CN112102311A

CN112102311A - Thyroid nodule image processing method and device and computer equipment

Info

Publication number: CN112102311A
Application number: CN202011035723.7A
Authority: CN
Inventors: 陈超; 卢沁阳; 张璐; 詹维伟; 黄凌云; 刘玉宇
Original assignee: Ping An Technology Shenzhen Co Ltd
Current assignee: Ping An Technology Shenzhen Co Ltd
Priority date: 2020-09-27
Filing date: 2020-09-27
Publication date: 2020-12-18
Anticipated expiration: 2040-09-27
Also published as: WO2021169452A1; CN112102311B

Abstract

The application relates to artificial intelligence, is applicable to intelligent medical treatment, provides thyroid nodule image's processing method, device and computer equipment, and the method includes: generating a nodule mask image according to the ultrasonic image; generating a nodule image corresponding to the minimum circumscribed rectangle of the nodule mask image; processing the node image to generate a first node image and obtain a sound and shadow candidate area; determining a sound shadow region from the first nodal image; cutting a sound and shadow area in the nodule image to obtain a second nodule image, and processing the second nodule image to obtain a third nodule image; acquiring a cystic candidate region of the third nodule image; calculating a first area of the cystic candidate region, a second area of the nodule region and a third area related to the first area and the second area to generate a coarse thyroid nodule classification result; determining a cystic area from the third nodule image; and generating a fine classification result of the thyroid nodule according to the area of the cystic area, the second area and the third area, and accurately identifying the thyroid nodule.

Description

Thyroid nodule image processing method and device and computer equipment

Technical Field

The application relates to the technical field of artificial intelligence, in particular to a method and a device for processing thyroid nodule images and computer equipment.

Background

Thyroid nodules are a very common clinical condition of the thyroid gland, and are a lump existing within the thyroid gland and are classified as benign and malignant. If a patient's thyroid nodule is diagnosed as malignant, then he has a high probability of developing thyroid cancer. Due to the advantages of low price, no risk, simple use and the like, the ultrasonic image becomes a preferred method for thyroid examination. In the ultrasonic image, thyroid nodules can be well found and the nature of the thyroid nodules can be judged according to the strength of echoes (namely, the gray value in the image). The formation of thyroid nodules is an important index of thyroid image reports and data systems, and is divided into solidity, solidity-based, cystic, and cystic. When an ultrasound image of a thyroid nodule is generated, it would be of great help to screen for malignancy of the thyroid nodule if its composition could be quickly determined.

However, in the conventional method for determining the composition of a thyroid nodule, it is general to preliminarily determine whether the thyroid nodule is cystic or solid by determining the gray distribution of an ultrasound image using a gray value as a determination criterion. For example, the determination may be made using the HI value (difference between the gray scale standard deviation and the mean of all points within the thyroid nodule), and the greater the HI value, the higher the probability that the thyroid nodule is substantial. However, this composition determination method only uses the gray-scale values as the determination criteria for identifying the thyroid nodule composition, and does not consider other factors related to the thyroid nodule composition, so that a large identification error is easily caused, and the identification accuracy of the thyroid nodule composition is low.

Disclosure of Invention

The application mainly aims to provide a thyroid nodule image processing method, a thyroid nodule image processing device, a computer device and a storage medium, and aims to solve the technical problem that an existing thyroid nodule composition judgment method is low in identification accuracy.

The application provides a method for processing a thyroid nodule image, which comprises the following steps:

acquiring an input ultrasonic image with a thyroid nodule, marking the ultrasonic image with a nodule region, and generating a nodule mask image corresponding to the nodule region;

intercepting an image corresponding to the minimum circumscribed rectangle of the nodule mask image to obtain a nodule image;

performing binary segmentation processing on the nodule image according to a preset OTSU segmentation algorithm to generate a processed first nodule image, and acquiring a sound and shadow candidate region from the first nodule image;

determining a sound shadow region from the first node image according to a non-sound shadow part in the sound shadow candidate region and a node boundary of the node region;

cutting out the sound and shadow area in the nodule image to obtain a corresponding second nodule image, and performing binary segmentation processing on the second nodule image according to the OTSU segmentation algorithm to obtain a processed third nodule image;

acquiring a black partial region in the third nodule image, wherein the black partial region is positioned in the nodule region, and taking the black partial region as a cystic candidate region;

calculating a first area of the cystic candidate region, a second area of the nodule region, and a third area corresponding to an intersection of the nodule region and the sound shadow region;

generating a coarse structural classification result of the thyroid nodule according to a first preset rule according to the first area, the second area and the third area, wherein the coarse structural classification result is whether cystic property is dominant or cystic property, or whether the coarse structural classification result is substantial property is dominant or substantial property;

determining a cystic region from the third nodule image according to the gradient of the third nodule image and the cystic candidate region;

calling a preset calculation rule corresponding to the coarse classification result according to a fourth area, the second area and the third area of the cystic area to calculate and generate a fine classification result of the thyroid nodule, wherein the fine classification result comprises: the cystic property is mainly, cystic property, and the actual property is mainly or actually.

Optionally, the step of determining a sound shadow region from the first node image according to a non-sound shadow portion in the sound shadow candidate region and a nodule boundary includes:

acquiring a non-sound shadow part in the sound shadow candidate area;

eliminating the non-sound shadow part to obtain a processed sound shadow candidate area;

acquiring a first connecting domain which passes through a nodule boundary of the nodule region in the processed sound and image candidate region;

and taking the first connected domain as the sound shadow area.

Optionally, the step of generating a coarse thyroid nodule configuration classification result according to a first preset rule according to the first area, the second area, and the third area includes:

calculating a first difference of the second area minus the third area;

calculating a quotient value obtained by dividing the first difference value by 2;

judging whether the first area is larger than the quotient value or not;

if the first area is larger than the quotient, judging that the forming coarse classification result of the thyroid nodule is cystic main or cystic;

and if the first area is not larger than the quotient, judging that the result of the coarse thyroid nodule classification is substantial or substantial.

Optionally, the step of determining a cystic region from the third nodule image according to the gradient of the third nodule image and the cystic candidate region includes:

calculating the gradient of the third node image and generating a corresponding gradient map;

finding out seed points which are in the cystic candidate region and have the gray scale smaller than a first preset threshold value and the gradient smaller than a second preset threshold value in the gradient map;

performing region growing treatment on the seed points according to a second preset rule to generate corresponding specified connected domains;

carrying out corrosion treatment on the specified connected domain;

calculating the product of the second area and a specified value;

screening out a second connected domain with the connected domain area larger than the product from all the specified connected domains;

determining the second connected domain as the cystic region.

