Characterization of contrast enhanced ultrasound images

Abstract

This invention relates to a framework for characterizing contrast-enhanced ultrasound (CEUS) images. The framework derives luminance mode (B-mode) and contrast image sequences from a sequence of contrast-enhanced ultrasound (CEUS) images. The B-mode images and contrast images within the B-mode and contrast image sequences are spatially aligned and temporally subsampled. A region of interest may be selected from a frame of the B-mode and contrast image sequences. The region of interest is subsequently characterized based on the B-mode and contrast image sequences.

Description

Technology Field

[0001] The present disclosure generally relates to medical imaging, and more specifically to a framework for characterizing contrast-enhanced ultrasound images. Background Technology

[0002] Ultrasonography is a non-invasive medical examination that assists doctors in diagnosing and treating diseases. The procedure is performed by placing a small probe, referred to as a transducer, directly against the skin to transmit and receive high-frequency sound waves into the body. These sound waves are used to generate medical diagnostic images of the body's internal structures.

[0003] Contrast-enhanced ultrasound (CEUS) improves the visualization of blood vessels and organs by combining a special type of intravenous contrast agent with abdominal ultrasound. To make organs and blood vessels within the abdomen and pelvis more visible, the contrast agent may contain gas-filled microbubbles. Abdominal CEUS examinations can evaluate various diseases and conditions of the liver, spleen, kidneys, pancreas, intestines, and / or bladder. The problem to be solved

[0004] CEUS can significantly improve the accuracy of ultrasound diagnosis in the detection and characterization of focal liver lesions. The purpose of a liver CEUS examination is to determine the type of focal liver lesion by injecting a contrast agent into the patient and observing wash-in and wash-out characteristics. Wash-in generally refers to the enhancement of tissue or masses after contrast agent injection and is observed in benign or non-cancerous tissues. Wash-out generally refers to the tissue or mass losing its contrast effect more rapidly than normal liver tissue and is observed in cancerous or malignant tissues. Since wash-in occurs very rapidly (e.g., within 20–30 seconds), images can be saved to observe the wash-in process. Wash-out images can be acquired individually for up to approximately 5 minutes, for example, at 1-minute intervals. However, it can be difficult for medical personnel to track specific lesions within the images and / or individual images.

[0005] In some applications, data frames acquired over time are integrated. The resulting images can provide useful diagnostic information, such as microvessels or perfusion pathways. However, due to operator movements (e.g., sweeping) or internal patient movements (e.g., heavy breathing), combining information from different frames may result in blurred images or inaccurate information. means of solving the problem

[0006] Described herein is a framework for characterizing contrast-enhanced ultrasound (CEUS) images. The framework derives brightness mode (B-mode) and contrast image sequences from a sequence of contrast-enhanced ultrasound (CEUS) images. The B-mode images and contrast images within the B-mode and contrast image sequences are spatially aligned and temporally subsampled. A region of interest may be selected from frames of the B-mode and contrast image sequences. The region of interest is subsequently characterized based on the B-mode and contrast image sequences. Brief explanation of the drawing

[0007] A more complete understanding of the present disclosure and its incidental embodiments will be readily obtained by referring to the following detailed description together with the accompanying drawings. Figure 1 is a block diagram showing an exemplary imaging system. Figure 2 is an illustration of an exemplary characterization method. Figure 3 is a city diagram of an exemplary timeline plot. Specific details for implementing the invention

[0008] In the following description, numerous specific details, such as examples of specific components, devices, methods, etc., are presented to provide a thorough understanding of embodiments of the present framework. However, it will be apparent to those skilled in the art that these specific details are not necessarily required to be adopted to carry out embodiments of the present framework. In other cases, to avoid unnecessarily obscuring embodiments of the present framework, well-known materials or methods have not been described in detail. The present framework may have various modifications and alternative forms, but specific embodiments are illustrated by example in the drawings and will be described in detail in this specification. However, it should be understood that there is no intention to limit the present invention to the specific forms disclosed, but rather to cover all modifications, equivalents, and alternatives that fall within the spirit and scope of the present invention. Furthermore, for ease of understanding, specific method steps are described as separate steps; however, these separate steps should not be interpreted as necessarily being performed in a specific order.

