Medical imaging data compression and extraction on the client side

Abstract

A device and computer-implemented method for compressing and extracting three-dimensional (3D) volumetric imaging data (particularly including medical and dental imaging data) can receive 3D volumetric image data and prepare compressed 3D volumetric image data for compression by analyzing relevant regions of the 3D volumetric image data. The method may also include compressing pre-processed static 3D volumetric image data into compressed 3D volumetric image data using a video compression scheme. Various other methods, systems, and computer-readable media are also disclosed.

Description

[0001] Cross-references to related applications

[0002] This patent application claims priority to U.S. Provisional Patent Application No. 62 / 979,325, filed February 20, 2020, entitled “MEDICAL IMAGING DATA COMPRESSION AND EXTRACTION ON CLIENT SIDE,” the entire contents of which are incorporated herein by reference.

[0003] Incorporation

[0004] All publications and patent applications mentioned in this specification are incorporated herein by reference in their entirety to the same extent that each individual publication or patent application is specifically and individually indicated to be incorporated by reference. Background Technology

[0005] Modern medicine increasingly relies on medical imaging for the diagnosis and treatment of patients. For example, medical imaging can provide a visual representation of the inside of a patient's body. Various medical imaging techniques (e.g., X-ray radiography, CT scans, magnetic resonance imaging (MRI), and ultrasound) can be used to generate image data of a patient's body. For example, cone-beam computed tomography (CBCT) is one such medical imaging technique in which X-rays form a cone for scanning, which is used to image the patient. During imaging, the CBCT scanner can be rotated around the region of interest to obtain a large number (e.g., hundreds or thousands) of different images that form a volumetric dataset. The volumetric data can be used to reconstruct the digital volume of the region of interest. The digital volume can be defined by three-dimensional voxels of anatomical data.

[0006] However, as medical imaging technologies become more complex, the volume of image data has increased, and existing methods for processing this data may be less than ideal, at least in some respects. The aforementioned imaging methods can be used for dental or orthodontic imaging, and in at least some cases, the treating professionals may be located remotely from the imaging system. While dentists or orthodontists may be able to view and manipulate digital volumes to diagnose and treat areas of interest, significant delays can occur in data transmission, at least in some cases. Furthermore, datasets can be transmitted to remote locations for volumetric data processing via methods such as tooth segmentation for planning dental and orthodontic procedures. Although digital volumes can provide accurate 3D representations, the storage and transmission requirements for volumetric data can be cumbersome and, at least in some cases, less than ideal. For example, CBCT scanners may generate volumetric data, and large volumes of data may be difficult to transmit consistently to remote locations, and consistent transmission to remote locations is time-consuming. Moreover, storing or otherwise archiving multiple volumetric datasets in multiple locations, for example, may be more challenging than ideal.

[0007] Therefore, this disclosure identifies and addresses the need for systems and methods for client-side compression and extraction of medical imaging data. Summary of the Invention

[0008] This document describes methods and apparatus (e.g., systems and devices, including software, hardware, and firmware) for the compression and extraction of imaging data. In particular, these methods and apparatus can be used for medical imaging data, such as three-dimensional (3D) volumetric image data from, for example (but not limited to), a CBCT scanner. Generally, 3D volumetric image data can be static data. 3D volumetric image data can include multiple 2D images (segments or slices), through which the 3D volumetric image data can be collectively referred to as a 3D volume. A 3D volume can include predetermined segments or images (2D images), or these 2D segments or images can be generated from a 3D volume.

[0009] 3D volumetric image data can be preprocessed by aligning it (e.g., by analyzing relevant regions of the 3D volumetric data). Preprocessing may also include selecting and / or setting coordinate axes (e.g., x, y, z). The coordinate axes may be based on one or more identified anatomical planes from the image data. Therefore, preprocessing can be used to align and maximize symmetry within the 3D volumetric image data. In some examples, preprocessing may include, for example, cropping the 3D volume parallel to the identified anatomical planes, such that the 3D volume has a regular shape (e.g., rectangular, cubic, etc.). In some examples, the 3D volume may be filled, for example, with empty spaces to maintain a regular shape. 3D volumetric image data can also be preprocessed by reducing the dynamic range and / or by segmenting pre-determined clinically relevant features. Specifically, for dental imaging, clinically relevant features may include bone, soft tissue (e.g., jawbone, gingiva, etc.), tooth roots, crowns, internal tooth structures (e.g., dentin, enamel, etc.), etc.

[0010] Preprocessed 3D volumetric image data can be compressed using any suitable compression technique. Specifically, one or more video compression techniques can be used by converting the spatial axis of the 3D volumetric image data into a time axis to form a time series of 2D images and then applying a video compression scheme. By compressing preprocessed 3D volumetric image data, the methods and apparatus described herein can provide client-side solutions for compressing and / or extracting medical imaging data. The systems and methods described herein can improve the transmission and storage of medical imaging data by reducing the amount of data to be uploaded to the server.

[0011] Furthermore, the systems and methods described in this paper can improve the functionality of computing devices by more effectively applying compression schemes and reducing bandwidth through the transmission of compressed data. These systems and methods can also improve the field of medical imaging by reducing the data storage requirements of computational processes.

[0012] This document also describes devices (e.g., systems) for performing any of the methods described herein. These devices may be integrated with imaging apparatuses or systems (e.g., CBCT scanners, ultrasound scanners, etc.). For example, this document describes a system for compressing a three-dimensional (3D) volumetric image dataset comprising multiple image segments forming a 3D volume. The system includes: one or more processors; and a memory coupled to the one or more processors, storing computer program instructions that, when executed by the one or more processors, perform a computer-implemented method comprising: identifying one or more anatomical planes within the 3D volumetric image dataset and setting coordinate planes using the one or more anatomical planes; cropping the 3D volume parallel to the coordinate planes; adjusting the dynamic range of the 3D volumetric image dataset; and converting the spatial axes of the 3D volume into temporal axes to form a time series of 2D images, and applying a video compression scheme to the time series of the 2D images to form a compressed 3D volumetric image dataset.

[0013] Computer-implemented methods can identify one or more anatomical planes within a 3D volumetric image dataset and set coordinate planes to increase their symmetry. In some examples, computer-implemented methods crop the 3D volume parallel to the coordinate plane to minimize blank areas within the 3D volume. Computer-implemented methods can also include filling the 3D volume with blank areas to maintain symmetry after cropping. In some examples, computer-implemented methods adjust the dynamic range of the 3D volumetric image dataset through histogram analysis. For example, computer-implemented methods can adjust the dynamic range of the 3D volumetric image dataset by segmenting it using clinically relevant regions (e.g., which may include soft tissue, bone, crowns, and roots).

[0014] For example, this paper describes a method for compressing a three-dimensional (3D) volumetric image dataset. A 3D volumetric dataset may include multiple image segments that form a 3D volume. For example, a 3D (e.g., static) volumetric image dataset can be compressed by: identifying one or more anatomical planes within the 3D volumetric image dataset and using these one or more anatomical planes to set coordinate planes; cropping the 3D volume parallel to at least two coordinate planes; adjusting the dynamic range of the 3D volumetric image dataset; and converting the spatial axes of the 3D volume to temporal axes to form a time series of 2D images, and applying a video compression scheme to the time series of the 2D images to form the compressed 3D volumetric image dataset.

[0015] Any of these methods may include identifying one or more anatomical planes within a 3D volumetric image dataset and setting the coordinate planes to increase their symmetry. In some examples, the method also includes cropping the 3D volume parallel to the coordinate planes to minimize blank areas in the 3D volume, and / or filling the 3D volume with blank areas to maintain symmetry of the 3D volume after cropping.

[0016] Adjusting the dynamic range of a 3D volumetric image dataset can include adjustments via histogram analysis. Any of these methods can include segmenting the 3D volumetric image dataset using clinically relevant regions. Clinically relevant regions can include, for example, soft tissue, bone, crowns, and roots.

[0017] Any of these methods may include: dividing the image segment forming the 3D volume into a first half and a second half that are symmetrical to each other before converting the spatial axis of the 3D volume to the temporal axis, determining the difference between the first half and the second half, and reducing the 3D volume by replacing the second half with the difference between the first half and the second half.

[0018] These methods may also include storing or transmitting the compressed 3D volumetric image dataset. For example, any of these methods may include transmitting the compressed 3D volumetric dataset to a remote server and decompressing the 3D volumetric dataset on the remote server. The remote server may decompress the 3D volumetric image dataset.

[0019] In any of these methods, applying a video compression scheme to a time series of 2D images to form a compressed 3D volumetric image dataset can include forming the compressed 3D volumetric image dataset at a compression ratio between 50 and 2500. In some examples, applying a video compression scheme to a time series of 2D images to form a compressed 3D volumetric image dataset includes forming the compressed 3D volumetric image dataset at a compression ratio of 50 or greater. Generally, these methods can include compression using a dice coefficient (Dice coefficient) greater than 0.90.

[0020] In any of these methods, applying a video compression scheme to a time series of 2D images can include applying macroblock compression using discrete cosine transform (DCT). Any of these methods can also include using entropy coding to encode the compressed 3D volumetric image dataset.

[0021] For example, a method for compressing a three-dimensional (3D) volumetric image dataset comprising multiple image segments forming a 3D volume may include: identifying at least two anatomical planes within the 3D volumetric image dataset and using these at least two anatomical planes to set at least two coordinate planes to increase the symmetry of the coordinate planes; cropping the 3D volume parallel to the coordinate planes; adjusting the dynamic range of the 3D volumetric image dataset through histogram analysis and segmenting the 3D volumetric image dataset using clinically relevant regions, including soft tissue, bone, crowns, and roots; dividing the image segments forming the 3D volume into a first half and a second half that are symmetrical to each other, determining the difference between the first half and the second half, and reducing the 3D volume by replacing the second half with the difference between the first half and the second half; applying a video compression scheme to the 3D volume to form a compressed 3D volumetric image dataset by converting the spatial axis of the 3D volume into a temporal axis to form a time series of 2D images; and storing or transmitting the compressed 3D volumetric image dataset.