Optionally, the step of performing region growing processing on the seed points according to a third preset rule to generate corresponding designated connected domains includes:

acquiring a designated seed point, wherein the designated seed point is any one of all the seed points;

merging pixels adjacent to the designated seed point into the same set according to the composition condition of the connected region to generate a designated pixel set, wherein the composition condition of the connected region comprises that the pixel values are the same and are adjacent;

and taking the generated specified set as a connected domain corresponding to the specified seed point.

Optionally, after the step of calculating the gradient of the third node image and generating the corresponding gradient map, the method includes:

screening abnormal gradients in the gradient map by a median filtering algorithm;

deleting the anomalous gradient from the gradient map.

Optionally, the step of invoking a preset calculation rule corresponding to the coarse classification result according to the fourth area, the second area, and the third area of the cystic region to calculate and generate a fine classification result of the thyroid nodule includes:

calculating a second difference of the second area minus the third area;

calculating a ratio between the fourth area and the second difference;

when the coarse classification result is that the cystic property is main or the cystic property, judging whether the ratio is greater than a preset first ratio threshold value;

if the ratio is larger than the first ratio threshold, judging that the structural fine classification result of the thyroid nodule is cystic, otherwise, judging that the structural fine classification result of the thyroid nodule is cystic;

when the coarse classification result is that the real property is dominant or real, judging whether the ratio is smaller than a preset second ratio threshold value;

and if the ratio is smaller than the second ratio threshold, judging that the thyroid nodule formation fine classification result is substantial, otherwise, judging that the thyroid nodule formation fine classification result is substantial.

The present application further provides a processing apparatus for thyroid nodule images, including:

the system comprises a first acquisition module, a second acquisition module and a third acquisition module, wherein the first acquisition module is used for acquiring an input ultrasonic image with thyroid nodules, marking the ultrasonic image with nodule areas and generating nodule mask images corresponding to the nodule areas;

the first generation module is used for intercepting an image corresponding to the minimum circumscribed rectangle of the nodule mask image to obtain a nodule image;

the first processing module is used for performing binary segmentation processing on the nodule image according to a preset OTSU segmentation algorithm to generate a processed first nodule image and acquiring a sound shadow candidate region from the first nodule image;

a first determining module, configured to determine a sound shadow region from the first nodal image according to a non-sound shadow portion in the sound shadow candidate region and a nodule boundary of the nodule region;

the second processing module is used for cutting the sound and shadow area in the nodule image to obtain a corresponding second nodule image, and performing binary segmentation processing on the second nodule image according to the OTSU segmentation algorithm to obtain a processed third nodule image;

a second obtaining module, configured to obtain a black partial region inside the nodule region in the third nodule image, and use the black partial region as a cystic candidate region;

a calculation module for calculating a first area of the cystic candidate region, a second area of the nodule region, and a third area corresponding to an intersection of the nodule region and the sound shadow region;

a second generating module, configured to generate a coarse structural classification result of the thyroid nodule according to a first preset rule according to the first area, the second area, and the third area, where the coarse structural classification result is cystic dominant or cystic dominant, or the coarse structural classification result is substantial dominant or substantial;

a second determining module, configured to determine a cystic region from the third nodule image according to the gradient of the third nodule image and the cystic candidate region;

a third generating module, configured to invoke a preset calculation rule corresponding to the coarse classification result according to a fourth area, the second area, and the third area of the cystic region, and calculate and generate a fine classification result of the thyroid nodule, where the fine classification result includes: the cystic property is mainly, cystic property, and the actual property is mainly or actually.

The present application further provides a computer device, comprising a memory and a processor, wherein the memory stores a computer program, and the processor implements the steps of the above method when executing the computer program.

The present application also provides a computer-readable storage medium having stored thereon a computer program which, when being executed by a processor, carries out the steps of the above-mentioned method.

The thyroid nodule image processing method, the thyroid nodule image processing device, the computer equipment and the storage medium have the following beneficial effects:

the thyroid nodule image processing method, the thyroid nodule image processing device, the thyroid nodule image processing computer equipment and the storage medium comprise a two-step identification process from coarse to fine for a thyroid nodule, in the coarse identification process, a sound and shadow physical characteristic in the thyroid ultrasound scanning process is firstly utilized to extract a sound and shadow region in a nodule image and remove the sound and shadow region, so that the situation that the sound and shadow region in the nodule image is wrongly judged as a cystic region cannot occur, and therefore a thyroid nodule forming coarse classification result is accurately generated according to a first area of a candidate cystic region in the nodule image after the sound and shadow region is removed, a second area of the nodule region, and a third area corresponding to the intersection of the nodule region and the sound and shadow region. And after the formation coarse classification result is obtained, determining a cystic region in the nodule image by combining the gray scale and gradient information of the nodule image, and calling a preset calculation rule corresponding to the formation coarse classification result according to the fourth area, the second area and the third area of the cystic region to quickly and accurately calculate and generate a formation fine classification result of the thyroid nodule. According to the method and the device, the composition of the thyroid nodule can be accurately identified, on one hand, an exact analysis report related to the composition of the thyroid nodule can be further generated, and on the other hand, the composition of the thyroid nodule can be input into a corresponding neural network model to judge whether the thyroid nodule is benign or malignant.

Drawings

Fig. 1 is a schematic flowchart of a method for processing thyroid nodule images according to an embodiment of the present application;

fig. 2 is a schematic structural diagram of a thyroid nodule image processing apparatus according to an embodiment of the present application;

fig. 3 is a schematic structural diagram of a computer device according to an embodiment of the present application.

The implementation, functional features and advantages of the objectives of the present application will be further explained with reference to the accompanying drawings.

Detailed Description

It should be understood that the specific embodiments described herein are merely illustrative of the present application and are not intended to limit the present application.

As used herein, the singular forms "a", "an", "the" and "the" are intended to include the plural forms as well, unless the context clearly indicates otherwise. It will be further understood that the terms "comprises" and/or "comprising," when used in this specification, specify the presence of stated features, integers, steps, operations, elements, and/or components, but do not preclude the presence or addition of one or more other features, integers, steps, operations, elements, components, and/or groups thereof. It will be understood that when an element is referred to as being "connected" or "coupled" to another element, it can be directly connected or coupled to the other element or intervening elements may also be present. Further, "connected" or "coupled" as used herein may include wirelessly connected or wirelessly coupled. As used herein, the term "and/or" includes all or any element and all combinations of one or more of the associated listed items.