[0009] Unless otherwise specified in the following description, terms such as “partition,” “generate,” “register,” “determine,” “align,” “position,” “process,” “calculate,” “select,” “estimate,” “detect,” and “trace” will be understood to refer to the operations and processes of a computer system or similar electronic computing device that manipulate data represented as physical (e.g., electronic) quantities within the registers and memory of a computer system to convert it into other data similarly represented as physical quantities within the computer system memory or registers or other devices for storing, transmitting, or displaying such information. Embodiments of the methods described herein may be implemented using computer software. If written in a programming language conforming to recognized standards, a set of instructions designed to implement the methods may be compiled to run on various hardware platforms and interface with various operating systems. Furthermore, the implementation of this framework is not described by reference to a specific programming language. It will be understood that various programming languages ​​may be used.

[0010] One aspect of the present framework is to provide a tool that generates a summary of acquired data, enabling physicians to review data on a single still-image timeline instead of viewing images and observing individual frames. Another aspect of the present framework derives a spatially aligned image sequence of selected frames from an ultrasound image sequence containing B-mode images and contrast images. Both B-mode images and contrast images are used to ensure reliable tracking of the lesion throughout the contrast agent life cycle and to facilitate accurate visualization and measurement by compensating for movement (e.g., operator and / or internal movement). Accurate tracking is not possible using B-mode images alone because B-mode images are affected by contrast agent wash-in and are unreliable for use during tracking. The above and other exemplary advantages and features will be described in more detail in the following description.

[0011] FIG. 1 is a block diagram illustrating an exemplary medical imaging system (100). In some embodiments, the system (100) comprises a computer system (101) coupled to a medical imaging device (114). The computer system (101) comprises one or more non-transient computer-readable media (105) (e.g., computer storage or memory device), an input / output device (108) (e.g., monitor, mouse, touchpad, or keyboard), and a processor device (104) coupled to a communication module (110). The processor device (104) may comprise, for example, a central processing unit (CPU), a graphics processing unit (GPU), a field-programmable gate array (FPGA), or a combination thereof. The computer system (101) may further comprise supporting circuits such as a cache, a power supply or battery, a clock circuit, and a communication bus (not shown). Various other peripheral devices, such as client devices (e.g., workstations) and additional data storage devices and printing devices, can also be connected to the computer system (101).

[0012] The present invention may be implemented in various forms of hardware, software, firmware, special-purpose processors, or combinations thereof, and may be implemented as part of a microinstruction code or as part of or combinations thereof of an application or software product executed through an operating system. In some embodiments, the invention described herein is implemented as computer-readable program code substantially implemented on one or more non-transient computer-readable media (105). In particular, the invention may be implemented by a processing engine (107). The non-transient computer-readable media (105) may include RAM (random access memory), ROM (read-only memory), magnetic floppy disks, flash memory, and other types of memory or combinations thereof. The computer-readable program code is executed by a processor device (104) to process data acquired, for example, by a medical imaging device (114). The computer-readable program code is not intended to be limited to any specific programming language and its implementation. It will be understood that various programming languages ​​and their coding may be used to implement the contents of the disclosures contained herein. The same or different computer-readable media (105) may be used to store a database including, but not limited to, image data sets, knowledge bases, individual subject data, medical records, diagnostic reports (or documents) for subjects, or a combination thereof.

[0013] A communication module (110) enables a computer system (101) to communicate with an external system and / or network. In some embodiments, the communication module (110) is equipped with a high-speed digital interface such as Thunderbolt™, USB (Universal Serial Bus), multi-gigabit Ethernet, fiber optics, waveguide technology, or a wireless interface. Other types of interfaces are also useful. In some embodiments, the communication module (110) is equipped with a wireless signal transceiver that communicates signals using common communication protocols such as the Global System for Mobile Communications (GSM), WIFI, Bluetooth, Zigbee, LoRa, and TCP / IP.