[0022] Any of these computer-implemented methods may further include: dividing an image segment forming the 3D volume into a first half and a second half that are symmetrical to each other before converting the spatial axis of the 3D volume to a time axis, determining the difference between the first half and the second half, and reducing the 3D volume by replacing the second half with the difference between the first half and the second half.

[0023] As mentioned, any of these systems may include an imaging device (e.g., a CBCT system, etc.) that communicates with one or more processors.

[0024] Computer-implemented methods may also include storing or transmitting the compressed 3D volumetric image dataset. In some examples, the computer-implemented methods further include transmitting the compressed 3D volumetric dataset to a remote server and decompressing the 3D volumetric image dataset on the remote server. Computer-implemented methods can apply video compression schemes to time series of 2D images to form compressed 3D volumetric image datasets with compression ratios between 50 and 2500. In some examples, computer-implemented methods apply video compression schemes to time series of 2D images to form compressed 3D volumetric image datasets with compression ratios of 50 times or greater. Compression can be accomplished using dice scores greater than 0.9.

[0025] A computer-implemented method can apply a video compression scheme by applying macroblock compression using discrete cosine transform (DCT) to the time series of 2D images to form a compressed 3D volumetric image dataset.

[0026] In some examples, the computer-implemented method also includes using entropy coding to encode the compressed 3D volumetric image dataset.

[0027] For example, a system for compressing a three-dimensional (3D) volumetric image dataset comprising multiple image segments forming a 3D volume includes: one or more processors; and a memory coupled to the processors, the memory storing computer program instructions that, when executed by the processors, perform a computer-implemented method comprising: identifying at least two anatomical planes within the 3D volumetric image dataset and using the at least two anatomical planes to establish at least two coordinate planes to increase the symmetry of the coordinate planes; cropping the 3D volume parallel to the coordinate planes; and adjusting the 3D volume through histogram analysis. The dynamic range of the volumetric image dataset is determined, and the 3D volumetric image dataset is segmented using clinically relevant regions, including soft tissue, bone, crowns, and roots. The image segments forming the 3D volume are divided into a first half and a second half that are symmetrical to each other, the differences between the first half and the second half are determined, and the 3D volume is reduced by replacing the second half with the differences between the first half and the second half. A video compression scheme is applied to the 3D volume to form a compressed 3D volumetric image dataset by converting the spatial axis of the 3D volume to the temporal axis to form a time series of 2D images. The compressed 3D volumetric image dataset is then stored or transmitted. Attached Figure Description

[0028] A better understanding of the features, advantages, and principles of this disclosure will be obtained by referring to the following detailed description of illustrative embodiments and the accompanying drawings:

[0029] Figure 1 A portion of 3D volumetric image data is shown based on some examples;

[0030] Figure 2 The reconstruction of patient teeth based on 3D volumetric image data is shown in some examples;

[0031] Figure 3 A block diagram of an example system for medical imaging data compression and extraction is shown, based on some examples.

[0032] Figure 4 A block diagram of an additional example system for compression and extraction of medical imaging data, based on some examples, is shown;

[0033] Figure 5 A flowchart illustrating an example method for compressing medical imaging data, based on several examples, is shown;

[0034] Figure 6A and Figure 6BThe diagram shows geometric preprocessing based on some examples;

[0035] Figure 7 An exemplary graph is shown based on histogram analysis of some examples;

[0036] Figure 8 Examples of re-encoded voxels based on some examples are shown;

[0037] Figure 9 A flowchart illustrating an example method for extracting medical imaging data from compressed data is shown, based on several examples.

[0038] Figure 10A and Figure 10B Tables and graphs showing compression metrics based on some examples are provided.

[0039] Figure 11A and Figure 11B A visual comparison of compression results based on some examples is shown;

[0040] Figure 12 A flowchart is shown illustrating an example method for extracting data from compressed volumetric image data, based on several examples.

[0041] Figure 13 A block diagram of an example computing system that implements one or more of the examples described and / or shown herein is presented, based on some examples;

[0042] Figure 14 A block diagram of an example computational network, based on several examples, is shown that enables the implementation of one or more of the examples described and / or shown herein; and

[0043] Figure 15A A flowchart of an example method for compressing (e.g., dense) 3D volumetric imaging data is shown. Figure 15B Another example flowchart shows an example method for compressing 3D volumetric imaging data. Detailed Implementation

[0044] The following detailed description, based on the examples disclosed herein, provides a better understanding of the features and advantages of the invention described herein. Although the detailed description includes many specific examples, these are provided by way of example only and should not be construed as limiting the scope of the invention disclosed herein.

[0045] The following will refer to Figures 1 to 2 Detailed descriptions of imaging and modeling are provided. These examples may be specific to medical (e.g., dental) systems and methods, but the methods and devices described herein can generally be applied to any imaging technique, including non-medical ones. (The text will be combined with...) Figures 3 to 4A detailed description of an example system for compressing and extracting medical imaging data is provided. This will also be combined with... Figure 5 A detailed description of the corresponding computer-implemented method is provided. A detailed description of an exemplary geometric preprocessing will be provided with reference to Figure 6. Figure 7 Provides a detailed description of histogram analysis. This will be combined with... Figure 8 Provides a description of voxel recoding. This will be combined with... Figure 9 A detailed description of a computer-implemented method for extracting medical imaging data is provided. A detailed description of evaluating the compression results is also provided, in conjunction with Figures 10 and 11. Figure 12 A detailed description of the additional methods is provided. Furthermore, they will be combined separately. Figure 13 and Figure 14 Provide a detailed description of example computing systems and network architectures that can implement one or more of the examples described in this article.

[0046] Figure 1 Image data 100 is shown, which can be a single image from 3D volumetric image data such as CBCT scan data. 3D volumetric image data can include multiple separate images taken around an object. Each image can correspond to a scan of the object, for example, acquired at different angles, different scan offsets, etc. 3D volumetric data can be used to reconstruct the digital volume of the object. The digital volume can include voxels representing values ​​in three-dimensional space. These values ​​can correspond to anatomical structures. Figure 1 As seen, image data 100 includes skeletal structure 110, tissue structure 120, and blank space 130.

[0047] Figure 2 Reconstructions 200 with various tooth structures 210 are shown. 3D volumetric data can be reconstructed into a 3D model of the object. In some examples, segmentation can be performed on the 3D volumetric data to remove irrelevant regions from the 3D model. Reconstruction 200 includes only the tooth structures 210 without irrelevant regions. Orthodontists can often use reconstructions such as reconstruction 200 to diagnose a patient's teeth. Therefore, the accuracy of reconstruction 200 can be an important consideration. While larger datasets of 3D volumetric images may yield higher resolution reconstructions, the data storage requirements can be daunting.

[0048] Figure 3 This is a block diagram of an example system 300 for compressing and extracting medical imaging data. As shown in the figure, the example system 300 may include one or more modules 302 for performing one or more tasks. As will be explained in more detail below, module 302 may include a receiving module 304, a preparation module 306, a compression module 308, and a recovery module 310. Although shown as separate elements, Figure 3One or more modules 302 in the document can represent a single module or part of an application.

[0049] In some examples, Figure 3 One or more modules 302 may represent one or more software applications or programs that, when executed by a computing device, enable the computing device to perform one or more tasks. For example, as will be described in more detail below, one or more modules 302 may represent those stored and configured to be used in one or more computing devices (such as...) Figure 4 The modules running on the devices shown, such as computing device 402 and / or server 406. Figure 3 One or more modules 302 may also represent all or part of one or more special computers configured to perform one or more tasks.

[0050] like Figure 3 As shown, example system 300 may also include one or more memory devices, such as memory 340. Memory 340 generally refers to any type or form of volatile or non-volatile storage device or medium capable of storing data and / or computer-readable instructions. In one example, memory 340 may store, load, and / or maintain one or more modules 302. Examples of memory 340 include, but are not limited to, random access memory (RAM), read-only memory (ROM), flash memory, hard disk drive (HDD), solid-state drive (SSD), optical disk drive, cache, variations or combinations thereof, and / or any other suitable storage memory.

[0051] like Figure 3 As shown, the example system 300 may also include one or more physical processors, such as physical processor 330. Physical processor 330 generally represents a processing unit of any type or form of hardware implementation capable of interpreting and / or executing computer-readable instructions. In one example, physical processor 330 may access and / or modify one or more modules 302 stored in memory 340. Additionally or alternatively, physical processor 330 may execute one or more modules 302 to facilitate the compression and / or extraction of medical imaging data. Examples of physical processor 330 include, but are not limited to, microprocessors, microcontrollers, central processing units (CPUs), graphics processing units (GPUs), field-programmable gate arrays (FPGAs) implementing soft-core processors, application-specific integrated circuits (ASICs), portions of one or more of these, variations or combinations of one or more of these, and / or any other suitable physical processor.

[0052] like Figure 3As shown, the example system 300 may also include one or more data elements 320, such as 3D volumetric image data 322, preprocessed 3D volumetric image data 324, compressed 3D volumetric image data 326, and restored 3D volumetric image data 328. Data elements 320 typically represent data of any type or form, such as medical imaging data and its permutations, as will be further described below.

[0053] Figure 3 The example system 300 can be implemented in a variety of ways. For example, all or part of the example system 300 can represent Figure 4 The example system 400 is shown in the image. Figure 4 As shown, system 400 may include computing device 402 that communicates with server 406 via network 404. In one example, all or part of the functionality of module 302 may be performed by computing device 402, server 406, and / or any other suitable computing system. As will be described in more detail below, from Figure 3 One or more modules 302 may, when executed by at least one processor of computing device 402 and / or server 406, enable computing device 402 and / or server 406 to compress and / or extract medical imaging data. For example, as will be described in more detail below, one or more modules 302 may enable computing device 402 and / or server 406 to prepare preprocessed 3D volumetric image data and compress the preprocessed 3D volumetric image data into compressed 3D volumetric image data.