It will be understood by those skilled in the art that, unless otherwise defined, all terms (including technical and scientific terms) used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this invention belongs. It will be further understood that terms, such as those defined in commonly used dictionaries, should be interpreted as having a meaning that is consistent with their meaning in the context of the prior art and will not be interpreted in an idealized or overly formal sense unless expressly so defined herein.

The scheme can be applied to the digital medical field in the smart city, so that the construction of the smart city is promoted.

Referring to fig. 1, a method for processing a thyroid nodule image according to an embodiment of the present application includes:

s1: acquiring an input ultrasonic image with a thyroid nodule, marking the ultrasonic image with a nodule region, and generating a nodule mask image corresponding to the nodule region;

s2: intercepting an image corresponding to the minimum circumscribed rectangle of the nodule mask image to obtain a nodule image;

s3: performing binary segmentation processing on the nodule image according to a preset OTSU segmentation algorithm to generate a processed first nodule image, and acquiring a sound and shadow candidate region from the first nodule image;

s4: determining a sound shadow region from the first node image according to a non-sound shadow part in the sound shadow candidate region and a node boundary of the node region;

s5: cutting out the sound and shadow area in the nodule image to obtain a corresponding second nodule image, and performing binary segmentation processing on the second nodule image according to the OTSU segmentation algorithm to obtain a processed third nodule image;

s6: acquiring a black partial region in the third nodule image, wherein the black partial region is positioned in the nodule region, and taking the black partial region as a cystic candidate region;

s7: calculating a first area of the cystic candidate region, a second area of the nodule region, and a third area corresponding to an intersection of the nodule region and the sound shadow region;

s8: generating a coarse structural classification result of the thyroid nodule according to a first preset rule according to the first area, the second area and the third area, wherein the coarse structural classification result is whether cystic property is dominant or cystic property, or whether the coarse structural classification result is substantial property is dominant or substantial property;

s9: determining a cystic region from the third nodule image according to the gradient of the third nodule image and the cystic candidate region;

s10: calling a preset calculation rule corresponding to the coarse classification result according to a fourth area, the second area and the third area of the cystic area to calculate and generate a fine classification result of the thyroid nodule, wherein the fine classification result comprises: the cystic property is mainly, cystic property, and the actual property is mainly or actually.

As described in the above steps S1 to S10, the execution subject of the embodiment of the present method is a processing device of thyroid nodule images. In practical applications, the processing device for the thyroid nodule image may be implemented by a virtual device, such as a software code, or may be implemented by a physical device in which a relevant execution code is written or integrated, and may perform human-computer interaction with a user through a keyboard, a mouse, a remote controller, a touch panel, or a voice control device. The processing device of the thyroid nodule image in the embodiment can quickly and accurately identify the composition of the thyroid nodule in the ultrasonic image. Specifically, an input ultrasound image with a thyroid nodule is acquired, a nodule region is marked on the ultrasound image, and a nodule mask image corresponding to the nodule region is generated. And then, intercepting an image corresponding to the minimum circumscribed rectangle of the nodule mask image to obtain a nodule image. After the nodule image is obtained, binary segmentation processing is carried out on the nodule image according to a preset OTSU segmentation algorithm to generate a processed first nodule image, and a sound and shadow candidate region is obtained from the first nodule image. The OTSU segmentation algorithm is a self-adaptive threshold calculation method, and comprises the steps of firstly graying an original slice image, dividing all pixel points of the image into two different categories, namely a foreground category and a background category, according to the gray value of the image, reflecting the difference between the two categories in an inter-category variance, finding a proper threshold by traversing all gray values by the OTSU segmentation algorithm when the difference between the foreground and the background is larger and the variance between the two categories is larger. In addition, the OTSU segmentation algorithm may determine a first threshold value that is optimal for binarization of an image corresponding to the first node image, and perform binary segmentation processing on the first node image according to the first threshold value to obtain the first node image, where the sound-shadow candidate region is a foreground (white) portion in the first node image. Specifically, the formula of the OTSU segmentation algorithm is as follows: omega₀＝N₀/(M*N)，ω₁＝N₁/(M*N)，σ＝ω₀ω₁(μ₀-μ₁)². M is the length of the nodule image, N is the noduleImage width, M N stands for nodule area, N₀Is the area of the foreground pixel, N₁The area of the background pixel point is divided into a foreground part and a background part by a certain threshold T, and the ratio of the foreground pixel point is omega₀The ratio of the background pixel points is omega₁The gray average values of the foreground and background are respectively mu₀、μ₁And finally obtaining the between-class variance sigma. And calculating different thresholds T in a traversal mode, and finding the threshold T which can minimize the inter-class variance sigma, which is the result of the OTSU segmentation algorithm. After the sound shadow candidate area is obtained, a final sound shadow area is determined from the first node image according to the non-sound shadow part in the sound shadow candidate area and the node boundary of the node area. The non-sound-shadow part can be screened out from the sound-shadow candidate region according to the physical characteristics of the sound shadow to be eliminated, and then the first connected domain which passes through the nodule boundary of the nodule region in the sound-shadow candidate region after the elimination processing is used as the final sound-shadow region. And then cutting out the final sound and shadow area in the nodule image to obtain a corresponding second nodule image, and performing binary segmentation processing on the second nodule image according to the OTSU segmentation algorithm to obtain a processed third nodule image. Since the acoustic shadow region in the second nodule image is already eliminated, the acoustic shadow region in the nodule image is not mistakenly judged as the cystic region. In addition, the processing procedure of performing binary segmentation processing on the second nodule image according to the OTSU segmentation algorithm may refer to the processing procedure of performing binary segmentation processing on the nodule image according to the OTSU segmentation algorithm, and only the previously used node area (M × N) is changed to a designated node area, that is, the area of the nodule area is subtracted by a third area (M × N- (M × N) # a,) corresponding to the intersection of the nodule area and the final sound-shadow area, where a is the final sound-shadow area. After the third nodule image is obtained, a black partial region inside the nodule region (i.e., a background portion inside the nodule region) in the third nodule image is obtained, and the black partial region is used as a cystic candidate region. Wherein is at the knotThe black part area inside the nodule area refers to the background part area inside the nodule area. And calculating a first area of the cystic candidate region, a second area of the nodule region, and a third area corresponding to an intersection of the nodule region and the final sound-shadow region. And generating a coarse structural classification result of the thyroid nodule according to a first preset rule based on the first area, the second area and the third area, wherein the coarse structural classification result is mainly cystic or the coarse structural classification result is mainly substantial or substantial. In addition, the area of the cystic candidate region may be compared in size with one-half of the area of the designated nodule obtained by subtracting the area of the sound-shadow region included in the nodule from the area of the node, and a coarse classification result corresponding to the structural composition of the thyroid nodule may be generated from the corresponding size comparison result. And then determining a final cystic region from the third knot image according to the gradient of the third knot image and the cystic candidate region. The cystic region in the nodule image can be accurately identified by combining the gray level and the gradient of the nodule image, the gradient map of the third nodule image is generated, the seed points meeting the preset conditions are determined from the gradient map, and the final cystic region is obtained according to a seed filling method. And finally, calling a preset calculation rule corresponding to the coarse classification result according to the final fourth area, the second area and the third area of the cystic area to calculate and generate a fine classification result of the thyroid nodule, wherein the fine classification result comprises: the cystic property is mainly, cystic property, and the actual property is mainly or actually. In addition, for two different types of coarse classification results of thyroid nodules, two different types of calculation rules for generating fine classification results are correspondingly preset, and the two different types of calculation rules are provided with two corresponding ratio thresholds, specifically, the ratio between the areas of designated nodules is obtained by calculating the area of the final cystic region and the area of the nodes minus the area of the sound and shadow region included in the nodules, and the ratio is compared with the preset ratio threshold, so that the thyroid nodules can be quickly classified according to the corresponding size comparison resultsThe constitutive fine classification results of thyroid nodules are generated quickly and accurately. In the rough identification process, the sound and shadow region in the nodule image is extracted by using the sound and shadow physical characteristics during thyroid ultrasonic scanning and is removed, so that the situation that the sound and shadow region in the nodule image is wrongly judged as the cystic region can not occur, and the thyroid nodule forming rough classification result is accurately generated according to the first area of the candidate cystic region, the second area of the nodule region and the third area corresponding to the intersection of the nodule region and the sound and shadow region in the nodule image after the sound and shadow region is removed. And after the formation coarse classification result is obtained, determining a cystic region in the nodule image by combining the gray scale and gradient information of the nodule image, and calling a preset calculation rule corresponding to the formation coarse classification result according to the fourth area, the second area and the third area of the cystic region to quickly and accurately calculate and generate a formation fine classification result of the thyroid nodule. According to the method and the device, the composition of the thyroid nodule can be accurately identified, on one hand, an exact analysis report related to the composition of the thyroid nodule can be further generated, and on the other hand, the composition of the thyroid nodule can be input into a corresponding neural network model to judge whether the thyroid nodule is benign or malignant. This application is applicable in wisdom medical treatment, digital medical field, through the optimization to medical image analysis.