[0014] The medical imaging device (114) is a radiographic device that acquires medical image data revealing internal structures hidden by the skin and bone of a subject. In some embodiments, the medical imaging device (114) is a contrast-enhanced ultrasound (CEUS) system. The CEUS system acquires a B-mode image of the tissue and displays it along with a contrast image that is superimposed on the B-mode image or displayed alongside the B-mode image. The CEUS system may be equipped with a transmitting beamformer, a transducer, and a receiving beamformer. Additional, different, or fewer components may be provided. For example, a separate memory for buffering or storing data frames may be provided.

[0015] It should also be understood that since some of the system components and method steps illustrated in the attached drawings may be implemented in software, the actual connections between system components (or processing steps) may vary depending on how the framework is programmed. Based on the contents provided in this specification, a person skilled in the art will be able to conceive of the above and similar embodiments or configurations of the framework.

[0016] FIG. 2 is an illustration of an exemplary characterization method (200). It should be understood that the steps of the method (200) may be performed in the illustrated order or in a different order. Additional, different, or fewer steps may be provided. Additionally, the method (200) may be implemented by the system (100) of FIG. 1, other systems, or a combination thereof.

[0017] In 202, the processing engine (107) receives a contrast-enhanced ultrasound (CEUS) image sequence of at least one structure of interest. The CEUS image sequence may be acquired (e.g., in real time) by a medical imaging device (114) or may be generated in advance and retrieved, for example, from a non-transient computer-readable medium (105). The CEUS image sequence may be substantially continuous or periodic (e.g., acquired at least once per cardiac cycle). The CEUS sequence may be an image containing data frames representing a region of interest or structure scanned at different points in time after the administration of a contrast agent.

[0018] The structure of interest may be any anatomical structure identified for further study (e.g., liver). The structure of interest comprises a region that may contain a contrast agent, or an administered contrast agent. The contrast agent may respond to ultrasound energy. Part or all frames of the sequence contain information from the contrast agent as well as responses from tissues or body fluids.

[0019] In some embodiments, the CEUS image sequence is acquired in two modes. Both the B-mode image and the contrast image are recorded simultaneously, for example, at the same frame rate and duration. The B-mode image, also known as the luminance mode image, is a two-dimensional ultrasound image generated by converting the amplitude of the echo into various shades of gray. The contrast image is a two-dimensional color image that reflects the spatial distribution of the contrast agent (e.g., microbubbles). The contrast image is formed by detecting and separating the nonlinear components of both the linear and nonlinear signals from the contrast agent within the tissue.

[0020] In 204, the processing engine (107) derives B-mode and contrast image sequences from the CEUS image sequence. The B-mode and contrast image sequences include a series of B-mode images and a corresponding series of contrast images extracted from the CEUS image sequence. Each frame within the B-mode series corresponds to a frame within the contrast image series and is spatially aligned. In simultaneous mode, pairs of B-mode images and contrast images may be acquired simultaneously. In alternating mode, pairs of B-mode images and contrast images may be acquired alternately. Typically, in alternating mode, the quality of the B-mode images is better, but the contrast images and B-mode images may not be temporally aligned. Simultaneous mode provides temporally aligned B-mode images and contrast images.

[0021] The B-mode image and the contrast image within the derived image sequence are spatially aligned and temporally subsampled. In some embodiments, the step of deriving the image sequence includes the step of subsampling frames having temporally uniform intervals from the CEUS image sequence. In other words, the time interval between the acquisition times of consecutive frames in each series is the same.