[0054] Computing device 402 generally refers to any type or form of computing device capable of reading computer-executable instructions. Computing device 402 can be a user device, such as a desktop computer or a mobile device. Additional examples of computing device 402 include, but are not limited to, laptops, tablets, desktops, servers, cellular phones, personal digital assistants (PDAs), multimedia players, embedded systems, wearable devices (e.g., smartwatches, smart glasses, etc.), smart vehicles, smart packaging (e.g., active packaging or smart packaging), game consoles, so-called Internet of Things (IoT) devices (e.g., smart appliances, etc.), variations or combinations of one or more of these, and / or any other suitable computing device.

[0055] Server 406 generally refers to any type or form of computing device capable of storing and / or processing imaging data. Additional examples of server 406 include, but are not limited to, security servers, application servers, web servers, storage servers, and / or database servers configured to run certain software applications and / or provide various security, web, storage, and / or database services. Although in Figure 4While represented as a single entity, server 406 may include and / or represent multiple servers working and / or running together.

[0056] Network 404 typically refers to any medium or architecture capable of facilitating communication or data transfer. In one example, network 404 could facilitate communication between computing device 402 and server 406. In this example, network 404 could facilitate communication or data transfer using wireless and / or wired connections. Examples of network 404 include, but are not limited to, intranets, wide area networks (WANs), local area networks (LANs), personal area networks (PANs), the Internet, power line communication (PLC), cellular networks (e.g., Global System for Mobile Communications (GSM) networks), portions of one or more of them, variations or combinations of one or more of them, and / or any other suitable network.

[0057] Figure 5 This is a flowchart of an example computer-implemented method 500 for compressing medical imaging data. Figure 5 The steps shown can be performed by any suitable computer executable code and / or computing system (including...). Figure 3 System 300 in Figure 4 The system (system 400 and / or one or more variations or combinations thereof) is executed. In one example, Figure 5 Each step shown can represent an algorithm whose structure includes and / or is represented by multiple sub-steps, examples of which will be provided in more detail below.

[0058] like Figure 5 As shown, at step 502, one or more systems described herein can receive 3D volumetric image data. For example, a receiving module 304, as part of computing device 402, can receive 3D volumetric image data 322. 3D volumetric image data 322 may include patient scan data. 3D volumetric image data 322 may include computed tomography (CT) images, cone-beam computed tomography (CBCT) images, or magnetic resonance imaging (MRI) images. 3D volumetric image data 322 may include 3D volumetric medical digital imaging and communication (DICOM) images.

[0059] In one example, an orthodontist can receive raw CBCT scan data of the patient's head from a scanner on their computing device. For example, 3D volumetric image data 322 may include multiple teeth.

[0060] In other examples, the 3D volumetric image data 322 may include one or more separable tissue structures. Each of the one or more separable tissue structures may include an outer surface that surrounds the interior of the one or more separable tissue structures. More specifically, the one or more separable tissue structures may include multiple teeth. Each of the multiple teeth may include an outer surface that surrounds the interior.

[0061] like Figure 5 As shown, at step 504, one or more systems described herein can prepare preprocessed 3D volumetric image data for compression by analyzing relevant regions of the 3D volumetric image data. For example, preparation module 306, as part of computing device 402, can prepare preprocessed 3D volumetric image data 324 by analyzing relevant regions of 3D volumetric image data 322. The preprocessed 3D volumetric image data 324 may include data analyzed by preparation module 306 to determine improvements and other modifications for optimizing compression. Preparation module 306 can prepare preprocessed 3D volumetric image data 324 in various ways.

[0062] In some examples, preparation module 306 can prepare preprocessed 3D volumetric image data 324 by performing geometric preprocessing on 3D volumetric image data 322. For example, preparation module 306 can identify anatomical planes from 3D volumetric image data 322. Anatomical planes can be one or more of the sagittal, coronal, or axial planes. Preparation module 306 can rotate the volume captured in 3D volumetric image data 322 to align the anatomical planes with coordinate axes that may be defined in 3D volumetric image data 322. Preprocessed 3D volumetric image data 324 may include the rotated volume.

[0063] Figure 6A An image 600 is shown, including anatomical plane 610 and volume 620. (See image 600.) Figure 6A As seen, volume 620 can be rotated to align the anatomical plane 610 with the coordinate axes. For example, volume 620 can be rotated to make the anatomical plane 610 parallel to the X, Y, or Z axis. This rotation can reduce the complexity of the data structure of the preprocessed 3D volumetric image data 324 (e.g., by making the data structure more symmetrical), which can further optimize compression.

[0064] The preparation module 306 can perform geometric preprocessing by identifying the axis of symmetry from the 3D volumetric image data 322 to divide the volume captured in the 3D volumetric image data 322 into a first part and a second part. The preparation module 306 can determine the difference between the first part and the second part and store the first part and the difference as preprocessed 3D volumetric image data 324.

[0065] Figure 6B A segmented image 602 is shown, comprising a first portion 630 and a second portion 640. The first portion 630 and the second portion 640 can be derived from an axis of symmetry (e.g., Figure 6A The anatomical plane 610 in the image is used to divide the image so that the first part 630 may be nearly symmetrical to the second part 640. Although the first part 630 may resemble a mirror image of the second part 640, there may be differences, which may include related data. However, storing the first part 630 and the differences can reduce the storage size of the preprocessed 3D volumetric image data 324 compared to the storage size of the 3D volumetric image data 322, and compression can be further optimized.

[0066] The preparation module 306 can also perform geometric preprocessing by identifying and cropping irrelevant regions from the 3D volumetric image data 322, so that the preprocessed 3D volumetric image data 324 may not include irrelevant regions. Irrelevant regions can be blank areas. For example, they can be cropped. Figure 1 The blank space 130 in the image. Compared with the storage size of the 3D volumetric image data 322, cropping the irrelevant area can reduce the storage size of the preprocessed 3D volumetric image data 324, and can further optimize compression.

[0067] In some examples, the preparation module 306 can prepare preprocessed 3D volumetric image data 324 by identifying the root structure or skeletal structure from the 3D volumetric image data 322 as relevant regions and labeling the identified relevant regions. For example, the preparation module 306 can prepare preprocessed 3D volumetric image data 324 by identifying the root structure or skeletal structure from the 3D volumetric image data 322 as relevant regions and labeling the identified relevant regions. Figure 1 The skeletal structure 110 in the volume is identified and marked. The preparation module 306 can perform segmentation to divide the volume into relevant and irrelevant regions.

[0068] In some examples, preparation module 306 can perform histogram analysis to identify relevant regions. Figure 7 Histogram 700 is shown. (Example) Figure 7 As seen, certain values ​​can correspond to certain types of structures. The preparation module 306 can analyze the voxel values ​​of the 3D volumetric image data 322.

[0069] Labeling relevant regions can facilitate further preprocessing of the 3D volumetric image data 322. In some examples, the preparation module 306 can re-encode the voxels of the 3D volumetric image data 322 to reduce the dynamic range of bits per voxel. Each voxel can include a value corresponding to the type of anatomical structure. As the number of types increases (e.g., the range of possible values ​​increases), the number of bits required to store each value for each voxel may increase. Increasing the number of bits per voxel may result in an increase in the data storage requirements of the 3D volumetric image data 322. However, since some types of structures may be irrelevant, for example, as determined by histogram analysis, less data related to irrelevant regions can be retained without losing data related to relevant regions.

[0070] For example, the type of structure can be reduced to blank space, soft tissue, bone, or teeth. Using four possible intensity values, each voxel can be encoded with 2 bits per voxel. In other examples, more detailed segmentation can produce 4 to 8 bits per voxel. Therefore, the dynamic range can be reduced from more than 8 bits per voxel to 2 to 8 bits per voxel.

[0071] Figure 8 This illustrates re-encoding image data 810 800 into re-encoded image data 820. For example... Figure 8 As seen in the diagram, recoding may result in the loss of some details, while preserving relevant structural details.

[0072] return Figure 5 At step 506, one or more systems described herein may use a compression scheme to compress the preprocessed 3D volumetric image data into compressed 3D volumetric image data. For example, compression module 308, as part of computing device 402, may use a compression scheme to compress the preprocessed 3D volumetric image data 324 into compressed 3D volumetric image data 326. Compression module 308 may compress the preprocessed 3D volumetric image data 324 in various ways.

[0073] In some examples, the compression scheme may be a video codec. Because volumetric image data (e.g., 3D volumetric image data 322 and preprocessed 3D volumetric image data 324) may comprise multiple images, similar to a video file, the compression module 308 may utilize a video codec. Preprocessing performed by the preparation module 306 may further optimize the preprocessed 3D volumetric image data 324 for compression. In some examples, the compression scheme may include a discrete cosine transform (DCT). In some examples, the compression scheme may include a motion compensation scheme. In some examples, the compression scheme may include an entropy coding scheme.

[0074] Figure 9This is a flowchart of an example computer-implemented method 900 for extracting medical imaging data from compressed data. Figure 9 The steps shown can be performed by any suitable computer executable code and / or computing system (including...). Figure 3 System 300 in Figure 4 The system (system 400 and / or one or more variations or combinations thereof) is executed. In one example, Figure 9 Each step shown can represent an algorithm whose structure includes and / or is represented by multiple sub-steps, examples of which will be provided in more detail below.

[0075] like Figure 9 As shown, at step 902, one or more systems described herein can decompress the compressed 3D volumetric image data using a compression scheme. For example, as Figure 4 The restoration module 310, a part of the computing device 402 and / or server 406, can decompress the compressed 3D volumetric image data 326 into restored 3D volumetric image data 328.

[0076] In some examples, the orthodontist can send the compressed 3D volumetric image data 326 from the computing device 402 to a server 406, which may be, for example, a cloud server, a lab server, or an external storage device. The server 406 can decompress the compressed 3D volumetric image data 326. In some examples, the computing device 402 can send a compression scheme to the server 406. In other examples, the compression scheme can be predetermined.

[0077] At step 904, one or more systems described herein can recover previously modified image data from the decompressed 3D volumetric image data to produce recovered 3D volumetric image data. For example, as Figure 4 The restoration module 310, a part of the computing device 402 and / or server 406, can restore the restored 3D volumetric image data 328 by restoring the modifications of the preprocessed 3D volumetric image data 324 to the 3D volumetric image data 322.

