 300 can include a local variance value and an autocorrelation value. In this example, system 300 can classify pixels with a local variance value higher than the variance threshold and an autocorrelation value higher than the autocorrelation threshold as display tissue. Similarly, system 300 can classify pixels with a local variance value lower than the variance threshold and / or an autocorrelation value lower than the autocorrelation threshold as display non - tissue. These thresholds can be determined in a variety of different ways, some of which are described herein.

[0049] As another example, system 300 can merely determine the local variance value for each pixel. In this example, system 300 can classify pixels with a local variance value higher than the variance threshold as display tissue and pixels with a local variance value lower than the variance threshold as display non - tissue.

[0050] Additionally or alternatively, system 300 can classify pixels as display tissue or display non - tissue by providing the local descriptor values as inputs to a machine learning model and based on the output of the machine learning model, classify each pixel in region of interest 404 as display tissue or display non - tissue. The machine learning model can be supervised and / or unsupervised and can be implemented by any suitable algorithm, such as logistic regression, classification and regression trees, random forests, and / or neural networks.

[0051] Additionally or alternatively, system 300 may classify a pixel as display tissue or display non - tissue by evaluating any other type of function that may serve a particular implementation. The function may output a binary classification of display tissue or non - tissue or a fuzzy value indicating the probability that the pixel is display tissue or non - tissue. In the latter case, the probability may then be compared to a threshold for a binary classification of display tissue or non - tissue.

[0052] Once the pixels in the region of interest 404 are classified as display tissue or display non - tissue, system 300 may determine the contact state of the ultrasound probe based on the classification of each pixel as display tissue or display non - tissue. The contact state indicates whether the ultrasound probe is in surgical physical contact with the patient's tissue.

[0053] System 300 may use the classification of each pixel as display tissue or display non - tissue to determine the contact state in any suitable manner. For example, system 300 may determine an average pixel classification, which represents the number of pixels classified as display tissue compared to the number of pixels classified as display non - tissue. The average pixel classification may be the ratio of pixels classified as display tissue to pixels classified as display non - tissue and this ratio is compared to a contact state threshold, which may be determined in a variety of different ways as described herein. Additionally or alternatively, the average pixel classification may be a mean, median, or other suitable metric.

[0054] If the average pixel classification is higher than the contact state threshold, system 300 may determine that the ultrasound probe 104 is in a first contact state, which indicates that the ultrasound probe 104 is in surgical physical contact with the patient's tissue. If the average pixel classification is lower than the contact state threshold, system 300 may determine that the ultrasound probe 104 is in a second contact state, which indicates that the ultrasound probe 104 is not in surgical physical contact with the patient's tissue.

[0055] In some examples, system 300 may use two different contact state thresholds for debouncing purposes. For example, system 100 may initially compare the average pixel classification to a first contact state threshold. Once the average pixel classification is higher than the first contact state threshold, system 300 may determine that the ultrasound probe 104 is in a first contact state indicating that the ultrasound probe 104 is in surgical physical contact with the patient tissue. While the ultrasound probe 104 is in the first contact state, the average pixel classification must be lower than a second contact state threshold (the second contact state threshold is lower than the first contact state threshold of system 300) to determine that the ultrasound probe 104 is in a second contact state where the ultrasound probe 104 is not in surgical physical contact with the patient's tissue.

[0056] System 300 may determine the contact state of the ultrasound probe 104 in any other suitable manner. For example, system 300 may provide a classification to a machine learning model and use the output of the machine learning model to determine the contact state of the ultrasound probe 104. As another example, system 300 may evaluate any suitable function based on the classification to determine the contact state of the ultrasound probe 104.

[0057] In some examples, before determining the local descriptor values, system 300 may optionally determine the background intensity of the ultrasound image 114 and generate a reduced ultrasound image by subtracting the background intensity from the ultrasound image 114. Then system 300 may determine the local descriptor values of the pixels in the ultrasound image 114 by determining the local descriptor values of the pixels included in the reduced ultrasound image.

[0058] Specific processing heuristics that may be performed by system 300 in accordance with the principles described herein to determine the contact state of the ultrasound probe 104 will now be described. It will be appreciated that the processing heuristics are examples of various different processing heuristics that may be performed by system 300 to determine the contact state of the ultrasound probe 104.