[0022] Alternatively, the step of deriving the image sequence includes the step of sub-sampling frames with temporally non-uniform intervals from the CEUS image sequence. In this embodiment, specific frames are selected from the CEUS image sequence to form a B-mode image series and a contrast image series. Frames may be selected to be included in each series based on at least one characteristic of the image data. Such characteristics include, but are not limited to, motion displacement and similarity between frames. For example, frames associated with significant motion and / or frames very similar to previously selected frames are not selected to be included. The selected frames are "best" for the quantification of tissue perfusion. The "best" frames have no significant motion [e.g., out-of-plane motion] and have sufficient signal intensity to indicate proper penetration of the contrast agent and proper sampling of temporal dynamics. Out-of-plane motion cannot be corrected, but in-plane motion can be corrected using registration techniques.

[0023] Frames within each series may be spatially aligned to compensate for in-plane movement between frames. In-plane movement may be caused by transducer movement, patient movement, and / or tissue movement within the region of interest. To compensate for movement, relative translation and / or rotation along one or more dimensions are determined. Data from one frame is correlated with different regions within other frames of data to determine the best or sufficient match. Correlation, cross-correlation, minimum sum of absolute differences, and / or other similarity measures may be used. In non-rigid motion models, rigid or non-rigid motion models, such as torsion, may be provided in addition to translation and rotation. The entire frame of data or a data window may be used to determine the best match and corresponding movement.

[0024] In some embodiments, the extracted B-mode image and the contrast image are spatially aligned to correct (or modify) motion (e.g., in-plane motion). Unlike conventional methods, the present framework uses the B-mode image together with the contrast image for motion correction. The B-mode image and / or the contrast image may be used for motion correction based on the timing of contrast agent administration. For example, only the B-mode image acquired during the early wash-in phase may be used for motion correction because it better represents the lesion boundaries, whereas only the contrast image acquired during the late wash-out phase may be used for motion correction because it provides better information. Early wash-in generally refers to a wash-in that can be clearly detected earlier than a predetermined time (e.g., 60 seconds) after contrast agent administration. Late wash-out generally refers to a wash-out that can be clearly detected at or after a predetermined time (e.g., 60 seconds) after contrast agent administration. Alternatively, if the lesion-to-hepatic contrast is high and the B-mode image is unaffected by contrast fill, both the B-mode image and the contrast image are used for motion correction.

[0025] In step 206, the processing engine (107) selects at least one region of interest in the first frame of the B-mode image series and / or the contrast image series. The region of interest within the first frame may be selected by an operator, for example, through a user interface. Alternatively, the region of interest may be detected semi-automatically or automatically in the first frame, for example, by machine learning technology. The region of interest may correspond to a lesion or other abnormal area within the structure of interest. Two or more regions of interest (e.g., multiple lesions) may be selected.

[0026] In step 208, the processing engine (107) characterizes the region of interest based on the derived image sequence. The output of this characterization may be, for example, qualitative parameters of the region of interest, quantitative parameters of the region of interest, a timeline plot, or a combination thereof. The characterization output may be presented (or displayed) on a user interface of a user device, for example, to facilitate diagnosis. The characterization output may also be stored in an electronic health record to be accessed, for example, by a patient and a healthcare provider.

[0027] To generate qualitative parameters, the derived image sequences may be input into a diagnostic function module. A B-mode image series may be used, for example, to evaluate the size, volume, shape, echo incidence, and arrangement of the region of interest, and a contrast image series may be used to evaluate hemodynamics and vascularization patterns, such as arterial phase contrast wash-in characteristics (e.g., filling pattern, dynamics, timing) and portal phase wash-out characteristics (e.g., wash-out degree, timing). Additionally, the characteristics may further include the type of lesion (e.g., benign or malignant). The diagnostic function module may implement deep learning techniques or any other appropriate techniques to, for example, extract contrast characteristics or predict the lesion type (e.g., malignant, benign), lesion class (e.g., hepatocellular carcinoma or HCC, focal nodular hyperplasia or FNH, hemangioma), or Liver Imaging Reporting and Data System (LI-RADS) category.