[0078] The restored 3D volumetric image data 328 can retain information from the 3D volumetric image data 322. In some examples, the 3D volumetric image data 322 may include a first spatial resolution, while the restored 3D volumetric image data 328 may include a second spatial resolution. The first spatial resolution can be matched with the second spatial resolution. The DICE score or coefficient between the 3D volumetric image data 322 and the restored 3D volumetric image data 328 can measure the similarity between the original data and the decompressed data. The DICE score is known to those skilled in the art, and the DICE score is sometimes referred to as... Coefficients. DICE scores typically correspond to the volume overlap of structures, such as the volume overlap of one or more teeth. For example, a relevant (e.g., segmented) region from 3D volumetric image data 322 can be compared with the same region from the restored 3D volumetric image data 328. Figure 10A Table 1000 shows the DICE coefficients for a given compression ratio. Figure 10B The corresponding figure 1002 is shown. For example... Figures 10A to 10B As seen, compression ratios as high as approximately 2000 can produce sufficient similarity (e.g., from approximately 0.90 to approximately 0.95), while compression ratios of nearly 6000 may produce unusable results.

[0079] In some examples, a compression ratio of around 200 can be used. Higher compression ratios may incur additional processing overhead without yielding significant gains in data retention. By compressing 3D volumetric image data, it becomes easier to transmit the compressed 3D volumetric image data, for example, requiring less bandwidth for transmission.

[0080] Figure 11A The reconstruction of 1100 with a compression ratio of 5x is shown. Figure 11B The reconstructed 1102 is shown with a compression ratio of approximately 2000x. Shaded areas correspond to the restored data, while white areas correspond to the original, uncompressed data. (See diagram.) Figures 11A to 11B The visual comparison shows that the data retained after compression and restoration is important enough for successful reconstruction.

[0081] In some examples, 3D volumetric image data 322 may include multiple teeth, and compressed 3D volumetric image data 326 may also include multiple teeth. The compression ratio of 3D volumetric image data 322 to compressed 3D image data 326 may include values ​​ranging from about 50 to about 2000. Compared to compressed 3D volumetric image data 326, the DICE score of multiple teeth from 3D volumetric image data 322 may range from about 0.95 to about 0.90.

[0082] In some examples, 3D volumetric image data 322 may include one or more separable tissue structures, and compressed 3D volumetric image data 326 may include one or more separable tissue structures. Each of the one or more separable tissue structures may include an outer surface that surrounds the interior of the one or more separable tissue structures. The compression ratio of 3D volumetric image data 322 to compressed 3D image data 326 may include values ​​ranging from about 50 to about 2000. The voxel overlap of the one or more separable tissue structures in 3D volumetric image data 322 may range from about 0.95 to about 0.90 compared to compressed 3D volumetric image data 326.

[0083] In some examples, as Figure 4 The restoration module 310, a part of the computing device 402 and / or server 406, can perform segmentation to isolate relevant structures from the restored 3D volumetric image data 328. The restored volumetric image data 328 may include multiple voxels, each encoded as one of blank space, soft tissue, bone, or teeth. Relevant structures can be isolated based on the encoding of each of the multiple voxels. In some examples, the relevant structures may include individual tooth structures.

[0084] Figure 12 This is a flowchart of an example computer-implemented method 1200 for extracting medical imaging data from compressed data. Figure 12 The steps shown can be performed by any suitable computer executable code and / or computing system (including...). Figure 3 System 300 in Figure 4 The system (system 400 and / or one or more variations or combinations thereof) is executed. In one example, Figure 12 Each step shown can represent an algorithm whose structure includes and / or is represented by multiple sub-steps, examples of which will be provided in more detail below.

[0085] like Figure 12 As shown, at step 1202, one or more systems described herein can receive 3D volumetric image data including multiple discrete tissue structures. For example, as Figure 4A receiving module 304, a part of the computing device 402 and / or server 406, can receive compressed 3D volumetric image data 326. The compressed 3D volumetric image data 326 may include various discrete tissue structures. For example, the compressed 3D volumetric image data 326 may have been generated from original 3D volumetric image data (e.g., 3D volumetric image data 322) including multiple teeth, such that the compressed 3D volumetric image data 326 includes those teeth. The compression ratio between the original 3D volumetric image data and the compressed 3D image data may include values ​​ranging from about 50 to about 2000, and the DICE score of the multiple teeth from the original 3D volumetric image data may range from about 0.95 to about 0.90 compared to the restored 3D volumetric image data.

[0086] In another example, the compressed 3D volumetric image data may have been generated from original 3D volumetric image data including one or more separable tissue structures, and the compressed 3D volumetric image data may include the one or more separable tissue structures. Each of the one or more separable tissue structures may include an outer surface that surrounds the interior of the one or more separable tissue structures. The compression ratio of the original 3D volumetric image data to the compressed 3D image data may include values ​​ranging from about 50 to about 2000. The voxel overlap of the one or more separable tissue structures in the original 3D volumetric image data may range from about 0.95 to about 0.90 compared to the compressed 3D volumetric image data.

[0087] In yet another example, compressed 3D volumetric image data can be generated from raw 3D volumetric image data that includes a first spatial resolution. The restored 3D volumetric image data may include a second spatial resolution that matches the first spatial resolution. The raw 3D volumetric image data may include a dynamic range greater than 8 bits, while the restored volumetric image data may include a dynamic range ranging from 2 bits per voxel to 8 bits per voxel.

[0088] like Figure 12 As shown, at step 1204, one or more systems described herein can decompress the compressed 3D volumetric image data using a compression scheme to generate the restored 3D volumetric image data. For example, as Figure 4 The restoration module 310, a part of the computing device 402 and / or server 406, can decompress the compressed 3D volumetric image data 326 into restored 3D volumetric image data 328.

[0089] At step 1206, one or more systems described herein can segment the restored 3D volumetric image data into multiple segmented tissue structures. For example, as Figure 4The restoration module 310, a part of the computing device 402 and / or server 406, can segment the restored 3D volumetric image data 328 into various segmented tissue structures, such as... Figure 2 , Figure 11A and Figure 11B As seen in the text.

[0090] In some examples, the restoration module 310, which is part of the computing device 402 and / or server 406, can restore the image data that was previously modified in preparation for the preprocessed 3D volumetric image data from the decompressed 3D volumetric image data to produce the restored 3D volumetric image data.

[0091] While the systems and methods for orthodontic treatment have been described above, anonymization methods and devices can be used in other medical settings, such as plastic surgery, in other implementations. Alternatively, anonymization methods and devices can be used outside of medical settings, such as for generating surrogates or concealing the identities of minors. In such settings, the clinically relevant area may correspond to, or be defined by, important physical features relevant to a given environment.

[0092] Figure 13 This is a block diagram of an example computing system 1310 capable of implementing one or more examples described and / or shown herein. For example, all or part of the computing system 1310 can perform one or more steps described herein (such as...). Figure 5 One or more steps shown), and / or as a means of performing one or more steps described herein, either alone or in combination with other elements (such as... Figure 5 The computing system 1310 may also perform any other steps, methods, or processes described and / or shown herein, and / or serve as a device for performing any other steps, methods, or processes described and / or shown herein.

[0093] The term "computing system 1310" broadly refers to any single-processor or multi-processor computing device or system capable of executing computer-readable instructions. Examples of computing system 1310 include, but are not limited to, workstations, laptops, client-side terminals, servers, distributed computing systems, handheld devices, or any other computing system or device. In its most basic configuration, computing system 1310 may include system memory 1316 and at least one processor 1314.

[0094] Processor 1314 generally refers to any type or form of physical processing unit (e.g., a hardware-implemented central processing unit) capable of processing data or interpreting and executing instructions. In some examples, processor 1314 may receive instructions from a software application or module. These instructions may cause processor 1314 to perform the functions of one or more examples described and / or shown herein.

[0095] System memory 1316 generally refers to any type or form of volatile or non-volatile storage device or medium capable of storing data and / or other computer-readable instructions. Examples of system memory 1316 include, but are not limited to, random access memory (RAM), read-only memory (ROM), flash memory, or any other suitable memory device. Although not required, in some examples, computing system 1310 may include volatile memory cells (such as, for example, system memory 1316) and non-volatile storage devices (such as, for example, main storage device 1332, as described in detail below). In one example, Figure 3 One or more modules 302 can be loaded into system memory 1316.

[0096] In some examples, system memory 1316 may store and / or load operating system 1340 for execution by processor 1314. In one example, operating system 1340 may include and / or represent software that manages computer hardware and software resources, and / or provides public services to computer programs and / or applications on computing system 1310. Examples of operating system 1340 include, but are not limited to, LINUX, JUNOS, MICROSOFT WINDOWS, WINDOWS MOBILE, MAC OS, APPLE's IOS, UNIX, GOOGLE CHROME OS, GOOGLE's ANDROID, Solaris, variations of one or more of them, and / or any other suitable operating system.

[0097] In some examples, in addition to processor 1314 and system memory 1316, example computing system 1310 may also include one or more components or elements. For example, such as Figure 13As shown, the computing system 1310 may include a memory controller 1318, an input / output (I / O) controller 1320, and a communication interface 1322, each of which may be interconnected via a communication infrastructure 1312. The communication infrastructure 1312 generally refers to any type or form of infrastructure capable of facilitating communication between one or more components of the computing device. Examples of the communication infrastructure 1312 include, but are not limited to, communication buses (such as Industry Standard Bus (ISA), External Device Interconnect Bus (PCI), Serial Bus (PCI Express, PCIe), or similar buses) and networks.

[0098] The memory controller 1318 generally refers to any type or form of device capable of processing memory or data, or controlling communication between one or more components of the computing system 1310. For example, in some examples, the memory controller 1318 may control communication between the processor 1314, the system memory 1316, and the I / O controller 1320 via the communication infrastructure 1312.

[0099] I / O controller 1320 generally refers to any type or form of module capable of coordinating and / or controlling the input and output functions of a computing device. For example, in some examples, I / O controller 1320 may control or facilitate data transfer between one or more components of computing system 1310, such as processor 1314, system memory 1316, communication interface 1322, display adapter 1326, input interface 1330, and storage interface 1334.