Further, in an embodiment of the present application, the step S4 of determining the sound shadow region from the first nodal image according to the non-sound shadow portion and the nodule boundary in the sound shadow candidate region includes:

s400: acquiring a non-sound shadow part in the sound shadow candidate area;

s401: eliminating the non-sound shadow part to obtain a processed sound shadow candidate area;

s402: acquiring a first connecting domain which passes through a nodule boundary of the nodule region in the processed sound and image candidate region;

s403: and taking the first connected domain as the sound shadow area.

As described in steps S400 to S403, the step of determining the sound shadow region from the first node image according to the non-sound shadow portion and the nodule boundary in the sound shadow candidate region may specifically include: first, the non-sound shadow part in the sound shadow candidate area is obtained. Because the sound shadow has a starting point which is always inside the nodule, the sound shadow can continue for a distance outside the boundary of the nodule, and the graph in the sound shadow does not have the physical characteristics of a large number of faults. Therefore, according to the physical characteristics, the non-sound shadow part in the sound shadow candidate area can be screened out by traversing each row in the first node image from top to bottom by the linear array probe. And then, eliminating the non-sound shadow part to obtain a processed sound shadow candidate area. Wherein, by eliminating the non-sound shadow part in the sound shadow candidate area, the accuracy of the sound shadow candidate area after the subsequent generation and processing can be improved. And then acquiring a first connecting domain which passes through the nodule boundary of the nodule region in the processed sound and image candidate region. Before the first connected domain of the processed sound and image candidate region, which passes through the nodule boundary of the nodule region, is obtained, the processed sound and image candidate region may be expanded in advance to eliminate fine dots in the processed sound and image candidate region, so as to avoid the fine dots from affecting the subsequently obtained first connected domain, and improve the accuracy of the obtained first connected domain. Finally, when the first communication region is obtained, the first communication region is set as the final sound and shadow region so that the final sound and shadow region can be cut out from the nodule image to obtain the corresponding second nodule image, and since the sound and shadow region in the second nodule image is already eliminated, namely, the sound and shadow region in the nodule image is not mistakenly judged as the cystic region, the identification processing of the thyroid nodule structure can be accurately performed according to the second nodule image.

Further, in an embodiment of the present application, the step S8 of generating a coarse thyroid nodule configuration classification result according to a first preset rule based on the first area, the second area, and the third area includes:

s800: calculating a first difference of the second area minus the third area;

s801: calculating a quotient value obtained by dividing the first difference value by 2;

s802: judging whether the first area is larger than the quotient value or not;

s803: if the first area is larger than the quotient, judging that the forming coarse classification result of the thyroid nodule is cystic main or cystic;

s804: and if the first area is not larger than the quotient, judging that the result of the coarse thyroid nodule classification is substantial or substantial.