[0028] In some embodiments, the processing engine (107) performs quantification of the region of interest based on the derived image sequence to generate quantitative parameters. Quantification may be performed by extracting a time-intensity ratio curve between the calculated lesion intensity and the inter-intensity, or by using deep learning-based techniques. Such curves may provide information about contrast agent wash-in and wash-out characteristics as previously described. The processing engine (107) may select a "best" frame from each of the series for quantification using deep learning-based techniques used for object tracking or for measuring similarity with a reference frame (e.g., a first frame).

[0029] In some embodiments, the processing engine (107) generates a timeline plot that tracks the region of interest from the derived image sequence. The timeline plot is a visual representation of a series of B-mode images adjacent to (e.g., above or below) a series of contrast images progressing over time. The timeline plot may provide a single static representation of the region of interest characteristics, such as an arterial phase (AP) wash-in pattern (e.g., centrifugal, centripetal, rimmed, spherical), wash-out timing, etc.

[0030] FIG. 3 is an illustration of an exemplary timeline plot (302). The timeline plot (302) comprises a series of B-mode images (304a-304b) displayed over a series of contrast images (306a-306b). Although a static horizontal timeline plot (302) is illustrated, it should be noted that other configurations of the timeline plot (e.g., vertical) are also possible. The timeline plot (302) comprises both arterial phase (AP) wash-in images (304a, 306a). The AP wash-in images (304a, 306a) are finely subsampled and pre-selected. Additionally, portosystemic wash-out images (304b, 306b) may also be provided. The portosystemic wash-out images (304b, 306b) may be sparsely sampled. The acquisition time (308) can be displayed on the timeline plot (302).

[0031] Additional timeline plots may be generated to indicate additional regions of interest or the administration of multiple contrast agents to a single region of interest. For example, multiple lesions may exist in a person's liver, or multiple contrast agents may be injected to visualize a single lesion. Multiple timeline plots may be displayed to the user to provide additional information regarding the behavior of the contrast agent. Multiple timeline plots for multiple lesions may be displayed simultaneously to facilitate visual comparison of the lesions.

[0032] The following is a list of non-limiting exemplary embodiments disclosed in this specification:

[0033] Exemplary Example 1. An image characterization method comprising: receiving a sequence of contrast-enhanced ultrasound (CEUS) images; deriving a luminance mode (B-mode) and contrast image sequence from the CEUS image sequence, wherein the B-mode image and the contrast image within the B-mode and contrast image sequence are spatially aligned and temporally sub-sampled; selecting at least one region of interest in the B-mode and contrast image sequence; and characterizing at least one region of interest based on the B-mode and contrast image sequence.

[0034] Exemplary Example 2. The method of Exemplary Example 1, wherein the step of deriving B-mode and contrast image sequences comprises the step of sub-sampling frames having temporally uniform intervals.

[0035] Exemplary Example 3. A method in any one of Exemplary Examples 1-2, wherein the step of deriving B-mode and contrast image sequences comprises the step of sub-sampling frames having temporally non-uniform intervals.

[0036] Exemplary Example 4. The method of Exemplary Example 3, wherein a frame is selected from a CEUS image sequence based on motion displacement, similarity between frames, or a combination thereof.

[0037] Exemplary Example 5. A method in any one of Exemplary Examples 1-4, wherein the step of deriving B-mode and contrast image sequences includes the step of spatially aligning the B-mode image and the contrast image for motion correction.

[0038] Exemplary Example 6. A method in which only the B-mode image acquired in the early wash-in phase and only the contrast image acquired in the late wash-out phase are used for motion correction in Exemplary Example 5.

[0039] Exemplary Example 7. The method of Exemplary Example 5, wherein both the B-mode image and the contrast image are used for motion correction.

[0040] Exemplary Example 8. A method in any one of Exemplary Examples 1-7, wherein the step of characterizing at least one region of interest based on B-mode and contrast image sequences comprises the step of generating one or more qualitative parameters.

[0041] Exemplary Example 9. A method in any one of Exemplary Examples 1-8, wherein the step of characterizing at least one region of interest based on B-mode and contrast image sequences comprises the step of generating one or more quantitative parameters.