[0059] As previously mentioned, due to speckle, ultrasound images may appear noisy. However, the intensity distribution and spatial autocorrelation of speckle are different from those of noise. Since the image content and gain settings can vary across the image, the autocovariance function can be locally evaluated according to the following equation: W j，k (x, y) = E[(I(x, y) - μ(x, y))(I(x + j, y + k) - μ(x + j, y + k))].

[0060] In the equation, W j，k (x, y) is the spatial autocovariance at positions x and y, I(x, y) is the image intensity value, and μ(x, y) is the local average intensity.

[0061] To distinguish between noise and speckle (representing tissue), system 300 may determine one or more (also referred to as coefficients) of the local average intensity and the autocovariance function.

[0062] For example, system 300 may first perform background subtraction on the ultrasound image 114. For illustration, system 300 may use a box filter H1 (e.g., a 7×7 pixel filter) to evaluate the background intensity and then subtract the background intensity from the original ultrasound image 114 to produce a reduced image, where,

[0063] System 300 may then determine one or more of the autocovariance function. For example, system 300 may determine the evaluation values within the local neighborhood around each pixel For example, system 300 may be based on the following equation and use a second box filter H2 (e.g., a 13×13 pixel filter).

[0064] System 300 may then generate a binary tissue map T(x, y) that shows which pixels are consistent with signals from ultrasonic waves reflected or backscattered from tissue. For example, the binary tissue map may be generated according to the following equation:

[0065] In this equation, v and AC1 are threshold parameters corresponding to the minimum variance and lag-1 autocorrelation in the vertical direction. In the examples herein, the autocorrelation is the autocovariance function normalized by variance (i.e., ).

[0066] System 300 may optionally apply morphological processing to remove isolated pixels from T(x, y) and produce a smoother map. The morphological processing may be performed in any suitable manner.

[0067] System 300 may use the pixel ratio within the region of interest 404 (where tissue is detected) to determine the contact state of the ultrasonic probe 104 according to the following equation: ∑ ROI T(x, y) / N ROI .

[0068] In some examples, to prevent jitter between contact states, system 300 may use two thresholds. For example, if ∑ ROI T(x, y) / N ROI is higher than the first contact state threshold, system 300 may determine that the ultrasonic probe 104 is in a first contact state indicating that the ultrasonic probe 104 is in surgical physical contact with the patient's tissue. Once in this state, before system 300 determines that the ultrasonic probe 104 is in a second contact state indicating that the ultrasonic probe 104 is not in surgical physical contact with the patient's tissue, ∑ ROI T(x, y) / N ROI must be lower than the second contact state threshold (which is lower than the first contact state threshold).

[0069] In some alternative embodiments, system 300 may obtain a local evaluation of the autocovariance function by using a frequency domain method based on the short-time Fourier transform (STFT) or wavelet transform. The STFT coefficients or the coefficients of another wavelet transform may be directly used to generate the tissue maps described herein. In some examples, the coefficients of the autocovariance function described herein may be replaced with the coefficients of the STFT or wavelet transform.

[0070] In some examples, any of the thresholds described herein (e.g., the local descriptor threshold and the contact state threshold described herein) can be set by system 300 in response to user input. In this way, the user can manually adjust the threshold to an appropriate level. Additionally or alternatively, any of the thresholds described herein can be set based on the output of a machine learning model. The thresholds described herein can additionally or alternatively be determined in any other way.

[0071] System 300 can perform various operations based on the contact state of ultrasound probe 104. For example, based on the contact state of ultrasound probe 104, system 300 can control the display of ultrasound image 114 within the visual image displayed by display device 106.

[0072] For illustration, Figures 5A to 5B an exemplary visual image 502 displayed by display device 106 is shown. Visual image 502 includes an endoscopic image of a surgical area within a patient captured by an endoscope. As shown in Figures 5A to 5B both, the endoscopic image depicts tissue 504 (e.g., an organ within the patient), a surgical tool 506 configured to manipulate tissue 504 in response to user input, and ultrasound probe 104. Although visual image 502 is depicted as a two-dimensional image in Figures 5A to 5B this, it will be appreciated that in other examples, visual image 502 can alternatively be a three-dimensional image.

[0073] In some examples, visual image 502 can further include a preoperative model of the patient's anatomy within the surgical area depicted in visual image 502. This is more fully described in U.S. Provisional Patent Application No. 62 / 855,755, the contents of which are incorporated herein by reference in their entirety. The preoperative model can be registered with the endoscopic image such that the positioning of the model within visual image 502 corresponds to the actual positioning of the patient's anatomy. For example, the preoperative model can include a three-dimensional model of the internal structure of tissue 504 generated based on preoperative imaging (e.g., MRI and / or CT scan imaging).