As described in the foregoing steps S800 to S804, the step of generating the coarse classification result of the thyroid nodule according to the first area, the second area, and the third area and according to a first preset rule may specifically include: first, a first difference value obtained by subtracting the third area from the second area is calculated. The second area is an area of a nodule region, the third area is an area corresponding to an intersection of the nodule region and the final sound-shadow region, and a first difference obtained by subtracting the third area from the second area is calculated, that is, an area of the nodule region minus an area of a sound-shadow region included in the nodule is calculated, so that an accurate designated nodule area can be obtained. A quotient is then calculated by dividing the first difference by 2. And then judging whether the first area is larger than the quotient or not. And if the first area is judged to be larger than the quotient, judging that the result of the coarse classification of the thyroid nodule is the cystic character or the cystic character. Wherein the first area is an area of a cystic candidate region in the third nodule image, and when the area of the cystic candidate region is greater than one-half of the area of the designated nodule, it is preliminarily determined whether the configuration of the thyroid gland is cystic dominant or cystic. And if the first area is not larger than the quotient, judging that the result of the coarse thyroid nodule classification is substantial or substantial. When the area of the cystic candidate region is not greater than one-half of the area of the designated nodule, the constitution of the thyroid gland can be preliminarily determined to be dominant or substantial. In the embodiment, the size of the area of the cystic candidate region is compared with one half of the area of the designated nodule obtained by subtracting the area of the sound-shadow region included in the nodule from the area of the node, and then the structural coarse classification result corresponding to the structural composition of the thyroid nodule is generated according to the corresponding size comparison result, so that the structural fine classification result of the thyroid nodule is further generated according to the structural coarse classification result.

Further, in an embodiment of the application, the step S9 of determining the cystic region from the third nodule image according to the gradient of the third nodule image and the cystic candidate region includes:

s900: calculating the gradient of the third node image and generating a corresponding gradient map;

s901: finding out seed points which are in the cystic candidate region and have the gray scale smaller than a first preset threshold value and the gradient smaller than a second preset threshold value in the gradient map;

s902: performing region growing treatment on the seed points according to a second preset rule to generate corresponding specified connected domains;

s903: carrying out corrosion treatment on the specified connected domain;

s904: calculating the product of the second area and a specified value;

s905: screening out a second connected domain with the connected domain area larger than the product from all the specified connected domains;

s906: determining the second connected domain as the cystic region.

As described in steps S900 to S906 above, the present embodiment is not limited to using only the gray scale information of the nodule image, but can accurately identify the cystic region in the nodule image by combining the gray scale and the gradient of the nodule image. Specifically, the step of determining the cystic region from the third nodule image according to the gradient of the third nodule image and the cystic candidate region may include: the gradient of the third nodal image is calculated first, and a corresponding gradient map is generated. Wherein, can pass through the formula

Calculating to generate a gradient map corresponding to the third node image, g_xAnd g_yAnd respectively calculating the third node image in the horizontal direction and the vertical direction to obtain a gradient image g. And then finding out the seed points which are in the cystic candidate region and have the gray scale smaller than a first preset threshold value and the gradient smaller than a second preset threshold value in the gradient map. The first preset threshold and the second preset threshold are not particularly limited, and may be set according to actual requirements, for example, they may be set to 2 and 4, respectively. And after the seed points are obtained, performing region growing treatment on the seed points according to a second preset rule to generate corresponding specified connected domains. The second preset rule may specifically be a seed filling method, and the process of the seed filling method includes: selecting a foreground pixel point as a seed point, then combining foreground pixels adjacent to the seed into the same set according to the composition condition of a connected region, and finally obtaining a pixel set which is a connected region. After the specified connected domain is obtained, the specified connected domain is subjected to corrosion treatment. The designated connected domain is subjected to corrosion treatment, holes can be filled, and the connecting part between the designated connected domain and the non-nodular region is removed, so that the thyroid nodule shape can be refined. And calculating the product of the second area and the specified value. The above-mentioned designated value is not particularly limited, and may be set according to actual requirements, for example, may be set to 0.001. And screening out a second connected domain with the connected domain area larger than the product from all the specified connected domains. The connected regions with too small areas are regarded as nonsense regions, and in order to avoid the influence of the nonsense regions on the cystic regions, the nonsense regions need to be removed from the cystic candidate regions. Finally, the second connected domain is determined as the final cystic region, so that a preset calculation rule corresponding to the coarse classification result can be called to obtain a final fourth area of the cystic region, the second area and the third areaAnd calculating the structural fine classification result of the thyroid nodule quickly and accurately.

Further, in an embodiment of the application, the step S902 of performing region growing processing on the seed points according to a third preset rule to generate a corresponding designated connected domain includes:

s9020: acquiring a designated seed point, wherein the designated seed point is any one of all the seed points;

s9021: merging pixels adjacent to the designated seed point into the same set according to the composition condition of the connected region to generate a designated pixel set, wherein the composition condition of the connected region comprises that the pixel values are the same and are adjacent;

s9022: and taking the generated specified set as a connected domain corresponding to the specified seed point.

As described in the foregoing steps S9020 to S9022, the step of performing region growing processing on the seed point according to a third preset rule to generate a corresponding designated connected domain may specifically include: firstly, a designated seed point is obtained, wherein the designated seed point is any one of all the seed points. Then merging the pixels adjacent to the designated seed points into the same set according to the composition conditions of the connected regions to generate a designated pixel set; wherein, the composition condition of the connected region includes that the pixel values are the same and the pixel values are adjacent. And finally, taking the generated designated set as a connected domain corresponding to the designated seed point. According to the method and the device, the designated connected region of the seed point after the growth filling processing can be quickly and conveniently obtained according to the composition condition of the connected region, so that the final cystic region in the third nodule image can be quickly determined according to the designated connected region, and the composition fine classification result of the thyroid nodule can be quickly and accurately calculated and generated by calling the preset calculation rule corresponding to the composition coarse classification result according to the obtained fourth area, the second area and the third area of the cystic region.

Further, in an embodiment of the present application, after step S900 of calculating a gradient of the third node image and generating a corresponding gradient map, the method includes:

s9000: screening abnormal gradients in the gradient map by a median filtering algorithm;

s9001: deleting the anomalous gradient from the gradient map.

As described in steps S9000 to S9001, after the gradient of the third node image is calculated and a corresponding gradient map is generated, the gradient map may be further subjected to a median filtering process to filter out useless noise data. Specifically, after the step of calculating the gradient of the third node image and generating the corresponding gradient map, the method includes: firstly, screening abnormal gradients in the gradient map by a median filtering algorithm. After the abnormal gradient is obtained, the abnormal gradient is deleted from the gradient map. In the embodiment, the abnormal gradient in the gradient map is removed by using the median filtering algorithm, so that the accuracy of the subsequently searched seed point can be improved, and the accuracy of the subsequently generated final cystic region is further improved.