[0100] like Figure 13 As shown, the computing system 1310 may further include at least one display device 1324, which is coupled to the I / O controller 1320 via a display adapter 1326. The display device 1324 generally refers to any type or form of device capable of visually displaying information forwarded by the display adapter 1326. Similarly, the display adapter 1326 generally refers to any type or form of device configured to forward graphics, text, and other data from the communication infrastructure 1312 (or from a frame buffer, as known in the art) for display on the display device 1324.

[0101] like Figure 13 As shown, the example computing system 1310 may also include at least one input device 1328, which is coupled to the I / O controller 1320 via an input interface 1330. The input device 1328 generally refers to any type or form of input device capable of providing computer-generated or artificially generated input to the example computing system 1310. Examples of the input device 1328 include, but are not limited to, keyboards, pointing devices, voice recognition devices, variations or combinations thereof, and / or any other input device.

[0102] Additionally or alternatively, the example computing system 1310 may include additional I / O devices. For example, the example computing system 1310 may include I / O device 1336. In this example, I / O device 1336 may include and / or represent a user interface that facilitates human interaction with the computing system 1310. Examples of I / O device 1336 include, but are not limited to, a computer mouse, keyboard, monitor, printer, modem, camera, scanner, microphone, touchscreen device, variations or combinations thereof, and / or any other I / O device.

[0103] Communication interface 1322 broadly refers to any type or form of communication device or adapter capable of facilitating communication between example computing system 1310 and one or more additional devices. For example, in some examples, communication interface 1322 may facilitate communication between computing system 1310 and a private or public network that includes additional computing systems. Examples of communication interface 1322 include, but are not limited to, wired network interfaces (such as network interface cards), wireless network interfaces (such as wireless network interface cards), modems, and any other suitable interfaces. In at least one example, communication interface 1322 may provide a direct connection to a remote server via a direct link to a network (such as the Internet). Communication interface 1322 may also provide such connections indirectly via, for example, a local area network (such as Ethernet), a personal area network, a telephone or cable network, a cellular telephone connection, a satellite data connection, or any other suitable connection.

[0104] In some examples, communication interface 1322 may also represent a host adapter configured to facilitate communication between computing system 1310 and one or more additional network or storage devices via an external bus or communication channel. Examples of host adapters include, but are not limited to, Small Computer System Interface (SCSI) host adapters, Universal Serial Bus (USB) host adapters, Institute of Electrical and Electronics Engineers (IEEE) 1394 host adapters, Advanced Technology Attachment (ATA) host adapters, Parallel Advanced Technology Attachment (PATA) host adapters, Serial Advanced Technology Attachment (SATA) host adapters, and External Serial Advanced Technology Attachment (eSATA) host adapters, Fibre Channel interface adapters, Ethernet adapters, etc. Communication interface 1322 may also allow computing system 1310 to participate in distributed or remote computing. For example, communication interface 1322 may receive instructions from or send instructions to a remote device for execution.

[0105] In some examples, system memory 1316 may store and / or load network communication program 1338 for execution by processor 1314. In one example, network communication program 1338 may include and / or represent software that enables computing system 1310 to communicate with another computing system via communication interface 1322. Figure 13 (Not shown) Establishing a network connection 1342 and / or communicating with another computing system. In this example, network communication program 1338 can direct the flow of outgoing traffic, which is sent to another computing system via network connection 1342. Additionally or alternatively, network communication program 1338 can direct the processing of incoming traffic, which is received from another computing system via network connection 1342 connected to processor 1314.

[0106] Despite Figure 13 While not shown in this manner, the network communication program 1338 may alternatively be stored and / or loaded in the communication interface 1322. For example, the network communication program 1338 may include and / or represent at least a portion of software and / or firmware executed by a processor and / or application-specific integrated circuit (ASIC) incorporated in the communication interface 1322.

[0107] like Figure 13 As shown, the example computing system 1310 may also include a primary storage device 1332 and a backup storage device 1333, which are coupled to the communication infrastructure 1312 via a storage interface 1334. Storage devices 1332 and 1333 generally represent any type or form of storage device or medium capable of storing data and / or other computer-readable instructions. For example, storage devices 1332 and 1333 may be disk drives (e.g., so-called hard disk drives), solid-state drives, floppy disk drives, tape drives, optical disk drives, flash drives, etc. Storage interface 1334 generally represents any type or form of interface or device for transferring data between storage devices 1332 and 1333 and other components of the computing system 1310. In one example, from Figure 3 The data element 320 can be stored and / or loaded in the main storage device 1332.

[0108] In some examples, storage devices 1332 and 1333 may be configured to read from and / or write to a removable storage unit configured to store computer software, data, or other computer-readable information. Examples of suitable removable storage units include, but are not limited to, floppy disks, magnetic tapes, optical disks, flash memory devices, etc. Storage devices 1332 and 1333 may also include other similar structures or means for allowing computer software, data, or other computer-readable instructions to be loaded into computing system 1310. For example, storage devices 1332 and 1333 may be configured to read and write software, data, or other computer-readable information. Storage devices 1332 and 1333 may also be part of computing system 1310 or may be separate devices accessed through other interface systems.

[0109] Many other devices or subsystems can be connected to the computing system 1310. Conversely, it is not necessary for them to exist. Figure 13 All components and devices shown herein are intended to practice the examples described and / or illustrated herein. The devices and subsystems mentioned above may also be used in different ways. Figure 13 Interconnection is performed as shown. The computing system 1310 may also employ any number of software, firmware, and / or hardware configurations. For example, one or more of the examples disclosed herein may be encoded as a computer program (also referred to as computer software, software application, computer-readable instructions, or computer control logic) on a computer-readable medium. As used herein, the term "computer-readable medium" generally refers to any form of device, carrier, or medium capable of storing or carrying computer-readable instructions. Examples of computer-readable media include, but are not limited to, transport media (such as carrier waves) and non-transient media, such as magnetic storage media (e.g., hard disk drives, magnetic tape drives, and floppy disks), optical storage media (e.g., compressed disks (CDs), digital video optical discs (DVDs), and Blu-ray discs), electronic storage media (e.g., solid-state drives and flash memory media), and other distribution systems.

[0110] A computer-readable medium including a computer program may be loaded into computing system 1310. Subsequently, all or part of the computer program stored on the computer-readable medium may be stored in system memory 1316, and / or in various portions of storage devices 1332 and 1333. When executed by processor 1314, the computer program loaded into computing system 1310 may cause processor 1314 to perform the functions of one or more examples described and / or illustrated herein, and / or act as a device for performing the functions of one or more examples described and / or illustrated herein. Additionally or alternatively, one or more examples described and / or illustrated herein may be implemented in firmware and / or hardware. For example, computing system 1310 may be configured to implement an application-specific integrated circuit (ASIC) of one or more examples disclosed herein.

[0111] Figure 14 This is a block diagram of an example network architecture 1400, in which client systems 1410, 1420, and 1430, and servers 1440 and 1445, can be coupled to network 1450. As described above, all or part of network architecture 1400 can perform one or more of the steps disclosed herein (such as...). Figure 5 One or more steps shown), and / or as a means of performing one or more steps disclosed herein, alone or in combination with other elements (such as... Figure 5 The device may be used to perform one or more steps as shown in the present disclosure. All or part of the network architecture 1400 may also be used to perform other steps and features set forth in this disclosure, and / or as a device for performing other steps and features set forth in this disclosure.

[0112] Client systems 1410, 1420, and 1430 generally represent any type or form of computing device or system, such as Figure 13 Example computing system 1310. Similarly, server 1440 and server 1445 generally represent computing devices or systems (such as application servers or database servers) configured to provide various database services and / or run certain software applications. Network 1450 generally represents any telecommunications network or computer network, including, for example, an intranet, WAN, LAN, PAN, or the Internet. In one example, client systems 1410, 1420, and / or 1430 and / or server 1440 and / or server 1445 may include data from... Figure 3 All or part of the system 300.

[0113] like Figure 14As shown, one or more storage devices 1460(1)-(N) may be directly attached to server 1440. Similarly, one or more storage devices 1470(1)-(N) may be directly attached to server 1445. Storage devices 1460(1)-(N) and 1470(1)-(N) generally represent any type or form of storage device or medium capable of storing data and / or other computer-readable instructions. In some examples, storage devices 1460(1)-(N) and 1470(1)-(N) may represent network attached storage (NAS) devices configured to communicate with servers 1440 and 1445 using various protocols such as Network File System (NFS), Server Message Block (SMB), or Common Internet File System (CIFS)

[0114] Servers 1440 and 1445 can also be connected to a Storage Area Network (SAN) structure 1480. SAN structure 1480 generally refers to any type or form of computer network or architecture capable of facilitating communication between multiple storage devices. SAN structure 1480 can facilitate communication between servers 1440 and 1445 and multiple storage devices 1490(1)-(N) and / or intelligent storage array 1495. SAN structure 1480 can also facilitate communication between client systems 1410, 1420, and 1430 and storage devices 1490(1)-(N) and / or intelligent storage array 1495 via network 1450 and servers 1440 and 1445, such that devices 1490(1)-(N) and array 1495 appear as locally attached devices to client systems 1410, 1420, and 1430. Similar to storage devices 1460(1)-(N) and 1470(1)-(N), storage devices 1490(1)-(N) and intelligent storage arrays 1495 generally refer to any type or form of storage device or medium capable of storing data and / or other computer-readable instructions.

[0115] In some examples, reference Figure 13 Example computing system 1310, communication interface (such as Figure 13The communication interface 1322 can be used to provide a connection between each client system 1410, 1420, and 1430 and the network 1450. Client systems 1410, 1420, and 1430 can use, for example, a web browser or other client software to access information on server 1440 or server 1445. Such software can allow client systems 1410, 1420, and 1430 to access data hosted by server 1440, server 1445, storage devices 1460(1)-(N), storage devices 1470(1)-(N), storage devices 1490(1)-(N), or intelligent storage array 1495. Although... Figure 14 The use of networks (such as the Internet) to exchange data is described, but the examples described and / or shown herein are not limited to the Internet or any particular network-based environment.