[0074] In Figure 5A this, ultrasound probe 104 is in surgical physical contact with tissue 504. Accordingly, system 300 can determine that the contact state of ultrasound probe 104 indicates that ultrasound probe 104 is in surgical physical contact with tissue 504. Based on this determination and as shown in Figure 5AAs shown, system 300 can display ultrasound image 114 within visual image 502. As shown, ultrasound image 114 can be located at a position within visual image 502 that appears to be directly below the bottom surface of ultrasound probe 104. By positioning ultrasound image 114 in this manner, system 300 can allow a user to more easily identify the relative positions of structures within tissue 504 and included within ultrasound image 114, where other content is shown in visual image 502. Alternatively, ultrasound imager 114 can be located at any other position within visual image 502 for a particular implementation.

[0075] Figure 5B It is shown that ultrasound probe 104 has been repositioned to a position where it is not in physical contact with tissue 504. This repositioning can occur in response to user manipulation of ultrasound probe 104 and / or in any other manner. In response to the repositioning, system 300 can determine that the contact state of the ultrasound probe now indicates that the ultrasound probe is not in surgical physical contact with tissue 504. In response and as Figure 5B shown, system 300 can forgo displaying (e.g., by hiding or otherwise not showing) ultrasound image 114 in visual image 502.

[0076] By intelligently controlling the display of ultrasound image 114 in this manner, system 300 can ensure that ultrasound image 114 is only displayed when it includes information useful to the user. Otherwise, ultrasound image 114 is hidden so as not to obscure other content in visual image 502.

[0077] In some examples, system 300 can display only a portion of ultrasound image 114 in response to determining that the contact state of ultrasound probe 104 indicates that ultrasound probe 104 is in surgical physical contact with tissue 504. For example, if a particular region (e.g., a pie slice) of ultrasound image 114 includes useful information but the remainder of ultrasound image 114 does not, this can indicate that only a portion of the ultrasound image is in surgical physical contact with tissue 504. In response, system 300 can generate and display a cropped ultrasound image that includes only a portion of ultrasound image 114. The cropped ultrasound image can include the region containing useful information and can be determined based on pixel classification as displaying tissue or displaying non-tissue.

[0078] For illustration, Figure 6A shown is visual image 502 displayed via display device 106. As shown, instead of displaying full ultrasound image 114 within visual image 502, system 300 displays cropped ultrasound image 602 within visual image 502. For comparison, in Figure 6AA dashed outline 604 is shown that represents what the full ultrasound image 114 looks like when displayed. The dashed outline 604 may or may not actually be displayed in the visual image 502 for a particular implementation.

[0079] Figure 6B Another example is shown where only a portion of the ultrasound image 114 is displayed in the visual image 502. In this example, the system 300 displays a cropped ultrasound image 606 instead of the full ultrasound image 114, with the full ultrasound image 114 again represented by the dashed line 604, which may or may not actually be displayed in the visual image 502. As shown, the cropped ultrasound image 606 does not include the distal region of the full ultrasound image 114. This type of cropped ultrasound image 606 may be beneficial for display in situations where signal loss in deeper tissue regions causes the distal region of the full ultrasound image 114 to include more noise than useful content.

[0080] The system 300 can additionally or alternatively set (e.g., adjust) parameters of the ultrasound imaging machine 102 based on the contact state of the ultrasound probe 104. For example, the system 300 can set the frequency and / or gain of the sound transmitted or received by the ultrasound probe 104 based on the contact state of the ultrasound probe 104. The system 300 can additionally or alternatively set the sector depth of the ultrasound image 114 based on the contact state of the ultrasound probe 104. By setting one or more parameters based on the contact state of the ultrasound probe 104, the system 300 can be configured to automatically obtain a better-quality ultrasound image 114.

[0081] For example, the contact state of the ultrasound probe 104 can indicate that the ultrasound probe 102 is in little to no physical contact with the tissue 504 (e.g., if the above ratio is just above the contact state threshold). In such a situation, the system 300 can increase the gain of the sound received by the ultrasound probe 104 to improve the image quality of the ultrasound image 114.