Further, in an embodiment of the application, the step S10 of invoking a preset calculation rule corresponding to the coarse classification result to calculate and generate a fine classification result of the thyroid nodule according to the fourth area, the second area, and the third area of the cystic region includes:

s1000: calculating a second difference of the second area minus the third area;

s1001: calculating a ratio between the fourth area and the second difference;

s1002: when the bag property is the main or bag property, judging whether the ratio is larger than a preset first ratio threshold value;

s1003: if the ratio is larger than the first ratio threshold, judging that the structural fine classification result of the thyroid nodule is cystic, otherwise, judging that the structural fine classification result of the thyroid nodule is cystic;

s1004: when the coarse classification result is that the real property is dominant or real, judging whether the ratio is smaller than a preset second ratio threshold value;

s1005: and if the ratio is smaller than the second ratio threshold, judging that the thyroid nodule formation fine classification result is substantial, otherwise, judging that the thyroid nodule formation fine classification result is substantial.

As described in steps S1000 to S1005, two different calculation rules for generating a fine classification result are preset for two different coarse classification results of thyroid nodules, and two different calculation rules are set with two corresponding ratio thresholds. The step of generating a structural fine classification result of the thyroid nodule by calling a preset calculation rule corresponding to the structural coarse classification result according to the fourth area, the second area, and the third area of the cystic region may specifically include: first, a second difference value obtained by subtracting the third area from the second area is calculated. And calculating a ratio between the fourth area and the second difference. The second area is an area of a nodule region, the third area is an area corresponding to an intersection of the nodule region and the final sound-shadow region, and a first difference obtained by subtracting the third area from the second area is calculated, that is, an area of the nodule region minus an area of a sound-shadow region included in the nodule is calculated, so that an accurate designated nodule area can be obtained. In addition, the ratio of the fourth area to the second difference is a ratio of the area of the final cystic region to the area of the designated nodule. And when the bag property is the main or bag property, judging whether the ratio is larger than a preset first ratio threshold value. The first ratio threshold is not particularly limited, and may be set according to actual requirements, for example, may be set to 0.95. And if the ratio is judged to be larger than the first ratio threshold, judging that the structural fine classification result of the thyroid nodule is cystic, otherwise, judging that the structural fine classification result of the thyroid nodule is cystic. And when the coarse classification result is substantial or substantial, judging whether the ratio is smaller than a preset second ratio threshold. The second ratio threshold is not particularly limited, and may be set according to actual requirements, for example, may be set to 0.08. And if the ratio is judged to be smaller than the second ratio threshold, judging that the thyroid nodule formation fine classification result is substantial, otherwise, judging that the thyroid nodule formation fine classification result is substantial. After the result of the coarse classification of the thyroid nodule is obtained, the ratio between the areas of the designated nodules is calculated by subtracting the areas of the sound and shadow areas included in the nodules from the areas of the cystic areas and the nodes, and the ratio is compared with the preset ratio threshold, so that the result of the fine classification of the thyroid nodule can be quickly and accurately generated according to the corresponding comparison result. According to the embodiment, the composition of the thyroid nodule can be accurately identified, on one hand, an exact analysis report related to the composition of the thyroid nodule can be further generated, and on the other hand, the composition of the thyroid nodule can be input into a corresponding neural network model to make judgment about whether the thyroid nodule is benign or malignant.

The thyroid nodule image processing method in the embodiment of the present application may also be applied to the field of blockchain, for example, data such as the structural fine classification result of the thyroid nodule is stored on the blockchain. By storing and managing the fine classification result of the thyroid nodule structure using the block chain, the safety and tamper resistance of the fine classification result of the thyroid nodule structure can be effectively ensured.

The block chain is a novel application mode of computer technologies such as distributed data storage, point-to-point transmission, a consensus mechanism and an encryption algorithm. A block chain (Blockchain), which is essentially a decentralized database, is a series of data blocks associated by using a cryptographic method, and each data block contains information of a batch of network transactions, so as to verify the validity (anti-counterfeiting) of the information and generate a next block. The blockchain may include a blockchain underlying platform, a platform product service layer, an application service layer, and the like.

The block chain underlying platform can comprise processing modules such as user management, basic service, intelligent contract and operation monitoring. The user management module is responsible for identity information management of all blockchain participants, and comprises public and private key generation maintenance (account management), key management, user real identity and blockchain address corresponding relation maintenance (authority management) and the like, and under the authorization condition, the user management module supervises and audits the transaction condition of certain real identities and provides rule configuration (wind control audit) of risk control; the basic service module is deployed on all block chain node equipment and used for verifying the validity of the service request, recording the service request to storage after consensus on the valid request is completed, for a new service request, the basic service firstly performs interface adaptation analysis and authentication processing (interface adaptation), then encrypts service information (consensus management) through a consensus algorithm, transmits the service information to a shared account (network communication) completely and consistently after encryption, and performs recording and storage; the intelligent contract module is responsible for registering and issuing contracts, triggering the contracts and executing the contracts, developers can define contract logics through a certain programming language, issue the contract logics to a block chain (contract registration), call keys or other event triggering and executing according to the logics of contract clauses, complete the contract logics and simultaneously provide the function of upgrading and canceling the contracts; the operation monitoring module is mainly responsible for deployment, configuration modification, contract setting, cloud adaptation in the product release process and visual output of real-time states in product operation, such as: alarm, monitoring network conditions, monitoring node equipment health status, and the like.

Referring to fig. 2, an embodiment of the present application further provides a device for processing a thyroid nodule image, including:

the system comprises a first acquisition module 1, a second acquisition module and a third acquisition module, wherein the first acquisition module is used for acquiring an input ultrasonic image with thyroid nodules, marking the ultrasonic image with nodule areas and generating nodule mask images corresponding to the nodule areas;

the first generation module 2 is used for intercepting an image corresponding to the minimum circumscribed rectangle of the nodule mask image to obtain a nodule image;

the first processing module 3 is configured to perform binary segmentation processing on the nodule image according to a preset OTSU segmentation algorithm, generate a processed first nodule image, and acquire a sound and shadow candidate region from the first nodule image;

a first determining module 4, configured to determine a sound shadow region from the first nodal image according to a non-sound shadow portion in the sound shadow candidate region and a nodule boundary of the nodule region;

the second processing module 5 is configured to cut out the sound and shadow region in the nodule image to obtain a corresponding second nodule image, and perform binary segmentation processing on the second nodule image according to the OTSU segmentation algorithm to obtain a processed third nodule image;

a second obtaining module 6, configured to obtain a black partial region inside the nodule region in the third nodule image, and use the black partial region as a cystic candidate region;

a calculating module 7, configured to calculate a first area of the cystic candidate region, a second area of the nodule region, and a third area corresponding to an intersection of the nodule region and the sound shadow region;

a second generating module 8, configured to generate a coarse structural classification result of the thyroid nodule according to a first preset rule according to the first area, the second area, and the third area, where the coarse structural classification result is a cystic property or a cystic property, or the coarse structural classification result is a substantial property or a substantial property;

a second determining module 9, configured to determine a cystic region from the third nodule image according to the gradient of the third nodule image and the cystic candidate region;

a third generating module 10, configured to invoke a preset calculation rule corresponding to the coarse classification result according to a fourth area, the second area, and the third area of the cystic region, and calculate and generate a fine classification result of the thyroid nodule, where the fine classification result includes: the cystic property is mainly, cystic property, and the actual property is mainly or actually.