[0042] Exemplary Example 10. A method in any one of Exemplary Examples 1-9, wherein the step of characterizing at least one region of interest based on B-mode and contrast image sequences comprises the step of generating a timeline plot.

[0043] Exemplary Example 11. The method of Exemplary Example 10, wherein the step of generating a timeline plot includes the step of generating a static horizontal timeline plot.

[0044] Exemplary Example 12. In any one of Exemplary Examples 1-11, the step of characterizing at least one region of interest based on B-mode and contrast image sequences comprises the step of generating a plurality of timeline plots for a plurality of contrast agent administrations to the region of interest.

[0045] Exemplary Example 13. An image processing system comprising: a non-transient memory device for storing computer-readable program code; and a processor device communicating with the non-transient memory device, wherein the processor device operates with computer-readable program code to derive a luminance mode (B-mode) and a contrast image sequence from a contrast-enhanced ultrasound (CEUS) image sequence, wherein the B-mode image and the contrast image within the B-mode and contrast image sequence are spatially aligned and temporally sub-sampled; the step of selecting at least one region of interest in the B-mode and contrast image sequence; and the step of characterizing at least one region of interest based on the B-mode and contrast image sequence.

[0046] Exemplary Example 14. An image processing system in which, in Exemplary Example 13, the processor device operates with computer-readable program code to derive B-mode and contrast image sequences by sub-sampling frames having temporally uniform intervals.

[0047] Exemplary Example 15. An image processing system in any one of Exemplary Examples 13-14, wherein the processor device operates with computer-readable program code to derive B-mode and contrast image sequences by sub-sampling frames having temporally non-uniform intervals.

[0048] Exemplary Example 16. An image processing system in any one of Exemplary Examples 13-15, wherein the processor device operates with computer-readable program code to select at least one region of interest by selecting one or more lesions.

[0049] Exemplary Example 17. An image processing system in any one of Exemplary Examples 13-16, wherein the processor device operates with computer-readable program code to characterize at least one region of interest based on B-mode and contrast image sequences by generating one or more qualitative parameters, quantitative parameters, timeline plots, or combinations thereof.

[0050] Exemplary Example 18. An image processing system in any one of Exemplary Examples 13-17, wherein the processor device operates with computer-readable program code to characterize at least one region of interest based on B-mode and contrast image sequences by generating a static horizontal timeline plot.

[0051] Exemplary Example 19. An image processing system in any one of Exemplary Examples 13-18, wherein the processor device operates with computer-readable program code to characterize at least one region of interest based on B-mode and contrast image sequences by generating a plurality of timeline plots for a plurality of contrast agent administrations to a region of interest.

[0052] Exemplary Example 20. One or more non-transient computer-readable media for executing machine-executable commands to perform a task, wherein the task comprises the step of deriving a luminance mode (B-mode) and a contrast image sequence from a contrast-enhanced ultrasound (CEUS) image sequence, wherein the B-mode image and the contrast image within the B-mode and contrast image sequence are spatially aligned and temporally sub-sampled; the step of selecting at least one region of interest in the B-mode and contrast image sequence; and the step of characterizing at least one region of interest based on the B-mode and contrast image sequence.

[0053] Although this framework has been described in detail with reference to exemplary embodiments, those skilled in the art will understand that various modifications and substitutions may be made without departing from the spirit and scope of the invention as set forth in the appended claims. For example, elements and / or features of different exemplary embodiments may be combined and / or substituted with one another within the scope of this disclosure and the appended claims.