[0082] System 300 may additionally or alternatively generate a control signal based on the contact state of the ultrasound probe 104, the control signal being configured to be used by a computer-assisted surgical system to control the positioning of the ultrasound probe 104 (e.g., to achieve and / or maintain tissue contact). For example, the shaft of the ultrasound probe 104 may be coupled to the manipulator arm of the computer-assisted surgical system. In this example, the computer-assisted surgical system may be configured to adjust the positioning of the ultrasound probe 104 based on the control signal by repositioning the manipulator arm. As another example, different surgical tools (e.g., grasping forceps) controllable by the computer-assisted surgical system may be configured to hold and reposition the ultrasound probe 104. In either example, the control signal may indicate that the ultrasound probe 102 is not in surgical physical contact with the tissue 504. In response, the computer-assisted surgical system may reposition the ultrasound probe 104 until the control signal indicates that the ultrasound probe 102 is in surgical physical contact with the tissue 504.

[0083] Figure 7 An exemplary computer-assisted surgical system 700 (“surgical system 700”) is shown. As described herein, the ultrasound machine 102 and system 300 may be implemented by, connected to, and / or otherwise used in conjunction with the surgical system 700.

[0084] As shown, the surgical system 700 may include a manipulation system 702, a user control system 704, and an assistance system 706 that are communicatively coupled to each other. The surgical system 700 may be used by a surgical team to perform a computer-assisted surgical procedure on a patient 708. As shown, the surgical team may include a surgeon 710-1, an assistant 710-2, a nurse 710-3, and an anesthesiologist 710-4, who may all be collectively referred to as “surgical team members 710”. Additional or alternative surgical team members may be present in a surgical consultation for a particular implementation.

[0085] Although Figure 7 a minimally invasive surgical procedure is shown being performed, it should be understood that the surgical system 700 may similarly be used to perform open surgical procedures or other types of surgical procedures that may similarly benefit from the accuracy and convenience of the surgical system 700. Additionally, it should be understood that an entire surgical consultation in which the surgical system 700 may be employed may include not only the operative phase of a surgical procedure, as Figure 7 shown, but may also include pre-operative, post-operative, and / or other suitable phases. A surgical procedure may include any procedure that uses manual and / or instrumental techniques on a patient to examine or treat the patient's physical condition.

[0086] AsFigure 7 As shown, the manipulation system 702 may include a plurality of manipulator arms 712 (e.g., manipulator arms 712-1 to 712-4), to which a plurality of surgical instruments may be coupled. Each surgical instrument may be implemented by any suitable surgical tool (e.g., a tool with tissue interaction function), medical tool, imaging device (e.g., an endoscope), sensor instrument (e.g., a force-sensing surgical instrument), diagnostic instrument, etc. These surgical instruments may be used to perform a computer-assisted surgical procedure on the patient 708 (e.g., by being at least partially inserted into the patient 708's body and being manipulated to perform a computer-assisted surgical procedure on the patient 708). Although the manipulation system 702 is depicted and described herein as including four manipulator arms 712, it should be recognized that the manipulation system 702 may include only a single manipulator arm 712 or any other number of manipulator arms for a particular implementation.

[0087] The manipulator arm 712 and / or the surgical instrument attached to the manipulator arm 712 may include one or more displacement sensors, orientation sensors, and / or position sensors for generating natural (i.e., uncorrected) kinematic information. One or more components of the surgical system 700 may be configured to use the kinematic information to track (e.g., determine its position) and / or control the surgical instrument.

[0088] The user control system 704 may be configured to facilitate a surgeon 710-1 to control the manipulator arm 712 and the surgical instrument attached to the manipulator arm 712. For example, the surgeon 710-1 may interact with the user control system 704 to remotely move or manipulate the manipulator arm 712 and the surgical instrument. To this end, the user control system 704 may provide the surgeon 710-1 with images (e.g., high-resolution 3D images) of the surgical area associated with the patient 708 captured by an imaging system (e.g., any of the medical imaging systems described herein). In some examples, the user control system 704 may include a stereoscopic viewer with two displays, where the stereoscopic images of the surgical area associated with the patient 708 and generated by a stereoscopic imaging system may be viewed by the surgeon 710-1. The surgeon 710-1 may utilize the images to perform one or more procedures using one or more surgical instruments attached to the manipulator arm 712.