In this embodiment, the implementation processes of the functions and actions of the first obtaining module, the first generating module, the first processing module, the first determining module, the second processing module, the second obtaining module, the calculating module, the second generating module, the second determining module and the third generating module in the processing apparatus for thyroid nodule images are specifically detailed in the implementation processes corresponding to steps S1 to S10 in the processing method for thyroid nodule images, and are not described herein again.

Further, in an embodiment of the application, the first determining module includes:

the first obtaining submodule is used for obtaining a non-sound shadow part in the sound shadow candidate area;

the first processing submodule is used for eliminating the non-sound shadow part to obtain a processed sound shadow candidate area;

a second obtaining sub-module, configured to obtain a first connection domain that passes through a nodule boundary of the nodule region in the processed sound-image candidate region;

and the first determining submodule is used for taking the first connected domain as the sound shadow region.

In this embodiment, the implementation processes of the functions and functions of the first obtaining sub-module, the first processing sub-module, the second obtaining sub-module, and the first determining sub-module in the processing apparatus for a thyroid nodule image are specifically detailed in the implementation processes corresponding to steps S400 to S403 in the processing method for a thyroid nodule image, and are not described herein again.

Further, in an embodiment of the application, the second generating module includes:

a first calculation submodule for calculating a first difference of the second area minus the third area;

the second calculation submodule is used for calculating a quotient value obtained by dividing the first difference value by 2;

the first judgment submodule is used for judging whether the first area is larger than the quotient value or not;

the first judging submodule is used for judging whether the constituting coarse classification result of the thyroid nodule is cystic main or cystic if the first area is larger than the quotient;

and the second judging submodule is used for judging whether the constitutive coarse classification result of the thyroid nodule is substantial or substantial if the first area is not larger than the quotient.

In this embodiment, the implementation processes of the functions and functions of the first calculating submodule, the second calculating submodule, the first determining submodule and the second determining submodule in the processing apparatus for a thyroid nodule image are specifically detailed in the implementation processes corresponding to steps S800 to S804 in the processing method for a thyroid nodule image, and are not described herein again.

Further, in an embodiment of the application, the second determining module includes:

the third calculation submodule is used for calculating the gradient of the third node image and generating a corresponding gradient map;

the searching submodule is used for searching seed points, with the gray scale smaller than a first preset threshold value and the gradient smaller than a second preset threshold value, in the cystic candidate region in the gradient map;

the first processing submodule is used for carrying out region growing processing on the seed points according to a second preset rule to generate corresponding specified connected domains;

the second processing submodule is used for carrying out corrosion processing on the specified connected domain;

the fourth calculation submodule is used for calculating the product of the second area and a specified numerical value;

the screening submodule is used for screening out a second connected domain with the connected domain area larger than the product from all the specified connected domains;

a determination submodule for determining the second connected component as the cystic area.

In this embodiment, the implementation processes of the functions and functions of the third computation submodule, the search submodule, the first processing submodule, the second processing submodule, the fourth computation submodule, the screening submodule and the determination submodule in the processing device for the thyroid nodule image are specifically detailed in the implementation processes corresponding to steps S900 to S906 in the processing method for the thyroid nodule image, and are not described herein again.

Further, in an embodiment of the application, the first processing sub-module includes:

the device comprises an acquisition unit, a judgment unit and a control unit, wherein the acquisition unit is used for acquiring a specified seed point, and the specified seed point is any one of all the seed points;

the generating unit is used for merging pixels adjacent to the specified seed point into the same set according to the composition condition of the connected region, and generating a specified pixel set, wherein the composition condition of the connected region comprises that the pixel values are the same and are adjacent;

and the determining unit is used for taking the generated specified set as a connected domain corresponding to the specified seed point.

In this embodiment, the implementation processes of the functions and functions of the obtaining unit, the generating unit, and the determining unit in the processing apparatus for thyroid nodule images are specifically detailed in the implementation processes corresponding to steps S9020 to S9022 in the processing method for thyroid nodule images, and are not described herein again.

the screening unit is used for screening abnormal gradients in the gradient map through a median filtering algorithm;

a deleting unit for deleting the abnormal gradient from the gradient map.

In this embodiment, the implementation processes of the functions and actions of the screening unit and the deleting unit in the processing apparatus for thyroid nodule images are specifically detailed in the implementation processes corresponding to steps S9000 to S9001 in the processing method for thyroid nodule images, and are not described again here.

Further, in an embodiment of the present application, the third generating module includes:

a fifth calculation submodule for calculating a second difference of the second area minus the third area;

a sixth calculation submodule for calculating a ratio between the fourth area and the second difference;

the second judgment submodule is used for judging whether the ratio is greater than a preset first ratio threshold value or not when the coarse classification result is that the cystic property is dominant or the cystic property is dominant;

a third determination submodule, configured to determine that a structural fine classification result of the thyroid nodule is cystic if the ratio is greater than the first ratio threshold, and otherwise determine that the structural fine classification result of the thyroid nodule is cystic;

a third judging submodule, configured to judge whether the ratio is smaller than a preset second ratio threshold when the coarse classification result is substantial or substantial;

and the fourth judging submodule is used for judging that the fine classification forming result of the thyroid nodule is substantial if the ratio is smaller than the second ratio threshold, and otherwise, judging that the fine classification forming result of the thyroid nodule is substantial.

In this embodiment, the implementation processes of the functions and functions of the fifth calculation submodule, the sixth calculation submodule, the second determination submodule, the third determination submodule and the fourth determination submodule in the processing apparatus for thyroid nodule images are specifically detailed in the implementation processes corresponding to steps S1000 to S1005 in the processing method for thyroid nodule images, and are not described herein again.