[0116] In at least one example, all or part of one or more examples disclosed herein may be encoded as a computer program and loaded onto and executed by: server 1440, server 1445, storage devices 1460(1)-(N), storage devices 1470(1)-(N), storage devices 1490(1)-(N), intelligent storage array 1495, or any combination thereof. All or part of one or more examples disclosed herein may also be encoded as a computer program, stored in server 1440, run by server 1445, and distributed to client systems 1410, 1420, and 1430 via network 1450.

[0117] As described in detail above, one or more components of the computing system 1310 and / or network architecture 1400 may perform one or more steps of the example method for compressing and extracting medical imaging data, and / or serve as devices for performing one or more steps of the example method for compressing and extracting medical imaging data, either alone or in combination with other elements.

[0118] While the foregoing disclosures use specific block diagrams, flowcharts, and examples to illustrate various examples, each block diagram component, flowchart step, operation, and / or component described and / or illustrated herein can be implemented individually and / or collectively using a wide range of hardware, software, or firmware (or any combination thereof) configurations. Furthermore, any disclosure of components included within other components should be considered illustrative in nature, as many other architectures can be implemented to achieve the same functionality.

[0119] In some examples, Figure 3The example system 300 in the document may represent all or part of a cloud computing environment or a network-based environment. A cloud computing environment can provide various services and applications via the Internet. These cloud-based services (e.g., software as a service, platform as a service, infrastructure as a service, etc.) are accessible via a web browser or other remote interface. The various functionalities described herein can be provided through a remote desktop environment or any other cloud-based computing environment.

[0120] In various examples, Figure 3 All or part of the example system 300 described herein can facilitate multi-tenancy implementation within a cloud-based computing environment. In other words, the software modules described herein can configure a computing system (e.g., a server) to facilitate multi-tenancy implementation for one or more of the functions described herein. For example, one or more software modules described herein can program a server to enable two or more clients (e.g., customers) to share an application running on the server. A server programmed in this manner can share applications, operating systems, processing systems, and / or storage systems among multiple customers (i.e., tenants). One or more modules described herein can also partition the data and / or configuration information of the multi-tenant application for each customer, preventing one customer from accessing the data and / or configuration information of another customer.

[0121] Based on various examples, Figure 3 All or part of the example system 300 described herein can be implemented in a virtual environment. For example, the modules and / or data described herein can reside and / or execute in a virtual machine. As used herein, the term "virtual machine" generally refers to any operating system environment extracted from computing hardware by a virtual machine manager (e.g., a monitoring program). Additionally or alternatively, the modules and / or data described herein can reside and / or execute in a virtualization layer. As used herein, the term "virtualization layer" generally refers to a layer that overlays the operating system environment and / or any data layer and / or application layer extracted from the operating system environment. The virtualization layer can be managed by a software virtualization solution (e.g., a file system filter) that presents the virtualization layer as if it were part of the underlying base operating system. For example, a software virtualization solution can redirect calls initially directed to locations in the base file system and / or registry to locations in the virtualization layer.

[0122] In some examples, Figure 3All or part of the example system 300 described herein may represent a portion of a mobile computing environment. A mobile computing environment can be implemented by a wide range of mobile computing devices, including mobile phones, tablets, e-book readers, personal digital assistants, wearable computing devices (e.g., computing devices with head-mounted displays, smartwatches, etc.), etc. In some examples, a mobile computing environment may have one or more distinct characteristics, including, for example, battery power dependence, presentation of only one front-end application at any given time, remote management features, touchscreen features, location and mobility data (e.g., provided by a GPS, gyroscope, accelerometer, etc.), a restricted platform that limits modifications to system-level configuration and / or the ability of third-party software to inspect the behavior of other applications, controls that restrict application installation (e.g., limiting to applications originating only from approved app stores), etc. The various functionalities described herein may be provided for and / or may interact with a mobile computing environment.

[0123] also, Figure 3 The example system 300 may represent, in whole or in part, a portion of one or more systems for information management, interact with one or more systems for information management, use data generated by one or more systems for information management, and / or generate data used by one or more systems for information management. As used herein, the term "information management" may refer to the protection, organization, and / or storage of data. Examples of systems for information management may include, but are not limited to, storage systems, backup systems, archiving systems, replication systems, high-availability systems, data search systems, virtualization systems, etc.

[0124] In some examples, Figure 3 The example system 300 may represent, in whole or in part, a portion of one or more systems for information security, generate data protected by one or more systems for information security, and / or communicate with one or more systems for information security. As used herein, the term "information security" may refer to control over access to protected data. Examples of systems for information security may include, but are not limited to, systems that provide managed security services, data loss prevention systems, authentication systems, access control systems, encryption systems, policy compliance systems, intrusion detection and prevention systems, electronic discovery systems, etc.

[0125] Methods and apparatuses (e.g., systems, which may include software, hardware, and / or firmware for performing the techniques described herein) are generally used to compress large image datasets, such as (but not limited to) cone-beam computed tomography (CBCT) images or magnetic resonance imaging (MRI) datasets. As discussed above, such datasets can be extremely large, and typical compression techniques cannot compress them without significant loss of information and / or the introduction of artifacts. The methods and apparatuses described herein can provide compression ratios of up to 2000x (e.g., compression ratio). These methods and apparatuses can greatly simplify data transfer between devices that perform / collect imaging data (e.g., a physician's CBCT scanner) and one or more other facilities (e.g., the cloud, external laboratories, external storage, etc.). These methods and apparatuses can also increase the speed of processing and analyzing imaging data.

[0126] The challenge in transmitting CBCT data lies in the large volume of data generated in each CBCT scan and the time-consuming process of uploading this data. The methods and apparatus described in this paper can significantly reduce the amount of data to be transmitted without losing essential information. In some examples, these methods or apparatuses can be integrated as part of an imaging system; in one example, they can be integrated as part of a CBCT scanner and / or as part of a web browser upload page.

[0127] For example, Figure 15A An example of a method for compressing a 3D volumetric image dataset is shown. The method may begin by receiving (e.g., in a processor) raw 3D volumetric image data (e.g., DICOM data) 1503. In some examples, these methods (and the devices used to perform them) may include geometric preprocessing of the raw imaging data 1505. Geometric processing may include identifying anatomical planes from the raw data (e.g., DICOM normalized data), which may be, for example, one or more of the following: sagittal plane, coronal plane, lateral plane, and / or axial plane. Once the anatomical planes are identified from the data, the X, Y, and Z axes of the dataset can be set to align with the anatomical planes. For example, the dataset may be translated (e.g., rotated, offset, etc.) so that they are parallel to the X, Y, and Z axes. Thus, the volume can initially be made more symmetrical. The volume can then be cropped according to the new X, Y, and Z axes to exclude blank areas 1507. In some cases, the volume may be padded to give it uniform edges (e.g., filled with blank spaces).

[0128] In some examples, histogram analysis (e.g., of the dynamic range of the dataset) can be performed to identify regions or subsets within the dynamic range that include most of the information from the imaging volume.1509 As mentioned above, imaging (e.g., DICOM) volumes may have large dynamic ranges (e.g., up to or more than 16 bits per voxel). However, dental structure (e.g., teeth, roots, and bone) reconstruction information is typically concentrated in the lower regions of the dynamic range. Therefore, the methods and apparatus described herein can remove one or more portions of the dynamic range that do not include important data (e.g., regions that include less useful data (e.g., dental data related to fillings, inlays, etc.)) that may be highly reflective and thus “bright.”

[0129] In some examples, histogram analysis can reduce the dynamic range by segmenting data into clinically relevant regions (e.g., anatomical regions, particularly tooth categories). For example, clinically relevant regions (categories) can include bone, soft tissue, crowns, roots, etc. Each of these clinically relevant regions can be encoded using reference markers (e.g., 4 to 8 digits, such as 0 for empty space, 1 for soft tissue, 2 for bone, 3 for teeth, etc.). Therefore, these methods and / or devices can segment data (e.g., voxel data) using these predefined clinically relevant (particularly tooth-related) categories. In some cases, the device may include a machine learning agent to segment (e.g., identify) voxels.

[0130] In some examples, a modified uniform (optionally cropped) volume can be analyzed to divide it into symmetrical segments (e.g., halves, such as left / right halves) that are sufficiently similar in the image. The method or device can then identify these symmetrical regions. Any of these methods and devices can then compare one or more identified symmetrical regions to determine differences, e.g., based on segmentation differences.

[0131] The preprocessed data (the modified 3D volume, modified as described above) can then be compressed using video compression.1513 For example, macroblock compression (e.g., using a compression scheme such as Discrete Cosine Transform (DCT) with prediction) can be used to compress the 3D volume including the difference calculation. Finally, the compressed dataset can be encoded, for example, using a lossless data compression scheme (e.g., entropy coding, such as Huffman coding).1515 As discussed and illustrated above, these techniques can provide highly accurate compression of up to 200x without significant loss of information.

[0132] Any suitable image dataset can be used, including 3D volumetric datasets or video datasets. For example, CT scan data, similar to video sequence data, can be considered volumetric data, where images of the same region can be taken at different times. Therefore, the scan data can be viewed as a series of slices (e.g., a series of thin image “slices”) that can be processed and compressed as described herein. CT scan images can be considered dense datasets, which can be particularly beneficial for the techniques described herein. Dense volumes may consist of a series of 2D frames taken at different times; this data can be compressed as described herein. The preprocessing steps discussed above can align the dataset and identify symmetrical regions, which can then be used to simplify dense datasets by identifying differences between symmetrical regions. For example, after aligning the images and performing appropriate trimming (and / or padding), the left and right portions of the scanned body may be symmetrical. For example, when imaging images of a patient's head (e.g., jaw, teeth, etc.), the position of the subject's head can be estimated, and the X, Y, and Z axes can be set based on the data. The dataset can then be symmetrically sliced ​​on the left and right sides. As mentioned above, the use of histogram analysis can help identify accurate and useful dynamic ranges. Each voxel can be reduced (e.g., from an initial 16-bit depth) to between 2-bit or 8-bit depth.