[0089] To facilitate the control of surgical instruments, the user control system 704 may include a set of master controls. These master controls can be manipulated by the surgeon 710-1 to control the movement of the surgical instruments (e.g., by utilizing robotics and / or teleoperation techniques). The master controls can be configured to detect various hand, wrist, and finger movements of the surgeon 710-1. In this way, the surgeon 710-1 can intuitively perform procedures using one or more surgical instruments.

[0090] The auxiliary system 706 may include one or more computing devices that are configured to perform the primary processing operations of the surgical system 700. In such a configuration, the one or more computing devices included in the auxiliary system 706 can control and / or coordinate the operations performed by the various other components of the surgical system 700 (e.g., the manipulation system 702 and the user control system 704). For example, the computing devices included in the user control system 704 can transmit instructions to the manipulation system 702 through the one or more computing devices included in the auxiliary system 706. As another example, the auxiliary system 706 can receive and process image data representing images captured by an imaging device attached to one of the manipulator arms 712.

[0091] In some examples, the auxiliary system 706 can be configured to present visual content to surgical team members 710 who may not have access to the images provided to the surgeon 710-1 at the user control system 704. To this end, the auxiliary system 706 can include a display monitor 714 that is configured to display one or more user interfaces, such as images of the surgical area (e.g., 2D images), information associated with the patient 708 and / or the surgical procedure, and / or any other visual content for a particular implementation. For example, the display monitor 714 can display an image of the surgical area along with additional content (e.g., graphical content, contextual information, etc.) that is displayed simultaneously with the image. In some embodiments, the display monitor 714 is implemented as a touchscreen display with which the surgical team members 710 can interact (e.g., by touch gestures) to provide user input to the surgical system 700.

[0092] The manipulation system 702, the user control system 704, and the auxiliary system 706 can be communicatively coupled to each other in any suitable manner. For example, as Figure 7As shown, the manipulation system 702, the user control system 704, and the assistance system 706 can be communicatively coupled via control lines 716, which can represent any wired or wireless communication link for a particular implementation. To this end, the manipulation system 702, the user control system 704, and the assistance system 706 can each include one or more wired or wireless communication interfaces, such as one or more local area network interfaces, Wi-Fi network interfaces, cellular interfaces, etc.

[0093] Figure 8 An exemplary method 800 is shown. Although Figure 8 the exemplary operations shown are in accordance with one embodiment, other embodiments may omit, add, reorder, combine, and / or modify Figure 8 any of the steps shown. Figure 8 One or more of the operations shown can be performed by the system 300, any components included therein, and / or any implementation thereof.

[0094] In operation 802, the contact detection system determines local descriptor values for a plurality of pixels included in an ultrasound image captured by an ultrasound probe located within a patient. Operation 802 can be performed in any of the ways described herein.

[0095] In operation 804, the contact detection system classifies each of the plurality of pixels as showing tissue or showing non-tissue based on the local descriptor values. Operation 804 can be performed in any of the ways described herein.

[0096] In operation 806, the contact detection system determines the contact state of the ultrasound probe based on the classification of each of the plurality of pixels as showing tissue or showing non-tissue, the contact state indicating whether the ultrasound probe is in surgical physical contact with patient tissue. Operation 806 can be performed in any of the ways described herein.

[0097] Figure 9 Another exemplary method 900 is shown. Although Figure 9 the exemplary operations shown are in accordance with one embodiment, other embodiments may omit, add, reorder, combine, and / or modify Figure 9 any of the steps shown. Figure 9 One or more of the operations shown can be performed by the system 300, any components included therein, and / or any implementation thereof.

[0098] In operation 902, the contact detection system determines local descriptor values for a plurality of pixels included in an ultrasound image captured by an ultrasound probe located within a patient. Operation 902 can be performed in any of the ways described herein.

[0099] In operation 904, the contact detection system determines the contact state of the ultrasound probe based on local descriptor values, where the contact state indicates whether the ultrasound probe is in physical surgical contact with the patient's tissue. Operation 904 can be performed in any of the ways described herein.

[0100] In operation 906, the contact detection system controls the display of the ultrasound image within the visible image displayed on the display device based on the contact state of the ultrasound probe. Operation 906 can be performed in any of the ways described herein.

[0101] Figure 10 Another exemplary method 1000 is shown. Although Figure 10 shows exemplary operations according to one embodiment, other embodiments may omit, add, reorder, combine, and / or modify Figure 10 any of the steps shown. Figure 10 One or more of the operations shown can be performed by system 300, any of the components included therein, and / or any of its implementations.