Referring to fig. 3, a computer device, which may be a server and whose internal structure may be as shown in fig. 3, is also provided in the embodiment of the present application. The computer device comprises a processor, a memory, a network interface, a display screen, an input device and a database which are connected through a system bus. Wherein the processor of the computer device is designed to provide computing and control capabilities. The memory of the computer device comprises a nonvolatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, a computer program, and a database. The internal memory provides an environment for the operation of an operating system and computer programs in the non-volatile storage medium. The database of the computer device is used for storing data such as a nodule mask image, a nodule image, a third nodule image, a final cystic area, a fine classification result of the thyroid nodule and the like. The network interface of the computer device is used for communicating with an external terminal through a network connection. The display screen of the computer equipment is an indispensable image-text output equipment in the computer, and is used for converting digital signals into optical signals so that characters and figures are displayed on the screen of the display screen. The input device of the computer equipment is the main device for information exchange between the computer and the user or other equipment, and is used for transmitting data, instructions, some mark information and the like to the computer. The computer program is executed by a processor to implement a method of processing thyroid nodule images.

The processor executes the processing method of the thyroid nodule image, and the processing method comprises the following steps:

Those skilled in the art will appreciate that the structure shown in fig. 3 is only a block diagram of a part of the structure related to the present application, and does not constitute a limitation to the apparatus and the computer device to which the present application is applied.

An embodiment of the present application further provides a computer-readable storage medium, on which a computer program is stored, where the computer program, when executed by a processor, implements a method for processing a thyroid nodule image, and specifically includes:

To sum up, the thyroid nodule image processing method, device, computer equipment and storage medium provided in the embodiment of the present application include two steps of identification processes from thick to thin for thyroid nodule formation, in the thick identification process, the sound and shadow physical characteristics when the thyroid ultrasound scans can be utilized to extract the sound and shadow region in the nodule image and eliminate the sound and shadow region, so that the situation that the sound and shadow region in the nodule image is wrongly judged as the cystic region cannot occur, and thus the second area of the nodule region and the third area corresponding to the intersection of the nodule region and the sound and shadow region accurately generate the coarse classification result of the thyroid nodule. And after the formation coarse classification result is obtained, determining a cystic region in the nodule image by combining the gray scale and gradient information of the nodule image, and calling a preset calculation rule corresponding to the formation coarse classification result according to the fourth area, the second area and the third area of the cystic region to quickly and accurately calculate and generate a formation fine classification result of the thyroid nodule. According to the embodiment of the application, the composition of the thyroid nodule can be accurately identified, on one hand, an exact analysis report related to the composition of the thyroid nodule can be further generated, and on the other hand, the composition of the thyroid nodule can be input into a corresponding neural network model to make judgment about whether the thyroid nodule is benign or malignant.

It will be understood by those skilled in the art that all or part of the processes of the methods of the above embodiments may be implemented by hardware associated with instructions of a computer program, which may be stored on a non-volatile computer-readable storage medium, and when executed, may include processes of the above embodiments of the methods. Any reference to memory, storage, database, or other medium provided herein and used in the examples may include non-volatile and/or volatile memory. Non-volatile memory can include read-only memory (ROM), Programmable ROM (PROM), Electrically Programmable ROM (EPROM), Electrically Erasable Programmable ROM (EEPROM), or flash memory. Volatile memory can include Random Access Memory (RAM) or external cache memory. By way of illustration and not limitation, RAM is available in a variety of forms such as Static RAM (SRAM), Dynamic RAM (DRAM), Synchronous DRAM (SDRAM), double-rate SDRAM (SSRSDRAM), Enhanced SDRAM (ESDRAM), synchronous link (Synchlink) DRAM (SLDRAM), Rambus Direct RAM (RDRAM), direct bus dynamic RAM (DRDRAM), and memory bus dynamic RAM (RDRAM).

It should be noted that, in this document, the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, apparatus, article, or method that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, apparatus, article, or method. Without further limitation, an element defined by the phrase "comprising an … …" does not exclude the presence of other like elements in a process, apparatus, article, or method that includes the element.

The above description is only a preferred embodiment of the present application, and not intended to limit the scope of the present application, and all modifications of equivalent structures and equivalent processes, which are made by the contents of the specification and the drawings of the present application, or which are directly or indirectly applied to other related technical fields, are also included in the scope of the present application.

Claims

1. A method for processing thyroid nodule images, comprising:

2. The method for processing a thyroid nodule image according to claim 1, wherein the step of determining a sound shadow region from the first nodule image based on the non-sound shadow part in the sound shadow candidate region and a nodule boundary comprises:

acquiring a non-sound shadow part in the sound shadow candidate area;

and taking the first connected domain as the sound shadow area.

3. The method for processing the thyroid nodule image according to claim 1, wherein the step of generating the coarse classification result of the thyroid nodule according to a first preset rule based on the first area, the second area and the third area comprises:

calculating a first difference of the second area minus the third area;

judging whether the first area is larger than the quotient value or not;

4. The method for processing a thyroid nodule image according to claim 1, wherein the step of determining a cystic region from the third nodule image based on the gradient of the third nodule image and the cystic candidate region comprises:

carrying out corrosion treatment on the specified connected domain;

calculating the product of the second area and a specified value;

determining the second connected domain as the cystic region.

5. The method for processing the thyroid nodule image according to claim 4, wherein the step of performing region growing processing on the seed points according to a third preset rule to generate corresponding designated connected domains comprises:

6. The method of processing a thyroid nodule image according to claim 4, wherein the step of calculating the gradient of the third nodule image and generating a corresponding gradient map comprises:

deleting the anomalous gradient from the gradient map.

7. The method for processing the thyroid nodule image according to claim 1, wherein the step of invoking a preset calculation rule corresponding to the coarse classification result to calculate and generate a fine classification result of the thyroid nodule according to the fourth area, the second area and the third area of the cystic region comprises:

calculating a second difference of the second area minus the third area;

calculating a ratio between the fourth area and the second difference;

when the bag property is the main or bag property, judging whether the ratio is larger than a preset first ratio threshold value;

8. A thyroid nodule image processing apparatus comprising:

9. A computer device comprising a memory and a processor, the memory having stored therein a computer program, characterized in that the processor, when executing the computer program, implements the steps of the method according to any one of claims 1 to 7.

10. A computer-readable storage medium, on which a computer program is stored, which, when being executed by a processor, carries out the steps of the method of any one of claims 1 to 7.