[0133] In some examples, some depth information can be completely removed from an image dataset. For instance, as mentioned above, hard structures (e.g., highly reflective structures), details such as inlays and / or metallic infills (or any metallic details) may be included in the dataset and may appear very “bright” in the imaging data, potentially leading to a loss of dynamic range due to a bias towards high-density / reflectance values. As described above, the methods and apparatus described herein can reduce the dynamic range to focus on anatomical features.

[0134] Any methods and apparatus described herein may include compressing a static 3D volumetric dataset by using one or more video compression techniques, transforming it into a series of two-dimensional images in a time series. Therefore, a volumetric dataset can be processed by treating multiple slices throughout the 3D volumetric dataset as a time-point sequence in a video loop to compress the volumetric data using a video compression scheme. For example, a video compression technique can be used to compress the 3D volume, which includes, after preprocessing as described above (e.g., identifying and / or setting the X, Y, Z axes, alignment and cropping and / or padding, adjusting dynamic range, etc.), converting one axis to a time axis instead of a spatial axis.

[0135] The above describes examples of video compression, including, for example, using macroblock compression (e.g., using DCT) and / or using video codecs. The result may be compressed data.

[0136] Figure 15B An example of a method for compressing dental imaging data as described herein is shown, which may be a specific application of the more general method for compressing 3D volumetric image datasets discussed above. In this example, optionally, the method for compressing a three-dimensional (3D) volumetric image dataset may include receiving 3D volumetric image data. The 3D volumetric image data may include multiple image segments (e.g., across a patient's jaw) forming a 3D volume. The method may include identifying at least two anatomical planes within the 3D volumetric image dataset and using these at least two anatomical planes to set at least two coordinate planes to increase the symmetry of the coordinate planes 1551. The method may also include cropping the 3D volume parallel to the coordinate planes 1553, adjusting the dynamic range of the 3D volumetric image dataset through histogram analysis, and segmenting the 3D volumetric image dataset using clinically relevant regions (including, for example, soft tissue, bone, crowns, and roots) 1555. The method may also include dividing the image segments forming the 3D volume into a first half and a second half that are symmetrical to each other, determining the difference between the first half and the second half, and reducing the 3D volume 1557 by replacing the second half with the difference between the first half and the second half.

[0137] The preprocessed 3D volume can then be compressed by applying a video compression scheme to the 3D volume, thereby forming a compressed 3D volumetric image dataset 1559 by converting the spatial axis of the 3D volume into a time axis to form a time series of 2D images. The resulting compressed 3D volumetric image dataset 1561 can then be stored and / or transmitted.

[0138] The process parameters and order of steps described and / or illustrated herein are given by way of example only and may be changed as needed. For example, while the steps shown and / or described herein may be shown or discussed in a particular order, these steps do not necessarily have to be performed in the order shown or discussed. The various example methods described and / or illustrated herein may also omit one or more steps described or illustrated herein, or may include additional steps beyond those disclosed.

[0139] While this document describes and / or illustrates various examples in the context of a full-featured computing system, one or more of these examples can be distributed as program products in various forms, regardless of the specific type of computer-readable medium used to actually perform the distribution. The examples disclosed herein can also be implemented using software modules that perform certain tasks. These software modules may include scripts, batch files, or other executable files that can be stored on computer-readable storage media or in a computing system. In some examples, these software modules may configure a computing system to perform one or more of the examples disclosed herein.

[0140] As described herein, the computing devices and systems described and / or illustrated herein broadly represent any type or form of computing device or system capable of executing computer-readable instructions, such as those contained in the modules described herein. In their most basic configuration, these computing devices may each include at least one memory device and at least one physical processor.

[0141] As used herein, the term "memory" or "memory device" generally refers to any type or form of volatile or non-volatile storage device or medium capable of storing data and / or computer-readable instructions. In one example, a memory device may store, load, and / or maintain one or more modules described herein. Examples of memory devices include, but are not limited to, random access memory (RAM), read-only memory (ROM), flash memory, hard disk drive (HDD), solid-state drive (SSD), optical disk drive, cache, variations or combinations thereof, or any other suitable storage memory.

[0142] Furthermore, as used herein, the term "processor" or "physical processor" generally refers to any type or form of hardware implementation of a processing unit capable of interpreting and / or executing computer-readable instructions. In one example, a physical processor may access and / or modify one or more modules stored in the aforementioned memory device. Examples of physical processors include, but are not limited to, microprocessors, microcontrollers, central processing units (CPUs), graphics processing units (GPUs), field-programmable gate arrays (FPGAs) implementing soft-core processors, application-specific integrated circuits (ASICs), portions of one or more of these, variations or combinations thereof, or any other suitable physical processor.

[0143] Although shown as separate elements, the method steps described and / or illustrated herein may represent portions of a single application. Furthermore, in some examples, one or more of these steps may represent or correspond to one or more software applications or programs that, when executed by a computing device, enable the computing device to perform one or more tasks, such as the method steps.

[0144] Furthermore, one or more devices described herein can transform data, physical devices, and / or representations of physical devices from one form to another. Additionally or alternatively, one or more modules described herein can transform a processor, volatile memory, non-volatile memory, and / or any other part of the physical computing device from one form of computing device to another by executing on a computing device, storing data on a computing device, and / or otherwise interacting with a computing device.

[0145] As used herein, the term "computer-readable medium" generally refers to any form of device, carrier, or medium capable of storing or carrying computer-readable instructions. Examples of computer-readable media include, but are not limited to, transmissive media (such as carrier waves) and non-transient media (such as magnetic storage media (e.g., hard disk drives, magnetic tape drives, and floppy disks), optical storage media (e.g., compressed disks (CDs), digital video optical discs (DVDs), and Blu-ray discs), electronic storage media (e.g., solid-state drives and flash memory media), and other distribution systems.

[0146] Those skilled in the art will recognize that any process or method disclosed herein can be modified in various ways. The process parameters and order of steps described and / or illustrated herein are given by way of example only and can be changed as needed. For example, while the steps shown and / or described herein may be shown or discussed in a particular order, these steps do not necessarily have to be performed in the order shown or discussed.

[0147] The various exemplary methods described and / or illustrated herein may omit one or more steps described or illustrated herein, or may include steps other than those disclosed. Furthermore, the steps of any method disclosed herein may be combined with any one or more steps of any other method disclosed herein.

[0148] The processor described herein can be configured to perform one or more steps of any of the methods disclosed herein. Alternatively or in combination, the processor can be configured to combine one or more steps of one or more methods disclosed herein.

[0149] Unless otherwise stated, the terms “connected to” and “coupled to” (and their derivatives) as used in the specification and claims shall be construed as allowing for direct and indirect connections (i.e., via other elements or components). Furthermore, the terms “a” or “an” as used in the specification and claims shall be construed as “at least one of…”. Finally, for ease of use, the terms “comprising” and “having” (and their derivatives) as used in the specification and claims may be used interchangeably with “including” and shall have the same meaning as “comprising”.

[0150] The processor disclosed herein may be configured with instructions to perform any one or more steps of any of the methods disclosed herein.

[0151] It should be understood that although the terms “first,” “second,” “third,” etc., may be used herein to describe various layers, elements, components, regions, or parts, this does not imply any particular order or sequence of events. These terms are used only to distinguish a layer, an element, a component, a region, or a part from another layer, another element, another component, another region, or another part. Without departing from the teachings of this disclosure, the first layer, first element, first component, first region, or first part described herein may be referred to as a second layer, second element, second component, second region, or second part.

[0152] As used herein, the term "or" is used to indicate items in alternatives and combinations of options in an inclusive manner.

[0153] The examples disclosed herein have been shown and described as set forth herein and are provided by way of example only. Many modifications, alterations, variations, and substitutions will be recognized by those skilled in the art without departing from the scope of this disclosure. Several alternatives and combinations of the examples disclosed herein may be used without departing from the scope of this disclosure and the invention disclosed herein. Therefore, the scope of the invention disclosed herein should be defined only by the scope of the appended claims and their equivalents.

Claims

1. A system for compressing a three-dimensional (3D) volumetric image dataset, the 3D volumetric image dataset comprising multiple image segments forming a 3D volume, the system comprising: One or more processors; A memory coupled to the one or more processors, the memory storing computer program instructions that, when executed by the one or more processors, perform a computer-implemented method, the method comprising: Receive a 3D volumetric image dataset, which includes cone-beam computed tomography (CBCT) data of the patient's dentition; Identify one or more anatomical planes within the 3D volumetric image dataset, and use the one or more anatomical planes to set the coordinate plane; The 3D volume is clipped parallel to the coordinate plane; The dynamic range of the cropped 3D volumetric image dataset is adjusted by assigning values ​​to each voxel of the 3D volumetric image dataset based on the type of anatomical structure and the corresponding four intensity values. The spatial axis of the dynamically range-adjusted and cropped 3D volume is converted into a time axis to form a time series of 2D images, and a video compression scheme is applied to the time series of the 2D images to form a compressed 3D volume image dataset. Transmit the compressed 3D volumetric image dataset to a remote server; Receive the compressed 3D volumetric image dataset from a remote server; and The restored 3D volumetric image dataset is generated based at least in part on a video compression scheme applied to the time series of the 2D images.

2. The system according to claim 1, wherein, The computer-implemented method identifies one or more anatomical planes within the 3D volumetric image dataset and sets the coordinate planes to increase their symmetry.

3. The system according to claim 1, wherein, The computer-implemented method clips the 3D volume parallel to the coordinate plane to minimize the blank area of ​​the 3D volume.

4. The system according to claim 1, wherein, The computer-implemented method further includes filling the 3D volume with blank areas to maintain the symmetry of the 3D volume after cropping.

5. The system according to claim 1, wherein, The computer-implemented method adjusts the dynamic range of the 3D volumetric image dataset through histogram analysis.

6. The system according to claim 1, wherein, Adjusting the dynamic range of 3D volumetric image datasets also includes: voxel recoding of 3D volumetric image data based on anatomical structures.

7. The system according to claim 1, wherein, Adjusting the dynamic range of the 3D volumetric image dataset also includes segmenting the 3D volumetric image dataset using clinically relevant regions, including soft tissue, bone, crowns, and roots.