[0102] In operation 1002, the contact detection system determines local descriptor values for a plurality of pixels included in an ultrasound image captured by an ultrasound probe located within a patient. Operation 1002 can be performed in any of the ways described herein.

[0103] In operation 1004, the contact detection system determines the contact state of the ultrasound probe based on the local descriptor values, where the contact state indicates whether the ultrasound probe is in physical surgical contact with the patient's tissue. Operation 1004 can be performed in any of the ways described herein.

[0104] In operation 1006, the contact detection system sets parameters of an ultrasound imaging machine connected to the ultrasound probe based on the contact state of the ultrasound probe. Operation 1006 can be performed in any of the ways described herein.

[0105] Figure 11 Another exemplary method 1100 is shown. Although Figure 11 shows exemplary operations according to one embodiment, other embodiments may omit, add, reorder, combine, and / or modify Figure 11 any of the steps shown. Figure 11 One or more of the operations shown can be performed by system 300, any of the components included therein, and / or any of its implementations.

[0106] In operation 1102, the contact detection system determines local descriptor values for a plurality of pixels included in an ultrasound image captured by an ultrasound probe located within a patient. Operation 1102 can be performed in any of the ways described herein.

[0107] In operation 1104, the contact detection system determines the contact state of the ultrasound probe based on local descriptor values, where the contact state indicates whether the ultrasound probe is in surgical physical contact with the patient's tissue. Operation 1104 can be performed in any of the ways described herein.

[0108] In operation 1106, the contact detection system generates a control signal based on the contact state of the ultrasound probe, where the control signal is configured to be used by a computer-assisted surgery system to control the positioning of the ultrasound probe. Operation 1106 can be performed in any of the ways described herein.

[0109] Figure 12 Another exemplary method 1200 is shown. Although Figure 12 exemplary operations according to one embodiment are shown, other embodiments may omit, add, reorder, combine, and / or modify Figure 12 any of the steps shown. Figure 12 One or more of the operations shown can be performed by system 300, any of the components included therein, and / or any implementation thereof.

[0110] In operation 1202, the contact detection system classifies each of a plurality of pixels included in an ultrasound image captured by an ultrasound probe located within a patient as displaying tissue or displaying non-tissue. Operation 1202 can be performed in any of the ways described herein.

[0111] In operation 1204, the contact detection system determines the contact state of the ultrasound probe based on the classification of each of the plurality of pixels as displaying tissue or displaying non-tissue, where the contact state indicates whether the ultrasound probe is in surgical physical contact with the patient's tissue. Operation 1204 can be performed in any of the ways described herein.

[0112] In some examples, a non-transitory computer-readable medium storing computer-readable instructions can be provided according to the principles described herein. When executed by a processor of a computing device, the instructions can direct the processor and / or the computing device to perform one or more operations, including one or more of the operations described herein. Any of a variety of known computer-readable media can be used to store and / or transmit such instructions.

[0113] As used herein, a non-transitory computer-readable medium may include any non-transitory storage medium that participates in providing data (e.g., instructions) that can be read and / or executed by a computing device (e.g., by a processor of the computing device). For example, the non-transitory computer-readable medium may include, but is not limited to, any combination of non-volatile storage media and / or volatile storage media. Exemplary non-volatile storage media include, but are not limited to, read-only memory, flash memory, solid-state drives, magnetic storage devices (e.g., hard disks, floppy disks, magnetic tapes, etc.), ferroelectric random access memory ("RAM"), and optical disks (e.g., compact disks, digital video disks, Blu-ray disks, etc.). Exemplary volatile storage media include, but are not limited to, RAM (e.g., dynamic RAM).

[0114] Figure 13 An exemplary computing device 1300 is shown, which may be specifically configured to execute one or more of the processes described herein. Any system, unit, computing device, and / or other component described herein may be implemented by the computing device 1300.

[0115] As Figure 13 shown, the computing device 1300 may include a communication interface 1302, a processor 1304, a storage device 1306, and an input / output ("I / O") module 1308 that are communicatively connected to each other via a communication infrastructure 1310. Although Figure 13 the exemplary computing device 1300 is shown, Figure 13 the components shown are not intended to be limiting. Additional or alternative components may be used in other embodiments. The components of the computing device 1300 shown in Figure 13 will now be described in more detail.

[0116] The communication interface 1302 may be configured to communicate with one or more computing devices. Examples of the communication interface 1302 include, but are not limited to, a wired network interface (e.g., a network interface card), a wireless network interface (e.g., a wireless network interface card), a modem, an audio / video connection, and any other suitable interface.