Claims

Claim 1 A method for characterizing images, comprising: receiving a sequence of contrast-enhanced ultrasound (CEUS) images; deriving a luminance mode (B-mode) and contrast image sequence from the CEUS image sequence, wherein the B-mode image and the contrast image within the B-mode and contrast image sequence are spatially aligned and temporally sub-sampled; selecting at least one region of interest in the B-mode and contrast image sequence; and characterizing at least one region of interest based on the B-mode and contrast image sequence. Claim 2 A method according to claim 1, wherein the step of deriving B-mode and contrast image sequences includes the step of sub-sampling frames having temporally uniform intervals. Claim 3 A method according to claim 1, wherein the step of deriving B-mode and contrast image sequences includes the step of sub-sampling frames having temporally non-uniform intervals. Claim 4 In paragraph 3, the method wherein the frame is selected from the CEUS image sequence based on motion displacement, similarity between frames, or a combination thereof. Claim 5 A method according to claim 1, wherein the step of deriving B-mode and contrast image sequences includes the step of spatially aligning the B-mode image and the contrast image for motion correction. Claim 6 A method according to claim 5, wherein only the B-mode image acquired in the early wash-in phase and only the contrast image acquired in the late wash-out phase are used for motion correction. Claim 7 A method according to claim 5, wherein both the B-mode image and the contrast image are used for motion correction. Claim 8 The method of claim 1, wherein the step of characterizing at least one region of interest based on B-mode and contrast image sequences includes the step of generating one or more qualitative parameters. Claim 9 The method of claim 1, wherein the step of characterizing at least one region of interest based on B-mode and contrast image sequences includes the step of generating one or more quantitative parameters. Claim 10 A method according to claim 1, wherein the step of characterizing at least one region of interest based on B-mode and contrast image sequences includes the step of generating a timeline plot. Claim 11 In claim 10, the step of generating a timeline plot includes the step of generating a static horizontal timeline plot. Claim 12 The method according to claim 1, wherein the step of characterizing at least one region of interest based on B-mode and contrast image sequences includes the step of generating a plurality of timeline plots for the administration of a plurality of contrast agents to the region of interest. Claim 13 An image processing system comprising: a non-transient memory device for storing computer-readable program code; and a processor device communicating with the non-transient memory device, wherein the processor device operates with computer-readable program code, A step of deriving a luminance mode (B-mode) and a contrast image sequence from a contrast-enhanced ultrasound (CEUS) image sequence, wherein the B-mode image and the contrast image within the B-mode and contrast image sequence are spatially aligned and temporally sub-sampled; A step of selecting at least one region of interest in a B-mode and contrast image sequence; and An image processing system that performs a step including characterizing at least one region of interest based on a B-mode and contrast image sequence. Claim 14 An image processing system according to claim 13, wherein the processor device operates with computer-readable program code to derive B-mode and contrast image sequences by sub-sampling frames having temporally uniform intervals. Claim 15 An image processing system according to claim 13, wherein the processor device operates with computer-readable program code to derive B-mode and contrast image sequences by sub-sampling frames having temporally non-uniform intervals. Claim 16 In paragraph 13, the processor device operates with computer-readable program code to select at least one region of interest by selecting one or more lesions, an image processing system. Claim 17 An image processing system according to claim 13, wherein the processor device operates with computer-readable program code to characterize at least one region of interest based on B-mode and contrast image sequences by generating one or more qualitative parameters, quantitative parameters, timeline plots, or combinations thereof. Claim 18 An image processing system according to claim 13, wherein the processor device operates with computer-readable program code to characterize at least one region of interest based on B-mode and contrast image sequences by generating a static horizontal timeline plot. Claim 19 An image processing system according to claim 13, wherein the processor device operates with computer-readable program code to characterize at least one region of interest based on B-mode and contrast image sequences by generating multiple timeline plots for multiple contrast agent administrations to the region of interest. Claim 20 One or more non-transient computer-readable media for executing machine-executable commands to perform a task, wherein the task comprises: a step of deriving a luminance mode (B-mode) and a contrast image sequence from a contrast-enhanced ultrasound (CEUS) image sequence, wherein the B-mode image and the contrast image within the B-mode and contrast image sequence are spatially aligned and temporally sub-sampled; a step of selecting at least one region of interest in the B-mode and contrast image sequence; and a step of characterizing at least one region of interest based on the B-mode and contrast image sequence.

Images