8. The system according to claim 1, wherein, The computer-implemented method further includes: before converting the spatial axis of the 3D volume into the time axis, dividing the image segment forming the 3D volume into a first half and a second half that are symmetrical to each other, determining the difference between the first half and the second half, and reducing the 3D volume by replacing the second half with the difference between the first half and the second half.

9. The system according to claim 1, further comprising: An imaging device that communicates with one or more processors.

10. The system according to claim 1, wherein, The computer-implemented method further includes storing or transmitting the compressed 3D volumetric image dataset.

11. The system according to claim 1, wherein, The computer-implemented method applies the video compression scheme to the time series of the 2D images, thereby forming the compressed 3D volumetric image dataset with a compression ratio between 50x and 2500x.

12. The system according to claim 1, wherein, The computer-implemented method applies the video compression scheme to the time series of the 2D images, thereby forming the compressed 3D volumetric image dataset with a compression ratio of 50 times or greater.

13. The system according to claim 1, wherein, The computer-implemented method applies the video compression scheme by applying macroblock compression using Discrete Cosine Transform (DCT) to the time series of the 2D images to form the compressed 3D volumetric image dataset.

14. The system according to claim 1, wherein, The computer-implemented method further includes: using entropy coding to encode the compressed 3D volumetric image dataset.

15. A system for compressing a three-dimensional (3D) volumetric image dataset, the 3D volumetric image dataset comprising multiple image segments forming a 3D volume, the system comprising: One or more processors; A memory coupled to the one or more processors, the memory storing computer program instructions that, when executed by the one or more processors, perform a computer-implemented method, the method comprising: Receive a 3D volumetric image dataset, which includes cone-beam computed tomography (CBCT) data of the patient's dentition; Identify at least two anatomical planes within the 3D volumetric image dataset, and use the at least two anatomical planes to set at least two coordinate planes to increase the symmetry of the coordinate planes; The 3D volume is clipped parallel to the coordinate plane; The dynamic range of the cropped 3D volumetric image dataset is adjusted by assigning values ​​to each voxel of the 3D volumetric image dataset based on the type of anatomical structure and the corresponding four intensity values. The image segment that forms the 3D volume after dynamic range adjustment and cropping is divided into a first half and a second half that are symmetrical to each other. The difference between the first half and the second half is determined, and the 3D volume is reduced by replacing the second half with the difference between the first half and the second half. A video compression scheme is applied to the 3D volume to form a compressed 3D volumetric image dataset by converting the spatial axis of the 3D volume into a time axis to form a time series of 2D images. Store or transmit the compressed 3D volumetric image dataset to a remote server; Receive the compressed 3D volumetric image dataset from a remote server; and The restored 3D volumetric image dataset is generated based at least in part on a video compression scheme applied to the time series of the 2D images.

16. A method for compressing a three-dimensional (3D) volumetric image dataset, the 3D volumetric image dataset comprising multiple image segments forming a 3D volume, the method comprising: Receive a 3D volumetric image dataset, which includes cone-beam computed tomography (CBCT) data of the patient's dentition; Identify one or more anatomical planes within the 3D volumetric image dataset, and use the one or more anatomical planes to set the coordinate plane; The 3D volume is clipped parallel to the coordinate plane; The dynamic range of the cropped 3D volumetric image dataset is adjusted by assigning values ​​to each voxel of the 3D volumetric image dataset based on the type of anatomical structure and the corresponding four intensity values. The spatial axis of the dynamically range-adjusted and cropped 3D volume is converted into a time axis to form a time series of 2D images, and a video compression scheme is applied to the time series of the 2D images to form a compressed 3D volume image dataset. Transmit the compressed 3D volumetric image dataset to a remote server; Receive the compressed 3D volumetric image dataset from a remote server; and The restored 3D volumetric image dataset is generated based at least in part on a video compression scheme applied to the time series of the 2D images.

17. The method according to claim 16, wherein, Identifying one or more anatomical planes within the 3D volumetric image dataset and setting the coordinate plane includes: setting the coordinate plane to increase the symmetry of the coordinate plane.

18. The method of claim 16, further comprising: The 3D volume is clipped parallel to the coordinate plane to minimize the blank area of ​​the 3D volume.

19. The method of claim 16, further comprising: Fill the 3D volume with blank areas to maintain the symmetry of the 3D volume after cropping.

20. The method of claim 16, wherein, Adjusting the dynamic range of the 3D volumetric image dataset includes adjusting it through histogram analysis.

21. The method of claim 20, further comprising: The 3D volumetric image dataset was segmented using clinically relevant regions.

22. The method according to claim 21, wherein, The clinically relevant areas include: soft tissue, bone, crown, and root.

23. The method of claim 16, further comprising: Before converting the spatial axis of the 3D volume to the temporal axis, the image segment forming the 3D volume is divided into a first half and a second half that are symmetrical to each other, the difference between the first half and the second half is determined, and the 3D volume is reduced by replacing the second half with the difference between the first half and the second half.

24. The method of claim 16, further comprising: Store or transmit the compressed 3D volumetric image dataset.

25. The method according to claim 16, wherein, Applying the video compression scheme to the time series of the 2D images to form the compressed 3D volumetric image dataset includes: forming the compressed 3D volumetric image dataset at a compression ratio between 50x and 2500x.

26. The method of claim 16, wherein, Applying the video compression scheme to the time series of the 2D images to form the compressed 3D volumetric image dataset includes: forming the compressed 3D volumetric image dataset with a compression ratio of 50 times or greater.

27. The method according to claim 16, wherein, Applying the video compression scheme to the time series of the 2D image includes: applying macroblock compression using Discrete Cosine Transform (DCT).

28. The method of claim 16, further comprising: Entropy coding is used to encode the compressed 3D volumetric image dataset.

29. A method for compressing a three-dimensional (3D) volumetric image dataset, the 3D volumetric image dataset comprising multiple image segments forming a 3D volume, the method comprising: Receive a 3D volumetric image dataset, which includes cone-beam computed tomography (CBCT) data of the patient's dentition; Identify at least two anatomical planes within the 3D volumetric image dataset, and use the at least two anatomical planes to set at least two coordinate planes to increase the symmetry of the coordinate planes; The 3D volume is clipped parallel to the coordinate plane; The dynamic range of the cropped 3D volumetric image dataset is adjusted by assigning values ​​to each voxel of the 3D volumetric image dataset based on the type of anatomical structure and the corresponding four intensity values. The image segment that forms the 3D volume after dynamic range adjustment and cropping is divided into a first half and a second half that are symmetrical to each other. The difference between the first half and the second half is determined, and the 3D volume is reduced by replacing the second half with the difference between the first half and the second half. A video compression scheme is applied to the 3D volume to form a compressed 3D volumetric image dataset by converting the spatial axis of the 3D volume into a time axis to form a time series of 2D images. Store or transmit the compressed 3D volumetric image dataset to a remote server; Receive the compressed 3D volumetric image dataset from a remote server; and The restored 3D volumetric image dataset is generated based at least in part on a video compression scheme applied to the time series of the 2D images.

30. A system for compressing a three-dimensional volumetric image dataset, the 3D volumetric image dataset comprising multiple image segments forming a 3D volume, the system comprising: One or more processors; A memory coupled to the one or more processors, the memory storing computer program instructions that, when executed by the one or more processors, perform a computer-implemented method, the method comprising: Receive 3D volumetric image datasets; Identify one or more anatomical planes within the 3D volumetric image dataset, and use the one or more anatomical planes to set the coordinate plane; The 3D volume is clipped parallel to the coordinate plane; The dynamic range of the cropped 3D volumetric image dataset is adjusted based on the type of anatomical structure and the corresponding four intensity values ​​assigned to each voxel in the 3D volumetric image dataset; and The spatial axis of the dynamically adjusted and cropped 3D volume is converted into a time axis to form a time series of 2D images, and a video compression scheme is applied to the time series of the 2D images to form a compressed 3D volumetric image dataset.

31. A system for compressing a three-dimensional volumetric image dataset, the 3D volumetric image dataset comprising multiple image segments forming a 3D volume, the system comprising: One or more processors; A memory coupled to the one or more processors, the memory storing computer program instructions that, when executed by the one or more processors, perform a computer-implemented method, the method comprising: Receive 3D volumetric image datasets; Identify at least two anatomical planes within the 3D volumetric image dataset, and use the at least two anatomical planes to set at least two coordinate planes to increase the symmetry of the coordinate planes; The 3D volume is clipped parallel to the coordinate plane; The dynamic range of the cropped 3D volumetric image dataset is adjusted by assigning values ​​to each voxel of the 3D volumetric image dataset based on the type of anatomical structure and the corresponding four intensity values. The image segments that form the 3D volume after dynamic range adjustment and cropping are divided into a first half and a second half that are symmetrical to each other. The difference between the first half and the second half is determined, and the 3D volume is reduced by replacing the second half with the difference between the first half and the second half. By transforming the spatial axis of a 3D volume into a temporal axis to form a time series of 2D images, a video compression scheme is applied to the 3D volume to create a compressed 3D volumetric image dataset; and Store or transfer compressed 3D volumetric image datasets to a remote server.

32. A method for compressing a three-dimensional (3D) volumetric image dataset, the 3D volumetric image dataset comprising multiple image segments forming a 3D volume, the method comprising: Receive 3D volumetric image datasets; Identify at least two anatomical planes within the 3D volumetric image dataset, and use the at least two anatomical planes to set at least two coordinate planes to increase the symmetry of the coordinate planes; The 3D volume is clipped parallel to the coordinate plane; The dynamic range of the cropped 3D volumetric image dataset is adjusted by assigning values ​​to each voxel of the 3D volumetric image dataset based on the type of anatomical structure and the corresponding four intensity values. The image segment that forms the 3D volume after dynamic range adjustment and cropping is divided into a first half and a second half that are symmetrical to each other. The difference between the first half and the second half is determined, and the 3D volume is reduced by replacing the second half with the difference between the first half and the second half. By transforming the spatial axis of a 3D volume into a temporal axis to form a time series of 2D images, a video compression scheme is applied to the 3D volume to create a compressed 3D volumetric image dataset; and Store or transmit compressed 3D volumetric image datasets.

Images