[0117] The processor 1304 generally represents any type or form of processing unit capable of processing data and / or interpreting, executing, and / or guiding the execution of one or more instructions, processes, and / or operations described herein. The processor 1304 may perform operations by executing computer-executable instructions 1312 (e.g., applications, software, code, and / or other executable data instances) stored in the storage device 1306.

[0118] The storage device 1306 can include one or more data storage media, devices, or configurations and can employ any type, form, and combination of data storage media and / or devices. For example, the storage device 1306 can include, but is not limited to, any combination of the non-volatile media and / or volatile media described herein. Electronic data including the data described herein can be stored temporarily and / or permanently in the storage device 1306. For example, data representing computer-executable instructions 1312 configured to cause the processor 1304 to perform any of the operations described herein can be stored within the storage device 1306. In some examples, the data can be arranged in one or more databases resident within the storage device 1306.

[0119] The I / O module 1308 can include one or more I / O modules that are configured to receive user input and provide user output. The I / O module 1308 can include any hardware, firmware, software, or combination thereof that supports input and output capabilities. For example, the I / O module 1308 can include hardware and / or software for capturing user input, including but not limited to a keyboard or keypad, a touchscreen component (e.g., a touchscreen display), a receiver (e.g., an RF or infrared receiver), a motion sensor, and / or one or more input buttons.

[0120] The I / O module 1308 can include one or more devices for presenting output to the user, including but not limited to a graphics engine, a display (e.g., a display screen), one or more output drivers (e.g., a display driver), one or more audio speakers, and one or more audio drivers. In certain embodiments, the I / O module 1308 is configured to provide graphic data to a display for presentation to the user. The graphic data can represent one or more graphical user interfaces and / or any other graphical content for a particular implementation.

[0121] In the foregoing description, various exemplary embodiments have been described with reference to the accompanying drawings. However, it will be apparent that various modifications and changes can be made thereto, and additional embodiments can be implemented, without departing from the scope of the invention set forth in the appended claims. For example, certain features of one embodiment described herein can be combined with or substituted for features of another embodiment described herein. Accordingly, the description and drawings are to be regarded as illustrative rather than restrictive.

Claims

1. A system, comprising: a memory that stores instructions; and a processor communicatively coupled to the memory and configured to execute the instructions to: determine a plurality of local descriptor values, each local descriptor value corresponding to a different pixel among a plurality of pixels included in an ultrasound image captured by an ultrasound probe located within a patient; classify each pixel among the plurality of pixels as display tissue or display non - tissue, the classification including classifying a first pixel among the plurality of pixels as display tissue, classifying the first pixel based only on a first local descriptor value included in the plurality of local descriptor values and corresponding to the first pixel; determine an average pixel classification, the average pixel classification representing a comparison of the number of pixels classified as display tissue to the number of pixels classified as display non - tissue; if the average pixel classification is higher than a first contact state threshold, determine that the ultrasound probe is in a first contact state indicating that the ultrasound probe is in surgical physical contact with the tissue of the patient; and if the average pixel classification is lower than a second contact state threshold, determine that the ultrasound probe is in a second contact state indicating that the ultrasound probe is not in surgical physical contact with the tissue of the patient, the second contact state threshold being lower than the first contact state threshold.

2. The system according to claim 1, wherein the local descriptor value characterizes at least one of an intensity distribution and a spatial autocorrelation of each pixel among the plurality of pixels.

3. The system according to claim 1, wherein the classification includes: classifying pixels in the ultrasound image having local descriptor values higher than a local descriptor threshold as display tissue; and classifying pixels in the ultrasound image having local descriptor values lower than the local descriptor threshold as display non - tissue.

4. The system according to claim 1, wherein the classification includes: providing the local descriptor values as inputs to a machine learning model, and based on an output of the machine learning model, classifying each pixel among the plurality of pixels as display tissue or display non - tissue.

5. The system according to claim 1, wherein the local descriptor value includes one or more of a local variance value of the plurality of pixels or an autocorrelation value of the plurality of pixels.

6. The system according to claim 5, wherein: the determining the local descriptor values of the plurality of pixels includes determining both a local variance value and an autocorrelation value of each pixel included in the plurality of pixels; the classification includes: classifying pixels in the ultrasound image having a local variance value higher than a variance threshold and an autocorrelation value higher than an autocorrelation threshold as display tissue, and classifying pixels in the ultrasound image having a local variance value lower than the variance threshold or an autocorrelation value lower than the autocorrelation threshold as display non - tissue.

7. The system according to claim 1, wherein: the processor is further configured to execute the instructions to: determine a background intensity of the ultrasound image, and generate a reduced ultrasound image by subtracting the background intensity from the ultrasound image; and Said determining the local descriptor values of the plurality of pixels includes determining the local descriptor values of pixels included in the reduced ultrasound image.

8. The system according to claim 1, wherein the processor is further configured to execute the instructions to control the display of the ultrasound image within a visible image displayed by a display device based on the contact state of the ultrasound probe.

9. The system according to claim 8, wherein the visible image includes an endoscopic image of a surgical area within the patient captured by an endoscope.

10. The system according to claim 8, wherein the visible image further includes a preoperative model of the patient's anatomical structure within the surgical area of the patient, and the preoperative model is registered with the endoscopic image.

11. The system according to claim 8, wherein the controlling the display of the ultrasound image within the visible image includes: displaying the ultrasound image within the visible image if the contact state indicates that the ultrasound probe is in surgical physical contact with the tissue of the patient; and abandoning the display of the ultrasound image within the visible image if the contact state indicates that the ultrasound probe is not in surgical physical contact with the tissue of the patient.

12. The system according to claim 8, wherein the controlling the display of the ultrasound image within the visible image includes: determining that the contact state indicates that the ultrasound probe is in surgical physical contact with the tissue of the patient; generating a cropped ultrasound image in response to the determining that the contact state indicates that the ultrasound probe is in surgical physical contact with the tissue of the patient and based on the classification of the pixels as display tissue or display non-tissue, the cropped ultrasound image including only a portion of the ultrasound image; and displaying the cropped ultrasound image within the visible image.

13. The system according to claim 1, wherein the processor is further configured to execute the instructions to set parameters of an ultrasound imaging machine connected to the ultrasound probe based on the contact state of the ultrasound probe.

14. The system according to claim 13, wherein the parameters include at least one of a frequency of sound emitted by the ultrasound probe, a gain of the sound received by the ultrasound probe, and a sector depth of the ultrasound image.

15. The system according to claim 1, wherein the processor is further configured to execute the instructions to generate a control signal based on the contact state of the ultrasound probe, the control signal being configured to be used by a computer-assisted surgical system to control the positioning of the ultrasound probe.

16. The system according to claim 1, wherein the plurality of pixels are included in a region of interest within the ultrasound image, and the region of interest does not include a set of pixels within the ultrasound image.

17. The system according to claim 1, wherein the classification further comprises classifying a second pixel among the plurality of pixels as displaying non-tissue, classifying the second pixel based only on a second local descriptor value among the plurality of local descriptor values.

18. A method, comprising: determining, by a contact detection system, a plurality of local descriptor values, each local descriptor value corresponding to a different pixel among a plurality of pixels included in an ultrasound image captured by an ultrasound probe located within a patient; classifying, by the contact detection system, each pixel among the plurality of pixels as displaying tissue or displaying non-tissue, the classification comprising classifying a first pixel among the plurality of pixels as displaying tissue, classifying the first pixel based only on a first local descriptor value among the plurality of local descriptor values and corresponding to the first pixel; and determining, by the contact detection system, an average pixel classification that represents a comparison of the number of pixels classified as displaying tissue with the number of pixels classified as displaying non-tissue; if the average pixel classification is higher than a first contact state threshold, determining, by the contact detection system, that the ultrasound probe is in a first contact state indicating that the ultrasound probe is in surgical physical contact with the tissue of the patient; and if the average pixel classification is lower than a second contact state threshold, determining, by the contact detection system, that the ultrasound probe is in a second contact state indicating that the ultrasound probe is not in surgical physical contact with the tissue of the patient, the second contact state threshold being lower than the first contact state threshold.

19. The method according to claim 18, further comprising: determining, by the contact detection system, local descriptor values of a plurality of pixels included in the ultrasound image, the local descriptor values characterizing at least one of an intensity distribution and a spatial autocorrelation of each pixel among the plurality of pixels; wherein the classification is based on the local descriptor values.

20. The method according to claim 18, further comprising controlling, by the contact detection system, a display of the ultrasound image within a visual image displayed by a display device based on the contact state of the ultrasound probe.

Images